Live migration an advancement with which the whole running virtual machine (VM) is relocated beginning with one physical machine then onto the next. Migration at the level of the whole VM suggests that in-memory state can be moved in a reliable and effective design. Migrating operating system instances across distinct physical hosts is a beneficial tool for clusters and administrators. Along these outlines, a significant issue in live migration is the complete migration time and the downtime. To enrich the concert of live migration, an optimized iterative pre-copy procedure is used to decrease the dirty rate of virtual machines. In pre-copy approach that is essentially utilized as a part of live migration, total migration time, which influence on the performance of VM, is delayed by iterative copy operations and the noteworthy measure of transferring data during the entire migration process. In this paper, we presented a system that incorporates pre-processing phase in traditional pre-copy based live migration for decreasing the amount of transferred data. In pre-processing stage, we recommend the prediction working set algorithm to show that complete migration time as well as downtime is controlled by specific memory utilization patterns. Applying the proposed lazy counting based splay tree algorithm, the system can diminish the amount transferred memory page. The lazy counting-based splay algorithm along with traditional pre-copy approach that contains a pre-processing phase for diminishing the amount of transferring memory page and total migration time. © 2006-2017 Asian Research Publishing Network (ARPN).