Deep Reinforcement Learning for Competitive DER Pricing Problem of Virtual Power Plants

Zheng Xu; Ye Guo; Hongbin Sun; Wenjun Tang; Wenqi Huang

doi:10.17775/CSEEJPES.2022.00060

您当前的位置：

首页 >

文章列表页 >

Deep Reinforcement Learning for Competitive DER Pricing Problem of Virtual Power Plants

Regular Papers | 更新时间：2026-03-25

- Deep Reinforcement Learning for Competitive DER Pricing Problem of Virtual Power Plants
- CSEE Journal of Power and Energy Systems Vol. 12, Issue 1, Pages: 150-161(2026)
- 作者机构：
  
  1. Tsinghua-Berkeley Shenzhen Institute (TBSI), Tsinghua Shenzhen International Graduate School, Tsinghua University,Shenzhen,China
  2. Department of Electrical Engineering, State Key Laboratory of Power Systems, TBSI, Tsinghua University,Beijing,China
  3. Digital Grid Research Institute, China Southern Power Grid,Guangzhou,China
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2022.00060
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
Zheng Xu, Ye Guo, Hongbin Sun, et al. Deep Reinforcement Learning for Competitive DER Pricing Problem of Virtual Power Plants[J]. CSEE Journal of Power and Energy Systems, 2026, 12(1): 150-161.
DOI：

Zheng Xu, Ye Guo, Hongbin Sun, et al. Deep Reinforcement Learning for Competitive DER Pricing Problem of Virtual Power Plants[J]. CSEE Journal of Power and Energy Systems, 2026, 12(1): 150-161. DOI： 10.17775/CSEEJPES.2022.00060.

摘要

Abstract

Pricing competition between virtual power plants (VPPs) for distributed energy resources (DERs) is considered in this paper. Due to limited amount of DERs in one distributed area

VPPs have to compete for the rights to work with DERs and then sell electricity from internal DERs in the wholesale market. To address this pricing problem

a Markov decision process (MDP) with continuous state and action spaces is formulated for the VPP to consider future rewards brought by contract statuses of DERs. Deep deterministic policy gradient (DDPG) algorithm is applied to solve the pricing problem in MDP form. To deal with the non-stationary environment in the training process brought by competing VPP

a fictitious adversary method is put forward in this paper to combine with DDPG algorithm for the first time. The proposed fictitious adversary method can help the VPP in finding competitive and robust pricing strategies under competition. Numerical results demonstrate effectiveness of the proposed methodology in finding satisfying pricing strategies that consider competitor behavior and long-term values of DERs.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Coupon-Based Demand Response for Consumers Facing Flat-Rate Retail Pricing

Active Power Correction Strategies Based on Deep Reinforcement Learning—Part I: A Simulation-driven Solution for Robustness

Peer-to-Peer Energy Trading for Multi-Microgrids via Stackelberg Game and Multi-Agent Deep Reinforcement Learning

Hierarchical Demand Response Considering Dynamic Competing Interaction Based on Multi-agent Deep Deterministic Policy Gradient

Two-Stage Stochastic Scheduling of Virtual Power Plant Based on Transactive Control

Related Author

Hongxun Hui

Yi Ding

Kaining Luan

Tao Chen

Yonghua Song

Saifur Rahman

Peidong Xu

Jiajun Duan

Related Institution

Department of Electrical and Computer Engineering, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau

College of Electrical Engineering, Zhejiang University

State Grid Jiangsu Electric Power Co., LTD.

School of Electrical Engineering, Southeast University

Department of Electrical and Computer Engineering, Advanced Research Institute, Virginia Polytechnic Institute and State University

AI问答

⁰