基于粒子群优化算法的CE模型研究  

CE model based on particle swarm optimization algorithm

作　　者：汪瑾 王国军 胡静 WANG Jin;WANG Guo-jun;HU Jing(State Grid Ningxia Electric Power Co.,Ltd.,Yinchuan 750001,China)

机构地区：[1]国网宁夏电力有限公司,银川750001

出　　处：《信息技术》2020年第6期145-148,153,共5页Information Technology

摘　　要：针对CE模型多参数测量数据的融合性弱和自适应调度能力差的问题,提出基于粒子群优化算法的CE模型。首先构建多参数测量数据传输的约束进化参量,根据多参数测量数据融合的优化训练,得到粒子群的适应度函数,建立多参数测量数据传输模型,然后进行CE模型的约束参量输出控制。在此基础上采用粒子群寻优方法进行多参数测量数据的寻优控制,分布式检测多参数测量数据,建立多参数测量数据分布式检测模型,采用非线性重构的方法进行多参数测量数据CE模型构造过程中的自适应调度,实现多参数测量数据的稀疏性重组和融合调度。仿真结果表明,采用该方法进行多参数测量数据CE模型设计,提高了数据的融合和自适应调度能力,粒子群进化寻优的收敛性较好。In view of the weak fusion of multi parameter measurement data and poor adaptive scheduling ability of CE model,a CE model based on particle swarm optimization algorithm is proposed.Firstly,the constraint evolution parameters of multi parameter measurement data transmission are constructed.According to the optimal training of multi parameter measurement data fusion,the fitness function of particle swarm is obtained,the multi parameter measurement data transmission model is established,and then the constraint parameter output control of CE model is carried out.On this basis,particle swarm optimization method is used to control the optimization of multi parameter measurement data,multi parameter measurement data is detected by distribution,distributed detection model of multi parameter measurement data is built.Nonlinear reconstruction method is used to adaptive scheduling in the construction process of multi parameter measurement data CE model,and sparse reorganization and fusion scheduling of multi parameter measurement data are realized.The simulation results show that the CE model of multi parameter measurement data designed by this method improves the ability of data fusion and adaptive scheduling,and the convergence of particle swarm optimization is better.

关 键 词：粒子群优化 数据融合 CE模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]