Multi-Objective Optimization of Crop Planning Using Genetic Algorithm

Abstract

In this study, first introduce a novel approach to the long term multi-objective crop planning using Genetic Algorithm. Genetic Algorithm is one of the global optimization schemes that have gained popularity as a means to attain water resources optimization. It is an optimization technique, based on the principle of natural selection, derived from the theory of evolution, is used for solving optimization problems. In the present study Genetic Algorithm has been used to develop a policy for optimizing the maximum net benefits and minimize the irrigation water requirements. The study area is of Punjab and Bhakra Dam, India. The data used for this study has taken from many research papers and government sites. We analyze the relationship between GA control parameters (population size, crossover fraction, mutation probability) and performance. We identify a combination of population, crossover and mutation which searched the fitness landscape efficiently. The net benefits increases with increases in population size and decreases with increases in both crossover fraction and mutation probability. The constraints considered for this optimization are crop area restrictions, crop water restrictions and canal capacity restrictions. The results derived by using GA shows that net benefits has maximized in single objective optimization and in multi-objective optimization water requirements has maximized but with minimum net benefits.