Marina Zapater

Visiting Professor
+34 91 394 7541
Facultad de Informática UCM. Room 347
Contact Marina Zapater

I am currently Visiting Professor in the Department of Computer Architecture and Automation at Complutense University of Madrid (UCM). On the academic year 2014-2015 I was part-time lecturer at UCM. My research takes place in the ArTeCS group of UCM, but I am also part of the GreenLSI team at the Integrated Systems Lab (LSI) and the Center for Computational Simulation (CCS) of Universidad Politécnica de Madrid. I am also a post-doc researcher at the ESL group of École Polytechnique Fédérale de Lausanne, with Prof. David Atienza, with whom I’ve been collaborating since Fall 2015.

Marina @Boston
Marina @Boston

I received my PhD degree on April 2015 from Universidad Politécnica de Madrid. My thesis was on “Proactive and Reactive Thermal Aware Optimization Techniques to minimize the Environmental Impact of data centers”, was awarded Cum Laude.  My PhD Thesis was advised by Prof. José M. Moya and Prof. José L. Ayala, and was funded by a fellowship of the International Program for Attracting Talent (PICATA) of the Moncloa Campus of International Excellence.

On summer 2012 I did a 15-week research stay at the Performance and Energy-Aware Computing Lab. at Boston University under the supervision of Prof. Ayse K. Coskun. On fall 2014 I visited Prof. Coskun again for a 3-month period with a HiPEAC collaboration grant. Since 2012, we have published several papers together and our collaborating keeps on going.

I got a Master of Science in Electronic Engineering and a Master of Science in Telecommunication Engineering, both by ETSETB at Universitat Politècnica de Catalunya on 2010.

Resume

Short resume [English][Spanish]

PhD Thesis

Here you can find a link to download my PhD Thesis

Publications

2017

  • J. Pagan, M. Zapater, and J. L. Ayala, “Power transmission and workload balancing policies in eHealth mobile cloud computing scenarios,” Future generation computer systems, 2017.
    [BibTeX]
    @article{Pagan:2017:FGCS,
    author = {Pagan, Josue and Zapater, Marina and Ayala, Jose L.},
    citeulike-article-id = {14274578},
    journal = {Future Generation Computer Systems},
    keywords = {greendisc},
    posted-at = {2017-02-08 17:41:42},
    priority = {2},
    title = {Power Transmission and Workload Balancing Policies in {eHealth} Mobile Cloud Computing Scenarios},
    year = {2017}
    }

  • J. L. Risco-Martin, S. Mittal, J. C. Fabero Jimenez, M. Zapater, and R. Hermida Correa, “Reconsidering the performance of DEVS modeling and simulation environment using the DEVSton benchmark,” Simulation: transactions of the society for modeling and simulation international, pp. 1-18, 2017.
    [BibTeX]
    @article{Risco:2017:Simulation,
    author = {Risco-Martin, Jose L. and Mittal, Saurabh and Fabero Jimenez, Juan C. and Zapater, Marina and Hermida Correa, Roman},
    citeulike-article-id = {14272293},
    howpublished = {[Accepted, to appear on 2017]},
    journal = {Simulation: Transactions of the Society for Modeling and Simulation International},
    keywords = {greendisc},
    pages = {1--18},
    posted-at = {2017-02-06 16:01:15},
    priority = {2},
    title = {Reconsidering the performance of {DEVS} modeling and simulation environment using the {DEVSton} benchmark},
    year = {2017}
    }

2016

  • M. Zapater, J. L. Risco-Martín, P. Arroba, J. L. Ayala, J. M. Moya, and R. Hermida, “Runtime data center temperature prediction using grammatical evolution techniques,” Applied soft computing, 2016. doi:10.1016/j.asoc.2016.07.042
    [BibTeX] [Abstract] [Download PDF]

    Modeling methodology for temperature prediction in data centers Prediction of server {CPU} and inlet temperature under variable cooling setups Development of time-dependent multi-variable models based on Grammatical Evolution. Premature convergence techniques using Social Disaster Techniques and Random {Off-Spring} Generation. Comparison to other techniques such as {ARMA}, {N4SID} and {NARX}. Models tuned, trained and tested using measurements from real server and data center traces. Data Centers are huge power consumers, both because of the energy required for computation and the cooling needed to keep servers below thermal redlining. The most common technique to minimize cooling costs is increasing data room temperature. However, to avoid reliability issues, and to enhance energy efficiency, there is a need to predict the temperature attained by servers under variable cooling setups. Due to the complex thermal dynamics of data rooms, accurate runtime data center temperature prediction has remained as an important challenge. By using Gramatical Evolution techniques, this paper presents a methodology for the generation of temperature models for data centers and the runtime prediction of {CPU} and inlet temperature under variable cooling setups. As opposed to time costly Computational Fluid Dynamics techniques, our models do not need specific knowledge about the problem, can be used in arbitrary data centers, re-trained if conditions change and have negligible overhead during runtime prediction. Our models have been trained and tested by using traces from real Data Center scenarios. Our results show how we can fully predict the temperature of the servers in a data rooms, with prediction errors below {2°C} and {0.5°C} in {CPU} and server inlet temperature respectively.

    @article{Zapater:ASOC:2016,
    abstract = { Modeling methodology for temperature prediction in data centers Prediction of server {CPU} and inlet temperature under variable cooling setups Development of time-dependent multi-variable models based on Grammatical Evolution. Premature convergence techniques using Social Disaster Techniques and Random {Off-Spring} Generation. Comparison to other techniques such as {ARMA}, {N4SID} and {NARX}. Models tuned, trained and tested using measurements from real server and data center traces. Data Centers are huge power consumers, both because of the energy required for computation and the cooling needed to keep servers below thermal redlining. The most common technique to minimize cooling costs is increasing data room temperature. However, to avoid reliability issues, and to enhance energy efficiency, there is a need to predict the temperature attained by servers under variable cooling setups. Due to the complex thermal dynamics of data rooms, accurate runtime data center temperature prediction has remained as an important challenge. By using Gramatical Evolution techniques, this paper presents a methodology for the generation of temperature models for data centers and the runtime prediction of {CPU} and inlet temperature under variable cooling setups. As opposed to time costly Computational Fluid Dynamics techniques, our models do not need specific knowledge about the problem, can be used in arbitrary data centers, re-trained if conditions change and have negligible overhead during runtime prediction. Our models have been trained and tested by using traces from real Data Center scenarios. Our results show how we can fully predict the temperature of the servers in a data rooms, with prediction errors below {2°C} and {0.5°C} in {CPU} and server inlet temperature respectively. },
    author = {Zapater, Marina and Risco-Mart\'{\i}n, Jos\'{e} L. and Arroba, Patricia and Ayala, Jos\'{e} L. and Moya, Jos\'{e} M. and Hermida, Rom\'{a}n},
    citeulike-article-id = {14115570},
    citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.asoc.2016.07.042},
    doi = {10.1016/j.asoc.2016.07.042},
    issn = {15684946},
    journal = {Applied Soft Computing},
    keywords = {ee, greendisc, greenlsi},
    month = aug,
    posted-at = {2016-08-18 09:05:27},
    priority = {2},
    title = {Runtime Data Center Temperature Prediction using Grammatical Evolution Techniques},
    url = {http://dx.doi.org/10.1016/j.asoc.2016.07.042},
    year = {2016}
    }

  • A. Pahlevan, J. Picorel, A. P. Zarandi, D. Rossi, M. Zapater, A. Bartolini, P. G. del Valle, D. Atienza, L. Benini, and B. Falsafi, “Towards Near-Threshold server processors,” in Design automation and test in europe (date), 2016.
    [BibTeX]
    @inproceedings{citeulike:13938246,
    author = {Pahlevan, Ali and Picorel, Javier and Zarandi, Arash P. and Rossi, Davide and Zapater, Marina and Bartolini, Andrea and del Valle, Pablo G. and Atienza, David and Benini, Luca and Falsafi, Babak},
    booktitle = {Design Automation and Test in Europe (DATE)},
    citeulike-article-id = {13938246},
    keywords = {ee, epfl, greenlsi},
    month = mar,
    posted-at = {2016-02-22 14:24:16},
    priority = {5},
    title = {Towards {Near-Threshold} Server Processors},
    year = {2016}
    }

