Unleashing Collaborative Computing for Adaptive Video Streaming with Multi-objective Optimization in Satellite Terrestrial Networks

TL;DR

This work tackles the NP-hard problem of jointly optimizing task offloading and adaptive video streaming in satellite-terrestrial networks by decomposing it into path selection and resource allocation with adaptive bitrate control. It introduces CC-MASAC, a two-stage approach where a PSRU-based path-selection heuristic chooses end-to-end routes and a multi-agent soft actor-critic algorithm coordinates heterogeneous edge and satellite resources along the path to determine bitrate and allocations. Empirical results in a realistic STN simulation show CC-MASAC outperforms baselines in QoE, task completion rate, and delay while maintaining competitive energy usage, demonstrating the value of cross-layer collaboration and multi-agent learning for adaptive video streaming in STNs. The findings suggest significant practical benefits for scalable, low-latency video services over wide geographic areas where terrestrial and space networks must coordinate computing and communication resources.

Abstract

Satellite-terrestrial networks (STNs) are anticipated to deliver seamless IoT services across expansive regions. Given the constrained resources available for offloading computationally intensive tasks like video streaming, it is crucial to establish collaborative computing among diverse components within STNs. In this paper, we present the task offloading challenge as a multi-objective optimization problem, leveraging the collaboration between ground devices/users and satellites. We propose a collaborative computing scheme that optimally assigns computing tasks to various nodes within STNs to enhance service performance including quality of experience (QoE). This algorithm initially dynamically selects an end-to-end path that balances service time and resource utilization. For each selected path, a multi-agent soft actor-critic (MA-SAC)-based algorithm is introduced to make adaptive decisions and collaboratively assign optimal heterogeneous resources to the given computing tasks. In this algorithm, the ground station bridging satellite network and terrestrial network is treated as agent to extract the information from both STNs and users. Through MA-SAC, multiple agents cooperate to determine the adaptive bitrate and network resources for the arriving tasks. The numerical results demonstrate that our proposal outperforms comparative schemes across various computing tasks in terms of various criteria.

Figures (10)

• Figure 1: Network model.
• Figure 2: Overview of the proposed algorithm.
• Figure 3: Resource allocation with adaptive bitrate streaming control based on MA-SAC.
• Figure 4: Experimental network topology.
• Figure 5: Convergence performance for SAC-based scheme.