Fault Tolerant Load Balancing with Quadruple Osmotic Hybrid Classifier and Whale Optimization for Cloud Computing

Abstract

Cloud Computing (CC) environment is developing as a recently discovered caliber for computing applications over the network. Fault tolerance is one of the foremost issues in CC environment. Since the negligence in resource have a profound effect on job execution, throughput, response time and performance of the entire network. In this work, in order to address the issue, Quadruple Osmotic Hybrid Classification and Whale Optimization (QOHC-WO) is introduced to fault-tolerance under the requirement of different user request tasks. Initially, Quadruple Fault Tolerance Level is applied to allocate the fault tolerance level. Followed by, Hybrid Vector Classifier is used to categorize the user request tasks (task) and cloud server nodes (node). Then, the Osmotic function is employed for performing the migration among virtual machines with lesser response time. This helps to solve the maximum level of fault issue. Finally, Improved Whale Optimization Algorithm is applied to find the optimal allocation of tasks with the corresponding node. In addition, the Bandit function and Whale optimization are used to address the trade-off between exploitation and exploration. Experimental setup of the proposed QOHC-WO method and existing methods are carried out with different factors such as task response time, the number of VM migrations, and percentage of fault detected rate with respect to a number of tasks. The analyzed results validate that the proposed QOHC-WO method achieves a higher fault detection rate with minimum response time as well as task migration than the state-of-the-art methods.