  • J. C. Salinas-Hilburg, M. Zapater, J. L. Risco-Martín, J. M. Moya, and J. L. Ayala, “Unsupervised power modeling of Co-Allocated workloads for energy efficiency in data centers.” 2016.
    [BibTeX] [Abstract]

    Data centers are huge power consumers and their energy consumption keeps on rising despite the efforts to increase energy efficiency. A great body of research is devoted to the reduction of the computational power of these facilities, applying techniques such as power budgeting and power capping in servers. Such techniques rely on models to predict the power consumption of servers. However, estimating overall server power for arbitrary applications when running co-allocated in multi- threaded servers is not a trivial task. In this paper, we use Grammatical Evolution techniques to predict the dynamic power of the {CPU} and memory subsystems of an enterprise server using the hardware counters of each application. On top of our dynamic power models, we use fan and temperature-dependent leakage power models to obtain the overall server power. To train and test our models we use real traces from a presently shipping enterprise server under a wide set of sequential and parallel workloads running at various frequencies We prove that our model is able to predict the power consumption of two different tasks co-allocated in the same server, keeping error below {8W}. For the first time in literature, we develop a methodology able to combine the hardware counters of two individual applications, and estimate overall server power consumption without running the co-allocated application. Our results show a prediction error below {12W}, which represents a 7.3\% of the overall server power, outperforming previous approaches in the state of the art.

    @inproceedings{citeulike:13911603,
    abstract = {Data centers are huge power consumers and their
    energy consumption keeps on rising despite the efforts to increase
    energy efficiency. A great body of research is devoted to the
    reduction of the computational power of these facilities, applying
    techniques such as power budgeting and power capping in
    servers. Such techniques rely on models to predict the power
    consumption of servers. However, estimating overall server power
    for arbitrary applications when running co-allocated in multi-
    threaded servers is not a trivial task. In this paper, we use
    Grammatical Evolution techniques to predict the dynamic power
    of the {CPU} and memory subsystems of an enterprise server using
    the hardware counters of each application. On top of our dynamic
    power models, we use fan and temperature-dependent leakage
    power models to obtain the overall server power. To train and
    test our models we use real traces from a presently shipping
    enterprise server under a wide set of sequential and parallel
    workloads running at various frequencies We prove that our
    model is able to predict the power consumption of two different
    tasks co-allocated in the same server, keeping error below {8W}.
    For the first time in literature, we develop a methodology able
    to combine the hardware counters of two individual applications,
    and estimate overall server power consumption without running
    the co-allocated application. Our results show a prediction error
    below {12W}, which represents a 7.3\% of the overall server power,
    outperforming previous approaches in the state of the art.},
    author = {Salinas-Hilburg, J. C. and Zapater, M. and Risco-Mart\'{\i}n, J. L. and Moya, J. M. and Ayala, J. L.},
    citeulike-article-id = {13911603},
    journal = {Design, Automation and Test in Europe (DATE)},
    keywords = {ee, greenlsi},
    posted-at = {2016-01-20 15:34:04},
    priority = {2},
    title = {Unsupervised Power Modeling of {Co-Allocated} Workloads for Energy Efficiency in Data Centers},
    year = {2016}
    }

2015

  • M. Zapater, A. Turk, J. M. Moya, J. L. Ayala, and A. K. Coskun, “Dynamic workload and cooling management in High-Efficiency data centers,” in International green and sustainable computing conference (igsc), 2015.
    [BibTeX]
    @inproceedings{Zapater:IGCS:2015,
    author = {Zapater, Marina and Turk, Ata and Moya, Jos\'{e} M. and Ayala, Jos\'{e} L. and Coskun, Ayse K.},
    booktitle = {International Green and Sustainable Computing Conference (IGSC)},
    citeulike-article-id = {13697663},
    howpublished = {[Accepted, to appear in 2015]},
    keywords = {ee, greenlsi},
    month = dec,
    posted-at = {2015-08-08 12:52:47},
    priority = {2},
    title = {Dynamic Workload and Cooling Management in {High-Efficiency} Data Centers},
    year = {2015}
    }

  • R. Cattaneo, G. C. Durelli, J. Pagán, M. Zapater, M. Ferroni, A. Nacci, M. Vallejo, M. D. Santambrogio, J. L. Ayala, and S. Campanoni, “Power-awareness and smart-resource management in embedded computing systems,” in International conference on hardware/software codesign and system synthesis, 2015.
    [BibTeX]
    @inproceedings{Pagan:CODESS:2015,
    author = {Cattaneo, R. and Durelli, G. C. and Pag\'{a}n, Josu\'{e} and Zapater, Marina and Ferroni, M. and Nacci, A. and Vallejo, M. and Santambrogio, M. D. and Ayala, Jos\'{e} L. and Campanoni, Simone},
    booktitle = {International Conference on Hardware/Software Codesign and System Synthesis},
    citeulike-article-id = {13697661},
    howpublished = {[Accepted, to appear in 2015]},
    keywords = {artecs, ee, greenlsi},
    month = oct,
    posted-at = {2015-08-08 12:48:08},
    priority = {2},
    title = {Power-awareness and smart-resource management in embedded computing systems},
    year = {2015}
    }

  • J. C. Salinas-Hilburg, M. Zapater, J. L. Risco-Martín, J. M. Moya, and J. L. Ayala, “Using grammatical evolution techniques to model the dynamic power consumption of enterprise servers,” in International conference on complex, intelligent and software intensive systems, 2015.
    [BibTeX] [Abstract]

    The increasing demand for computational resources has led to a significant growth of data center facilities. A major concern has appeared regarding energy efficiency and consumption in servers and data centers. The use of flexible and scalable server power models is a must in order to enable proactive energy optimization strategies. This paper proposes the use of Evolutionary Computation to obtain a model for server dynamic power consumption. To accomplish this, we collect a significant number of server performance counters for a wide range of sequential and parallel applications, and obtain a model via Genetic Programming techniques. Our methodology enables the unsupervised generation of models for arbitrary server architectures, in a way that is robust to the type of application being executed in the server. With our generated models, we are able to predict the overall server power consumption for arbitrary workloads, outperforming previous approaches in the state-of-the-art.

    @inproceedings{jcsalinas:CISIS:2015,
    abstract = {The increasing demand for computational resources has led to a significant growth of data center facilities. A major concern has appeared regarding energy efficiency and consumption in servers and data centers. The use of flexible and scalable server power models is a must in order to enable proactive energy optimization strategies. This paper proposes the use of Evolutionary Computation to obtain a model for server dynamic power consumption. To accomplish this, we collect a significant number of server performance counters for a wide range of sequential and parallel applications, and obtain a model via Genetic Programming techniques. Our methodology enables the unsupervised generation of models for arbitrary server architectures, in a way that is robust to the type of application being executed in the server. With our generated models, we are able to predict the overall server power consumption for arbitrary workloads, outperforming previous approaches in the state-of-the-art.},
    author = {Salinas-Hilburg, Juan C. and Zapater, Marina and Risco-Mart\'{\i}n, Jos\'{e} L. and Moya, Jos\'{e} M. and Ayala, Jos\'{e} L.},
    booktitle = {International Conference on Complex, Intelligent and Software Intensive Systems},
    citeulike-article-id = {13696427},
    keywords = {ee, greenlsi},
    posted-at = {2015-08-06 18:14:47},
    priority = {2},
    publisher = {IEEE},
    title = {Using Grammatical Evolution Techniques to Model the Dynamic Power Consumption of Enterprise Servers},
    year = {2015}
    }

