Data center network energy-saving routing algorithm based on software defined network (SDN) architecture

Abstract

The invention request to protect a data center network energy-saving routing algorithm based on a software defined network (SDN) architecture, and belongs to the technical field of communication networks. The method designs a heuristic algorithm for computing a minimal energy consumption topology sub-set, and a load balancing mechanism is introduced into a traffic scheduling process of the minimal energy consumption topology sub-set aiming at the problem of congestion of a part of links that may be occurred in a network in existing energy-saving routing schemes, so that the problem of link congestion caused by uneven distribution of traffic is avoided while the maximal link utilization rate of the network is ensured. In addition, the method fully considers power consumption characteristics of different devices, a device power consumption scaling ratio is introduced into the energy-saving routing algorithm, a stream of which path distribution does not meet the best under the device power consumption scaling ratio is re-routed, thus achieving the best energy-saving routing computation under the power consumption characteristic of the device.

Description

technical field [0001] The invention belongs to the technical field of communication networks, in particular to an energy-saving routing algorithm for a data center network based on an SDN architecture. Background technique [0002] The new data center network widely adopts the "rich connection" topology. The introduction of a large number of switches increases the proportion of energy consumption in the network, resulting in serious waste of energy consumption under low load. Software Defined Network (Software Defined Network, SDN), as a new type of network architecture, provides a new idea for the green energy saving of data center network with its centralized control network characteristics. The real-time collection of network topology information and network device flow information through the SDN controller makes it convenient to deploy energy-saving traffic engineering on the entire network at the routing level. [0003] At present, the energy-saving solutions for da...

AI Technical Summary

Problems solved by technology

However, the existing network-level energy-saving technologies generally have the following problems: 1. The calculation complexity is high, the time-consuming is long, and it is difficult to implement in the actual network

2. The load balancing mechanism is not introduced into the flow path allocation process, resulting in some links being too congested

3. No further consideration is given to the power consumption characteristics of the device

Images