Power TAC models the high complexity of contemporary and future energy markets, allowing for large scale experimentation. Autonomous machine-learning trading agents, or 'brokers', act as intermediary profit maximization parties between the market and 'customers', who represent consumers, producers and prosumers. Customer models represent households, small and large businesses, multi-residential buildings, wind parks, solar panel owners, electric vehicle owners, etc. Brokers aim at making profit through offering electricity tariffs to customers and trading energy in the wholesale market, while carefully balancing supply and demand.

With each annual tournament, the models became more sophisticated, the platform more flexible and the results are enlightening.

Papers

• Power TAC: a competitive economic simulation of the smart grid. Energy Economics, 39 (September), 262-270. doi: 10.1016/j.eneco.2013.04.015
• D. Koolen, N. Sadat-Razavi & W. Ketter (2017). Machine Learning for Identifying Demand Patterns of Home Energy Management Systems with Dynamic Electricity Pricing. In Applied Sciences (pp. 1160)

For more information please contact:

Prof. Wolf Ketter

Professor next generation information systems