  • I. Aransay, M. Zapater, P. Arroba, and J. M. Moya, “A trust and reputation system for energy optimization in cloud data centers,” in Ieee international conference on cloud computing (cloud), 2015.
    [BibTeX] [Abstract]

    The increasing success of Cloud Computing applications and online services has contributed to the unsustainability of data center facilities in terms of energy consumption. Higher resource demand has increased the electricity required by computation and cooling resources, leading to power shortages and outages, specially in urban infrastructures. Current energy reduction strategies for Cloud facilities usually disregard the data center topology, the contribution of cooling consumption and the scalability of optimization strategies. Our work tackles the energy challenge by proposing a temperature-aware {VM} allocation policy based on a {Trust-and-Reputation} System ({TRS}). A {TRS} meets the requirements for inherently distributed environments such as data centers, and allows the implementation of autonomous and scalable {VM} allocation techniques. For this purpose, we model the relationships between the different computational entities, synthesizing this information in one single metric. This metric, called reputation, would be used to optimize the allocation of {VMs} in order to reduce energy consumption. We validate our approach with a state-of-the-art Cloud simulator using real Cloud traces. Our results show considerable reduction in energy consumption, reaching up to 46.16\% savings in computing power and 17.38\% savings in cooling, without {QoS} degradation while keeping servers below thermal redlining. Moreover, our results show the limitations of the {PUE} ratio as a metric for energy efficiency. To the best of our knowledge, this paper is the first approach in combining {Trust-and-Reputation} systems with Cloud Computing {VM} allocation.

    @inproceedings{iaransay:IEEECloud:2015,
    abstract = {The increasing success of Cloud Computing applications and online services has contributed to the unsustainability of data center facilities in terms of energy consumption. Higher resource demand has increased the electricity required by computation and cooling resources, leading to power shortages and outages, specially in urban infrastructures. Current energy reduction strategies for Cloud facilities usually disregard the data center topology, the contribution of cooling consumption and the scalability of optimization strategies. Our work tackles the energy challenge by proposing a temperature-aware {VM} allocation policy based on a {Trust-and-Reputation} System ({TRS}). A {TRS} meets the requirements for inherently distributed environments such as data centers, and allows the implementation of autonomous and scalable {VM} allocation techniques. For this purpose, we model the relationships between the different computational entities, synthesizing this information in one single metric. This metric, called reputation, would be used to optimize the allocation of {VMs} in order to reduce energy consumption. We validate our approach with a state-of-the-art Cloud simulator using real Cloud traces. Our results show considerable reduction in energy consumption, reaching up to 46.16\% savings in computing power and 17.38\% savings in cooling, without {QoS} degradation while keeping servers below thermal redlining. Moreover, our results show the limitations of the {PUE} ratio as a metric for energy efficiency. To the best of our knowledge, this paper is the first approach in combining {Trust-and-Reputation} systems with Cloud Computing {VM} allocation.},
    author = {Aransay, Ignacio and Zapater, Marina and Arroba, Patricia and Moya, Jos\'{e} M.},
    booktitle = {IEEE International Conference on Cloud Computing (CLOUD)},
    citeulike-article-id = {13696426},
    keywords = {cloud, ee, greenlsi},
    posted-at = {2015-08-06 18:11:43},
    priority = {2},
    publisher = {IEEE},
    title = {A Trust and Reputation system for energy optimization in Cloud data centers},
    year = {2015}
    }

  • M. Zapater, P. Arroba, J. Rodrigo, K. Herrero, and J. Fernandez, “Energy-Aware policies in ubiquitous computing facilities,” in Cloud computing with e-science applications, CRC Press, 2015, p. 267-286+. doi:10.1201/b18021-13
    [BibTeX] [Download PDF]
    @incollection{citeulike:13696422,
    author = {Zapater, Marina and Arroba, Patricia and Rodrigo, Jos\'{e}LuisAyala and Herrero, KatzalinOlcoz and Fernandez, Jos\'{e}ManuelMoya},
    booktitle = {Cloud Computing with e-Science Applications},
    citeulike-article-id = {13696422},
    citeulike-linkout-0 = {http://dx.doi.org/10.1201/b18021-13},
    comment = {doi:10.1201/b18021-13},
    day = {8},
    doi = {10.1201/b18021-13},
    isbn = {978-1-4665-9115-8},
    month = jan,
    pages = {267-286+},
    posted-at = {2015-08-06 17:52:52},
    priority = {2},
    publisher = {CRC Press},
    title = {{Energy-Aware} Policies in Ubiquitous Computing Facilities},
    url = {http://dx.doi.org/10.1201/b18021-13},
    year = {2015}
    }

  • M. Zapater, D. Fraga, P. Malagón, Z. Banković, and J. M. Moya, “Self-organizing maps versus growing neural gas in detecting anomalies in data centres,” Logic journal of igpl, p. jzv008+, 2015. doi:10.1093/jigpal/jzv008
    [BibTeX] [Abstract] [Download PDF]

    Reliability is one of the key performance factors in data centres. The out-of-scale energy costs of these facilities lead data centre operators to increase the ambient temperature of the data room to decrease cooling costs. However, increasing ambient temperature reduces the safety margins and can result in a higher number of anomalous events. Anomalies in the data centre need to be detected as soon as possible to optimize cooling efficiency and mitigate the harmful effects over servers. This article proposes the usage of clustering-based outlier detection techniques coupled with a trust and reputation system engine to detect anomalies in data centres. We show how self-organizing maps or growing neural gas can be applied to detect cooling and workload anomalies, respectively, in a real data centre scenario with very good detection and isolation rates, in a way that is robust to the malfunction of the sensors that gather server and environmental information.

    @article{Zapater:IGPL:2015,
    abstract = {Reliability is one of the key performance factors in data centres. The out-of-scale energy costs of these facilities lead data centre operators to increase the ambient temperature of the data room to decrease cooling costs. However, increasing ambient temperature reduces the safety margins and can result in a higher number of anomalous events. Anomalies in the data centre need to be detected as soon as possible to optimize cooling efficiency and mitigate the harmful effects over servers. This article proposes the usage of clustering-based outlier detection techniques coupled with a trust and reputation system engine to detect anomalies in data centres. We show how self-organizing maps or growing neural gas can be applied to detect cooling and workload anomalies, respectively, in a real data centre scenario with very good detection and isolation rates, in a way that is robust to the malfunction of the sensors that gather server and environmental information.},
    author = {Zapater, M. and Fraga, D. and Malag\'{o}n, P. and Bankovi\'{c}, Z. and Moya, J. M.},
    citeulike-article-id = {13581774},
    citeulike-linkout-0 = {http://dx.doi.org/10.1093/jigpal/jzv008},
    citeulike-linkout-1 = {http://jigpal.oxfordjournals.org/content/early/2015/04/01/jigpal.jzv008.abstract},
    citeulike-linkout-2 = {http://jigpal.oxfordjournals.org/content/early/2015/04/01/jigpal.jzv008.full.pdf},
    day = {2},
    doi = {10.1093/jigpal/jzv008},
    issn = {1368-9894},
    journal = {Logic Journal of IGPL},
    keywords = {anomalies, ee, greenlsi},
    month = apr,
    pages = {jzv008+},
    posted-at = {2015-08-06 17:35:39},
    priority = {2},
    publisher = {Oxford University Press},
    title = {Self-organizing Maps versus Growing Neural Gas in Detecting Anomalies in Data Centres},
    url = {http://dx.doi.org/10.1093/jigpal/jzv008},
    year = {2015}
    }

  • M. J. Colmenar, A. Cuesta, Z. Bankovic, J. L. Risco-Martin, M. Zapater, J. I. Hidalgo, J. L. Ayala, and J. M. Moya, “Comparative study of meta-heuristic 3D floorplanning algorithms,” Neurocomputing, vol. 150, pp. 67-81, 2015.
    [BibTeX] [Abstract]

    Constant necessity of improving performance has brought the invention of {3D} chips. The improvement is achieved due to the reduction of wire length, which results in decreased interconnection delay. However, {3D} stacks have less heat dissipation due to the inner layers, which leads to increased temperature and the appearance of hot spots. This problem can be mitigated through appropriate floorplanning. For this reason, in this work we present and compare five different solutions for floorplanning of {3D} chips. Each solution uses a different representation, and all are based on meta-heuristic algorithms, namely three of them are based on simulated annealing, while two other are based on evolutionary algorithms. The results show great capability of all the solutions in optimizing temperature and wire length, as they all exhibit significant improvements comparing to the benchmark floorplans.

