论文部分内容阅读
为提高流媒体代理服务器的缓存效率,从而提高整个流媒体服务系统的性能,提出一种基于用户访问模式的适应性媒体分段缓存策略。该策略充分考虑用户行为模式对具体影片访问特性的不同,采取有针对性的分段缓存管理策略,可显著提高代理缓存命中率。为避免由于分段策略所潜在引发的播放抖动问题,对相应的预取算法进行了理论分析。事件驱动试验结果表明:所提出的缓存算法命中率较之传统的定长分段算法及系统现有的间隔缓存策略均有显著的性能提高,系统稳定时缓存命中率分别高出后两者54%和31%。
In order to improve the cache efficiency of the streaming media proxy server and improve the performance of the whole streaming media service system, an adaptive media segment caching strategy based on user access mode is proposed. The strategy takes full account of the different characteristics of the user behavior patterns on specific video access, and adopts a targeted segmentation cache management strategy, which can significantly improve the proxy cache hit rate. In order to avoid the potential jitter caused by the segmentation strategy, the corresponding prefetching algorithm is analyzed theoretically. Event-driven test results show that the hit rate of the proposed cache algorithm is significantly improved compared with the traditional fixed-length segmentation algorithm and the existing interval buffer strategy. When the system is stable, the hit ratio of the cache is higher than the latter respectively % And 31%.