Dynamic Replica Management Strategy Based-on Data Accessing Popularity for Load Balancing and Optimizing Network Performance in Cloud Storage

Abstract

Network performance plays a vital role in organizational efficiency, where large volumes of data, fast transmission, and low latency significantly enhance productivity and reduce downtime. Cloud storage offers a service model that enables remote data management and efficient content distribution. In such systems, data replication is widely used to improve availability, reliability, fault tolerance, and throughput. However, static replication policies often allocate replicas during system initialization, failing to adapt to the dynamic and heterogeneous nature of cloud environments. These environments are susceptible to challenges such as data loss, node failures, and fluctuating demand, which can degrade service quality. To address this, we propose a dynamic replica management strategy that considers data popularity, active peer participation, and peer capacity. Virtual peers are grouped into strong, medium, and weak clusters based on their weight values, which are derived from bandwidth, CPU speed, memory size, and access delay. Content is categorized into Class I, II, and III based on access frequency. Highly popular data (Class I) is replicated in strong clusters, while less frequently accessed data is placed in medium and weak clusters. A hierarchical routing mechanism ensures that queries are directed to the appropriate cluster. The proposed system was implemented and evaluated through simulations. Results show up to 25% improvement in throughput, 20% reduction in packet drops, 97% query efficiency, and decreased bandwidth utilization under high load. By maintaining optimal replica counts without compromising availability, the system supports cloud SLA compliance while minimizing overhead. This solution is aligned with the ninth UN Sustainable Development Goal: Industry, Innovation, and Infrastructure.