    @article{citeulike:13337914,
    abstract = {Constant necessity of improving performance has brought the invention of {3D} chips. The improvement is achieved due to the reduction of wire length, which results in decreased interconnection delay. However, {3D} stacks have less heat dissipation due to the inner layers, which leads to increased temperature and the appearance of hot spots. This problem can be mitigated through appropriate floorplanning. For this reason, in this work we present and compare five different solutions for floorplanning of {3D} chips. Each solution uses a different representation, and all are based on meta-heuristic algorithms, namely three of them are based on simulated annealing, while two other are based on evolutionary algorithms. The results show great capability of all the solutions in optimizing temperature and wire length, as they all exhibit significant improvements comparing to the benchmark floorplans.},
    author = {Colmenar, J. Manuel and Cuesta, Alfredo and Bankovic, Zorana and Risco-Martin, Jose L. and Zapater, Marina and Hidalgo, Jose I. and Ayala, Jose L. and Moya, Jose M.},
    citeulike-article-id = {13337914},
    issn = {0925-2312},
    journal = {Neurocomputing},
    keywords = {ee, floorplanning, greenlsi},
    month = feb,
    pages = {67--81},
    posted-at = {2014-08-26 13:33:18},
    priority = {2},
    title = {Comparative study of meta-heuristic {3D} floorplanning algorithms},
    volume = {150},
    year = {2015}
    }

2014

  • P. Arroba, J. Risco-Martín, M. Zapater, J. Moya, and J. Ayala, “Enhancing regression models for complex systems using evolutionary techniques for feature engineering,” , pp. 1-15, 2014. doi:10.1007/s10723-014-9313-8
    [BibTeX] [Abstract] [Download PDF]

    This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer’s expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98 \%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.

    @article{Arroba:JGRID:2014,
    abstract = {This work proposes an automatic methodology for modeling complex systems. Our methodology is based on the combination of Grammatical Evolution and classical regression to obtain an optimal set of features that take part of a linear and convex model. This technique provides both Feature Engineering and Symbolic Regression in order to infer accurate models with no effort or designer's expertise requirements. As advanced Cloud services are becoming mainstream, the contribution of data centers in the overall power consumption of modern cities is growing dramatically. These facilities consume from 10 to 100 times more power per square foot than typical office buildings. Modeling the power consumption for these infrastructures is crucial to anticipate the effects of aggressive optimization policies, but accurate and fast power modeling is a complex challenge for high-end servers not yet satisfied by analytical approaches. For this case study, our methodology minimizes error in power prediction. This work has been tested using real Cloud applications resulting on an average error in power estimation of 3.98 \%. Our work improves the possibilities of deriving Cloud energy efficient policies in Cloud data centers being applicable to other computing environments with similar characteristics.},
    author = {Arroba, Patricia and Risco-Mart\'{\i}n, Jos\'{e}L and Zapater, Marina and Moya, Jos\'{e}M and Ayala, Jos\'{e}L},
    booktitle = {Journal of Grid Computing},
    citeulike-article-id = {13696419},
    citeulike-linkout-0 = {http://dx.doi.org/10.1007/s10723-014-9313-8},
    citeulike-linkout-1 = {http://link.springer.com/article/10.1007/s10723-014-9313-8},
    doi = {10.1007/s10723-014-9313-8},
    keywords = {cloud, ee, greenlsi},
    pages = {1--15},
    posted-at = {2015-08-06 17:41:38},
    priority = {2},
    publisher = {Springer Netherlands},
    title = {Enhancing Regression Models for Complex Systems Using Evolutionary Techniques for Feature Engineering},
    url = {http://dx.doi.org/10.1007/s10723-014-9313-8},
    year = {2014}
    }

  • M. Zapater, O. Tuncer, J. Ayala, J. Moya, K. Vaidyanathan, K. Gross, and A. K. Coskun, “Leakage-Aware cooling management for improving server energy efficiency,” Ieee transactions on parallel distributed systems, vol. pp, pp. 1-14, 2014. doi:10.1109/tpds.2014.2361519
    [BibTeX] [Abstract] [Download PDF]

    The computational and cooling power demands of enterprise servers are increasing at an unsustainable rate. Understanding the relationship between computational power, temperature, leakage, and cooling power is crucial to enable energy-efficient operation at the server and data center levels. This paper develops empirical models to estimate the contributions of static and dynamic power consumption in enterprise servers for a wide range of workloads, and analyzes the interactions between temperature, leakage, and cooling power for various workload allocation policies. We propose a cooling management policy that minimizes the server energy consumption by setting the optimum fan speed during runtime. Our experimental results on a presently shipping enterprise server demonstrate that including leakage awareness in workload and cooling management provides additional energy savings without any impact on performance.

    @article{Zapater:TPDS:2014,
    abstract = {The computational and cooling power demands of enterprise servers are increasing at an unsustainable rate. Understanding the relationship between computational power, temperature, leakage, and cooling power is crucial to enable energy-efficient operation at the server and data center levels. This paper develops empirical models to estimate the contributions of static and dynamic power consumption in enterprise servers for a wide range of workloads, and analyzes the interactions between temperature, leakage, and cooling power for various workload allocation policies. We propose a cooling management policy that minimizes the server energy consumption by setting the optimum fan speed during runtime. Our experimental results on a presently shipping enterprise server demonstrate that including leakage awareness in workload and cooling management provides additional energy savings without any impact on performance.},
    author = {Zapater, Marina and Tuncer, Ozan and Ayala, Jose and Moya, Jose and Vaidyanathan, Karthikeyan and Gross, Kenny and Coskun, Ayse K.},
    citeulike-article-id = {13696417},
    citeulike-linkout-0 = {http://dx.doi.org/10.1109/tpds.2014.2361519},
    citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=6915867},
    doi = {10.1109/tpds.2014.2361519},
    institution = {Marina Zapater is with the (CEI Campus Moncloa UCM-UPM, Madrid 28040, Spain (e-mail: marina@die.upm.es).},
    issn = {1045-9219},
    journal = {IEEE Transactions on Parallel Distributed Systems},
    keywords = {ee, greenlsi},
    month = dec,
    pages = {1--14},
    posted-at = {2015-08-06 17:38:57},
    priority = {2},
    publisher = {IEEE},
    title = {{Leakage-Aware} Cooling Management for Improving Server Energy Efficiency},
    url = {http://dx.doi.org/10.1109/tpds.2014.2361519},
    volume = {pp},
    year = {2014}
    }

  • P. Arroba, J. L. Risco-Martín, M. Zapater, J. M. Moya, J. L. Ayala, and K. Olcoz, “Evolutionary power modeling for high-end servers in cloud data centers,” in Mathematical modelling in engineering & human behaviour, 2014.
    [BibTeX]
    @inproceedings{Arroba:MMEHB:2014,
    author = {Arroba, Patricia and Risco-Mart\'{\i}n, Jose L. and Zapater, Marina and Moya, Jose M. and Ayala, Jose L. and Olcoz, Katzalin},
    booktitle = {Mathematical Modelling in Engineering \& Human Behaviour},
    citeulike-article-id = {13337906},
    keywords = {cloud, ee, greendisc, greenlsi},
    posted-at = {2014-08-26 13:26:29},
    priority = {2},
    title = {Evolutionary Power Modeling for High-end Servers in Cloud Data Centers},
    year = {2014}
    }

