Artificial Bee Colony Based Solution Technique for Generator Maintenance Scheduling

Abstract

Effective generator maintenance scheduling (GMS) is very important to a power utility for the economical and reliable operation of a power system. An optimal GMS increases the operation reliability, reduces power generating cost and extends the generator lifetime. The GMS problem has been formulated as a combinatorial optimisation task, with explicit and simultaneous treatment of multiple objectives: maximisation of reliability, minimisation of fuel costs and minimisation of constraint violations. Many mathematical methods and heuristic search techniques have been reported to find the optimal solution of GMS problem. However, these methods have many limitations and require valid approximations. This paper formulates a general GMS problem using a reliability criterion and a novel bio-inspired search technique, namely artificial bee colony (ABC), is applied to determine the optimal generator maintenance schedule. The performance and effectiveness of the proposed algorithm in solving the GMS problem is illustrated and compared with the recent reports on the standard 21-unit test system with two different peak load demands and crew requirements and a practical 49-unit Nigerian power system. The simulation results show that the proposed ABC is a very effective method for GMS problems.