A genetic algorithm for solving resource-constrained project scheduling problem

Genetic Algorithm (GA) is an effective method for solving the classical resource-constrained project scheduling problem. In this paper we propose a new GA approach to solve this problem. Our approach employs a new representation for solutions that is an activity list with two additional genes. The first, called serial-parallel scheduling generation scheme gene (S/P gene), determines which of the two decoding procedures is used to computer a schedule for the activity list. The second, called forward-backward gene (F/B gene), indicates the direction in which the activity list is scheduled. The two genes determine the decoding procedure and decoding direction for the related activity list simultaneously. This allows the GA to adapt itself to a problem instance. The performance evaluation done on the 156 benchmark instances shows that our GA yields better results than the other two GAs which make use of the activity list representation and the activity list with S/P gene representation respectively. It is applicable developing self-adapting GA for the related optimization problems.