Multi-source scheduling method on supply side of microgrid based on reinforcement learning algorithm

Sheng Yang; Zhicheng Zhou; Zhanlong Li; Yangtian Ning

doi:10.1117/12.2652443

6 September 2022 Multi-source scheduling method on supply side of microgrid based on reinforcement learning algorithm

Sheng Yang, Zhicheng Zhou, Zhanlong Li, Yangtian Ning

Proceedings Volume 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022); 123321K (2022) https://doi.org/10.1117/12.2652443
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 2022, Chengdu, China

Abstract

In order to improve the convergence and economy of resource scheduling on the supply side of microgrid, a multi-source scheduling method on the supply side of microgrid based on reinforcement learning algorithm is proposed. The structure of microgrid is analyzed, and the principle of reinforcement learning algorithm is given. Based on this principle, the objective function of multi-source optimal scheduling on the supply side of microgrid is designed, that is, the total operation cost of the system is the lowest, and the corresponding constraints are proposed, including the system power balance constraints and the operation constraints of energy storage battery. Based on the above established objective functions and constraints, a multi-source scheduling model on the supply side of the microgrid is constructed to maximize the operation income of the microgrid. The experimental results show that the convergence speed of this method is faster and the total operation cost of microgrid is reduced, which verifies its application value.

Citation Download Citation

Sheng Yang, Zhicheng Zhou, Zhanlong Li, and Yangtian Ning "Multi-source scheduling method on supply side of microgrid based on reinforcement learning algorithm", Proc. SPIE 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 123321K (6 September 2022); https://doi.org/10.1117/12.2652443

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available