The Optimization of LRU Algorithm Based on Pre-Selection and Cache Prefetching of Files in Hybrid Cloud

Abstract

In recent years, the research on caching in cloud environment has become an important research topic, and it has profound meaning to research the cache replacement algorithm in hybrid Cloud. There aren't enough considerations on some aspects, such as the selection of pending cache files, the prefetching of pending cache files among different clouds and the cost of recovery of files. Considering those shortages, this paper proposes an optimized LRU algorithm based on pre-selection and cache prefetching of files. This algorithm determines whether the file is to meet the pre-selection and cache prefetching conditions before adding a cache file, and it implements the LRU cache replacement algorithm which is based on priority. The algorithm divides the cache into multiple priority queues, and uses the LRU cache replacement algorithm to select the replacement file in each queue. Then select the files in each priority and put them together, select the file to perform replacement operation which has minimum probability of being accessed again. Compared with three typical cache replacement algorithm GD-Size, LRU, LFU, experimental results show that the cache replacement algorithm in this paper not only effectively save cost, but also greatly enhance the byte hit rate, delay savings rate and cache hit rate.