A Multicontroller Load Balancing Approach in Software-Defined Wireless Networks. (11th October 2015)

• Record Type: Journal Article
• Authors: Yao, Haipeng; Qiu, Chao; Zhao, Chenglin; Shi, Lei
• Other Names: Samn Sherwood W. Academic Editor.
• Is Part Of: International journal of distributed sensor networks. (2015)
• Publication Date: 2015-10-11
• Subjects: Sensor networks -- Periodicals; Intelligent agents (Computer software) -- Periodicals; Multisensor data fusion -- Periodicals; 681.2
• DOI: 10.1155/2015/454159
• Languages: English
• ISSNs: 1550-1329

Abstract

Abstract : Software-defined networking (SDN) is currently seen as one of the most promising future network technologies, which can realize the separation between control and data planes. Furthermore, the increasing complexity in future wireless networks (i.e., 5G, wireless sensor networks) renders the control and coordination of networks a challenging task. Future wireless networks need good separation of control and data planes and call for SDN method to handle the explosive increase of mobile data traffic. Relying on a single controller in future wireless networks imposes a potential scalability problem. To tackle this problem, the thought of using multiple controllers to manage the large wide-area wireless network has been proposed, where the load balance problem of multicontroller needs to be resolved. In this paper, we propose a multicontroller load balancing approach called HybridFlow in software-defined wireless networks, which adopts the method of distribution and centralization and designs a double threshold approach to evenly allocate the load. Simulation results reveal that the proposed approach can significantly relieve the working load on the super controller and reduces the load jitter of multicontroller load in a single cluster compared with the BalanceFlow method.