比例公平资源分配与双阈值早退推理用于安全协作多层边缘智能

中文摘要 AI 辅助

本文提出FREDI（边缘双阈值推理的公平资源分配），一种安全无线边缘智能框架，用于协作用户设备（UE）—边缘服务器（ES）—云系统中的事件触发推理。每个UE使用双置信阈值执行早退卷积神经网络（CNN）筛查，而关键事件被安全卸载到边缘服务器进行详细分类。我们构建了一个比例公平效用最大化问题，联合优化UE—ES关联、无线和处理资源以及置信阈值。FREDI将问题分解为比例公平资源分配和双阈值推理优化。我们证明了检测到的关键事件集在两个阈值上都是集合单调非增的，并利用有限经验置信域进行精确阈值优化。经验资源—效用响应包络产生了可计算的全局次优性界限和全局最优性的充分条件。通过预先消除不可行的UE—ES对并精确投影出带宽和发射功率变量，资源分配子问题被简化为一个混合整数指数锥规划，可在规定间隙内求解到认证的全局最优性。使用早退MobileNetV2和ShuffleNetV2的数值结果展示了近乎完美的UE公平性，聚合效用接近总和效用基准，揭示了安全引起的资源碎片化，并展示了Stage-A从6到144个UE的可扩展性，在测试配置中中位求解时间低于0.1秒。

英文摘要

This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-triggered inference in a cooperative user equipment (UE)--edge server (ES)--cloud system. Each UE performs early-exit convolutional neural network (CNN) screening using dual confidence thresholds, while critical events are securely offloaded to an edge server for detailed classification. We formulate a proportionally-fair utility maximization problem that jointly optimizes UE--ES association, wireless and processing resources, and confidence thresholds. FREDI decomposes the problem into proportional-fair resource allocation and dual-threshold inference optimization. We prove that the detected-critical event set is set-monotone non-increasing in both thresholds, and exploit the finite empirical confidence domain for exact threshold optimization. An empirical resource--utility response envelope yields a computable global suboptimality bound and a sufficient condition for global optimality. By pre-eliminating infeasible UE--ES pairs and exactly projecting out bandwidth and transmit-power variables, the resource-allocation subproblem is reduced to a mixed-integer exponential-cone program solvable to the certified global optimality within a prescribed gap. Numerical results with early-exit MobileNetV2 and ShuffleNetV2 demonstrate near-perfect UE fairness with aggregate utility close to a Sum-Utility benchmark, reveal security-induced resource fragmentation, and demonstrate the Stage-A scalability from 6 to 144 UEs with median solving time below 0.1~s in the tested configurations.

发表机构

• University of Wollongong（伍伦贡大学）
• Kennesaw State University（肯尼索州立大学）
• CodeZX Software Company Limited（CodeZX软件有限公司）

机构由 AI 辅助整理，请以论文原文为准。