Improvement Of NSGA-? And Its Application In Unit Commitment Optimization

Multi-objective optimization problem?MOP?refers to the problem that multiple targets need to be optimized simultaneously in the process of optimization.These goals are contradictory to each other,and optimizing one of them will lead to the degradation of others.The solution of this kind of problem is to find a set of solutions that can optimize the performance balance among various multi-objective.As a typical MOP,the study of unit combination optimization has great economic and environmental benefits.Genetic algorithm has advantage in solving combinatorial optimization problem,as a derivative algorithm of GA,NSGA-II has a high efficiency in solving MOP,but there are also some disadvantages,such as easy to fall into the local optimal,and the local search ability is weak and so on.Aiming at these problems,this paper studies and improves the algorithm and applies it to the unit commitment optimization.This paper improves the crossover operator and mutation operator of the traditional NSGA-II.The NDX and adaptive adjustment mutation operator are introduced to replace the SBX and polynomial mutation operator.These improvements enhance the spatial search ability of the algorithm,and it can speed up the convergence speed and ensure the diversity of the population.In this paper,the Simulate Anneal Arithmetic?SAA?is introduced into NSGA-II.By annealing the population generated of each generation,the local search ability of the algorithm is improved and the convergence speed is accelerated.The improved algorithm is applied to the unit combination optimization problem.Aiming at the problem of traditional unit commitment optimization which only considers economic benefits but ignores environmental benefits,this paper proposes an objective function with the lowest emission ofCO₂ andSO₂;This paper puts forward a step by step optimization strategy based on the NSGA-II;Finally,the partial small fuzzy satisfaction function is used to select the optimal compromise solution.The simulation experiments show that the improved algorithm has better convergence and distribution,and it can effectively reduce coal consumption and pollution gas emissions when applied to the unit combination problem.The improved algorithm has better economic and environmental benefits.