Search papers, labs, and topics across Lattice.
This paper introduces ProCAVE, a self-adaptive framework that integrates predictive bandwidth estimation with preference-aware deep reinforcement learning (DRL) to enhance edge caching for mobile video streaming. By utilizing a lightweight Transformer for throughput forecasting, a PPO-driven adaptive bitrate (ABR) agent, and a DDPG-based cache controller, ProCAVE significantly outperforms existing systems like FlyCache in terms of byte hit rate, backhaul load reduction, and user quality of experience (QoE). The findings underscore the importance of proactive, coordinated approaches in managing the complexities of real-world wireless environments for video delivery.
ProCAVE achieves a remarkable improvement in video streaming efficiency by leveraging predictive modeling and DRL, setting a new standard for edge caching frameworks.
The growing demand for mobile video streaming requires edge delivery systems that adapt efficiently to rapid network fluctuations and diverse user preferences. Existing approaches such as FlyCache rely on reactive ABR heuristics and loosely coupled cache policies, limiting their responsiveness and coordination under real-world wireless dynamics. We propose ProCAVE (Proactive Caching with Adaptive Video Experience), a self-adaptive DRL-based framework that unifies predictive bandwidth modeling, proactive bitrate selection, and preference-aware cache control. ProCAVE employs: (i) a lightweight Transformer for short-term throughput forecasting; (ii) a PPO-driven ABR agent; and (iii) a DDPG-based continuous cache controller operating on a high-dimensional global state. Experiments using MovieLens preference traces and Ghent 4G bandwidth measurements show that ProCAVE improves byte hit rate, reduces backhaul load, and enhances QoE compared with FlyCache and other baselines. These results highlight the benefits of predictive, DRL-coordinated control for efficient and user-centric edge video delivery.
