Jacob Chakareski of Ecole Polytechnique Federal de Lausanne presents an investigation of context-driven flow allocation and media delivery in online social networks. Information on contacts and content preferences found in social networks informs efficient networking services and operation at the underlying transport layer. A linear programming framework maximizes the information flow-cost ratio of the transport network serving the nodes in the social graph. For practical deployments, a distributed version of the optimization framework provides similar performance to its centralized counterpart at lower complexity. In addition, a tracker-based system for efficient content discovery in P2P systems is based on social network information. Finally, a context-aware packet scheduling technique maximizes the utility of media delivery among the members of the social network. The paper provides a comprehensive investigation of the performance of optimization strategies through both experiments and analysis. The presentation demonstrates significant advantages over several performance factors relative to conventional solutions that do not employ social network information in their operation.
An investigation of context-driven flow allocation and media delivery in online social networks. Information on contacts and content informs efficient networking services and operation at the transport layer.