DSPE: Profit Maximization in Edge-Cloud Storage System using Dynamic Space Partitioning with Erasure Code

2025-07-30

AI Summary

Edge cloud storage faces dual challenges: limited capacity and stringent latency requirements for high-temporal-data access under dynamic workloads, hindering profit maximization. To address this, we propose a profit-driven framework that jointly optimizes dynamic space partitioning and erasure coding. We introduce a novel storage layout dividing edge server capacity into heat-adaptive private and shared public zones. Further, we design an elastic data placement and cache replacement policy driven by request rates, integrated with erasure coding to enable cross-node redundancy and collaborative caching. Extensive experiments on synthetic workloads and real-world traces from Netflix and Spotify demonstrate that our approach improves system profitability by 5%–8% over state-of-the-art methods, while significantly enhancing both operational efficiency and economic viability of edge storage.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Distributed Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Edge Storage Systems have emerged as a critical enabler of low latency data access in modern cloud networks by bringing storage and computation closer to end users. However, the limited storage capacity of edge servers poses significant challenges in handling high volume and latency sensitive data access requests, particularly under dynamic workloads. In this work, we propose a profit driven framework that integrates three key mechanisms which are collaborative caching, erasure coding, and elastic storage partitioning. Unlike traditional replication, erasure coding enables space efficient redundancy, allowing data to be reconstructed from any subset of K out of K plus M coded blocks. We dynamically partition each edge server s storage into private and public regions. The private region is further subdivided among access points based on their incoming request rates, enabling adaptive control over data locality and ownership. We design a data placement and replacement policy that determines how and where to store or evict coded data blocks to maximize data access within deadlines. While the private region serves requests from local APs, the public region handles cooperative storage requests from neighboring servers. Our proposed Dynamic Space Partitioning and Elastic caching strategy is evaluated on both synthetic and real world traces from Netflix and Spotify. Experimental results show that our method improves overall system profitability by approximately 5 to 8% compared to state of the art approaches under varied workload conditions.

Problem

• Maximize profit in edge-cloud storage via dynamic partitioning
• Optimize data access latency with erasure coding and caching
• Balance private-public storage regions for adaptive request handling

Innovation

• Dynamic space partitioning for edge servers
• Erasure coding for efficient redundancy
• Elastic caching with adaptive data placement