Automatic electricity markets data extraction for realistic multi-agent simulations

This paper presents the development of a tool that provides a database with available information from real electricity markets, ensuring the required updating mechanisms. Some important characteristics of this tool are: capability of collecting, analyzing, processing and storing real electricity markets data available on-line; capability of dealing with different file formats and types, some of them inserted by the user, resulting from information obtained not on-line but based on the possible collaboration with market entities; definition and implementation of database gathering information from different market sources, even including different market types; machine learning approach for automatic definition of downloads periodicity of new information available on-line. This is a crucial tool to go a step forward in electricity markets simulation, since the integration of this database with a scenarios generation tool, based on knowledge discovery techniques, provides a framework to study real market scenarios allowing simulators improvement and validation.