A Data-Driven Approach for Enhancing the Efficiency in Chiller Plants: A Hospital Case Study
Serafín Alonso,
Antonio Morán,
Miguel Ángel Prada,
Perfecto Reguera,
Juan José Fuertes,
Manuel Domínguez
Affiliations
Serafín Alonso
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Antonio Morán
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Miguel Ángel Prada
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Perfecto Reguera
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Juan José Fuertes
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Manuel Domínguez
Grupo de Investigación en Supervisión, Control y Automatización de Procesos Industriales (SUPPRESS), Esc. de Ing. Industrial e Informática, Universidad de León, Campus de Vegazana s/n, 24007 León, Spain
Large buildings cause more than 20% of the global energy consumption in advanced countries. In buildings such as hospitals, cooling loads represent an important percentage of the overall energy demand (up to 44%) due to the intensive use of heating, ventilation and air conditioning (HVAC) systems among other key factors, so their study should be considered. In this paper, we propose a data-driven analysis for improving the efficiency in multiple-chiller plants. Coefficient of performance (COP) is used as energy efficiency indicator. Data analysis, based on aggregation operations, filtering and data projection, allows us to obtain knowledge from chillers and the whole plant, in order to define and tune management rules. The plant manager software (PMS) that implements those rules establishes when a chiller should be staged up/down and which chiller should be started/stopped according different efficiency criteria. This approach has been applied on the chiller plant at the Hospital of León.
