Optimization And Improvement Of Swarm Intelligent Algorithm And Its Application In Power Dispatching

In today's society,most problems are complex.For ease of handling,it is expressed as an optimization problem.The optimization problem is usually accompanied by the global optimal value or the local optimal value.The optimization using meta-heuristic has become a very popular research topic in recent years.Swarm intelligence?SI?is a general term for a group of intelligent groups with self-organizing behavior,that is,based on the aggregation of individual group members,it also exhibits independent intelligence.The swarm intelligence algorithm takes artificial bee colony algorithm and whale swarm algorithm as examples.This article mainly optimizes these two algorithms.They are:Bee Spices Transition with Rapid Global Optimization Algorithm?BSTRGOA?,a non-deterministic optimized whale group algorithm?A Non-deterministic Modified Whale Optimization Algorithm,NMWOA?,and apply them to power in scheduling applications,study algorithm performance.For the BSTRGOA algorithm,a strategy including bee species evolution and a global optimization fast search mechanism are proposed.In order to improve the global search capability of the ABC algorithm,the bee species evolution strategy function p?t?is introduced to dynamically change the number of lead bees and follower bees to balance the global exploration capability and local search capability;at the same time,the global optimization fast search mechanism is introduced,In this way,the exploration ability of the investigation bee is enhanced,the local optimum is effectively jumped out,and a better quality food source is searched.The BSTRGOA algorithm uses the CEC2017 benchmark test function for experiments,and compares it under a single-peak function and a complex multi-peak function.The results show that the BSTRGOA algorithm can effectively improve the convergence speed of the ABC algorithm,and it also shows better optimization performance on complex multi-peak functions,improving the optimization accuracy.Compared with other evolutionary algorithms,it also shows that the BSTRGOA algorithm has a better performance in solving the function optimization problem.In addition,the BSTRGOA algorithm is also suitable for power dispatch analysis,and the conclusion also proves to be effective.On the basis of the heuristic algorithm of whale group,a non-deterministic optimal whale group algorithm?A Non-deterministic Modified Whale Optimization Algorithm,NMWOA?is proposed for the problem of slow convergence speed and local extreme value.Firstly,in order to improve the initial target-free individual search efficiency of the NMWOA algorithm,the control coefficient?^??is optimized,and the trend optimization function f?t?is proposed.Then,the weight coefficient??t?is proposed and constructed to dynamically change the proportion of the current optimal solution,so as to strengthen the local search of the population.The CEC 2017 benchmark test function is selected in the experiment.The results show that the NMWOA algorithm has good performance in solving the multi-dimensional function optimization problem,and can effectively improve the convergence speed and optimization accuracy of the algorithm.Finally,the BSTRGOA and NMWOA algorithms were applied to the economic dispatching of the power system of 5 generating units,respectively.The results prove that the BSGTOA and NMWOA algorithms can effectively improve efficiency and reduce cost.