Economic load dispatch using memory based differential evolution

Many variants of differential evolution (DE) algorithm and its hybrid versions exist in the literature to solve economic load dispatch (ELD) problem. However, the performance of DE is highly affected by the inappropriate choice of its operators like mutation and crossover. Moreover, in general practice, DE does not employ any strategy of memorising the best results obtained so far in the initial part of the previous cycle. An attempt is made in this paper to propose a 'memory-based DE (MBDE)' where two 'swarm operators' have been introduced. These operators based on the pBEST and gBEST mechanism of particle swarm optimisation (PSO). The proposed MBDE is tested over four different power test systems of ELD problem with varying complexities. Numerical, statistical and graphical analysis reveals the competency of the proposed MBDE.