Energy-Aware Data Replication in Green Cloud Computing using Improved Bat Algorithm and Paralleling Technique

Abstract

Abstract In green cloud computing, resources are allocated in a reasonable way so that cloud computing systems are energy efficient and consume little power. In this paper, Parallel-based data replication with an Improved Fuzzy-Bat technique called PIF-Bat is proposed. At first, we introduce an Improved Fuzzy-Bat (IF-Bat) strategy that tunes some parameters of the standard Bat algorithm and controls the tradeoff between exploration and exploitation. By balancing the trade-offs among the five optimization objectives (i.e., availability, service time, load, latency, centrality, energy consumption), the PIF-Bat algorithm determines the optimal locations for replicas using a multi-objective optimization strategy based on the Improved Fuzzy-Bat technique. A successful attack against each site will reveal no useful information even if only a single part of the file is exposed. A fuzzy inference system is used in the PIF-Bat algorithm to determine whether to parallelize files based on data such as file size, free space, and average bandwidth at each node. In order to reduce retrieval time, a parallel download technique, which allows users to download portions of a file simultaneously from different sites, is applied. The experimental results and statistical tests with a set of well-known test functions demonstrate the superior exploitation and exploration ability of IF-Bat. Furthermore, PIF-Bat obtains lower access latency around 15%∼20% and better performance than other similar replication algorithms under high load conditions.