TRAFFIC ABNORMALITY MONITORING METHOD AND APPARATUS BASED ON MODEL, AND DEVICE AND STORAGE MEDIUM

摘要

The present application relates to the field of network security. Disclosed is a traffic abnormality monitoring method based on a model, the method comprising the following steps: collecting traffic monitoring data and taking same as sample data, and constructing a model function corresponding to an autoregressive moving average model; calculating a covariance matrix of a theoretical traffic value output by the model function and an actual value by means of a preset Kalman filtering algorithm; calculating, by means of the model function, a traffic value of a time to be measured, so as to obtain a second prediction value; calculating a traffic fluctuation range of said time according to the covariance matrix; monitoring an actual traffic value corresponding to said time, and determining whether the actual value is within the traffic fluctuation range; and if the actual value is not within the traffic fluctuation range, determining that traffic of said time is abnormal. Further disclosed are a traffic abnormality monitoring apparatus, and a device and a readable storage medium. According to the present application, comprehensive analysis of traffic is realized, the fluctuation range of the traffic is predicted more accurately, and thus, traffic abnormality monitoring is performed.