An Improved Particle Swarm Optimization Technique for Solving the Unit Commitment Problem

Automation of power system nowadays is one of the great spreading fields in electrical engineering. Artificial Intelligence Technique helps in developing and modifying the automated power system. The particle swarm optimization (PSO) technique is one of the recent artificial intelligent techniques. In this thesis a modified particle swarm optimization (MPSO) is utilized in Unit Commitment Problem (UCP). This paper presents a MPSO algorithm to solve a power generator scheduling problem known as the Unit Commitment Problem (UCP). The main objective of the unit commitment is to minimize the total production cost over the study period and to satisfy the constraints imposed on the system. The proposed technique is tested on 26 generator-scheduling problems with 24h scheduling horizon. The simulation results have been observed and analyzed. The developed technique can generate a high quality solution within short calculation time. Comparison of results with those of other methods justifies the flexibility, effectiveness and applicability of the proposed method with regards to minimizing both the total operation cost and execution time. KeywordsUnit Commitment (U.C), Modified Particle Swarm Optimization (MPSO), Economic Dispatch (E.D)