Cost-Effective Data Placement in Edge Storage Systems With Erasure Code

Edge computing, as a new computing paradigm, brings cloud computing’s and storage capacities to network edge for providing low latency services users. The networked servers in specific area constitute edge systems (ESSs), where popular data can be stored serve the users area. novel ESSs raise many opportunities well unprecedented challenges. Most existing studies of focus on replicas system ensure retrieval However, replica-based strategies easily incur high costs. It is not cost-effective store massive large-size data, especially those that do require real-time access at edge, e.g., upgrade files, app installation videos online games. may even possible due constrained resources servers. In this article, we make first attempt investigate use erasure codes edge. find optimal strategy placing coded blocks an ESS, aiming minimize cost while serving all system. We model Erasure Coding based Data Placement (EC-EDP) problem integer linear programming prove its $\mathcal {NP}$ -hardness. Then, propose approach named EC-EDP-O programming. Another approximation algorithm EC-EDP-V proposed address computation complexity large-scale EC-EDP scenarios efficiently. extensive experimental results demonstrate save average 68.58% (and up 81.16% scenarios) compared with approaches.