Scenarios Generation for Multi-Agent simulation of Electricity Markets based on Intelligent Data Analysis Gabriel Santos, Isabel Praça, Tiago Pinto, Sérgio Ramos, Zita Vale GECAD – Knowledge Engineering and Decision Support Research Center Institute of Engineering – Polytechnic of Porto (ISEP/IPP) Porto, Portugal {gajls, icp, tmcfp, scr, zav}@isep.ipp.pt Abstract— This document presents a tool able to automatically gather data provided by real energy markets and to generate scenarios, capture and improve market players’ profiles and strategies by using knowledge discovery processes in databases supported by artificial intelligence techniques, data mining algorithms and machine learning methods. It provides the means for generating scenarios with different dimensions and characteristics, ensuring the representation of real and adapted markets, and their participating entities. The scenarios generator module enhances the MASCEM (Multi-Agent Simulator of Competitive Electricity Markets) simulator, endowing a more effective tool for decision support. The achievements from the implementation of the proposed module enables researchers and electricity markets’ participating entities to analyze data, create real scenarios and make experiments with them. On the other hand, applying knowledge discovery techniques to real data also allows the improvement of MASCEM agents’ profiles and strategies resulting in a better representation of real market players’ behavior. This work aims to improve the comprehension of electricity markets and the interactions among the involved entities through adequate multi-agent simulation. Keywords— Electricity Markets; Knowledge Discovery in Databases; Machine Learning; Multi-Agent Simulators; Real Electricity Markets; Scenarios Generation I. INTRODUCTION Electricity markets worldwide suffered profound transformations such as: the privatization of previously nationally owned systems; the deregulation of privately owned systems that were regulated; and the internationalization of national systems [1]. The study of electricity markets operation has been gaining an increasing importance in the last years, as a result of new challenges that the electricity market restructuring produced. This restructuring increased the competitiveness of the market and hence its complexity. This growing complexity and unpredictability consequently increases the difficulty of decision making. Therefore, entities are forced to rethink their behavior and market strategies [2]. Good decision-support tools are generally required in competitive environments, such as the present electricity markets, to assist players in decision making. Relevant research is being conducted in this field, namely concerning player modeling and simulation, strategic bidding and decision-support. Several market models have arisen in order to overcome the mentioned challenges. Some pioneer countries’ experience provides guidance in what regards the implemented market models’ performance. However, it is still premature to take definitive conclusions. Thus, the use of tools enabling the study of different market mechanisms and the relationship between market entities becomes crucial. Market players and regulators are very interested in foreseeing the market behavior: regulators to test rules before they are implemented and to detect market inefficiencies; market players to understand market’s behavior and operate in order to maximize their profits. The need to understand those mechanisms and how the involved players’ interaction affects the outcomes of the markets, contributed to the growth of usage of simulation tools, with the purpose of taking the best possible results out of each market context for each participating entity. Multi-agent based software is particularly well-fitted to analyze dynamic and adaptive systems with complex interactions among its constituents, such as the Electricity Markets. Several modeling tools directed to the study of restructured wholesale power markets have emerged. Some relevant tools in this domain are MASCEM (Multi-Agent Simulator for Competitive Electricity Markets) [3, 4], EMCAS [5], and AMES [6]. Although these works confirm the adequate applicability of simulation to the study of Electricity Markets, particularly by using multi-agent systems, they present a common limitation: the lack of solid representation of realistic electricity market scenarios. This leads to the main subject of this work – the modeling of appropriate representation of real electricity markets, through the definition of scenarios which represent the reality and possible adaptations, in the fullest possible extent. This definition is critical for undertaking realistic simulations with MASCEM and other electricity markets simulators, allowing an adequate study of the electricity markets environment. The functioning of liberalized markets over the last years provides valuable information most of the times available to the community. Lessons can be learned from these last years to improve the knowledge about markets, to define adequate players’ profiles and behaviors, but also to test and validate the existing simulation tools making them suitable to represent reality and provide the means for a coherent and realistic analysis of its evolution (or possible alternative pathways for the future of the Electricity Markets sector). But before This work is supported by FEDER Funds through the “Programa Operacional Factores de Competitividade - COMPETE” program and by National Funds through FCT “Fundação para a Ciência e a Tecnologia” under project: FCOMP-01-0124-FEDER-PEst-OE/EEI/UI0760/2011, PTDC/EEA- EEL/099832/2008, PTDC/SEN-ENR/099844/2008 and PTDC/SEN-ENR /122174/2010. 5 978-1-4673-5881-1/13/$31.00 c 2013 IEEE