  • M. Zapater, J. L. Ayala, and J. M. Moya, “Proactive and reactive thermal aware optimization techniques to minimize the environmental impact of data centers,” in Design automation conference, 2014.
    [BibTeX]
    @inproceedings{Zapater:DAC:2014,
    author = {Zapater, Marina and Ayala, Jose L. and Moya, Jose M.},
    booktitle = {Design Automation Conference},
    citeulike-article-id = {13337901},
    keywords = {ee, greendisc, greenlsi},
    posted-at = {2014-08-26 13:23:47},
    priority = {2},
    series = {DAC'14},
    title = {Proactive and Reactive Thermal Aware Optimization Techniques to Minimize the Environmental Impact of Data Centers},
    year = {2014}
    }

  • P. Arroba, J. L. Risco-Martín, M. Zapater, J. M. Moya, J. L. Ayala, and K. Olcoz, “Server power modeling for Run-Time energy optimization of cloud computing facilities,” in International conference on sustainability in energy and buildings, 2014.
    [BibTeX]
    @inproceedings{citeulike:13166637,
    author = {Arroba, Patricia and Risco-Mart\'{\i}n, Jos\'{e} L. and Zapater, Marina and Moya, Jos\'{e} M. and Ayala, Jos\'{e} L. and Olcoz, Katzalin},
    booktitle = {International Conference on Sustainability in Energy and Buildings},
    citeulike-article-id = {13166637},
    keywords = {ee, greendisc, greenlsi},
    posted-at = {2014-05-12 17:16:37},
    priority = {2},
    title = {Server Power Modeling for {Run-Time} Energy Optimization of Cloud Computing Facilities},
    year = {2014}
    }

2013

  • M. Zapater, P. Malagón, J. de Goyeneche, and J. M. Moya, “Project-Based learning and agile methodologies in electronic courses: effect of student population and open issues,” Electronics journal, vol. 17, iss. 2, pp. 82-88, 2013. doi:10.7251/ELS1317082Z
    [BibTeX] [Abstract] [Download PDF]

    {Project-Based} Learning ({PBL}) and Agile methodologies have proven to be very interesting instructional strategies in Electronics and Engineering education, because they provide practical learning skills that help students understand the basis of electronics. In this paper we analyze two courses, one belonging to a Master in Electronic Engineering and one to a Bachelor in Telecommunication Engineering that apply {Agile-PBL} methodologies, and compare the results obtained in both courses with a traditional laboratory course. Our results support previous work stating that {Agile-PBL} methodologies increase student satisfaction. However, we also highlight some open issues that negatively affect the implementation of these methodologies, such as planning overhead or accidental complexity. Moreover, we show how differences in the student population, mostly related to the time spent on-campus, their commitment to the course or part-time dedication, have an impact on the benefits of {Agile-PBL} methods. In these cases, {Agile-PBL} methodologies by themselves are not enough and need to be combined with other techniques to increase student motivation.

    @article{mzapater:2013:electronics,
    abstract = {{Project-Based} Learning ({PBL}) and Agile methodologies have proven to be very interesting instructional strategies
    in Electronics and Engineering education, because they provide
    practical learning skills that help students understand the basis of electronics. In this paper we analyze two courses, one belonging to a Master in Electronic Engineering and one to a
    Bachelor in Telecommunication Engineering that apply {Agile-PBL} methodologies, and compare the results obtained in both courses with a traditional laboratory course. Our results support previous work stating that {Agile-PBL} methodologies increase
    student satisfaction. However, we also highlight some open issues that negatively affect the implementation of these methodologies, such as planning overhead or accidental complexity. Moreover, we show how differences in the student population, mostly related
    to the time spent on-campus, their commitment to the course or part-time dedication, have an impact on the benefits of {Agile-PBL} methods. In these cases, {Agile-PBL} methodologies by themselves are not enough and need to be combined with other techniques to increase student motivation.},
    author = {Zapater, Marina and Malag\'{o}n, Pedro and de Goyeneche, Juan-Mariano and Moya, Jos\'{e} M.},
    citeulike-article-id = {13077862},
    citeulike-linkout-0 = {http://dx.doi.org/10.7251/ELS1317082Z},
    doi = {10.7251/ELS1317082Z},
    journal = {Electronics Journal},
    keywords = {education},
    month = dec,
    number = {2},
    pages = {82--88},
    posted-at = {2014-03-03 11:00:51},
    priority = {2},
    title = {{Project-Based} Learning and Agile Methodologies in Electronic Courses: Effect of Student Population and Open Issues},
    url = {http://dx.doi.org/10.7251/ELS1317082Z},
    volume = {17},
    year = {2013}
    }

  • M. Zapater, P. Arroba, J. L. Ayala, J. M. Moya, and K. Olcoz, “A novel energy-driven computing paradigm for e-health scenarios,” Future generation computer systems, 2013. doi:10.1016/j.future.2013.12.012
    [BibTeX] [Abstract] [Download PDF]

    A first-rate {e-Health} system saves lives, provides better patient care, allows complex but useful epidemiologic analysis and saves money. However, there may also be concerns about the costs and complexities associated with e-health implementation, and the need to solve issues about the energy footprint of the high-demanding computing facilities. This paper proposes a novel and evolved computing paradigm that: (i) provides the required computing and sensing resources; (ii) allows the population-wide diffusion; (iii) exploits the storage, communication and computing services provided by the Cloud; (iv) tackles the energy-optimization issue as a first-class requirement, taking it into account during the whole development cycle. The novel computing concept, and the multi-layer top-down energy-optimization methodology, obtain promising results in a realistic scenario for cardiovascular tracking and analysis, making the Home Assisted Living a reality.

    @article{ZAA+14,
    abstract = {A first-rate {e-Health} system saves lives, provides better patient care, allows complex but useful epidemiologic analysis and saves money. However, there may also be concerns about the costs and complexities associated with e-health implementation, and the need to solve issues about the energy footprint of the high-demanding computing facilities. This paper proposes a novel and evolved computing paradigm that: (i) provides the required computing and sensing resources; (ii) allows the population-wide diffusion; (iii) exploits the storage, communication and computing services provided by the Cloud; (iv) tackles the energy-optimization issue as a first-class requirement, taking it into account during the whole development cycle. The novel computing concept, and the multi-layer top-down energy-optimization methodology, obtain promising results in a realistic scenario for cardiovascular tracking and analysis, making the Home Assisted Living a reality.},
    author = {Zapater, Marina and Arroba, Patricia and Ayala, Jos\'{e} L. and Moya, Jos\'{e} M. and Olcoz, Katzalin},
    citeulike-article-id = {12882215},
    citeulike-linkout-0 = {http://www.sciencedirect.com/science/article/pii/S0167739X13002768},
    citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.future.2013.12.012},
    doi = {10.1016/j.future.2013.12.012},
    howpublished = {online},
    issn = {0167-739X},
    journal = {Future Generation Computer Systems},
    keywords = {ami, analysis, centers, cloud, computing, data, dc, efficiency, energy, green, greenlsi, it, josem, management, population, resource},
    month = dec,
    number = {0},
    posted-at = {2014-01-05 12:32:18},
    priority = {5},
    title = {A novel energy-driven computing paradigm for e-health scenarios},
    url = {http://www.sciencedirect.com/science/article/pii/S0167739X13002768},
    year = {2013}
    }

  • J. Pagán, M. Zapater, Ó. Cubo, P. Arroba, V. Martín, and J. M. Moya, “A Cyber-Physical approach to combined HW-SW monitoring for improving energy efficiency in data centers,” in Conference on design of circuits and integrated systems, 2013.
    [BibTeX] [Abstract]

    {High-Performance} Computing, Cloud computing and next-generation applications such {e-Health} or Smart Cities have dramatically increased the computational demand of Data Centers. The huge energy consumption, increasing levels of {CO2} and the economic costs of these facilities represent a challenge for industry and researchers alike. Recent research trends propose the usage of holistic optimization techniques to jointly minimize Data Center computational and cooling costs from a multilevel perspective. This paper presents an analysis on the parameters needed to integrate the Data Center in a holistic optimization framework and leverages the usage of {Cyber-Physical} systems to gather workload, server and environmental data via software techniques and by deploying a non-intrusive Wireless Sensor Network ({WSN}). This solution tackles data sampling, retrieval and storage from a reconfigurable perspective, reducing the amount of data generated for optimization by a 68\% without information loss, doubling the lifetime of the {WSN} nodes and allowing runtime energy minimization techniques in a real scenario.

