集群并发环境下大规模矢量数据负载均衡算法  

Content Grid Load Balancing Algorithm for Large-Scale Vector Data in the Server Cluster Concurrent Environment

作　　者：郭明强[1,2] 谢忠[1,2] 黄颖[2] 

机构地区：[1]中国地质大学(武汉)信息工程学院,武汉市鲁磨路388号430074 [2]教育部GIS软件与应用工程研究中心,武汉市关山一路特1号430074

出　　处：《武汉大学学报（信息科学版）》2013年第9期1131-1134,共4页Geomatics and Information Science of Wuhan University

基　　金：国家863计划资助项目(2009AA12Z21);国家"十二五"科技支撑计划资助项目(2011BAH06B04)

摘　　要：为了提高集群环境下网络地理信息系统(WebGIS)大规模矢量数据的并发访问性能,提出了集群并发环境下大规模矢量数据内容网格化负载均衡算法,研究了大规模矢量数据内容网格化方法,集群并发访问时内容网格的自动识别、分析、聚合、反馈算法,实现了面向任务的负载均衡。实验表明,本算法能在大规模、高强度的矢量数据提取和显示中均衡地分发请求,使集群服务器充分发挥其优势从而获得最小的请求响应时间。In order to improve the concurrent access performance with large-scale vector data in WebGIS, a content grid load balancing algorithm is proposed. The server processing capa- bility, service contents, and request time are taken into account. A proposed method to di- vide large-scale vector data into a content grid, the algorithm of content automatic identifica- tion, analysis, aggregation and feedback in the server cluster concurrent environment is dis- cussed. This algorithm implements all servers in the cluster to complete visualization tasks submitted by clients at the same time and realizes task-oriented load balancing. For the ex- traction and display of large-scale and high-intensity vector data, the algorithm balances the servers＇ load efficiently and responds to requests in minimal time. As compared to t tradi- tional load balancing algorithms, the algorithm proposed in this paper has the best perform- ance. The larger the scale, the more obvious is the load balancing effect.

关 键 词：网络地理信息系统 集群 矢量数据 网格 负载均衡 

分 类 号：P208[天文地球—地图制图学与地理信息工程] TP301[天文地球—测绘科学与技术]