Optimizing Live Streaming Quality: A QOE-Aware Approach Using Edge Computing

Abstract

Ensuring high-quality HTTP Live Streaming (HLS) has become a critical concern for streaming services with the increase in online video consumption. Because of changing network circumstances, heterogeneous devices, and different user expectations, traditional solutions frequently fail to maintain good Quality of Experience (QoE). This research presents a unique QoE-aware method to maximize the quality of video streaming in HLS by utilizing edge computing. We provide a complete system that combines adaptive bitrate methods with real-time QoE monitoring, leveraging edge computing to improve multimedia delivery. In order to lower latency and enhance streaming performance, our suggested system design incorporates edge nodes that handle, cache, and distribute video material closer to end users. The system ensures an ideal balance between network circumstances and video quality by dynamically adjusting video bitrates depending on real-time QoE parameters including startup latency, buffering ratio, and video resolution. In order to verify our methodology, we create a simulation model that replicates different network circumstances and user behaviors by utilizing [specify certain tools or platforms, such as NS-3, OMNeT++]. Comparing the simulation results to conventional adaptive bitrate approaches, we find that there are notable gains in QoE metrics, such as decreased buffering and improved video quality. Our comparative study demonstrates how edge computing may effectively control network traffic and enhance video transmission. The results of this study highlight how current HLS systems' shortcomings may be addressed by fusing edge computing with QoE-aware adaptive streaming. In addition to increasing customer happiness, this strategy offers insightful information to streaming service providers and content delivery networks (CDNs) looking to raise the caliber of their offerings.