Fit for purpose: Modeling wholesale electricity markets realistically with multi-agent deep reinforcement learning

被引：8
|
作者：
Harder, Nick [1 ]
Qussous, Ramiz [1 ]
Weidlich, Anke [1 ]
机构：
[1] Univ Freiburg, Dept Sustainable Syst Engn INATECH, Emmy Noether Str 2, D-79110 Freiburg, Germany
来源：
ENERGY AND AI | 2023年 / 14卷
关键词：
Agent-based modeling; Reinforcement learning; Machine learning; Electricity markets; Multi-agent reinforcement learning; DECISION-MAKING;
D O I：
10.1016/j.egyai.2023.100295
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Electricity markets need to continuously evolve to address the growing complexity of a predominantly renewable energy-driven, highly interconnected, and sector-integrated energy system. Simulation models allow testing market designs before implementation, which offers advantages for market robustness and efficiency. This work presents a novel approach to simulate the electricity market by using multi-agent deep reinforcement learning for representing revenue-maximizing market participants. The learning capability makes the agents highly adaptive, thereby facilitating a rigorous performance evaluation of market mechanisms under challenging yet practical conditions. Through distinct test cases that vary the number and size of learning agents in an energy-only market, we demonstrate the ability of the proposed method to diagnose market manipulation and reflect market liquidity. Our method is highly scalable, as demonstrated by a case study of the German wholesale energy market with 145 learning agents. This makes the model well-suited for analyzing large and complex electricity markets. The capability of the presented simulation approach facilitates market design analysis, thereby contributing to the establishment future-proof electricity markets to support the energy transition.
引用
收藏
页数：14
相关论文
共 50 条
  • [21] A Transfer Learning Framework for Deep Multi-Agent Reinforcement Learning
    Liu, Yi
    Wu, Xiang
    Bo, Yuming
    Wang, Jiacun
    Ma, Lifeng
    IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2024, 11 (11) : 2346 - 2348
  • [22] Multi-agent reinforcement learning for strategic bidding in power markets
    Tellidou, Athina C.
    Bakirtzis, Anastasios G.
    2006 3RD INTERNATIONAL IEEE CONFERENCE INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2006, : 400 - 405
  • [23] A review of cooperative multi-agent deep reinforcement learning
    Afshin Oroojlooy
    Davood Hajinezhad
    Applied Intelligence, 2023, 53 : 13677 - 13722
  • [24] Experience Selection in Multi-Agent Deep Reinforcement Learning
    Wang, Yishen
    Zhang, Zongzhang
    2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, : 864 - 870
  • [25] Multi-Agent Deep Reinforcement Learning with Emergent Communication
    Simoes, David
    Lau, Nuno
    Reis, Luis Paulo
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [26] Sparse communication in multi-agent deep reinforcement learning
    Han, Shuai
    Dastani, Mehdi
    Wang, Shihan
    NEUROCOMPUTING, 2025, 625
  • [27] Multi-Agent Deep Reinforcement Learning with Human Strategies
    Thanh Nguyen
    Ngoc Duy Nguyen
    Nahavandi, Saeid
    2019 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2019, : 1357 - 1362
  • [28] Cooperative Exploration for Multi-Agent Deep Reinforcement Learning
    Liu, Iou-Jen
    Jain, Unnat
    Yeh, Raymond A.
    Schwing, Alexander G.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [29] Competitive Evolution Multi-Agent Deep Reinforcement Learning
    Zhou, Wenhong
    Chen, Yiting
    Li, Jie
    PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND APPLICATION ENGINEERING (CSAE2019), 2019,
  • [30] Strategic Interaction Multi-Agent Deep Reinforcement Learning
    Zhou, Wenhong
    Li, Jie
    Chen, Yiting
    Shen, Lin-Cheng
    IEEE ACCESS, 2020, 8 : 119000 - 119009
12345