A Webgis Load-balancing Algorithm Based on Collaborative Task Clustering

This paper analyzes deficiencies of load-balancing technologies in the current webgis and discusses the necessity and feasibility to solve load-balancing in webgis through server farms. A new distributed dynamic scheduling model based on server farms is given. A webgis load-balancing algorithm based on collaborative task clustering is proposed. The new algorithm divides the collaborative computing task into n subtasks; then generates collaborative task clustering; at last, dynamically allocate them to every gis server which is in the above model. It maximizes the execution time of collaborative spatial computing; effectively improve the utilization and the parallel processing capacity of webgis, provides faster and better webgis service for users. A test-bed is established. A series of test results prove that the algorithm has good global load balancing performance.