Economic Battery Storage Dispatch with Deep Reinforcement Learning from Rule-Based Demonstrations
The application of deep reinforcement learning algorithms to economic battery dispatch problems has significantly increased recently. However, optimizing battery dispatch over long horizons can be challenging due to delayed rewards. In our experiments we observe poor performance of popular actor-critic algorithms when trained on yearly episodes with hourly resolution. To address this, we propose an approach extending soft actor-critic (SAC) with learning from demonstrations. The special feature of our approach is that, due to the absence of expert demonstrations, the demonstration data is generated through simple, rule-based policies. We conduct a case study on a grid-connected microgrid and use if-then-else statements based on the wholesale price of electricity to collect demonstrations. These are stored in a separate replay buffer and sampled with linearly decaying probability along with the agent's own experiences. Despite these minimal modifications and the imperfections in the demonstration data, the results show a drastic performance improvement regarding both sample efficiency and final rewards. We further show that the proposed method reliably outperforms the demonstrator and is robust to the choice of rule, as long as the rule is sufficient to guide early training into the right direction.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningSimilar Papers 제목 키워드 기반
Ensemble Nonlinear Model Predictive Control for Residential Solar-Battery Energy Management
In a dynamic distribution market environment, residential prosumers with solar power generation and battery energy storage devices can flexibly interact with the power grid via power exchange. Providing a schedule of thi…
energy managementManagementModel Predictive ControlA general framework for supporting economic feasibility of generator and storage energy systems through capacity and dispatch optimization
Integration of various electricity-generating technologies (such as natural gas, wind, nuclear, etc.) with storage systems (such as thermal, battery electric, hydrogen, etc.) has the potential to improve the economic com…
Computational EfficiencyDecision MakingReinforcement Learning for Battery Energy Storage Dispatch augmented with Model-based Optimizer
Reinforcement learning has been found useful in solving optimal power flow (OPF) problems in electric power distribution systems. However, the use of largely model-free reinforcement learning algorithms that completely i…
Deep Reinforcement LearningImitation Learningreinforcement-learningReinforcement Learning+1A comparison between central- and self-dispatch storage management principles in island systems
This paper presents a comparative evaluation of central and self-dispatch management concepts for battery energy storage (BES) facilities in island power systems with a high renewable energy source (RES) penetration. BES…
ManagementEnhancing Building Energy Efficiency through Advanced Sizing and Dispatch Methods for Energy Storage
Energy storage and electrification of buildings hold great potential for future decarbonized energy systems. However, there are several technical and economic barriers that prevent large-scale adoption and integration of…
Decision Making