@inproceedings{a82804ee9acc4f40b10d4d40b13cea77,
title = "Construction Method of Power Grid Simulation Environment for Reinforcement Learning",
abstract = "In recent years, with the construction of new power systems and the gradual maturity of the application of deep reinforcement learning technology, researchers have applied reinforcement learning technology to power system optimization and control. The training and application of reinforcement learning algorithms rely on the power grid simulation environment, which can simulate the operation status of the power grid and interact with the power grid dispatching intelligent agent. The current construction method of power grid simulation environment is only designed for a single scenario and does not have universality in the field of power grid dispatching and control. This article proposes a method for constructing a reinforcement learning oriented power grid simulation environment, constructing a universal power grid simulation environment in the field of power grid dispatching and control, and supporting reinforcement learning intelligent agent training in multi scenarios.",
keywords = "power grid simulation environment, reinforcement learning, space design",
author = "Yupeng Huang and Nan Yang and Yifang Jin and Lei Song and Zhaowei Ling and Kai Wang",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 11th Joint International Information Technology and Artificial Intelligence Conference, ITAIC 2023 ; Conference date: 08-12-2023 Through 10-12-2023",
year = "2023",
doi = "10.1109/ITAIC58329.2023.10408884",
language = "English",
series = "IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "542--546",
editor = "Bing Xu and Kefen Mou",
booktitle = "IEEE ITAIC 2023 - IEEE 11th Joint International Information Technology and Artificial Intelligence Conference",
address = "United States",
}