Collaborative caching and QoE-driven video bitrate adaptation based on social and physical graphs for edge networks
Author Identifier (ORCID)
Abstract
With the continuous demands for high-definition videos, caching popular contents in edge nodes has emerged as an effective approach to reducing end-to-end transmission latency. By deploying finite caching capacity at edge nodes, network congestion over backhaul links is relieved, and the quality of experience (QoE) is enhanced. Furthermore, mobile users are easily influenced by social media trends. If implicit information is extracted from their interactions, edge caching performance can be further enhanced. To this end, we propose a QoE-driven collaborative video caching and bitrate adaptation framework based on social and physical graphs. This architecture operates across two timescales. In the large timescale, a two-tier collaborative video caching architecture is designed to hierarchically and partially cache popular videos across small-cell base stations (SBSs) and important users (IUs). The physical and social attributes are integrated into our caching mechanism. Based on the constructed social and physical aware graph, a greedy strategy based caching policy is designed. In the small timescale, we construct a multi-metric instantaneous QoE model and employ the Lagrange duality method to obtain the optimal video transmission bitrate by solving the real-time QoE maximization problem. Extensive simulations demonstrate that the proposed framework significantly outperforms traditional algorithms. Compared to the global most popular caching strategy, the performance gain in cache hit rate is up to 72.0%. When compared with the non-adaptive video streaming policy, our design results in a gain of 67.1% regarding the overall user QoE.
Keywords
adaptive video streaming, cooperative caching, edge caching, quality of experience (QoE), social and physical graphs, video transcoding
Document Type
Journal Article
Date of Publication
1-1-2026
Volume
12
Publication Title
IEEE Transactions on Cognitive Communications and Networking
Publisher
IEEE
School
School of Engineering
Copyright
subscription content
Content Type
Metadata only
First Page
9641
Last Page
9655
Recommended Citation
Zhang, X., Li, B., Ren, Y., Jiang, F., & Ni, W. (2026). Collaborative caching and QoE-driven video bitrate adaptation based on social and physical graphs for edge networks. IEEE Transactions on Cognitive Communications and Networking, 12, 9641–9655. https://doi.org/10.1109/TCCN.2026.3709899