.png){kind=icon}
.png){kind=icon}
Return
Incentive Communication Enabled Holonic Framework for Urban-Wide P2P Energy Trading
.png){kind=icon}
PRE
AI
L
F
X
DOI：10.1109/TSG.2025.3645193.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Peer-to-peer (P2P) energy trading has been recognized as a paradigm that can effectively promote energy sharing among end energy entities, foster local energy economy in urban systems, and maximize the value of distributed renewable energy assets. The current P2P energy trading solutions have performance limitations in supporting trading among large-scale prosumers. This paper proposes a new P2P energy trading system that features a multi-layer holonic structure. Based on the real-time operational condition, the system dynamically forms prosumer coalitions at different scales in a bottom-up manner, supporting on-demand P2P energy trading among prosumers in different geographical locations in an urban system. A multi-level coalition formation scheme and a peer-matching scheme are proposed to facilitate this process, and an incentive communication-enabled deep reinforcement learning-based approach is developed to enable individual prosumers to make energy trading decisions that account for multifaceted influencing factors. Besides, a power flow-aware energy trading adjustment scheme is integrated to ensure the settlement feasibility of the energy trading transactions. Numerical simulations are conducted on an IEEE benchmark system and real-world datasets to validate the proposed system.
Keywords:
Pricing
Energy resources
Real-time systems
Electronic mail
Prediction algorithms
Peer-to-peer computing
Numerical simulation
Market research
Deep reinforcement learning
Decision making
P2P energy trading
holonic structure
deep reinforcement learning
smart grid
Journal
IF:
9.8
Papers:
5.6K
Citations:
4.3W
Organization
Cited Papers