AI-in-the-Loop Sensing and Communication Joint Design for Edge Intelligence
Zhijie Cai, Xiaowen Cao, Xu Chen, Yuanhao Cui, Guangxu Zhu, Kaibin Huang, Shuguang Cui
TL;DR
This paper addresses the challenge of enabling robust edge intelligence under tight sensing and communication budgets by marrying AI-model-driven control with joint sensing and communication optimization. It introduces an AI-in-the-loop JSAC framework that ties the validation loss to tunable parameters, and proposes two core mechanisms: gradient-importance sampling for adaptive data collection and SGLD-inspired gradient noise control for transmission. The authors derive an explicit validation-loss bound, decompose the problem into data-distribution and weight-distribution subproblems, and develop practical AI-driven protocols for sensing and for noise-aware communication resource allocation. Experimental results on human motion and MNIST tasks demonstrate substantial improvements in generalization (up to 58% lower final validation loss) and dramatic reductions in communication energy (up to 77%) and sensing costs (up to 52%), illustrating the synergistic benefits of integrating AI into JSAC loops for edge intelligence.
Abstract
Recent breakthroughs in artificial intelligence (AI), wireless communications, and sensing technologies have accelerated the evolution of edge intelligence. However, conventional systems still grapple with issues such as low communication efficiency, redundant data acquisition, and poor model generalization. To overcome these challenges, we propose an innovative framework that enhances edge intelligence through AI-in-the-loop joint sensing and communication (JSAC). This framework features an AI-driven closed-loop control architecture that jointly optimizes system resources, thereby delivering superior system-level performance. A key contribution of our work is establishing an explicit relationship between validation loss and the system's tunable parameters. This insight enables dynamic reduction of the generalization error through AI-driven closed-loop control. Specifically, for sensing control, we introduce an adaptive data collection strategy based on gradient importance sampling, allowing edge devices to autonomously decide when to terminate data acquisition and how to allocate sample weights based on real-time model feedback. For communication control, drawing inspiration from stochastic gradient Langevin dynamics (SGLD), our joint optimization of transmission power and batch size converts channel and data noise into gradient perturbations that help mitigate overfitting. Experimental evaluations demonstrate that our framework reduces communication energy consumption by up to 77 percent and sensing costs measured by the number of collected samples by up to 52 percent while significantly improving model generalization -- with up to 58 percent reductions of the final validation loss. It validates that the proposed scheme can harvest the mutual benefit of AI and JSAC systems by incorporating the model itself into the control loop of the system.