Particle swarm optimization based generation maintenance scheduling using probabilistic approach

Abstract

This paper presents maintenance scheduling (MS) of generating units using particle swarm optimization (PSO) based probabilistic levelized risk method. The PSO for the generator maintenance scheduling generates optimal and feasible solution and overcome the limitations of the conventional methods. The maintenance of generators are directly associated with the overall reliability of the power system. The objective function of this paper is to reduce the loss of load probability (LOLP) for a power system. The capacity outage probability table (COPT) is the initial step in creating the maintenance schedule using the probabilistic levelized risk method. Probabilistic techniques are widely used in power system reliability evaluation of long-term planning. Moreover, this paper proposes the PSO to construct the generation model COPT without utilizing the analytical model. A case study for the roy billinton test system (RBTS) and real power system model, Thailand power system shows that the developed algorithm can achieve a substantial levelization in the reliability indices over the planning horizon and demonstrates the effectiveness of the proposed approach.