MODI: From planning towards operation: Data-driven predictive mode-based control algorithms for energy savings in buildings

Energy and Buildings, vol. 353, pp. 116845

Abstract

The operations of buildings contribute significantly to global energy consumption and emissions, accounting for 30% of global final energy use and 26% of energy-related emissions. To address this impact, enhancing building energy efficiency is critical. This paper introduces a novel data-driven approach that extends the application of mode-based control algorithms from the planning phase to the operational phase in building energy systems. By integrating Long Short-Term Memory (LSTM) networks for predictive modeling and hierarchical fuzzy logic controllers (HFLCs) for control implementation, the proposed method aims to optimize system operation by deciding appropriate operating modes. This methodology involves training LSTM-based predictors using operational data to forecast state variables and a data-driven process for automatic generation of HFLC. Additionally, a distributed implementation strategy ensures real-time operation by utilizing cloud platforms for prediction tasks and local Programmable Logic Controllers for control execution. A case study on a residential building’s ground source heat pump system demonstrates the effectiveness of this approach during the simulation phase, achieving significant reductions in 15% electricity consumption and 24% costs compared to the real-world operations.

Authors 4

1. Xiaoye Cai corresponding Aachen E.ON Energy Research Center Institute for Energy Efficient Buildings and Indoor Climate

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, E.ON Energy Research Center, Institute for Energy Efficient Buildings and Indoor Climate (EBC), Mathieustrasse 10, Aachen, 52064, Germany

2. Shiyao Ju Aachen E.ON Energy Research Center Institute for Energy Efficient Buildings and Indoor Climate

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, E.ON Energy Research Center, Institute for Energy Efficient Buildings and Indoor Climate (EBC), Mathieustrasse 10, Aachen, 52064, Germany

3. Martin Rätz Aachen E.ON Energy Research Center Institute for Energy Efficient Buildings and Indoor Climate

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, E.ON Energy Research Center, Institute for Energy Efficient Buildings and Indoor Climate (EBC), Mathieustrasse 10, Aachen, 52064, Germany

4. Dirk Müller Aachen E.ON Energy Research Center Institute for Energy Efficient Buildings and Indoor Climate

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, E.ON Energy Research Center, Institute for Energy Efficient Buildings and Indoor Climate (EBC), Mathieustrasse 10, Aachen, 52064, Germany