This paper presents an improved co-evolution genetic algorithm (ICGA). The structure of the algorithm is redesigned in the new algorithm to get better performance. The genetic algorithm applied to the subgroups. Information transfer mode is added to ICGA to provide greater decision-making space. ICGA is used to solve unconstrained optimization problems, constrained optimization problems, large-scale deceptive problems and the problem of large scale, long-term generation expansion planning of power systems.Results of numerical tests validate the algorithm's excellent performance. |