A mobile network performance early warning prediction method based on trend extrapolation clustering

Abstract

The invention relates to a mobile network performance early warning pre-judging method, in particular to a mobile network performance early warning pre-judging method based on trend extrapolation clustering. The method comprises the following steps that 1, trend extrapolation and a K center point clustering algorithm are utilized for calculating early warning thresholds of all performance indexes; 2, early warning and pre-judging of time granularity are calculated in real time to obtain the pre-judging change. The method can solve the problem that due to abnormal points of historical data, the early warning thresholds are inaccurate, the trend change can be reflected, the early warning thresholds can be more accurate, multiple pieces of early warning information are gathered into one piece of pre-judging according to the network topology, the pre-judging change can be reflected, and the performance change situation of a network can be reflected on the whole.

Description

technical field [0001] The present invention relates to a mobile network performance early warning and pre-judgment method, more specifically, to a mobile network performance early warning and pre-judgment method based on trend extrapolation and clustering. Background technique [0002] The mobile operator has carried out real-time monitoring on the network operation equipment, and each equipment will regularly generate monitoring data for a period of time for query and analysis. Current mobile network anomaly analysis generally includes two methods: one is: after discovering a network fault, query historical monitoring data and analyze the cause of the fault. This method generally has a certain hysteresis, that is, the cause can only be analyzed after the failure occurs, and then maintenance can be carried out. The second is: set the early warning threshold of each performance index, and monitor each current performance index in real time. If the index is found to exceed t...

AI Technical Summary

Problems solved by technology

This prediction method is more accurate for certain points after the prediction. If the number of prediction points is large, the error will be large, and if the latest sequence is predicted to be abnormal, it will have a greater impact on the prediction results and is prone to errors.

Images