A Multi-Agent Energy Trading Competition

Abstract

The need for a transition to renewable energy sources will lead to installation of large numbers of distributed renewable energy generators, which typically produce power intermittently. This trend conflicts with current power grid control strategies, where a few centralized control centers manage a limited number of large power plants such that their output meets the energy demands in real time. As the proportion of distributed and intermittent power production capacity increases, this task becomes much harder, especially as the local and regional distribution grids where renewable energy producers are usually installed are currently virtually unmanaged, lack real time metering and in many cases are not built to cope with power flow inversions. A more flexible, decentralized, and self organizing control infrastructure must be developed that can be actively managed to balance both the large grid as a whole, as well as the many lower voltage sub-grids. One candidate for this control infrastructure is energy markets at the retail level. To help mitigate the risk of instituting such markets in the real world, we are developing a competitive market simulation testbed that will stimulate research and development of market structures along with software agents that can support decision making in these markets. Participants in the competition will design intelligent agents that will act as brokers, building portfolios of energy producers and consumers, and matching energy supply from producers with energy demand from consumers. The competition will closely model reality by bootstrapping the simulation environment with real historic load, generation, and weather data.

Negotiated Learning for Smart Grid Agents: Entity Selection based on Dynamic Partially Observable Features

“…Further innovation is needed to enable wider adoption of RTP tariffs (Faruqui and Palmer 2012). The introduction of supplier competition in liberalized retail electricity markets is a key enabler because it encourages novel tariff structures and provides customers with a wider array of tariff choices so that they can select tariffs best suited for their specific consumption behavior and risk appetite (Block, Collins, and Ketter 2010). However, the resulting tariff selection problem, i.e., periodically selecting amongst the set of competitive tariffs, is difficult when prices are allowed to change rapidly.…”