Multi-target controller placement method based on evolution perception in network

Abstract

The invention discloses a multi-target controller placement method based on evolution perception in a network, and mainly solves the problems of overlong propagation delay, high placement cost and large network load difference caused by placement of a controller in a control network in the prior art. According to the implementation scheme, the method comprises the following steps: initializing network topology information and algorithm setting information; preprocessing the initialized information; generating an initialized population, and representing a controller deployment scheme by each individual in the current population; iteratively evolving the current population; checking the legitimacy of the population, and judging all legal individuals and all illegal individuals; correcting illegal individuals to obtain an approximate optimal controller deployment scheme; and placing the controller in the control network according to one scheme in the placement scheme set. According to the method, network resources can be utilized more fully and reasonably, propagation delay and placement cost are reduced, network performance is improved, and the method can be used in a dense wavelength division multiplexing (DWDM) wide-area optical network.

Description

technical field [0001] The invention relates to the field of network communication, in particular to a method for placing a multi-object controller, which can be used in dense wavelength division multiplexing DWDM wide-area optical networks. Background technique [0002] For a long time, the wide area network based on dense wavelength division multiplexing DWDM has been widely used in actual networks such as core network, metropolitan area network and access network due to its advantages of large transmission capacity, easy transmission of various signals and dynamic reconfiguration of the network. , as well as cutting-edge new technologies such as data center networks, virtualization technology, cloud computing, edge computing, and the Internet of Things, and can greatly meet relevant business needs. With the development of digital business and the popularization of mobile office, the demand for cloud computing services is increasing rapidly, information and communication t...

AI Technical Summary

Problems solved by technology

[0006] Most of the current research only involves the propagation delay between the controller and the switch it controls, but because the propagation delay between the controllers is not considered, it will not be possible to optimize the delay consumed by propagating control information between the controllers, and then Affect the performance of the network; at the same time, because there are few studies on the load balancing of controllers, the load of most controllers is too large or too small, resulting in insufficient or waste of controller storage resources in the final placement scheme; in addition, due to the current No relevant studies have focused on the cost of placement, which may lead to high cost of the final placement scheme, which is not conducive to the practical application of the placement scheme

Images