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.