    @inproceedings{citeulike:12651885,
    abstract = {{High-Performance} Computing, Cloud computing and next-generation applications such {e-Health} or Smart Cities have dramatically increased the computational demand of Data Centers. The huge energy consumption, increasing levels of {CO2} and the economic costs of these facilities represent a challenge for industry and researchers alike. Recent research trends propose the usage of holistic optimization techniques to jointly minimize Data Center computational and cooling costs from a multilevel perspective. This paper presents an analysis on the parameters
    needed to integrate the Data Center in a holistic optimization framework and leverages the usage of {Cyber-Physical} systems to gather workload, server and environmental data via software techniques and by deploying a non-intrusive Wireless Sensor Network ({WSN}). This solution tackles data sampling, retrieval and storage from a reconfigurable perspective, reducing the amount of data generated for optimization by a 68\% without information loss, doubling the lifetime of the {WSN} nodes and allowing runtime energy minimization techniques in a real scenario.},
    author = {Pag\'{a}n, Josu\'{e} and Zapater, Marina and Cubo, \'{O}scar and Arroba, Patricia and Mart\'{\i}n, Vicente and Moya, Jos\'{e} M.},
    booktitle = {Conference on Design of Circuits and Integrated Systems},
    citeulike-article-id = {12651885},
    keywords = {cps, greenlsi, wsn},
    month = nov,
    posted-at = {2013-09-25 18:50:19},
    priority = {2},
    title = {A {Cyber-Physical} Approach to Combined {HW}-{SW} Monitoring for Improving Energy Efficiency in Data Centers},
    year = {2013}
    }

  • P. Arroba, M. Zapater, J. L. Ayala, J. M. Moya, K. Olcoz, and R. Hermida, “On the Leakage-Power modeling for optimal server operation,” in Jornadas sarteco, 2013.
    [BibTeX] [Abstract]

    Leakage power consumption is a component of the total power consumption in data centers that is not traditionally considered in the set-point temperature of the room. However, the effect of this power component, increased with temperature, can determine the savings associated with the careful management of the cooling system, as well as the reliability of the system. The work presented in this paper detects the need of addressing leakage power in order to achieve substantial savings in the energy consumption of servers. In particular, our work shows that, by a careful detection and management of two working regions (low and high impact of thermal-dependent leakage), energy consumption of the datacenter can be optimized by a reduction of the cooling budget.

    @inproceedings{citeulike:12651866,
    abstract = {Leakage power consumption is a component of the total power consumption in data centers that is not traditionally considered in the set-point temperature of the room. However, the effect of this power component, increased with temperature, can determine the savings associated with the careful management of the cooling system, as well as the reliability of the system. The work presented in this paper detects the need of addressing leakage power in order to achieve substantial savings in the energy
    consumption of servers. In particular, our work shows that, by a careful detection and management of two
    working regions (low and high impact of thermal-dependent leakage), energy consumption of the datacenter can be optimized by a reduction of the cooling
    budget.},
    author = {Arroba, Patricia and Zapater, Marina and Ayala, Jos\'{e} L. and Moya, Jos\'{e} M. and Olcoz, Katzalin and Hermida, Rom\'{a}n},
    booktitle = {Jornadas SARTECO},
    citeulike-article-id = {12651866},
    keywords = {greendisc, greenlsi, modeling},
    month = sep,
    posted-at = {2013-09-25 18:44:28},
    priority = {2},
    title = {On the {Leakage-Power} Modeling for Optimal Server Operation},
    year = {2013}
    }

  • M. Zapater, J. L. Ayala, J. M. Moya, K. Vaidyanathan, K. Gross, and Ayse, “Leakage and temperature aware server control for improving energy efficiency in data centers,” in Design, automation and test in europe, 2013.
    [BibTeX] [Abstract]

    Reducing the energy consumption for computation and cooling in servers is a major challenge considering the data center energy costs today. To ensure energy-efficient operation of servers in data centers, the relationship among computational power, temperature, leakage, and cooling power needs to be analyzed. By means of an innovative setup that enables monitoring and controlling the computing and cooling power consumption separately on a commercial enterprise server, this paper studies temperature-leakage-energy tradeoffs, obtaining an empirical model for the leakage component. Using this model, we design a controller that continuously seeks and settles at the optimal fan speed to minimize the energy consumption for a given workload. We run a customized dynamic load-synthesis tool to stress the system. Our proposed cooling controller achieves up to 9\% energy savings and {30W} reduction in peak power in comparison to the default cooling control scheme.

    @inproceedings{Zapater_DATE_2013,
    abstract = {Reducing the energy consumption for computation and cooling in servers is a major challenge considering the data center energy costs today. To ensure energy-efficient operation of servers in data centers, the relationship among computational power, temperature, leakage, and cooling power needs to be analyzed. By means of an innovative setup that enables
    monitoring and controlling the computing and cooling power consumption separately on a commercial enterprise server, this paper studies temperature-leakage-energy tradeoffs, obtaining an empirical model for the leakage component. Using this model, we design a controller that continuously seeks and settles at the
    optimal fan speed to minimize the energy consumption for a given workload. We run a customized dynamic load-synthesis tool to stress the system. Our proposed cooling controller achieves up to 9\% energy savings and {30W} reduction in peak power in comparison to the default cooling control scheme.},
    author = {Zapater, Marina and Ayala, Jos\'{e} L. and Moya, Jos\'{e} M. and Vaidyanathan, Kalyan and Gross, Kenny and Ayse},
    booktitle = {Design, Automation and Test in Europe},
    citeulike-article-id = {12231242},
    keywords = {cooling, dc, greenlsi},
    posted-at = {2013-04-01 18:11:43},
    priority = {2},
    series = {DATE'13},
    title = {Leakage and Temperature Aware Server Control for Improving Energy Efficiency in Data Centers},
    year = {2013}
    }

2012

  • M. Zapater, J. L. Ayala, and J. M. Moya, “GreenDisc: a HW/SW energy optimization framework in globally distributed computation,” in Ubiquitous computing and ambient intelligence, J. Bravo, D. López-de Ipiña, and F. Moya, Eds., Springer Berlin Heidelberg, 2012, pp. 1-8. doi:10.1007/978-3-642-35377-2_1
    [BibTeX] [Abstract] [Download PDF]

    In recent future, wireless sensor networks ({WSNs}) will experience a broad high-scale deployment (millions of nodes in the national area) with multiple information sources per node, and with very specific requirements for signal processing. In parallel, the broad range deployment of {WSNs} facilitates the definition and execution of ambitious studies, with a large input data set and high computational complexity. These computation resources, very often heterogeneous and driven on-demand, can only be satisfied by high-performance Data Centers ({DCs}). The high economical and environmental impact of the energy consumption in {DCs} requires aggressive energy optimization policies. These policies have been already detected but not successfully proposed. In this context, this paper shows the following on-going research lines and obtained results. In the field of {WSNs}: energy optimization in the processing nodes from different abstraction levels, including reconfigurable application specific architectures, efficient customization of the memory hierarchy, energy-aware management of the wireless interface, and design automation for signal processing applications. In the field of {DCs}: energy-optimal workload assignment policies in heterogeneous {DCs}, resource management policies with energy consciousness, and efficient cooling mechanisms that will cooperate in the minimization of the electricity bill of the {DCs} that process the data provided by the {WSNs}.

