Dynamic pricing with traffic engineering for adaptive video streaming over software-defined content delivery networking

Pingting Hao, Liang Hu, Kuo Zhao, Jingyan Jiang, Tong Li, Xilong Che

Abstract: Multimedia content has become widespread in network traffic. The high volume of data and flexibility must be addressed to guarantee the quality of experience (QoE) in large-scale adaptive video streaming services. Despite the abundance of recently proposed strategies, most concentrate on improving different aspects of performance over user fairness and initiation. We propose Dynamic Pricing with Traffic Engineering (DPTE), a prototype that generates traffic distribution using a market-driven model. In DPTE, users specify required rates, and a price module gives the current value based on observation of the states of servers as well as networks. DPTE periodically runs a heuristic algorithm that selects the path with the appropriate pricing to guarantee the service based on the software-defined content delivery networking (SDCDN) platform. As a result, DPTE not only relies on pricing to reflect the objective properties from the performance perspective but also utilizes pricing rules to influence the choice of users. Evaluation results on Youtube data show that DPTE outperforms competitive pricing rules in most cases, including path utility, user satisfaction and revenue.