基于LSTM的云环境异常智能检测方法研究

Anomaly intelligent detection method in cloud environment based on LSTM

为提升运维人员响应速度,降低云环境异常对云上应用的影响,研究了一种基于长短期记忆(LSTM,Long Short-Term Memory)的云环境异常智能检测方法。通过将传统时间序列分析算法同LSTM神经网络相结合,实现在线预测云环境监控数据,并通过正态分布和贝叶斯推理定义预测波动范围,快速准确地判别云环境异常。在铁路云数据中心环境中进行测试验证,同其他时序预测方法的比较证明,本方法具有判别准确性高、对各种场景适用性强的优点,可为铁路大规模云数据中心智能运维实施提供一种有效的异常检测手段。

In order to improve the response speed of operation and maintenance personnel and reduce the impact of cloud environment exceptions on cloud applications,this paper studied an anomaly intelligent detection method in cloud environment based on LSTM(Long Short-Term Memory).The paper combined traditional time series analysis algorithm with LSTM neural network to implement on-line prediction of cloud environment monitoring data,and defined the prediction fluctuation range by normal distribution and Bayesian inference to quickly and accurately identify cloud environment anomalies.Tested and verified in the railway cloud data center environment,Compared with other time series prediction methods,this method has the advantages of high discrimination accuracy and strong applicability to various scenarios.It can provide an effective anomaly detection method for the implementation of intelligent operation and maintenance of large-scale railway cloud data center.