网格数据查询优化中的缓存管理研究

发布时间：2018-05-16 20:29

本文选题：网格计算 + 缓存管理　；参考：《华中科技大学学报(自然科学版)》2007年S2期

【摘要】：鉴于缓存管理在分布式系统中可以减少网络流量,提高系统响应速度,尤其在网格计算环境中可以克服网络连接的带宽瓶颈,提出了一个用于优化网格信息查询的缓存管理模型.网格搜索引擎进行信息检索时,依据用户的查询需求,从网格异地异构数据库中查询并自动抽取信息,进行查询集成并存储在高速缓存中;根据缓存调度算法合理地组织中间结果;按照打分函数的控制,在生成的评分表下进行Top-K排序,合并生成最终结果;在保证网格查询准确性的同时,提高网格异构数据源查询速度.实验表明此方法是有效的.
[Abstract]:In view of the fact that cache management can reduce network traffic and improve system response speed in distributed systems, especially in grid computing environments, the bandwidth bottleneck of network connections can be overcome. A cache management model for optimizing grid information query is proposed. When the grid search engine carries on the information retrieval, according to the user's query demand, queries from the grid heterogeneous database and extracts the information automatically, carries on the query integration and stores in the cache; According to the buffer scheduling algorithm, the intermediate results are reasonably organized; according to the control of the scoring function, the Top-K is sorted under the generated score table, and the final results are merged to generate the final results. At the same time, the accuracy of the grid query is guaranteed. Improve the query speed of grid heterogeneous data sources. Experiments show that this method is effective.
【作者单位】：中国人民大学信息学院中国人民大学信息学院中国人民大学信息学院中国人民大学信息学院
【基金】：国家自然科学基金资助项目(60473069) 教育部下一代互联网示范工程资助项目(CNGI-04-15-7A) 中国人民大学科研基金资助项目(30206102.202.307)
【分类号】：TP393.02

【共引文献】