Traffic Differentiation on Internet of Things

Abstract

The Internet of Things (IoT) is expected to constitute a significant portion of the Internet in the future, both in terms of traffic, and market share. For it to achieve its full potential, innovative solutions are necessary to address several open challenges. In this context we discuss Network Neutrality, which states that all traffic in the Internet must be treated equally, i.e., without traffic differentiation (TD). Unfair traffic management may result in a non-competitive market, affecting selectively the quality of experience of different IoT applications. This scenario might hinder innovation, threatening IoT success. Monitoring TD on the IoT is thus important for a more competitive market. In this paper, we first study the impact of TD on common IoT traffic patterns, such as periodic updates and real-time notifications. We present simulation results, and discuss which types of IoT applications are most affected by TD. We then discuss a solution for monitoring TD on IoT. The solution takes advantage of the IoT to address several open challenges of TD detection. For instance, the large amount of devices results in a prolific environment for making TD-related measurements. The solution can thus employ machine learning for continuously monitoring TD as the numerous IoT devices and applications communicate.