    @incollection{Zapater_UCAMI_2012,
    abstract = {In recent future, wireless sensor networks ({WSNs}) will experience a broad high-scale deployment (millions of nodes in the national area) with multiple information sources per node, and with very specific requirements for signal processing. In parallel, the broad range deployment of {WSNs} facilitates the definition and execution of ambitious studies, with a large input data set and high computational complexity. These computation resources, very often heterogeneous and driven on-demand, can only be satisfied by high-performance Data Centers ({DCs}). The high economical and environmental impact of the energy consumption in {DCs} requires aggressive energy optimization policies. These policies have been already detected but not successfully proposed.
    In this context, this paper shows the following on-going research lines and obtained results. In the field of {WSNs}: energy optimization in the processing nodes from different abstraction levels, including reconfigurable application specific architectures, efficient customization of the memory hierarchy, energy-aware management of the wireless interface, and design automation for signal processing applications. In the field of {DCs}: energy-optimal workload assignment policies in heterogeneous {DCs}, resource management policies with energy consciousness, and efficient cooling mechanisms that will cooperate in the minimization of the electricity bill of the {DCs} that process the data provided by the {WSNs}.},
    author = {Zapater, Marina and Ayala, Jos\'{e} L. and Moya, Jose M.},
    booktitle = {Ubiquitous Computing and Ambient Intelligence},
    citeulike-article-id = {11824300},
    citeulike-linkout-0 = {http://dx.doi.org/10.1007/978-3-642-35377-2\_1},
    doi = {10.1007/978-3-642-35377-2\_1},
    editor = {Bravo, Jos\'{e} and L\'{o}pez-de Ipi\~{n}a, Diego and Moya, Francisco},
    keywords = {ami, ee, greendisc, greenlsi},
    pages = {1--8},
    posted-at = {2012-12-04 18:52:00},
    priority = {0},
    publisher = {Springer Berlin Heidelberg},
    series = {Lecture Notes in Computer Science},
    title = {{GreenDisc}: A {HW}/{SW} Energy Optimization Framework in Globally Distributed Computation},
    url = {http://dx.doi.org/10.1007/978-3-642-35377-2\_1},
    year = {2012}
    }

  • M. Zapater, J. L. Ayala, and J. M. Moya, “Leveraging heterogeneity for energy minimization in data centers,” in Proceedings of the 2012 12th ieee/acm international symposium on cluster, cloud and grid computing (ccgrid 2012), Washington, DC, USA, 2012. doi:10.1109/CCGrid.2012.34
    [BibTeX] [Abstract] [Download PDF]

    Energy consumption in data centers is nowadays a critical objective because of its dramatic environmental and economic impact. Over the last years, several approaches have been proposed to tackle the energy/cost optimization problem, but most of them have failed on providing an analytical model to target both the static and dynamic optimization domains for complex heterogeneous data centers. This paper proposes and solves an optimization problem for the energy-driven configuration of a heterogeneous data center. It also advances in the proposition of a new mechanism for task allocation and distribution of workload. The combination of both approaches outperforms previous published results in the field of energy minimization in heterogeneous data centers and scopes a promising area of research.

    @inproceedings{Zapater:2012:CCGrid,
    abstract = {Energy consumption in data centers is nowadays a critical objective because of its dramatic environmental and economic impact. Over the last years, several approaches have been proposed to tackle the energy/cost optimization problem, but most of them have failed on providing an analytical model to target both the static and dynamic optimization domains for complex heterogeneous data centers. This paper proposes and solves an optimization problem for the energy-driven configuration of a heterogeneous data center. It also advances in the proposition of a new mechanism for task allocation and distribution of workload. The combination of both approaches outperforms previous published results in the field of energy minimization in heterogeneous data centers and scopes a promising area of research.},
    address = {Washington, DC, USA},
    author = {Zapater, Marina and Ayala, Jose L. and Moya, Jose M.},
    booktitle = {Proceedings of the 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012)},
    citeulike-article-id = {11736902},
    citeulike-linkout-0 = {http://dx.doi.org/10.1109/CCGrid.2012.34},
    doi = {10.1109/CCGrid.2012.34},
    isbn = {978-0-7695-4691-9},
    keywords = {dc, greenlsi},
    posted-at = {2012-11-20 22:34:56},
    priority = {0},
    publisher = {IEEE Computer Society},
    series = {CCGRID '12},
    title = {Leveraging Heterogeneity for Energy Minimization in Data Centers},
    url = {http://dx.doi.org/10.1109/CCGrid.2012.34},
    year = {2012}
    }

  • P. Malagón, J. de Goyeneche, M. Zapater, J. M. Moya, and Z. Banković, “Compiler optimizations as a countermeasure against Side-Channel analysis in MSP430-based devices,” Sensors, vol. 12, iss. 6, pp. 7994-8012, 2012. doi:10.3390/s120607994
    [BibTeX] [Abstract] [Download PDF]

    Ambient Intelligence ({AmI}) requires devices everywhere, dynamic and massively distributed networks of low-cost nodes that, among other data, manage private information or control restricted operations. {MSP430}, a 16-bit microcontroller, is used in {WSN} platforms, as the {TelosB}. Physical access to devices cannot be restricted, so attackers consider them a target of their malicious attacks in order to obtain access to the network. Side-channel analysis ({SCA}) easily exploits leakages from the execution of encryption algorithms that are dependent on critical data to guess the key value. In this paper we present an evaluation framework that facilitates the analysis of the effects of compiler and backend optimizations on the resistance against statistical {SCA}. We propose an optimization-based software countermeasure that can be used in current low-cost devices to radically increase resistance against statistical {SCA}, analyzed with the new framework.

    @article{citeulike:10853003,
    abstract = {Ambient Intelligence ({AmI}) requires devices everywhere, dynamic and massively distributed networks of low-cost nodes that, among other data, manage private information or control restricted operations. {MSP430}, a 16-bit microcontroller, is used in {WSN} platforms, as the {TelosB}. Physical access to devices cannot be restricted, so attackers consider them a target of their malicious attacks in order to obtain access to the network. Side-channel analysis ({SCA}) easily exploits leakages from the execution of encryption algorithms that are dependent on critical data to guess the key value. In this paper we present an evaluation framework that facilitates the analysis of the effects of compiler and backend optimizations on the resistance against statistical {SCA}. We propose an optimization-based software countermeasure that can be used in current low-cost devices to radically increase resistance against statistical {SCA}, analyzed with the new framework.},
    author = {Malag\'{o}n, Pedro and de Goyeneche, Juan-Mariano and Zapater, Marina and Moya, Jos\'{e} M. and Bankovi\'{c}, Zorana},
    citeulike-article-id = {10853003},
    citeulike-linkout-0 = {http://dx.doi.org/10.3390/s120607994},
    day = {08},
    doi = {10.3390/s120607994},
    issn = {1424-8220},
    journal = {Sensors},
    keywords = {security},
    month = jun,
    number = {6},
    pages = {7994--8012},
    posted-at = {2012-11-19 23:30:31},
    priority = {2},
    title = {Compiler Optimizations as a Countermeasure against {Side-Channel} Analysis in {MSP430}-Based Devices},
    url = {http://dx.doi.org/10.3390/s120607994},
    volume = {12},
    year = {2012}
    }

  • M. Zapater, C. Sanchez, J. L. Ayala, J. M. Moya, and J. L. Risco-Martín, “Ubiquitous green computing techniques for high demand applications in smart environments,” Sensors, vol. 12, iss. 8, pp. 10659-10677, 2012. doi:10.3390/s120810659
    [BibTeX] [Abstract] [Download PDF]

    Ubiquitous sensor network deployments, such as the ones found in Smart cities and Ambient intelligence applications, require constantly increasing high computational demands in order to process data and offer services to users. The nature of these applications imply the usage of data centers. Research has paid much attention to the energy consumption of the sensor nodes in {WSNs} infrastructures. However, supercomputing facilities are the ones presenting a higher economic and environmental impact due to their very high power consumption. The latter problem, however, has been disregarded in the field of smart environment services. This paper proposes an energy-minimization workload assignment technique, based on heterogeneity and application-awareness, that redistributes low-demand computational tasks from high-performance facilities to idle nodes with low and medium resources in the {WSN} infrastructure. These non-optimal allocation policies reduce the energy consumed by the whole infrastructure and the total execution time.

