基于产消者驱动的碳感知配电节点边际电价的数据驱动型点对点能源交易

Peer-to-peer(P2P)energy trading enables an effi-cient regulation of distributed renewable energy among prosum-ers,implicitly promoting low-carbon operation.This study pro-poses a novel P2P energy trading scheme with coupled electrici-ty-carbon(E/C)market that co-optimizes both power and car-bon emission flows.To facilitate the low-carbon operations in the market,we introduce a prosumer-driven carbon-aware dis-tribution locational marginal price(PDC-DLMP)to serve as a pricing signal for the distribution system operator(DSO).To ef-ficiently determine the optimal trading solutions,we adopt a two-layer data-driven approach.The first layer employs a rein-forcement learning algorithm named multi-agent twin-delayed deep deterministic policy gradient(MATD3);the second layer uses a deep neural network(DNN)driven surrogate model,which is designed to map the PDC-DLMP signals,thereby elimi-nating the need for direct DSO intervention during market op-eration.This approach protects the physical model parameters of the distribution network and ensures multi-level privacy pro-tection.Simulation results validate the effectiveness of the pro-posed P2P energy trading scheme with coupled E/C market,demonstrating its ability to achieve both reduced carbon emis-sions and lower operational costs for microgrid prosumers.