The power system is undergoing a transformation towards a more decentralized architecture with the development of local energy markets. These markets enable end-users to actively participate in energy transactions by submitting buy/sell bids. While many studies have applied various strategic bidding techniques to wholesale markets, there is a notable research gap in exploring their application to smaller environments such as local flexibility markets and peer-to-peer (P2P) energy markets. In such frameworks, information is often unavailable in advance, and users must frequently adapt their strategies to random scenarios. Furthermore, existing studies on bidding strategies in local markets often focus on market design rather than the behavior of agents, leaving the latter aspect as an auxiliary feature rather than the core focus of the study. This project aims to cover this gap by conducting two separate studies. The first is a theoretical analysis of existing bidding strategies that could be applied to local energy markets, evaluating the strengths and weaknesses of each approach. The second is a practical case study where a selected bidding technique is implemented to demonstrate its technical and economic potential using artificial intelligence and/or machine learning methods. The results of this research will provide valuable insights into the adaptability and effectiveness of AI-driven bidding strategies in local energy markets, with a focus on agent behaviour as a key factor.
