Adaptive Processing for Video Streaming with Energy Constraint: A Multi-Agent Reinforcement Learning Method

• Published in: GLOBECOM 2023 - 2023 IEEE Global Communications Conference pp. 122 - 127
• Main Authors: Liu, Hongze, Fu, Haotian, Yuan, Shijing, Wu, Chentao, Luo, Yuan, Li, Jie
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04-12-2023
• Subjects: Adaptive Video Streaming; Heuristic algorithms; Multi-access Edge Computing; Multi-agent Reinforcement Learning; Performance evaluation; Redundancy; Reinforcement learning; Streaming media; Task analysis; Video compression
• ISSN: 2576-6813
• DOI: 10.1109/GLOBECOM54140.2023.10437053

Edge computing is a highly promising technology that empowers mobile devices to offload video streaming tasks to edge servers, thereby improving the video stream analysis performance. However, most existing research on edge video streaming has failed to give adequate attention to the joint optimization of video streaming tasks with respect to dynamics, redundancy, and long-term energy constraints. To address this limitation, we propose a novel method based on a multi-agent reinforcement learning algorithm, which significantly enhances the performance of edge video stream analysis under long-term energy constraints. Specifically, our proposed method conducts video compression and offloading under long-term energy constraints to maximize the long-term rewards of video task processing. Experimental evaluations have demonstrated the convergence of the proposed method, which outperforms the baseline solutions, achieving higher long-term rewards.