A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications

TL;DR

This paper introduces a constrained deep reinforcement learning approach to optimize cost-efficient, reliable delivery of latency-sensitive packets in next-generation networks, outperforming existing methods in ensuring timely delivery.

Contribution

It formulates the network control problem as a constrained Markov decision process and applies CDRL to effectively minimize costs while meeting strict delay requirements.

Findings

Ensures timely packet delivery under strict delay constraints.

Achieves lower resource costs compared to throughput-maximizing baselines.

Outperforms existing stochastic optimization methods in reliability and cost-efficiency.

Abstract

Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed by the application while minimizing overall resource allocation cost. A large body of work has leveraged stochastic optimization techniques to design efficient dynamic routing and scheduling solutions under average delay constraints; however, these methods fall short when faced with strict per-packet delay requirements. We formulate the minimum-cost delay-constrained network control problem as a constrained Markov decision process and utilize constrained deep reinforcement learning (CDRL) techniques to effectively minimize total resource allocation cost while maintaining timely throughput above a target reliability level. Results indicate that the proposed CDRL-based solution can ensure timely packet delivery even when existing baselines fall short, and it achieves lower cost compared to other throughput-maximizing methods.