Control Policy Correction Framework for Reinforcement Learning-based Energy Arbitrage Strategies

no code implementations • 29 Apr 2024 • Seyed Soroush Karimi Madahi, Gargya Gokhale, Marie-Sophie Verwee, Bert Claessens, Chris Develder

A continuous rise in the penetration of renewable energy sources, along with the use of the single imbalance pricing, provides a new opportunity for balance responsible parties to reduce their cost through energy arbitrage in the imbalance settlement mechanism.

Knowledge Distillation reinforcement-learning +1

Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers

no code implementations • 18 Mar 2024 • Gargya Gokhale, Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder

Accounting for about 25% of final energy consumption globally, the residential sector is an important (potential) source of energy flexibility.

energy management Reinforcement Learning (RL)

Distributional Reinforcement Learning-based Energy Arbitrage Strategies in Imbalance Settlement Mechanism

no code implementations • 23 Dec 2023 • Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder

Our proposed control framework takes a risk-sensitive perspective, allowing BRPs to adjust their risk preferences: we aim to optimize a weighted sum of the arbitrage profit and a risk measure while constraining the daily number of cycles for the battery.

Distributional Reinforcement Learning Q-Learning +1