CONTENT DELIVERY NETWORK FOR OPTIMAL PERFORMANCE AND ENERGY EFFICIENT

Abstract

The explosive growth of digital media, driven by high-definition video streaming, mobile social networking (MSN), and real-time interactive applications, has fundamentally altered the landscape of internet traffic. Content Delivery Networks (CDNs) have become the backbone of modern web infrastructure, mitigating latency by caching content closer to end-users at the network edge. However, the massive deployment of edge servers and the continuous synchronization of data centers have introduced a critical challenge: exorbitant energy consumption. This paper presents a comprehensive framework for optimizing both the performance and the energy efficiency of CDNs. We propose a novel architecture that integrates a machine learning-based dynamic caching strategy with an energy-aware routing algorithm. By proactively predicting content popularity and dynamically routing user requests based on the real-time thermal and power states of edge nodes, our system significantly reduces the carbon footprint of content delivery without compromising Quality of Experience (QoE). Extensive simulations reveal that the proposed dual-optimization approach improves cache hit ra-tios by up to 24% and reduces overall CDN energy consumption by 18.5% compared to traditional static caching and shortest-path routing methodologies.