Using the knowledge of the constraints network to design an evolutionary algorithm that solves CSP

This paper describes an Evolutionary Algorithm to solve Constraint Satisfaction Problems. Knowledge about properties of the constraint network can permit us to define a fitness function which is used to improve the stochastic search. A selection mechanism which exploits this fitness function has been defined. The algorithm has been tested by running experiments on randomly generated k-colouring graphs, with different constraints networks. The results suggest that the technique may be successfully applied to other CSP.