A Reinforcement Learning-Based Network Traffic Prediction Mechanism in Intelligent Internet of Things

Intelligent Internet of Things (IIoT) is comprised of various wireless and wired networks for industrial applications, which makes it complex and heterogeneous.The openness of IIoT has led to the intractable problems of network security and management. Many network security and management functions rely on network traffic prediction techniques, such as anomaly detection and predictive network planning. Predicting IIoT network traffic is significantly difficult because its frequently updated topology and diversified services lead to irregular network traffic fluctuations. Motivated by these observations, we proposed a reinforcement learning-based mechanism in this article. We modeled the network traffic prediction problem as a Markov decision process, and then, predicted network traffic by Monte Carlo Q-learning. Furthermore, we addressed the real-time requirement of the proposed mechanism and we proposed a residual-based dictionary learning algorithm to improve the complexity of Monte Carlo Q-learning. Finally, the effectiveness of our mechanism was evaluated using the real network traffic.

I. Introduction

To Provide support to intelligent Internet of Things (IIoTs) with adequate throughput for industrial applications, the 5G-enabled communication network, which is involved in IIoTs, is expected to be complex and heterogeneous with a dense deployment of infrastructures. Aiming at distinct kinds of industrial applications, various access techniques have been used in 5G-enabled networks to guarantee the quality-of-service and quality-of-experience of IIoTs [1]–[4]. In this case, the network security and management obtain unprecedented attentions. Nevertheless, the openness of 5G heterogeneous networks (5G HetNets) arises the main challenges in network security. Meanwhile, the dense deployment of infrastructure using smaller cells requires more efficient management mechanisms [5]–[7].