With the technological advancements, Distributed Generation (DG) has become a common method of overwhelming the issues like power losses and voltage drops which accompanies with the leaf of the feeders of radial distribution networks. Many researchers have used several optimization techniques and tools which could be used to locate and size the DG units in the system. Particle Swarm Optimization (PSO) is one of the famous optimization techniques. However, the premature convergence is identified as a fundamental adverse effect of this optimization technique. Therefore, the optimization problem can direct the objective function to a local minimum. This paper presents a variant of PSO techniques, “Comprehensive Learning Particle Swarm Optimization (CLPSO)” to determine the optimal placement and sizing of the DGs, which uses a novel learning strategy whereby all other particles’ historical best information and learning probability value are used to update a particle’s velocity. The CLPSO particles learn from one exampler for few iterations, instead of learing from global and personal best values in every iteration in PSO and this technique retains the swarm's variability to avoid premature convergence. A detailed analysis was conducted for the IEEE 33 bus system. The comparison results have revealed a higher convergence and an accuracy than the PSO.
Advanced Pareto Front Non-Dominated Sorting Multi-Objective Particle Swarm Optimization for Optimal Placement and Sizing of Distributed Generation
