Distributed Cooperative Caching in Unreliable Edge Environments

Caching popular contents at the network edge is promising to reduce the retrieval latency, the network congestion, and the number of requests to the remote content provider during peak hours. In general, edge caching resource is costly and highly limited. Nevertheless, it is possible to provide cost-effective caching services using unreliable resources, which are resources reserved for other applications but have not been fully used or resources on vulnerable servers. In this paper, we consider the problem of caching popular contents over unreliable resources as a less expensive solution to limited edge caching capacity. In particular, to address the unreliability of edge resources, erasure coding is leveraged to increase the availability of cached contents. We formulate the problem as a discrete optimization problem and prove it is NP-hard. We start with two special cases of the problem and provide optimal algorithms for them. We then design an algorithm for the general version of the proposed problem and provide a provable performance guarantee. Real-world data-driven simulations demonstrate that the proposed algorithms significantly outperform popular baselines, and the rewards for the general version of the problem are near-optimal.