Research on scheduling method based on traffic matrix for IoT security. Issue 2 (11th February 2020)

• Record Type: Journal Article
• Authors: Cao, Shaohua; Zhu, Dongjie; Li, Guofu; Zhang, Yanwu; Fan, Xiani; Geng, Shanshan; Du, Haiwen; Cao, Ning
• Other Names: Meng Weizhi guestEditor.; Cofta Piotr guestEditor.; Grandison Tyrone W.A. guestEditor.
• Is Part Of: International journal of network management. Volume 31:Issue 2(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-02-11
• Subjects: Computer networks -- Management -- Periodicals; 004.6
• DOI: 10.1002/nem.2101
• Languages: English
• ISSNs: 1055-7148

Abstract

Summary: With the increasing number of sensors in the Internet of Things (IoT), network nodes are prone to load imbalance, which seriously affects the reliability and scalability of the IoT. In this paper, a method of load balancing is proposed to reduce the pressure of switches in IoT and improve the efficiency of switch. The method is based on software defined network (SDN) technology using dynamic traffic scheduling of server cluster (DTSSC) model. It obtains the traffic and load matrices for each server and achieves load balancing on each of them. This method has high efficiency and low overhead and is easy to deploy. The validity of this method is verified through experiments; ie, the load ratio of each server is balanced. Abstract : In this paper, a method of load balancing is proposed to reduce the pressure of switches in IoT and improve the efficiency of switch. The method is based on software defined network (SDN) technology using dynamic traffic scheduling of server cluster (DTSSC) model. It obtains the traffic and load matrices for each server and achieves load balancing on each of them. This method has high efficiency and low overhead and is easy to deploy.