Abstract
Although most electric power is presently generated using fossil fuels, two abundant renewable and clean energy sources, solar and wind, are increasingly cost-competitive and offer the potential of decentralized (and hence more robust) sourcing. However, the intermittent nature of solar and wind power presents difficulties in connection with integrating them into national power grids. One approach to addressing these challenges is through an agent-based architecture for coordinating locally-connected energy micro-grids, each of which manages its own local energy production, distribution, and storage. By integrating these micro-grids into a larger network structure, there is the opportunity for them to be more responsive to local needs and hence more cost effective overall. In such an arrangement, the micro-grids have agents that can choose to resell their excess energy in an open, regional market in alignment with respect to their specific goals (which could be to reduce carbon emissions or to maximize their financial outcomes). In this study, we have investigated how agents operating in such an open environment can learn to optimize their individual trading strategies by employing Markov-Decision-Process-based reasoning and reinforcement learning. We empirically show that our learning trading strategies improve net profit loss by up to 29 % and can reduce carbon emissions by 78 % when compared to the original (non-learning) trading strategies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Net Profit/Loss = ((cash in - generation cost) - cash out).
- 2.
Carbon emission stores the amount of carbon di oxide emitted during electricity production, transmission and distribution.
References
M. Alam, S. Ramchurn, and A. Rogers. Cooperative Energy Exchange for the Efficient Use of Energy and Resources in Remote Communities. In 12th Autonomous Agents and Multiagent Systems (AAMAS) Conference, pages 731–738, Saint Paul Minnesota, USA, 2013
Cossentino, M., Lodato, C., Pucci, M., Vitale, G.: A multi-agent architecture for simulating and managing microgrids. In: Federated Conference on Computer Science and Information Systems (FedCSIS), Szczecin, Poland, pp. 619–622 (2011)
IESO: Independent Electricity System Operator Canada. http://www.ieso.ca/. Accessed 10 Feb 2014
Ishowo-oloko, F., Vytelingum, P., Jennings, N., Rahwan, I.: A storage pricing mechanism for learning agents in Masdar City smart grid. In: 11th International Conference on Autonomous Agents and Multiagent Systems, Valencia, Spain, pp. 1167–1168 (2012)
Jacobson, M.Z., Delucchi, M.A.: Providing all global energy with wind, water, and solar power, part i: technologies, energy resources, quantities and areas of infrastructure, and materials. Energy Policy 39(3), 1154–1169 (2011)
Miller, A., Muljadi, E., Zinger, D.S.: A variable speed wind turbine power control. Energy Convers. 12(2), 181–186 (1997)
Ministry for Environment New Zealand: Guidance for voluntary corporate greenhouse gas reporting data and methods for the 2010 calendar year. Technical report, Wellington, New Zealand (2010)
Nicolaisen, J., Petrov, V., Tesfatsion, L.: Market power and efficiency in a computational electricity market with discriminatory double auction pricing. IEEE Trans. Evol. Comput. 5(5), 504–523 (2001)
G. Nordic Energy: Electricity Market Group. http://www.nordicenergy.org/. Accessed 08 Feb 2014
Peters, M., Ketter, W., Saar-Tsechansky, M., Collins, J.: A reinforcement learning approach to autonomous decision-making in smart electricity markets. Mach. Learn. 92(1), 5–39 (2013)
Pietsch, H.: Property service Division. http://www.propserv.otago.ac.nz/. Accessed 1 Feb 2014
Rahimi-kian, A., Sadeghi, B., Member, S., Thomas, R.J.: Q-learning based supplier-agents for electricity markets. In: 2002 IEEE Power Engineering Society Summer Meeting, Chicago, IL, USA, pp. 1–8 (2002)
Reddy, P.P., Veloso, M.M.: Strategy learning for autonomous agents in smart grid markets (2013)
Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Xiong, G., Hashiyama, T., Okuma, S.: An electricity supplier bidding strategy through Q-Learning. In: Power Engineering Society Summer Meeting, Chicago, IL, USA (2002)
Yasir, M., Purvis, M.K., Purvis, M., Savarimuthu, B.T.R.: Agent-based community coordination of local energy distribution. AI Soc. (2013). doi:10.1007/s00146-013-0528-1
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Yasir, M., Purvis, M., Purvis, M., Savarimuthu, B.T.R. (2014). An Intelligent Learning Mechanism for Trading Strategies for Local Energy Distribution. In: Ceppi, S., et al. Agent-Mediated Electronic Commerce. Designing Trading Strategies and Mechanisms for Electronic Markets. AMEC AMEC TADA TADA 2014 2013 2014 2013. Lecture Notes in Business Information Processing, vol 187. Springer, Cham. https://doi.org/10.1007/978-3-319-13218-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-13218-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13217-4
Online ISBN: 978-3-319-13218-1
eBook Packages: Computer ScienceComputer Science (R0)