A multipopulation cultural algorithm for the electrical generator scheduling problem

The electrical generator maintenance scheduling problem has been tackled by a variety of traditional optimisation techniques over the years. This paper proposes a method to solve the maintenance scheduling problem, called the parallel co-operating cultural algorithm (PARCA). In the proposed model, a variety of selection mechanisms, operators, communication methods, and local search procedures are applied to each solution generated by genetic operators and parameters as explained in the sequel. Our cultural algorithm framework combines the weak search method with the knowledge representation scheme for collecting and reasoning knowledge about individual experience. (C) 2002 IMACS. Published by Elsevier Science B.V. All rights reserved.