摘要
针对大规模电力通信网络故障恢复问题,提出一种基于改进差分进化的故障恢复策略生成方法。首先以最大化恢复业务数量为目标建立优化模型,然后利用反向学习策略优化差分进化的种群初始化,构建自适应交叉概率和变异因子,并基于模拟退火算法改进选择机制,在提升算法全局寻优能力的同时,加快算法收敛速度。实验结果表明,该方法能够有效实现电力通信网络故障恢复,在同等恢复资源条件下,恢复更多的通信业务。
Aiming at the problem of large-scale power communication network fault recovery,a method of fault recovery strategy generation is proposed based on improved differential evolution.Firstly,the optimization model is established to maximize the number of recovery services.Then,the population initialization of differential evolution is optimized by using reverse learning strategy.Adaptive crossover probability and mutation factor are constructed.The selection mechanism is improved based on simulated annealing algorithm.This method not only improves the global optimization ability of the algorithm,but also speeds up the convergence speed of the algorithm.The experimental results show that this method can effectively recover the power communication network fault,and recover more communication services under the same recovery resources.
作者
王浩
金广祥
李疆生
刘丽榕
WANG Hao;JIN Guang-xiang;LI Jiang-sheng;LIU Li-rong(State Power Economic Research Institute,Beijing 102209,China)
出处
《信息技术》
2020年第9期110-114,120,共6页
Information Technology
关键词
电力通信网络
故障恢复
差分进化
模拟退火
power communication network
fault recovery
differential evolution
simulated annealing