Research On Optimization Solution Strategy Of Steam Power System Operation In Petrochemical Enterprises

Intelligent optimization algorithm is widely used in Steam Power System(SPS)optimization scheduling.Particle swarm optimization algorithm is widely used to solve various optimization problems because of its advantages such as few adjustment parameters,simple learning strategy,fast convergence and easy implementation.However,particle swarm optimization algorithm has some problems,such as poor processing of discrete optimization problems,loss of diversity and prematurity.Aiming at the problems existing in the traditional particle swarm optimization algorithm,this paper takes the optimization scheduling problem of steam power system in petrochemical enterprises as the research object,and improves the particle swarm optimization algorithm in order to reduce the total cost.The performance of particle swarm optimization depends on the choice of inertia weight and acceleration factor to a large extent.In this paper,a TVAFIWPSO algorithm is proposed.Eight classical test functions were selected for simulation experiment,and the simulation results were compared and analyzed with the optimal value,mean value and variance.Friedman test was carried out with SPSS software,and the results were analyzed and tested.The results were compared with particle swarm optimization algorithm of inertia weight Gaussian decreasing strategy,particle swarm optimization algorithm of linear variable parameters,and basic particle swarm optimization algorithm.Test the performance of the new algorithm.The simulation results show that the new strategy can effectively enhance the particle’s ability to jump out of the local extreme value in the optimization process,and improve the efficiency and convergence accuracy of the algorithm.Combining the optimization characteristics of particle swarm optimization algorithm with the partitioning ideas of K-means algorithm,combining TVAFIWPSO algorithm with K-means algorithm and LCPPSO optimization algorithm with linear change parameters,a K-means dual particle swarm optimization algorithm is proposed.Ten test functions were selected for simulation experiments to test the performance of the algorithm.The K-TLPSO optimization algorithm was compared with four other particle swarm optimization algorithms,and the simulation results were compared with the mean value,variance and optimal value.Friedman test was carried out with SPSS software,and the test output results were analyzed.The simulation results show that this strategy enhances the information sharing among particles,enhances the optimization ability of particle swarm,and can obtain the optimal solution faster.Two engineering examples are used to simulate the TVAFIWPSO algorithm and K-TLPSO optimization algorithm.The results show that the new strategy provides the optimal operation scheme in line with the actual demand,and reduces the total cost of system operation in different degrees.The results show that the new strategy is reliable in optimization and can deal with the optimization scheduling problem of steam power system better.