Intelligent agents for negotiation and game-based decision support in electricity markets

Abstract

In this paper we propose a Multi-Agent system architecture to simulate and analyse Competitive Electricity Markets combining bilateral trading with power exchange mechanisms. This Multi-Agent environment includes several heterogeneous and autonomous intelligent agents representing the different independent entities in Electricity Markets. Agents are endowed with historical information about the market including past strategies of other players, and have strategic behaviour to face the market. This paper focuses on the different negotiation mechanisms supported by the simulator, and on agents' strategic behaviour to face them. A special emphasis is devoted to the structure of market players, Seller and Buyer agents, particularly in what concerns their decision analysis process to face the challenging market. A detailed description of an algorithm for Decision Support is presented. This is a promising algorithm to improve agents bidding process and counter-proposals definition.