为了提高电能质量扰动(power quality disturbance,PQD)识别结果的准确性,笔者提出一种基于改进灰狼优化算法(improved grey wolf optimization,IGWO)优化最小二乘支持向量机(least squares support vector machine,LSSVM)的PQD识别方法.通过采用收敛因数指数调整、自适应位移和权重动态修订等措施对灰狼优化算法进行改进,得到IGWO算法;以PQD信号的 9 个特征量为支持向量、7 种PQD类型为输出量,利用IGWO算法寻找LSSVM的最优参数,建立基于IGWO-LSSVM的PQD识别模型并进行仿真分析,且与其他模型的识别结果进行对比.结果表明,相比算例中列出的几种对比模型,IGWO-LSSVM模型识别结果的正确率更高,验证了所提PQD识别方法的有效性和实用性.
Power Quality Disturbance Identification Method Based on LSSVM Optimized by IGWO Algorithm
In order to improve the accuracy of power quality disturbance(PQD)identification results,a PQD identification method based on improved grey wolf optimization algorithm(IGWO)optimized least squares support vector machine(LSSVM)is proposed.The grey wolf optimization algorithm is improved by using convergence factor index adjustment,adaptive displacement and weight dynamic revision,and the IGWO is obtained.Taking nine characteristic quantities of PQD signal as support vectors and seven PQD types as output quantities,the IGWO is used to find the optimal parameters of LSSVM,and the PQD recognition model based on IGWO-LSSVM is established.The simulation analysis is carried out and the recognition results are compared with those of other models.The results show that compared with several comparison models listed in the example,the IGWO-LSSVM model has higher recognition accuracy,which verifies the effectiveness and practicability of the proposed PQD recognition method.
power quality disturbanceidentificationimproved grey wolf optimizationleast squares support vector machines-transformation
国家科技期刊平台
NSTL
万方数据
