Cloudcomputing network flow prediction method and device based on time sequence statistical segmentation

Abstract

The invention relates to a cloud computing network flow prediction method based on time sequence statistics segmentation, which comprises the following steps: carrying out time-phased resource occupation statistics on a virtual machine in a cloud computing network, establishing a Markov state model according to a statistical result, and carrying out network flow prediction in a next time period according to the model. Compared with the prior art, for non-periodic network behaviors, the method carries out time sequence data analysis and prediction on a network boundary bandwidth monitoring result, flow characteristics and time sequence trends of different services in the network are identified, and the possibility of network adjacent flow interference hidden troubles in a future period of time is judged, so that a resource adjustment strategy is optimized, and too frequent scheduling and adjustment are avoided.

Description

technical field [0001] The invention relates to a network traffic prediction method, in particular to a cloud computing network traffic prediction method and device based on time series statistics and segmentation. Background technique [0002] Due to the variety of services and applications carried in the cloud computing environment, and different applications have different requirements for network resources, in particular, in today's cloud computing environment where multiple applications coexist, a prominent problem is "adjacent traffic interference" (Noisy Neigbour) problem, that is, while sharing resources, due to insufficient isolation and scheduling of resources, some applications will interfere with other adjacent and related applications when they generate a large amount of resource requirements or generate a large amount of network traffic, affecting Performance stability for other applications. [0003] In order to solve the impact of adjacent traffic interferen...

AI Technical Summary

Problems solved by technology

[0002] Due to the variety of services and applications carried in the cloud computing environment, and different applications have different requirements for network resources, in particular, in today's cloud computing environment where multiple applications coexist, a prominent problem is "adjacent traffic interference" (Noisy Neigbour) problem, that is, while sharing resources, due to insufficient isolation and scheduling of resources, some applications will interfere with other adjacent and related applications when they generate a large amount of resource requirements or generate a large amount of network traffic, affecting Performance stability for other applications

[0003] In order to solve the impact of adjacent traffic interference on other users on network resources, the current countermeasures mainly include virtual machine scheduling, network scheduling, resource isolation, etc., but these have a certain time overhead, that is, they cannot respond to network changes. real-time response, and may also have a certain impact on network performance itself. For example, virtual machine migration itself requires a certain amount of network bandwidth, so frequent adjustments cannot be made

Images