基于Mallat算法的在推理机集群负载均衡中应用研究  

Research on application of Mallat algorithm in load balancing of inference engine cluster

作　　者：徐江涛[1] 刘萍萍[1] XU Jiang-tao;LIU Ping-ping(Computer Department,Xi’an Technological University,Xi’an 710021,China)

机构地区：[1]西安工业大学计算机学院,陕西西安710021

出　　处：《电子设计工程》2020年第12期39-43,共5页Electronic Design Engineering

摘　　要：针对航天器的健康管理问题,采用预测技术可提前预知航天器故障,为航天器的故障排除赢得了宝贵时间,从而提高了航天器运行安全性和可靠性。针对遥测数据的非平稳性和周期性特点,引入Mallat算法的时间序列短期预测模型。通过推理机进程负载均衡软件的实际运行结果分析,预测结果边界和实际数据突变的趋势基本一致,预测数据与实际数据相似度在95%以上。In view of the problem of spacecraft health management,the prediction technology can predict the failure of spacecraft in advance,which has won precious time for the troubleshooting of spacecraft,thus improving the safety and reliability of spacecraft operation.According to the non⁃stationary and periodic characteristics of telemetry data,a short⁃term prediction model of time series based on Mallat algorithm is introduced.Through the analysis of the actual operation results of the load balancing software of the inference engine process,the trend of the prediction result boundary and the actual data mutation is basically the same,and the similarity between the prediction data and the actual data is more than 95%.

关 键 词：MALLAT 时间序列预测法 周期自回归模型 负载均衡 

分 类 号：TN0[电子电信—物理电子学]