作者: Noriaki Kamiyama , Yuusuke Nakano , Kohei Shiomoto
关键词:
摘要: The transmission bandwidth consumed by delivering rich content is enormous, so it urgent for Internet service providers to design an efficient delivery system that minimizes the amount of network resources consumed, i.e., minimizing hop length flows. Content networks are widely used reduce flow and response time when obtaining items. To improve cache efficiency, various methods replacing caches have been proposed, with target improving hit ratio. However, although effect items from depends on distance origin server users, these do not consider distance. We propose here a cache-replacement policy based servers. divide storage capacity severs into multiple virtual manage separately also optimal method designing capacities maximizes total expected reduction length. Through numerical evaluation, we show proposed can increase average about 20% 80% compared normal LRU (least recently used).