Optimizing intelligent startup strategy of power system using PPO algorithm
Uloženo v:
| Název: | Optimizing intelligent startup strategy of power system using PPO algorithm |
|---|---|
| Autoři: | Yan Sun, Yin Wu, Yan Wu, Kai Liang, Cuihong Dong, Shiwei Liu |
| Zdroj: | Intelligent Decision Technologies. 18:3091-3104 |
| Informace o vydavateli: | SAGE Publications, 2024. |
| Rok vydání: | 2024 |
| Popis: | This article aimed to use the proximal policy optimization (PPO) algorithm to address the limitations of power system startup strategies, to enhance the adaptability, coping ability, and overall robustness of the system to variable grid demand and integrated renewable energy, the constraints in the power system start-up strategy are optimized. Firstly, this article constructed a dynamic model of the power system, including key components such as generators, transformers, and transmission lines; secondly, it integrated the PPO algorithm and designed interfaces that allow the algorithm to interact with the power system model; afterward, the state variables of the power system were determined, and a reward function was designed to evaluate the startup efficiency and stability of the system. Next, this article adjusted the reward function and trained and iterated multiple times in the simulation environment to guide the algorithm to learn the optimal startup strategy. Finally, an effective evaluation of the strategy can be conducted. The research results showed that after optimization by the PPO algorithm, the stable frequency startup of the power system only took about 23 seconds, and the system recovery time was reduced by 33.3% under a sudden load increase. The algorithm used can significantly optimize the intelligent startup strategy of the power system. |
| Druh dokumentu: | Article |
| Jazyk: | English |
| ISSN: | 1875-8843 1872-4981 |
| DOI: | 10.3233/idt-240122 |
| Rights: | URL: https://journals.sagepub.com/page/policies/text-and-data-mining-license |
| Přístupové číslo: | edsair.doi...........b4a89fc2f4e50e0f1bad7ecca0fdc380 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | This article aimed to use the proximal policy optimization (PPO) algorithm to address the limitations of power system startup strategies, to enhance the adaptability, coping ability, and overall robustness of the system to variable grid demand and integrated renewable energy, the constraints in the power system start-up strategy are optimized. Firstly, this article constructed a dynamic model of the power system, including key components such as generators, transformers, and transmission lines; secondly, it integrated the PPO algorithm and designed interfaces that allow the algorithm to interact with the power system model; afterward, the state variables of the power system were determined, and a reward function was designed to evaluate the startup efficiency and stability of the system. Next, this article adjusted the reward function and trained and iterated multiple times in the simulation environment to guide the algorithm to learn the optimal startup strategy. Finally, an effective evaluation of the strategy can be conducted. The research results showed that after optimization by the PPO algorithm, the stable frequency startup of the power system only took about 23 seconds, and the system recovery time was reduced by 33.3% under a sudden load increase. The algorithm used can significantly optimize the intelligent startup strategy of the power system. |
|---|---|
| ISSN: | 18758843 18724981 |
| DOI: | 10.3233/idt-240122 |