A novel deep learning based peer‐to‐peer transaction method for prosumers under two‐stage market environment

With the development of electricity market, peer-to-peer (P2P) transaction plays an important role in promoting local consumption renewable energy and arousing enthusiasm prosumers. However, due to diversification prosumers, confidentiality information interaction between there are increasing challenges for traditional model-based optimisation methods both P2P modelling model solution accuracy. Therefore, this paper proposes a novel method based on deep learning under two-stage market environment, which uses data-driven approach build behaviour public information. The neural network Long Short-Term Memory (LSTM) is utilised characterise prosumers transactions effectively. Based model, plans bids optimised accordingly. Through simulation test example system with six results show that established can well represent proposed effectively improve efficiency economic benefits providing reference decision-making transactions.