Julian Ruddick, Cedric De Cauwer, Thierry Coosemans, Maarten Messagie
原文摘要
As dwellings electrify and more complex electricity pricing spreads in Belgium, the question arises: What are the potential benefits of installing an advanced energy management systems in an electrified Belgian dwelling ? To answer this question, we simulate 500 representative Belgian dwellings in which fossil systems are replaced by controllable electric technologies: space heating via air-to-air heat pumps, domestic hot water via electric boilers, and private transport via electric vehicles with home chargers. Photovoltaic systems are assigned according to current adoption rates. We evaluate two advanced energy management systems (EMS): model predictive control (MPC) and TreeC, a machine learning method using decision trees to model the EMS strategy. These are compared to a rule-based controller (RBC) that mimics default operation and an MPC with perfect forecasts (MPC P) as an upper bound. Performance for these EMSs is assessed for 2023 under a real contract with hourly prices and a monthly peak tariff. Average annual savings versus RBC are 82.5 EUR, 116.6 EUR, and 177.4 EUR for TreeC, MPC, and MPC P, respectively. All EMSs deliver similar thermal comfort (26-31 Kh). MPC saves more, while TreeC achieves higher EV charge completion (93.3% vs 88.8% for MPC, with a max charge of 95%) and a smoother aggregate load across the 500 dwellings. Savings remain modest relative to EMS purchase (280-680 EUR) and subscription (0-360 EUR/year) costs which is not favourable towards widespread adoption. The data and code to reproduce this study are available at https://github.com/EVERGi/should_belgians_install_advanced_ems_paper.
The transition from fossil fuels presents significant challenges in energy management. To ensure a sustainable energy future, it is crucial to reduce energy consumption when possible and to synchronize electricity consumption and storage with the production from sources with low greenhouse gas emissions. This thesis explores a variety of energy management methods used to manage batteries, heat pumps, and other energy-related systems. The thesis presents three simulation cases alongside one real-world experiment to compare energy management done through simple rules, optimization, and machine learning methods. Furthermore, this thesis introduces TreeC, a novel machine learning-based method that learns understandable yet efficient energy management strategies, applicable to many cases. The three key contributions of this thesis can be summarized as follows: 1) The developed TreeC method demonstrates competitive performance compared to a variety of energy management approaches, such as model predictive control and reinforcement learning, across a diverse set of energy management problems. The understandability of TreeC's energy management strategies greatly improves the transparency and trustworthiness of machine learning-based energy management. 2) The real-world experiment highlights the need to validate energy management methods on actual hardware and not solely on simulations. Both TreeC and model predictive control performed worse than in simulations, due to, respectively, insufficiently representative training data and the real-time input data not being reliable enough. 3) Energy management algorithms reduce costs in electrified Belgian dwellings, particularly in poorly insulated dwellings, electric vehicle chargers, and photovoltaic installations. However, on average, these cost savings do not yet outweigh the current costs and effort required to implement such algorithms.