Title: Research on adaptive dispatching of smart grid considering the cost of renewable energy power generation

Authors: Wenchao Qin; Jinding He

Addresses: Yunnan Electric Power Dispatching Control Centre, Kunming, Yunnan, China ' Yunnan Electric Power Dispatching Control Centre, Kunming, Yunnan, China

Abstract: In order to overcome the problems of poor convergence, high cost and long completion time of scheduling tasks in traditional methods, an adaptive dispatching method of smart grid considering the cost of renewable energy power generation is proposed. Firstly, the operation cost of smart grid is calculated from the total operation cost of conventional power generation unit, renewable energy power generation unit and energy storage unit. Then, combined with the benefits of flexible load, a smart grid adaptive dispatching model is built. Finally, under various constraints, the distributed reinforcement learning is used to solve the scheduling model and the adaptive scheduling results of smart grid are obtained. The experimental results show that the scheduling model solving algorithm of this method converges in 43 iterations, and the total operation cost of smart grid is 5.68 × 10⁷ yuan, and the scheduling task completion time is always less than 0.48 s.

Keywords: cost of renewable energy power generation; smart grid; adaptive scheduling; conventional power generation unit; energy storage unit; distributed reinforcement learning.

DOI: 10.1504/IJGEI.2024.141924

International Journal of Global Energy Issues, 2024 Vol.46 No.6, pp.585 - 602

Received: 24 Nov 2022
Accepted: 25 Jan 2023
Published online: 03 Oct 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article