A Unit Commitment Solution Using Differential Evolution and Economic Dispatch Using Shuffled Complex Evolution with Principal Component Analysis

This paper presents a new algorithm based on differential evaluation, adaptable crossover using Triangular distribution factor and Shuffled complex evolution with Principal component analysis namely DE-TCR-SP-UCI for the solution of Unit Commitment-Economic Load Dispatch problem. The salient features of the proposed algorithm are: (1) An adaptable crossover using triangular distribution factor is included. Hence, the algorithm is able to interlink the cross over probability in conjunction with the non-separable and decision variable dependency of UC problems. (2) A local search in each chromosome of algorithm using Sequential Quadratic Programming (SQP) is performed. This approach has proved in improving the performance of the classical DE algorithm (3) The SP-UCI algorithm solves the problem of population degeneration. (4) The SP-UCI algorithm also combines the strength of shuffled complex, the Nelder-Mead simplex and multi-normal re-sampling to achieve efficient and effective high-dimensional optimization. (5) By representing the chromosome intelligently, the chromosome length and population size is reduced. The proposed algorithm is tested with standard 4 units, 8hour and standard 10 units, 24 hour test systems. Results indicate that the proposed method finds better optimal solution when compared to the conventional known methods reported in the literature.