基于机器学习的通信调度故障预警技术  

Communication Scheduling Fault Early Warning Technology Based on Machine Learning

作　　者：宋曦 窦琛琛 尚为良 戴芮 SONG Xi;DOU Chenchen;SHANG Weiliang;DAI Rui(State Grid Gansu Electric Power Company,Lanzhou 730000,China;Information and Communication Company of State Grid Gansu Electric Power Company,Lanzhou 730050,China)

机构地区：[1]国网甘肃省电力公司,甘肃兰州730000 [2]国网甘肃省电力公司信息通信公司,甘肃兰州730050

出　　处：《微型电脑应用》2023年第4期179-182,共4页Microcomputer Applications

摘　　要：针对电力通信网络出现的故障因素,为了提高网络通信能力和质量,该研究提出一种基于机器学习的通信调度故障预警技术。设计了基于S3C6410的控制芯片,并提出了基于DM9000单芯片的通信控制器,二者互相配合,实现了电力通信网络的控制,而且功耗低、故障模式判断能力强。所提方案还通过提取电力网络运行状态特征,分析通信网络输出信息,构建自适应调度算法模型提高通信调度故障预警能力。试验表明,所提方案可靠性好,正确率在90%以上,准确度高,为通信调度故障预警技术做出一定的贡献。Aiming at the fault factors of the power communication network,in order to improve the network communication capacity and quality,this research proposes a communication scheduling fault warning technology based on machine learning,designs a control chip based on S3C6410,and proposes a communication based on DM9000 chip.The two controllers cooperate to realize the control of the power communication network,with low power consumption and strong fault mode judgment ability.The research proposes a scheme to improve the early warning capability of communication dispatching failures by extracting the characteristics of the power network operation status,analyzing the output information of the communication network,and constructs an adaptive dispatching algorithm model.Tests show that the presented proposal has good reliability,with a correct rate of over 90%and high accuracy.The institute’s proposal has made a certain contribution to the fault early warning technology of communication dispatch.

关 键 词：电力通信网络 网络通信 控制芯片 机械学习 自适应调度算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] TP30[自动化与计算机技术—计算机科学与技术]