Physics Informed Reinforcement Learning for Power Grid Control using Augmented Random Search

dc.contributor.author Mahapatra, Kaveri
dc.contributor.author Fan, Xiaoyuan
dc.contributor.author Li, Xinya
dc.contributor.author Huang, Yunzhi
dc.contributor.author Huang, Qiuhua
dc.date.accessioned 2021-12-24T17:50:04Z
dc.date.available 2021-12-24T17:50:04Z
dc.date.issued 2022-01-04
dc.description.abstract Wide adoption of deep reinforcement learning in energy system domain needs to overcome several challenges , including scalability, learning from limited samples, and high-dimensional continuous state and action spaces. In this paper, we integrated physics-based information from the generator operation state formula, also known as Swing Equation, into the reinforcement learning agent's neural network loss function, and applied an augmented random search agent to optimize the generator control under dynamic contingency. Simulation results demonstrated the reliability performance improvements in training speed, reward convergence, and future potentials in its transferability and scalability.
dc.format.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2022.427
dc.identifier.isbn 978-0-9981331-5-7
dc.identifier.uri http://hdl.handle.net/10125/79762
dc.language.iso eng
dc.relation.ispartof Proceedings of the 55th Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Monitoring, Control, and Protection
dc.subject augmented random search
dc.subject physics informed machine learning
dc.subject physics informed neural network
dc.subject power grid control
dc.title Physics Informed Reinforcement Learning for Power Grid Control using Augmented Random Search
dc.type.dcmi text
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
0344.pdf
Size:
2.61 MB
Format:
Adobe Portable Document Format
Description: