Intelligent and Metaheuristic Task Scheduling for Cloud using Black Widow Optimization Algorithm

Abstract

Cloud computing is an internet-based infrastructure for services such as computations, storage, etc., hosted on physical machines. The machines on cloud infrastructure scales between a few tens to thousands of machines that are linked in an unstructured way. In cloud computing, minimizing energy consumption and its associated costs is the primary goal while preserving efficiency and performance. It progresses the system’s overall productivity, reliability, and availability. Furthermore, reducing energy use not only lowers energy expenses but also helps to safeguard our natural environment by lowering carbon emissions. The objective of our proposed work is to reduce energy usage in the cloud environment and enhance its performance. We propose a hybrid approach that incorporates an energy-aware self-governing task scheduler, namely, Artificial Neural Network (ANN), and a metaheuristic Black Widow Optimization (BWO) algorithm to solve the optimization issues. Our suggested task scheduler focuses on minimizing energy consumption, improving the makespan, and reducing the operating cost while keeping a low number of active cloud racks. The cloud environment is highly scalable in this scenario since we adopt a metaheuristic BWO algorithm. CloudSim simulation framework is used for implementation and experimental analysis.