A Multitask Learning-Based Network Traffic Prediction Approach for SDN-Enabled Industrial Internet of Things

With the rapid advance of industrial Internet of Things (IIoT), to provide flexible access for various infrastructures and applications, software-defined networks (SDNs) have been involved in constructing current IIoT networks. To improve the quality of services of industrial applications, network traffic prediction has become an important research direction, which is beneficial for network management and security. Unfortunately, the traffic flows of the SDN-enabled IIoT network contain a large number of irregular fluctuations, which makes network traffic prediction difficult. In this article, we propose an algorithm based on multitask learning to predict network traffic according to the spatial and temporal features of network traffic. Our proposed approach can effectively obtain network traffic predictors according to the evaluations by implementing it on real networks.

I. Introduction

In Recent years, Internet of Things (IoT) has become an indispensable and important infrastructure to provide intelligent life, such as intelligent transportation system and smart home [1]. The increase of network users promotes the rapid development of IoT. As a special paradigm of IoT, industrial IoT (IIoT) is a novel term that provides ubiquitous connections for sensors, automated guided vehicles, machines, and industrial robots [2]. The applications of IIoT can improve industrial productivity and efficiency obviously [2], [3]. Software-defined network (SDN) improves network controllability by the separation of the data and control planes. Without introducing new link layer protocols, the SDN can be compatible with existing industrial communication protocols, and it is flexible to modify and reconstruct the network based on various qualities of service requirements of IIoT users. Hence, the SDN can improve the efficiency of IIoT and reduce network complexity significantly [4]–[6]. The structure diagram of the SDN-enabled IIoT network is shown in Fig. 1.