This paper studies edge caching in fog computing networks, where a
capacity-aware edge caching framework is proposed by considering both the
limited fog cache capacity and the connectivity capacity of base stations
(BSs). By allowing cooperation between fog nodes and cloud data center, the
average-download-time (ADT) minimization problem is formulated as a multi-class
processor queuing process. We prove the convexity of the formulated problem and
propose an Alternating Direction Method of Multipliers (ADMM)-based algorithm
that can achieve the minimum ADT and converge much faster than existing
algorithms. Simulation results demonstrate that the allocation of fog cache
capacity and connectivity capacity of BSs needs to be balanced according to the
network status. While the maximization of the edge-cache-hit-ratio (ECHR) by
utilizing all available fog cache capacity is helpful when the BS connectivity
capacity is sufficient, it is preferable to keep a lower ECHR and allocate more
traffic to the cloud when the BS connectivity capacity is deficient.

研究雾计算网络中的边缘缓存，通过考虑有限的雾缓存容量和基站连接容量，提出了一个容量感知的边缘缓存框架，并通过允许雾节点和云数据中心的协作来将平均下载时间（ADT）最小化， 通过多类处理器排队过程将此问题建模，提出了一种基于 ADMM 的算法，可实现最小化 ADT 并比现有算法更快地收敛。模拟结果表明，根据网络状态需要平衡雾缓存容量和基站连接能力的分配。当基站连接容量足够时，利用所有可用的雾缓存容量最大化边缘缓存命中率（ECHR）是有帮助的，但当基站连接容量不足时，最好保持较低的 ECHR 并将更多流量分配给云。