Pattern Learning and Decision Making in a Photovoltaic System

We study the effects of different decision making schemes on the accumulative rewards when photovoltaic (PV) facilities are intended as a potential replacement for conventional peaking power plants. As the amount of solar irradiance usable by a PV module follows a stochastic process, we compare the outcomes using the following two strategies in a stochastic environment: (1) employing an optimal decision making approach without any specific knowledge of the environment; and (2) optimal decision making based upon learning patterns of the environment process. We examine the possibility of integrating a pattern learning approach – called an ε-Machine – with a Partially Observable Markov Decision Process (POMDP). This approach has been motivated in part by the fact that efforts in extending traditional learning approaches to POMDPs have so far achieved only limited success. The PV facility in our model consists of a PV panel and a battery, with an associated local, non-critical load. Under the assumption that any PV generated power exceeding the maximum local consumption capacity must be dumped when the battery is full, the goal of the autonomous control agent is to maintain the maximum output potential to most effectively offset unexpected demand peaks, while minimizing energy wastage in the presence of strong solar irradiance. The environment is assumed to follow a Markov process of a different order than the part of the system under the influence of the agent.

Authors and Affiliations

1. Autonomous Systems Laboratory, CSIRO ICT Centre, Australia

   Rongxin Li & Peter Wang

Editors and Affiliations

1. School of Computer Science and information Technology, RMIT University, VIC 3001, Melbourne, Australia

   Xiaodong Li

2. Melbourne School Engineering, Department of Computer Science and Software Engineering, The University of Melbourne, VIC 3001, Melbourne, Australia

   Michael Kirley

3. School of Mathematics, Statistics and Computer Science, Victoria University of Wellington, P.O. Box 600, 6140, Wellington, New Zealand

   Mengjie Zhang

4. Faculty of Information Technology, Monash University, Clayton Campus, VIC 3800, Australia

   David Green

5. School of Computer Science and Information Technology, RMIT University, VIC 3001, Melbourne, Australia

   Vic Ciesielski

6. School of Information Technology and Electrical Engineering, Australian Defence Force Academy, University of New South Wales, Canberra, Australia

   Hussein Abbass

7. School of Computer Science, University of Adelaide, SA 5005, Adelaide, Australia

   Zbigniew Michalewicz

8. Faculty of Information and Communication Technologies, Swinburne University of Technology, Melbourne, Australia

   Tim Hendtlass

9. Indian Institute of Technology Kanpur, Department of Mechanical Engineering, Kanpur Genetic Algorithms Laboratory (KanGAL), 208016, Kanpur, Uttar Pradesh, India

   Kalyanmoy Deb

10. Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, 117576, Singapore

    Kay Chen Tan

11. Institute AIFB, University of Karlsruhe, 76128, Karlsruhe, Germany

    Jürgen Branke

12. Xi’an Jiaotong-Liverpool University, 215123, Suzhoum, China

    Yuhui Shi

Reprints and permissions

© 2008 Springer-Verlag Berlin Heidelberg

Policies and ethics