基于改进萤火虫算法优化的电力光纤线路状态预测模型研究  

Research on State Prediction Model of Power Optical Fiber Line Based on Firefly Algorithm Optimization

作　　者：孔历波 毛一凡 欧阳李亮 康恺 何超 KONG Libo;MAO Yifan;OUYANG Liliang;KANG Kai;HE Chao(Hangzhou Science and Technology Development Branch,Zhejiang Dayou Industrial Co.,Ltd.,Hangzhou 310052,China)

机构地区：[1]浙江大有实业有限公司杭州科技发展分公司,杭州310052

出　　处：《计算机测量与控制》2022年第8期50-55,61,共7页Computer Measurement &Control

摘　　要：为了提升电力通信系统光纤线路状态预测的准确率,提出一种基于改进萤火虫(FA)算法优化的电力光纤线路状态预测模型(FA-ARIMA-GRU);首先,针对FA寻优过早收敛和寻优精度低等问题,对整体距离进行指数加权平均,设计了迭代衰减步长因子,并且对偏差修正进行考虑,从而改善上述FA所存在的问题;其次,将改进的FA用于ARIMA-GRU光功率预测模型输入参数的优化,从而在一定程度上提升ARIMA-GRU预测模型输入参数的准确性;最终,通过仿真试验对FA-ARIMA-GRU预测模型的效果进行验证,结果表明FA-ARIMA-GRU预测模型具有较优的预测效果,精准预测光功率值,提前掌握电力光纤的线路状态,预知光纤线路故障、有效规避故障和保障电力通信传输通畅不间断。In order to improve the accuracy of state prediction of optical fiber lines in power communication system,a state prediction model for power optical fiber lines(FA-ARIMA-GRU,firefly algorithm auto represent integrated moving average mode gated recurrent unit)based on improved firefly algorithm is proposed.Firstly,aiming at the problems of premature convergence and low accuracy of the FA optimization,the overall distance is on the exponentially weighted average,the iterative attenuation step factor is designed,and the deviation correction is considered to improve the problems of the FA;Secondly,the improved FA is used to optimize the input parameters of the ARIMA-GRU optical power prediction model,so as to improve the accuracy of the input parameters of the ARIMA-GRU prediction model to a certain extent;Finally,the effect of the FA-ARIMA-GRU prediction model is verified through the simulation test.The results show that the FA-ARIMA-GRU prediction model has better prediction effect,can accurately predict the optical power value,master the line state of power optical fiber in advance,predict the optical fiber line fault,effectively avoid the fault and ensure the smooth and uninterrupted power communication transmission.

关 键 词：电力光纤 光功率 萤火虫算法 电力光纤线路状态预测模型 

分 类 号：TM216[一般工业技术—材料科学与工程]