Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling

Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling

Shengren, H. (TU Delft Intelligent Electrical Power Grids)
Salazar, Edgar Mauricio (Eindhoven University of Technology)
Vergara Barrios, P.P. (TU Delft Intelligent Electrical Power Grids)
Palensky, P. (TU Delft Intelligent Electrical Power Grids)

2022

Taking advantage of their data-driven and model-free features, Deep Reinforcement Learning (DRL) algorithms have the potential to deal with the increasing level of uncertainty due to the introduction of renewable-based generation. To deal simultaneously with the energy systems’ operational cost and technical constraints (e.g, generation-demand power balance) DRL algorithms must consider a trade-off when designing the reward function. This trade-off introduces extra hyperparameters that impact the DRL algorithms’ performance and capability of providing feasible solutions. In this paper, a performance comparison of different DRL algorithms, including DDPG, TD3, SAC, and PPO, are presented. We aim to provide a fair comparison of these DRL algorithms for energy systems optimal scheduling problems. Results show DRL algorithms’ capability of providing in real-time good-quality solutions, even in unseen operational scenarios, when compared with a mathematical programming model of the energy system optimal scheduling problem. Nevertheless, in the case of large peak consumption, these algorithms failed to provide feasible solutions, which can impede their practical implementation.

Energy management
Machine learning
Deep learning
Reinforcement learning

http://resolver.tudelft.nl/uuid:69215c2b-2d07-4abc-9d1e-e738400e9676

https://doi.org/10.1109/ISGT-Europe54678.2022.9960642

IEEE, Danvers

2023-05-28

978-1-6654-8033-8

Proceedings of 2022 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2022

2022 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 2022-10-10 → 2022-10-12, Novi Sad, Serbia

IEEE PES Innovative Smart Grid Technologies Conference Europe, 2022-October

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2022 H. Shengren, Edgar Mauricio Salazar, P.P. Vergara Barrios, P. Palensky