Constrained routing control system based on gns graph predictor

Abstract

The invention provides a constraint routing control system based on GNs graph predictor, including a QoS routing control system and a GNs graph predictor; Different communication traffic changes provide pre-judgment criteria to the QoS routing control system; the GNs graph predictor performs offline calculation of network communication traffic, and feeds the offline calculation results to the QoS routing control system to improve the current QoS routing implementation efficiency; the QoS routing control system regularly The historical data of network communication traffic is fed back to the GNs graph predictor, and the GNs graph predictor re-calculates offline according to the received feedback data. The invention simulates and calculates the node data propagation situation under the instantaneous peak load situation of local nodes through the GNs network, and constructs effective local isolation and routing changes according to this situation, so as to control the instantaneous peak load within a small range and avoid its impact on the overall communication. The impact and harm of the network.

Description

technical field [0001] The invention relates to the technical field of network routing control, in particular to the network load balancing technology, and in particular to a constrained routing control system based on a GNs graph predictor. Background technique [0002] With the advent of the 5G era, Internet multimedia applications, such as video chat, webcasting, Internet calling, and distance education, emerge one after another. Data transmission needs to meet different quality of service (QoS, quality of service) requirements, and multi-QoS constrained routing has become an effective way to solve the QoS problem. At the same time, under 5G network conditions, if the communication traffic of some nodes is instantaneously too high, these large-scale data will spread in the surrounding 5G nodes, causing local network congestion, blocking other normal traffic passing through these nodes, and affecting the entire network. network stability. Moreover, in the actual network ...

AI Technical Summary

Problems solved by technology

In some cases, when the network structure changes, there will be peak traffic due to some reasons. At this time, the existing routing control system will not be able to adjust in time for the changed network structure;

[0006] 3) The calculation of the large-scale blocking model is difficult

This kind of peak traffic is often sudden and irregular. This kind of peak traffic will bring a lot of load impact to the network, causing a large area of ​​network nodes to be overloaded.

In the face of such peak traffic, the existing routing management system is difficult to cope with

Images