Multiple controller energy saving optimization method based on data surface flow prediction

A flow prediction, multi-controller technology, applied in data exchange networks, digital transmission systems, electrical components, etc., can solve problems such as uneven load and unrealized load balance of controllers

CN104935460AActive Publication Date: 2015-09-23ZHEJIANG UNIV
5 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2015-09-23

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a multiple controller energy saving optimization method based on data surface flow prediction. The method creates a mode for controllers in a cluster to mutually communicate on the problem of flow, and dynamically regulates the quantity of movable controllers among cluster controllers based on flow prediction and flow bearing recording, so as to realize energy conservation and environment protection of the cluster controllers. According to the invention, when a network is in an idle state, the method can improve energy saving performance of SDN cluster controllers, and make the cluster controllers more environmentally friendly. A present SDN cluster controller, such as OpenDaylight, does not consider the problem of extra energy consumption of surplus controllers caused by reduced network flow. Accordingly, a present SDN cluster controller can employ the method to improve network energy saving performance. The method realizes reasonable arrangement of controllers in a distributed software-defined network, and avoids energy waste of excessive low load controllers in the software-defined network, thereby realizing network energy conversation.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of software-defined networks. In order to improve the energy saving of each controller in a multi-controller SDN network, a multi-controller energy-saving optimization method based on data plane traffic prediction is proposed. Background technique

[0002] In a multi-controller SDN network architecture, when there is a large drop in network traffic, such as in the middle of the night, the network pressure on some controllers in the controller cluster is not high, and can be merged to other controllers in the cluster. , thereby reducing the number of active controllers in the cluster controller, thereby reducing the energy consumption of the cluster controller, and making the overall SDN network cluster controller more energy-saving and environmentally friendly.

[0003] The content of the present invention relates to the following existing concepts or technologies in SDN:

[0004] The SDN controller is a ne...

Examples

Embodiment Construction

[0032] In the following, the present invention will be described in detail in conjunction with Tables 1 to 4 by taking the traffic distribution of super node A and SDN controller nodes B and C in the domain as an example.

[0033] like figure 1 As shown, the present invention is a multi-controller energy-saving optimization method based on data surface traffic prediction, comprising the following steps:

[0034](1) Cluster controller scheduling: super node A in the cluster initially defaults to the maximum control flow H of each controller i max is 0;

[0035] (2) Within the same time interval t, the super node A in the cluster initiates the controller scheduling of the controlled cluster and issues information collection commands; all controllers A, B, and C of the cluster begin to report their traffic characteristics at this time, the The steps are implemented through the following sub-steps:

[0036] (2.1) The controller uses the secure channel to send query messages to...