Miguel Molina-Solana

The increasing computational capabilities for information acquisition and storage have led to a massive increase of available data in different areas of interest to Energy Management; e.g. smart grid monitoring, equipment consumption measurement, user activity identification, supply and demand estimation, and building operation logging. Exploiting such big data offers a great opportunity to gain insights into many aspects of buildings energy performance, and therefore, to support the implementation of solid data-based policies for improving energy efficiency. Data Science comprises a set of techniques and technologies for building system models from large data volumes, with the aim of discovering and predicting trends, groups, parameter correlations, anomalies, exceptions, and other relevant patterns. Data Science has been identified as essential to address several energy efficiency challenges, such as demand prediction, operation optimization and network maintenance, to name some of them. This paper provides an introduction to the fundamentals of Data Science methods and their application to these problems. To illustrate the role Data Science in Building Energy Management, we present an illustrative example in the context of efficient building operation and maintenance.

@inproceedings{IEECB2016_Romero,
  title = {Advances in Data Science for Building Energy Management},
  author = {G\'omez-Romero, Juan and Ruiz, M.D. and Fern\'andez-Basso, C. and Molina-Solana, Miguel and Ros, Maria and Martin-Bautista, M.J.},
  booktitle = {Proc. 9th International Conference Improving Energy Efficiency in Commercial Buildings and Smart Communities (IEECB&SC’16)},
  year = {2016},
  address = {Frankfurt, Germany},
  month = mar,
  organization = {Messe Frankfurt and the European Commission DG JRC},
  timestamp = {121},
  url = {http://iet.jrc.ec.europa.eu/energyefficiency/node/9096}
}