Network optimization method and device

Abstract

The invention discloses a network optimization method and device. The method comprises that a polling period is determined according to the communication load; rolling sampling is carried out on all preset communication support cells according to the polling period to obtain the instantaneity index of each the communication support cell; and congestion of each communication support cell is predicted according to the obtained instantaneity index as well as historical performance index under the same communication support scene; and optimization adjustment is carried out according to the congestion prediction result of each communication support cell.

Description

technical field [0001] The invention relates to the field of mobile communication network management, in particular to a network optimization method and device. Background technique [0002] With the increase of communication users and the development of communication terminals, various communication networks have undergone major changes. In daily life, concerts, large-scale conferences, festivals and other user-gathering activities often occur in many areas, and operators are often unable to detect these activities in time due to reasons such as message lag, large network, and slow index extraction. In this way, in communication assurance, even if such cells are monitored, often because the network management can only extract 15-minute granularity data, the detection of cell congestion lags behind, and finally the effect of communication assurance is not good. [0003] In the existing technology, operators mainly use network management index extraction, Man Machine Languag...

AI Technical Summary

Problems solved by technology

In daily life, concerts, large-scale conferences, festivals and other user-gathering activities often occur in many areas, and operators are often unable to detect these activities in time due to reasons such as message lag, large network, and slow index extraction. In this way, in communication assurance, even if monitoring such cells is carried out, the network management can only extract data at a granularity of 15 minutes, which makes the detection of cell congestion lag behind, and finally leads to poor effect of communication assurance

[0003] In the existing technology, operators mainly use network management index extraction, Man Machine Language (MML, Man Machine Language) sampling, and resource release before guarantee to implement network optimization. However, these methods have the following defects: First, Sudden user aggregation behavior cannot be known in advance, and the best time for adjustment is often missed; second, the traditional network management index extraction is used for protection, and the data extraction cycle is too long to respond to some sudden user aggregation communication behaviors in time And lead to congestion; third, use the sampling results of a single base station occupancy for analysis, because the cycle is long and the single sampling is too random, the accuracy is low, and it is impossible to respond to sudden user gathering communication behaviors in time; fourth, advance The voice and data network resources have been fixed, and it is impossible to accurately evaluate the different needs of voice and data during busy hours. There is no method for dynamically adjusting base station resources, and it is impossible to release resources in time to improve user perception when idle.

[0004] At present, there is no mature network optimization method to quickly respond to user communication behaviors in various security scenarios; in order to cope with these sudden activities, the communication network needs to have a sufficiently fast discovery mechanism and adjustment countermeasures to adapt to such changes

Images