非对称网络环境中数据广播的带索引多盘调度算法

INDEXED MULTIDISK SCHEDULING ALGORITHMS FOR DATA BROADCASTING IN ASYMMETRIC NETWORK ENVIRONMENTS

在以无线网络为代表的非对称网络环境中，数据广播是一种有效的数据访问方式．针对非均匀的访问概率分布，为了节约移动计算机接听数据广播的电源消耗，同时兼顾访问时间的限制，文中提出了两种带索引多盘调度算法，即复制索引算法（ＩＭＤ－ＲＩ）和多路复用算法（ＩＭＤ－ＭＵＸ）．理论分析和实验结果表明，这两种算法通过在广播信道中加入索引信息，能够有效减小数据广播的调谐时间，同时仍保持较低的访问时间，因此更具有竞争性．

Data broadcasting is an effective way for data dissemination in an asymmetric communication network, like wireless network. To minimize the tuning time of the broadcast schedule with skewed access probabilities of data items, two indexed multidisk scheduling algorithms, called IMD RI and IMD MUX are proposed. The theoretical analysis and experimental results indicate that both of them are effective algorithms, because they can significantly reduce the tuning time of the broadcast schedule, while still keeping the access time within reasonable limit.