PSO embedded evolutionary programming technique for non-convex economic load dispatch

This paper proposes a hybrid method that integrates the main features of particle swarm optimization (PSO) and evolutionary programming (EP) for solution of non-convex economic load dispatch (ELD) problems having non-linearities like valve point loadings. Algorithms based on PSO, Evolutionary programming (EP) and PSO embedded EP techniques have been developed and tested on a practical non-convex ELD problem with valve point loading effects considered in the cost functions. Numerical results show that all the algorithms are capable of finding feasible near global solutions within a reasonable time but PSO embedded EP-algorithm with Gaussian mutation appears to outperform the other two in terms of convergence speed, solution time and quality of solution.