Improved Differential Evolution Algorithm And Its Application In Load Distribution Of Thermal Power Plant

Differential Evolution Algorithm(DE)is a newly developed group intelligent optimization calculation method.Compared with other intelligent optimization methods,it has the characteristics of simple evolution principle,few control parameters and strong robustness;the mutation operator and crossover operator designed by referring to the evolutionary mechanism of the natural population make it possible to optimize the solution without resorting to external feature information.Therefore,the DE algorithm is suitable for solving complex high-dimensional optimization problems.Thermal power plant load distribution is a nonlinear multi-objective multi-constraint optimization problem,the use of mathematical optimization methods based on analytical mathematics has the disadvantages of finding the optimal solution and large calculation time span,Therefore,there is an urgent need to design new and effective optimization methods.Due to its unique performance advantages,the DE algorithm is used by researchers to solve the load distribution problem of thermal power plants.This article will conduct research from three aspects: first,improve the performance of the DE algorithm;second,establish a single objective mathematical model for economic optimization of thermal power plant load distribution,and establish a dual objective mathematical model for economic and environmental optimization of thermal power plants;finally,the improved DE algorithm is applied to solve the above two thermal power plant load distribution problems.Main tasks as follows:(1)To improve the performance of the DE algorithm,this paper proposes a combination mutation strategy and parameter adaptive differential evolution algorithm(called: Co APDE).The adaptive adjustment strategy of scaling factor F and crossover rate CR is designed according to the number of individuals inherited from the parent and experimental populations;at the same time,two conventional and superior mutation strategies are screened out through experiments to form a combination of Co APDE algorithms Mutation strategy.Through the evaluation of 30 standard test functions of CEC2014 and comparison with five improved DE algorithms,the experimental results show that the Co APDE algorithm has a faster convergence speed and a stronger ability to seek optimization.(2)Aiming at the economic optimization problem of thermal power plant load distribution,establish a single objective mathematical model of thermal power plant economic load distribution problem,and consider the power balance equation and thermal power unit active power limit as constraints.At the same time,the Co APDE algorithm is used to solve the single-objective optimization problem of thermal power plant economic load distribution,and the following two problems are solved: the problem of three generator sets considering the valve point effect and the network loss constraint value,and the 13 considering only the valve point benefit constraint value Generator set problem.The experimental results show that the optimization of the Co APDE algorithm for this problem can reduce the coal consumption,and at the same time,it can reduce the network loss and obtain a satisfactory solution.(3)Aiming at the economic and environmental optimization problems of thermal power plant load distribution,establish a dual objective mathematical model of economic and environmental load distribution problems.At the same time,the Co APDE algorithm is used to solve the economic and environmental load distribution problems of ten thermal power units in a thermal power plant.According to the cost penalty factors of thermal power units,a dual-target mathematical model based on the mathematical model of fuel consumption and the mathematical model of pollutant emissions is constructed;at the same time,heuristic strategies are used to modify individual solutions that do not meet the constraints,and the principle of minimum value according to the priority list Distribute the output power of thermal power units.The experimental results show that the solution optimized by the Co APDE algorithm not only reduces the fuel consumption required by the thermal power unit,but also reduces the pollutant emissions.