基于自适应混合粒子群算法的分布式馈线故障定位

Adaptive Hybrid Particle Swarm Optimization-based Distributed Feeder Fault Location

针对分布式电源接入配电网后使传统故障定位方法不适用的问题,提出一种混合粒子群算法。将压缩因子与线性递减权重引入粒子群算法,借鉴遗传算法中杂交与自然选择思想,在每次迭代中根据杂交率令粒子两两杂交,并用适应度值优秀的一半粒子替换差的一半,同时对馈线网络构造无向图以方便计算。建立分布式电源的配电网络模型,模拟不同情况下通过优化算法进行故障定位,结果表明改进算法能快速、准确地定位故障。

A hybrid particle swarm optimization algorithm was proposed,aiming at addressing the inapplicability of conventional fault location methods to distributed generation-integrated distribution networks.The compression factor and linear decline weight were introduced into PSO,and the ideas of hybridization and natural selection in genetic algorithm were also borrowed.In each iteration,the particles were hybridized in pairs according to the hybrid rate,and half of the particles with higher fitness values were substituted for the other half with poor fitness values.The distribution network model for distributed generations was established to simulate the results of fault location under different conditions,which showed that the modified algorithm can locate faults quickly and accurately.