A data replica replacement algorithm based on value model in mobile grid environments

One of the major problems in mobile grid environments is the optimal distribution and replication of data files, in order to improve and maintain a high overall throughput of grid jobs that access files. A data replica replacement algorithm based on value model is proposed and the arithmetic method to calculate replica value is introduced. This algorithm adapts to the high variation environment in mobile grid environment. The value of a data replica reflects the usage history of the cache and the variability of it. We construct a data replica value evaluation system which makes those unstable or rarely used replicas first be deleted, when there is not enough storage space during replication. We also do some analysis and experiments on the algorithm. From analysis we can find that after we use value model, the whole grid system´s data replica use probability is more increased. Experimental results also show that the proposed algorithm can obtain better performance for grid tasks to access data replicas and it is feasible and effective