Toward Cost-Effective Mobile Video Streaming via Smart Cache With Adaptive Thresholding

Mobile video streaming has become the leading contributor to the explosive growth of mobile Internet traffic. As a key system parameter of mobile video apps, cache threshold plays an important role in regulating the downloading behavior of a mobile device, and directly affects the efficacy of mobile video streaming. In this paper, we first conduct a series of well-designed experiments to understand the mechanism of cache management in the Android OS and investigate the impact of cache threshold on the performance of mobile video streaming. The experiments show that the current static configuration of cache thresholds in the Android OS cannot well balance the tradeoff between cost incurred by unconsumed content and user quality of experience. To achieve cost-effective mobile video streaming, this paper further proposes a control-theoretic cache management algorithm called smart cache with adaptive thresholding (SCAT), which can intelligently tune cache thresholds to satisfy user preferences. The complexity of cache management and optimization can be decreased extensively by the SCAT strategy, facilitating its easy integration with the OS kernel codes. Finally, we implement and evaluate our proposed scheme on the real Android platform and the experimental results verify that our proposed scheme achieves significant gain over other alternative approaches. Compared to the Android's default scheme, SCAT achieves over 40% reduction of unconsumed content cost and nearly 30% reduction of freezing duration in the low-bandwidth network environment.