Demand Side
Demand-side management (DSM) focuses on optimizing energy consumption to improve grid stability and integrate renewable sources. Current research emphasizes developing intelligent control systems for residential and community-level energy resources, leveraging reinforcement learning algorithms (including those based on neural networks and decision trees) to manage diverse loads like batteries, electric vehicles, and heat pumps while maintaining user comfort and explainability. These advancements aim to unlock the flexibility inherent in distributed energy resources, improving grid efficiency and reducing carbon emissions. The ultimate goal is to create more resilient and sustainable energy systems through data-driven, adaptable control strategies.
Papers
Explainable Reinforcement Learning-based Home Energy Management Systems using Differentiable Decision Trees
Gargya Gokhale, Bert Claessens, Chris Develder
Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers
Gargya Gokhale, Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder