Bounded Low Latency via Inverse Reinforcement Learning

Accurate traffic prediction is essential for effective resource utilization and improving user experience quality in next generation wireless networks. Machine Learning (ML) techniques offer promising results for traditional scenarios; however, pre-sampling network traffic for training purposes often results in significant computing and memory requirements. Additionally, in many applications, such as wireless sensor networks (WSNs), the nodes’ energy constraints may limit the feasibility of network traffic sampling. Inverse Reinforcement Learning (IRL), which involves learning an agent’s objectives by observing its behavior, has gained significant attention in various fields, including autonomous driving, robotics, and aerial imagery-based navigation. In this paper, we propose the first application of IRL to network traffic flow prediction, used as an efficient tool for large-scale objective-aware traffic prediction purposes. We first model the traffic prediction problem using an IRL framework and then apply our proposed approach to a scheduling problem for packets with bounded latency requirements. Our simulation results demonstrate that IRL can provide better performance compared to well-known ML-based approaches while significantly reducing the amount of computation and memory required for real-time objective-oriented prediction scenarios. Therefore, this work presents a new direction for addressing network traffic prediction challenges by leveraging the benefits of IRL techniques. The proposed IRL-based approach offers a promising solution to reduce the computing and memory overheads associated with traditional ML-based approaches, leading to more efficient network traffic management.