Advertisement

Enhancing Agent Intelligence through Evolving Reservoir Networks for Predictions in Power Stock Markets

  • Kyriakos C. Chatzidimitriou
  • Antonios C. Chrysopoulos
  • Andreas L. Symeonidis
  • Pericles A. Mitkas
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7103)

Abstract

In recent years, Time Series Prediction and clustering have been employed in hyperactive and evolving environments –where temporal data play an important role– as a result of the need for reliable methods to estimate and predict the pattern or behavior of events and systems. Power Stock Markets are such highly dynamic and competitive auction environments, additionally perplexed by constrained power laws in the various stages, from production to transmission and consumption. As with all real-time auctioning environments, the limited time available for decision making provides an ideal testbed for autonomous agents to develop bidding strategies that exploit time series prediction. Within the context of this paper, we present Cassandra, a dynamic platform that fosters the development of Data-Mining enhanced Multi-agent systems. Special attention was given on the efficiency and reusability of Cassandra, which provides Plug-n-Play capabilities, so that users may adapt their solution to the problem at hand. Cassandra’s functionality is demonstrated through a pilot case, where autonomously adaptive Recurrent Neural Networks in the form of Echo State Networks are encapsulated into Cassandra agents, in order to generate power load and settlement price prediction models in typical Day-ahead Power Markets. The system has been tested in a real-world scenario, that of the Greek Energy Stock Market.

Keywords

Data Mining Power Stock Markets Reservoir Computing Multi-Agent System Neuroevolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Amin, M.: Restructuring the Electric Enterprise: Simulating the Evolution of the Electric Power Industry with Intelligent Agents. In: Electricity Pricing in Transition, pp. 27–50. Kluwer Academic Publishers (2002)Google Scholar
  2. 2.
    Amin, M., Ballard, D.: Defining new markets for intelligent agents. IEEE IT Professional 2(4), 29–35 (2000)CrossRefGoogle Scholar
  3. 3.
    Babinec, Š., Pospíchal, J.: Optimization of echo state neural networks for electric load forecasting. Neural Network World 2(7), 133–152 (2007)Google Scholar
  4. 4.
    Bell, M.: Service-Oriented Modeling: Service Analysis, Design, and Architecture. John Wiley and Sons, Inc. (2008)Google Scholar
  5. 5.
    Bremer, J., Andressen, S., Rapp, B., Sonnenschein, M., Stadler, M.: A modelling tool for interaction and correlation in demand-side market behavior. In: First European Workshop on Energy Market Modeling Using Agent-Based Computational Economics, Karlsruhe, pp. 77–91 (March 2008)Google Scholar
  6. 6.
    Cao, L., Gorodetsky, V., Mitkas, P.: Agent mining: The synergy of agents and data mining. IEEE Intelligent Systems 24(3), 64–72 (2009)CrossRefGoogle Scholar
  7. 7.
    Chatzidimitriou, K.C., Mitkas, P.A.: A NEAT way for evolving echo state networks. In: European Conference on Artificial Intelligence. IOS Press (August 2010)Google Scholar
  8. 8.
    Conzelmann, G., Boyd, G., Koritarov, V., Veselka, T.: Multi-agent power market simulation using emcas. In: IEEE 2005 Power Engineering Society General Meeting, vol. 3, pp. 2829–2834 (2005)Google Scholar
  9. 9.
    D’Inverno, M., Luck, M.: Understanding Agent Systems. Series on Agent Technology. Springer, Heidelberg (2003)zbMATHGoogle Scholar
  10. 10.
    Diosteanu, A., Cotfas, L.: Agent based knowledge management solution using ontology, semantic web services and gis. Informatica Economicǎ 13(4), 90–98 (2009)Google Scholar
  11. 11.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: An update. SIGKDD Explorations 11(1), 10–18 (2009)CrossRefGoogle Scholar
  12. 12.
    He, M., Jennings, N.R., Leung, H.: On agent-mediated electronic commerce. IEEE Transactions on Knowledge and Data Engineering 15(4), 985–1003 (2003)CrossRefGoogle Scholar
  13. 13.
    Jaeger, H.: Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the “ echo state network” approach. Tech. Rep. GMD Report 159, German National Research Center for Information Technology (2002), http://www.faculty.iu-bremen.de/hjaeger/pubs/ESNTutorialRev.pdf
  14. 14.
    Lukosevicius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Computer Science Review 3, 127–149 (2009)CrossRefzbMATHGoogle Scholar
  15. 15.
    Maximilien, M., Singh, M.: Agent-based architecture for autonomic web service selection. In: 1st International Workshop on Web Services and Agent Based Engineering, WSABE 2003 (2003)Google Scholar
  16. 16.
    Melzian, R.: Bidding and pricing in electricity markets - agent-based modelling using emsim. In: First European Workshop on Energy Market Modeling using Agent-Based Computational Economics, Karlsruhe, pp. 49–61 (March 2008)Google Scholar
  17. 17.
    Petrov, V., Shebl, G.: Power auctions bid generation with adaptive agents using genetic programming. In: 2000 North American Power Symposium, Waterloo-Ontario, Canada (October 2000)Google Scholar
  18. 18.
    Ponnekanti, S.R., Fox, A.: Sword: A developer toolkit for web service composition. In: 11th International WWW Conference (WWW 2002), Honolulu, HI, USA (2002)Google Scholar
  19. 19.
    Shia, A.: A novel personal agent framework for web services and commercial systems. In: 2006 International Conference on Semantic Web & Web Services, SWWS 2006. CSREA Press, Las Vegas (2006)Google Scholar
  20. 20.
    Showkati, H., Hejazi, A., Elyasi, S.: Short term load forecasting using echo state networks. In: The 2010 International Joint Conference on Neural Networks (IJCNN), Barcelona, pp. 1–5 (July 2010)Google Scholar
  21. 21.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar
  22. 22.
    Stone, P.: Learning and multiagent reasoning for autonomous agents. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence, pp. 13–30 (January 2007), http://www.ijcai-07.org/
  23. 23.
    Symeonidis, A.L., Mitkas, P.: Agent Intelligence through Data Mining. Springer, USA (2005)zbMATHGoogle Scholar
  24. 24.
    Symeonidis, A.L., Chatzidimitriou, K.C., Athanasiadis, I.N., Mitkas, P.A.: Data mining for agent reasoning: A synergy for training intelligent agents. Engineering Applications of Artificial Intelligence 20(8), 1097–1111 (2007)CrossRefGoogle Scholar
  25. 25.
    Tellidou, A., Bakirtzis, A.: Multi-agent reinforcement learning for strategic bidding in power markets. In: 3rd IEEE International Conference on Intelligent Systems, London, UK, pp. 408–413 (September 2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Kyriakos C. Chatzidimitriou
    • 1
    • 2
  • Antonios C. Chrysopoulos
    • 1
  • Andreas L. Symeonidis
    • 1
    • 2
  • Pericles A. Mitkas
    • 1
    • 2
  1. 1.Electrical and Computer Engineering DepartmentAristotle University of ThessalonikiGreece
  2. 2.Informatics and Telematics Institute Centre for Research and Technology HellasAristotle University of ThessalonikiThermiGreece

Personalised recommendations