🤖 AI Summary
This paper addresses the coexistence of ultra-reliable low-latency communication (URLLC) and distributed learning in industrial wireless networks, aiming to minimize distributed learning convergence time via device selection while guaranteeing URLLC reliability ≥99.999%.
Method: We formulate a joint optimization problem as a Markov decision process (MDP) and propose the Branching Soft Actor-Critic (BSAC) algorithm—the first to employ a dual-branch neural network architecture that decouples URLLC and learning tasks, enabling service-priority-aware, coordinated radio resource scheduling.
Contribution/Results: Evaluated on a 3GPP-compliant factory automation simulation platform with empirically calibrated channel models, BSAC significantly reduces training latency while achieving URLLC reliability and learning convergence performance close to those under dedicated-resource allocation. Our approach establishes a scalable, intelligent scheduling paradigm for heterogeneous time-sensitive services operating concurrently in shared spectrum.
📝 Abstract
Recent advances in distributed intelligence have driven impressive progress across a diverse range of applications, from industrial automation to autonomous transportation. Nevertheless, deploying distributed learning services over wireless networks poses numerous challenges. These arise from inherent uncertainties in wireless environments (e.g., random channel fluctuations), limited resources (e.g., bandwidth and transmit power), and the presence of coexisting services on the network. In this paper, we investigate a mixed service scenario wherein high-priority ultra-reliable low latency communication (URLLC) and low-priority distributed learning services run concurrently over a network. Utilizing device selection, we aim to minimize the convergence time of distributed learning while simultaneously fulfilling the requirements of the URLLC service. We formulate this problem as a Markov decision process and address it via BSAC-CoEx, a framework based on the branching soft actor-critic (BSAC) algorithm that determines each device's participation decision through distinct branches in the actor's neural network. We evaluate our solution with a realistic simulator that is compliant with 3GPP standards for factory automation use cases. Our simulation results confirm that our solution can significantly decrease the training delays of the distributed learning service while keeping the URLLC availability above its required threshold and close to the scenario where URLLC solely consumes all wireless resources.
