Genetic algorithm evolution of utility bidding strategies for the competitive marketplace

Abstract

This paper describes an environment in which distribution companies (discos) and generation companies (gencos), buy and sell power via double auctions implemented in a regional commodity exchange. The electric utilities' profits depend on the implementation of a successful bidding strategy. In this research, a genetic algorithm evolves bidding strategies as gencos and discos trade power. A framework in which bidding strategies may be tested and modified is presented. This simulated electric commodity exchange can be used offline to predict whether bid strategies will be profitable and successful. It can also be used to experimentally verify how bidding behavior affects the competitive electric marketplace.