    @article{citeulike:11021307,
    abstract = {Ubiquitous sensor network deployments, such as the ones found in Smart cities and Ambient intelligence applications, require constantly increasing high computational demands in order to process data and offer services to users. The nature of these applications imply the usage of data centers. Research has paid much attention to the energy consumption of the sensor nodes in {WSNs} infrastructures. However, supercomputing facilities are the ones presenting a higher economic and environmental impact due to their very high power consumption. The latter problem, however, has been disregarded in the field of smart environment services. This paper proposes an energy-minimization workload assignment technique, based on heterogeneity and application-awareness, that redistributes low-demand computational tasks from high-performance facilities to idle nodes with low and medium resources in the {WSN} infrastructure. These non-optimal allocation policies reduce the energy consumed by the whole infrastructure and the total execution time.},
    author = {Zapater, Marina and Sanchez, Cesar and Ayala, Jose L. and Moya, Jose M. and Risco-Mart\'{\i}n, Jos\'{e} L.},
    citeulike-article-id = {11021307},
    citeulike-linkout-0 = {http://dx.doi.org/10.3390/s120810659},
    day = {03},
    doi = {10.3390/s120810659},
    issn = {1424-8220},
    journal = {Sensors},
    keywords = {computing, green, greenlsi, wsn},
    month = aug,
    number = {8},
    pages = {10659--10677},
    posted-at = {2012-11-19 23:29:55},
    priority = {2},
    title = {Ubiquitous Green Computing Techniques for High Demand Applications in Smart Environments},
    url = {http://dx.doi.org/10.3390/s120810659},
    volume = {12},
    year = {2012}
    }

2011

  • Á. Araujo, J. M. Moya, P. Malagón, E. Romero, and M. Zapater, “Student motivation: taking marks out of the mix,” in Innovations 2011 – world innovations in engineering education and research, iNEER, 2011.
    [BibTeX]
    @incollection{Araujo_Innovations_2011,
    author = {Araujo, \'{A}lvaro and Moya, Jos\'{e} M. and Malag\'{o}n, Pedro and Romero, Elena and Zapater, Marina},
    booktitle = {Innovations 2011 – World Innovations in Engineering Education and Research},
    citeulike-article-id = {11737379},
    keywords = {teaching},
    posted-at = {2012-11-21 07:02:58},
    priority = {0},
    publisher = {iNEER},
    title = {Student Motivation: Taking marks Out of the Mix},
    year = {2011}
    }

  • M. Zapater, J. de Goyeneche, J. M. Moya, P. Malagón, and Z. Bankovic, “Thermal-Aware optimization of heterogeneous systems,” in 26th conference on design of circuits and integrated systems, 2011.
    [BibTeX]
    @inproceedings{Zapater_DCIS_2011,
    author = {Zapater, Marina and de Goyeneche, Juan-Mariano and Moya, Jos\'{e} M. and Malag\'{o}n, Pedro and Bankovic, Zorana},
    booktitle = {26th Conference on Design of Circuits and Integrated Systems},
    citeulike-article-id = {11737371},
    keywords = {ee, greenlsi},
    month = nov,
    posted-at = {2012-11-21 06:57:55},
    priority = {0},
    title = {{Thermal-Aware} Optimization of Heterogeneous Systems},
    year = {2011}
    }

  • M. Zapater, P. Arroba, J. M. Moya, and Z. Banković, “A State-of-the-Art on energy efficiency in today’s datacentres: researcher’s contributions and practical approaches,” Upgrade, vol. 12, iss. 4, pp. 67-74, 2011.
    [BibTeX] [Download PDF]
    @article{Zapater_CEPIS_2011,
    author = {Zapater, Marina and Arroba, Patricia and Moya, Jos\'{e} M. and Bankovi\'{c}, Zorana},
    citeulike-article-id = {11737365},
    citeulike-linkout-0 = {http://www.cepis.org/upgrade/media/zapater\_2011\_41.pdf},
    issn = {1684-5285},
    journal = {UPGRADE},
    keywords = {dc, greenlsi, state-of-art},
    number = {4},
    pages = {67--74},
    posted-at = {2012-11-21 06:53:37},
    priority = {2},
    publisher = {CEPIS},
    title = {A {State-of-the-Art} on Energy Efficiency in Today's Datacentres: Researcher's Contributions and Practical Approaches},
    url = {http://www.cepis.org/upgrade/media/zapater\_2011\_41.pdf},
    volume = {12},
    year = {2011}
    }

  • I. Álvarez, P. Malagón, M. Zapater, J. de Goyeneche, and J. M. Moya, “RFID performance in localization systems,” in Iwaal, 2011, pp. 73-78. doi:10.1007/978-3-642-21303-8_10
    [BibTeX] [Download PDF]
    @inproceedings{DBLP:conf/iwann/AlvarezMZGM11,
    author = {{\'{A}}lvarez, Iv{\'{a}}n and Malag{\'{o}}n, Pedro and Zapater, Marina and de Goyeneche, Juan-Mariano and Moya, Jos{\'{e}} M.},
    booktitle = {IWAAL},
    citeulike-article-id = {11733150},
    citeulike-linkout-0 = {http://link.springer.com/chapter/10.1007\%2F978-3-642-21303-8\_10},
    citeulike-linkout-1 = {http://dx.doi.org/10.1007/978-3-642-21303-8\_10},
    doi = {10.1007/978-3-642-21303-8\_10},
    editor = {Bravo, Jos{\'{e}} and Herv{\'{a}}s, Ram{\'{o}}n and Villarreal, Vladimir},
    keywords = {ami},
    pages = {73--78},
    posted-at = {2012-11-20 20:28:45},
    priority = {2},
    publisher = {Springer},
    series = {Lecture Notes in Computer Science},
    title = {{RFID} Performance in Localization Systems},
    url = {http://link.springer.com/chapter/10.1007\%2F978-3-642-21303-8\_10},
    volume = {6693},
    year = {2011}
    }

2010

  • M. Zapater, J. L. Risco, J. L. Ayala, and J. M. Moya, “Combined Dynamic-Static approach for Thermal-Awareness in heterogeneous data centers,” in Iwia, , 2010.
    [BibTeX]
    @inbook{Zapater_IWIA_2010,
    author = {Zapater, Marina and Risco, Jose L. and Ayala, Jose L. and Moya, Jose M.},
    booktitle = {IWIA},
    citeulike-article-id = {11737377},
    comment = {to appear on 2012},
    keywords = {dc, greenlsi},
    posted-at = {2012-11-21 07:01:51},
    priority = {0},
    title = {Combined {Dynamic-Static} Approach for {Thermal-Awareness} in Heterogeneous Data Centers},
    year = {2010}
    }

  • M. Zapater, Z. Bankovic, J. D. Goyeneche, A. Araujo, D. Fraga, J. C. Vallejo, E. Romero, J. Blesa, D. Villanueva, and O. Nieto-taladriz, “System simulation platform for the design of the SORU reconfigurable coprocessor,” in 25th conference on design of circuits and integrated systems, 2010.
    [BibTeX]
    @inproceedings{Zapater_DCIS_2010,
    author = {Zapater, Marina and Bankovic, Zorana and Goyeneche, Juan-mariano D. and Araujo, Alvaro and Fraga, David and Vallejo, Juan C. and Romero, Elena and Blesa, Javier and Villanueva, Daniel and Nieto-taladriz, Octavio},
    booktitle = {25th Conference on Design of Circuits and Integrated Systems},
    citeulike-article-id = {11737375},
    keywords = {security},
    month = nov,
    posted-at = {2012-11-21 07:01:01},
    priority = {0},
    title = {System Simulation Platform for the Design of the {SORU} Reconfigurable Coprocessor},
    year = {2010}
    }