Comprehensive bidding strategies with genetic programming/finite state automata

This research is an extension of the authors' previous work in double aucti ons aimed at developing bidding strategies for electric utilities which tra de electricity competitively. The improvements detailed in this paper come from using data structures which combine genetic programming and finite sta te automata termed GP-Automata. The strategies developed by the method desc ribed here are adaptive-reacting to input-whereas the previously developed strategies were only suitable in the particular scenario for which they had been designed. The strategies encoded in the GP-Automata are tested in an auction simulator. The simulator pits them against other distribution compa nies (distcos) and generation companies (gencos), buying and selling power via double auctions implemented in regional commodity exchanges. The GP-Aut omata are evolved with a genetic algorithm so that they possess certain cha racteristics. In addition to designing successful bidding strategies (whose usage would result in higher profits) the resulting strategies can also be designed to imitate certain types of trading behaviors. The resulting stra tegies can be implemented directly in online trading, or can be used as rea listic competitors in an off-line trading simulator.