Exploration on Innovation Methods of Chinese Rural Financial Reform on the View of Efficiency

A large number of infeasible solutions often occur in population of evolutionary Computation (EC) solving the constraint combinatorial optimization problems. The greater the number of infeasible solutions in the population, the worse the performance of EC to search the solution, in the worst case, the algorithm ceases to run. The existing methods, penalty function or multi-objective optimization, can relieve partly the worst case of EC to run. However, they are actually to restrain the infeasible solutions surviving in population, the performance of the EC is not improved. In this study we propose an approach using an important feature of the infeasible solutions in Genetic Algorithms (GA). The approach can not only solve the problem of algorithm ceases to run, but also improve effectively the performance of genetic algorithms searching the optimal solution. From examination of the proposed method on multidimensional knapsack problems, the application of method is effective tosolve the problem of algorithm ceases to run as well as to improve clearly.