提出 FREDI 框架优化边缘智能资源分配与安全推理
Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence
这篇论文提出了 FREDI 框架，用于优化边缘智能的资源分配和推理，特别是针对安全的多层协作系统，挺有意思的。
这篇论文提出 FREDI 框架，用于事件触发的无线边缘智能。每个用户设备（UE）使用双置信度阈值进行早期退出卷积神经网络（CNN）筛选，关键事件安全地卸载到边缘服务器（ES）进行详细分类。该框架通过联合优化 UE-ES 关联、无线和计算资源以及置信度阈值，来最大化公平效用。通过将问题分解为公平资源分配和双阈值推理优化，并利用有限的经验置信度域进行精确阈值优化，证明了检测到关键事件集合在阈值上是非递增的。数值实验使用早期退出的 MobileNetV2 和 ShuffleNetV2，显示接近完美的 UE 公平性，聚合效用接近 Sum-Utility 基准，并证明在 6 到 144 个 UE 之间具有 Stage-A 可扩展性，求解时间中位数低于 0.1 秒。
Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence
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.