The PowerTAC competition provides a multi-agent simulation platform for electricity markets, in which intelligent agents acting as electricity brokers compete with each other aiming to maximize their profits. Typically, the gains of agents increase as the number of their customers rises, but in parallel, costs also increase as a result of higher transmission fees that need to be paid by the electricity broker. Thus, agents that aim to take over a disproportionately high share of the market, often end up with losses due to being obliged to pay huge transmission capacity fees. In this paper, we present a novel trading strategy that, based on this observation, aims to balance gains against costs; and was utilized by the champion of the PowerTAC-2020 tournament, TUC-TAC. The approach also incorporates a wholesale market strategy that employs Monte Carlo Tree Search to determine TUC-TAC’s best course of action when participating in the market’s double auctions. The strategy is improved by making effective use of a forecasting module that seeks to predict upcoming peaks in demand, since in such intervals incurred costs significantly increase. A post-tournament analysis is also included in this paper, to help draw important lessons regarding the strengths and weaknesses of the various strategies used in the PowerTAC-2020 competition.
- Electricity brokers
- Trading agents
- Bidding strategies
This is a preview of subscription content, access via your institution.
Tax calculation will be finalised at checkout
Purchases are for personal use onlyLearn about institutional subscriptions
It has to be clarified that opponent tariffs with unusual features were considered as “baits” and were not evaluated. Such features could be very high early withdrawal penalties, unusually high periodic payments, or values of rates.
The complete results of PowerTAC 2020 are in https://powertac.org/log_archive/PowerTAC_2020_finals.html. An executable version of the TUC-TAC 2020 agent can be retrieved from https://www.powertac.org/wiki/index.php/TUC_TAC_2020.
Some specifics of their strategies were revealed during a post-tournament workshop.
This and subsequent figures (apart from Fig. 8) exclude the results of “Phoenix games” (see “categorization by balancing fees” below). The extraordinarily high fees paid by the agents in those games would just have added noise to the analysis.
Chowdhury, M.M.P., Kiekintveld, C., Tran, S., Yeoh, W.: Bidding in periodic double auctions using heuristics and dynamic Monte Carlo tree search. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, pp. 166–172 (2018)
Ghosh, S., Subramanian, E., Bhat, S.P., Gujar, S., Paruchuri, P.: Vidyutvanika: a reinforcement learning based broker agent for a power trading competition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 914–921 (2019)
Ketter, W., Collins, J., Reddy, P.: Power TAC: a competitive economic simulation of the smart grid. Energy Econ. 39, 262–270 (2013)
Natividad, F., Folk, R.Y., Yeoh, W., Cao, H.: On the use of off-the-shelf machine learning techniques to predict energy demands of power TAC consumers. In: Ceppi, S., David, E., Hajaj, C., Robu, V., Vetsikas, I.A. (eds.) AMEC/TADA 2015-2016. LNBIP, vol. 271, pp. 112–126. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54229-4_8
Özdemir, S., Unland, R.: The strategy and architecture of a winner broker in a renowned agent-based smart grid competition. In: Web Intelligence, pp. 165–183 (2017)
Özdemir, S., Unland, R.: AgentUDE17: a genetic algorithm to optimize the parameters of an electricity tariff in a smart grid environment. In: Demazeau, Y., An, B., Bajo, J., Fernández-Caballero, A. (eds.) PAAMS 2018. LNCS (LNAI), vol. 10978, pp. 224–236. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-94580-4_18
Serrano Cuevas, J., Rodriguez-Gonzalez, A.Y., Munoz de Cote, E.: Fixed-price tariff generation using reinforcement learning. In: Fujita, K., et al. (eds.) Modern Approaches to Agent-based Complex Automated Negotiation. SCI, vol. 674, pp. 121–136. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-51563-2_8
Shoham, Y., Leyton-Brown, K.: Multiagent systems: algorithmic, game-theoretic, and logical foundations. In: Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations (2008)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press (2018)
Sykulski, A., Chapman, A., Munoz de Cote, E., Jennings, N.: The winning strategy for the inaugural lemonade stand game tournament. Front. Artif. Intell. Appl. 215 (2010)
Urieli, D., Stone, P.: Tactex’13: a champion adaptive power trading agent. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28, no. 1 (2014)
Editors and Affiliations
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Orfanoudakis, S., Kontos, S., Akasiadis, C., Chalkiadakis, G. (2021). Aiming for Half Gets You to the Top: Winning PowerTAC 2020. In: Rosenfeld, A., Talmon, N. (eds) Multi-Agent Systems. EUMAS 2021. Lecture Notes in Computer Science(), vol 12802. Springer, Cham. https://doi.org/10.1007/978-3-030-82254-5_9
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82253-8
Online ISBN: 978-3-030-82254-5