Comparison of particle swarm optimizations for optimal operational planning of energy plants

This paper compares particle swarm optimizations (PSOs) for optimal operational planning of energy plants. In order to generate optimal operational planning for energy plants, startup/shutdown status and/or input/output values of the facilities for each control interval should be determined. The facilities may have nonlinear input-output characteristics. Therefore, the problem can be formulated as a mixed-integer nonlinear optimization problem (MINLP). PSO is one of the meta-heuristic techniques. Original PSO, evolutionary PSO, and adaptive PSO are compared using typical energy plant operational planning problems.