Sustainable cost-energy aware load balancing in cloud environment using intelligent optimization

Abstract

Managing a distributed environment with a shared resource pool in cloud computing requires efficient task scheduling across multiple Virtual Machines (VMs). The effectiveness of the load-balancing algorithm used largely influences the system's performance. However, traditional load-balancing methods often neglect critical factors such as cost and energy consumption, which are vital for both economic and environmental sustainability. To tackle these challenges, this study introduces a new approach, Cost-Energy Aware Spider Monkey Optimization (CE-SMO). This improved version of the Spider Monkey Optimization (SMO) algorithm incorporates cost and energy efficiency into the load-balancing process. CE-SMO seeks to enhance performance by considering economic aspects like computing, storage, data transfer costs, and energy consumption. The algorithm ensures balanced, cost-efficient, and eco-friendly resource allocation. Simulations demonstrate that CE-SMO outperforms existing methods in load balancing, reaction time, makespan, and resource utilization while addressing cost and energy efficiency concerns.