Closed-form congestion control via deep symbolic regression

TL;DR

This paper introduces a novel approach combining reinforcement learning and deep symbolic regression to derive closed-form congestion control policies suitable for ultra-low-latency 5G networks, enhancing interpretability and deployment feasibility.

Contribution

It presents a methodology to generate closed-form congestion control solutions from RL policies, addressing inference and interpretability challenges in real-time network environments.

Findings

Closed-form expressions closely approximate RL baseline performance

Enhanced interpretability of congestion control policies

Applicable to fronthaul-like ultra-low-latency networks

Abstract

As mobile networks embrace the 5G era, the interest in adopting Reinforcement Learning (RL) algorithms to handle challenges in ultra-low-latency and high throughput scenarios increases. Simultaneously, the advent of packetized fronthaul networks imposes demanding requirements that traditional congestion control mechanisms cannot accomplish, highlighting the potential of RL-based congestion control algorithms. Although learning RL policies optimized for satisfying the stringent fronthaul requirements is feasible, the adoption of neural network models in real deployments still poses some challenges regarding real-time inference and interpretability. This paper proposes a methodology to deal with such challenges while maintaining the performance and generalization capabilities provided by a baseline RL policy. The method consists of (1) training a congestion control policy specialized in fronthaul-like networks via reinforcement learning, (2) collecting state-action experiences from the baseline, and (3) performing deep symbolic regression on the collected dataset. The proposed process overcomes the challenges related to inference-time limitations through closed-form expressions that approximate the baseline performance (link utilization, delay, and fairness) and which can be directly implemented in any programming language. Finally, we analyze the inner workings of the closed-form expressions.