Optimized Scheduling of Jobs using Load Balancing in Cloud Computing With Economic Perspectives

Optimized Scheduling of Jobs using Load Balancing in Cloud Computing (With Economic Perspectives) The rapid growth of computing systems has primarily focused on performance and fast application processing across customer, scientific, and business domains. However, this progress has led to increased energy consumption, particularly in cloud data centres that host large-scale applications. Optimizing energy use in such environments remains a significant challenge. This work presents an enhanced task scheduling approach based on deadlines and resource management to address this issue. The proposed algorithm utilizes K-means clustering to classify tasks and virtual machines (VMs), overcoming limitations of existing scheduling techniques. By considering machine load prior to task assignment, the algorithm effectively reduces makespan, average waiting time, response time, and improves throughput. Simulation results demonstrate that the method enhances resource allocation efficiency, leading to faster processing and improved responsiveness—benefiting both cloud service providers and users. The proposed optimization approach also holds economic significance by potentially lowering operational costs for cloud service providers through energy efficiency and resource utilization. Reduced energy consumption and improved infrastructure performance translate directly into cost savings, enhancing the financial sustainability of cloud operations.