A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications
This work provides a method for network operators to cost-efficiently deliver latency-sensitive applications with strict per-packet delay requirements, which is an incremental improvement over existing stochastic optimization techniques.
This paper addresses the challenge of delivering latency-sensitive applications in next-generation networks by formulating the problem as a constrained Markov decision process. The proposed constrained deep reinforcement learning (CDRL) solution ensures timely packet delivery while minimizing resource allocation cost, outperforming existing baselines in timely delivery and achieving lower cost than throughput-maximizing methods.
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.