Hazard regressive multipoint elitist spiral search optimization for resource efficient task scheduling in cloud computing

Abstract

Cloud computing, a revolutionary paradigm, connects computing resources and users via the internet, offering services like cloud storage and on-demand computing. In this context, efficient task scheduling is crucial, aiming to minimize costs and makespan. We introduce hazard regressive multipoint elitist spiral search optimization (HRMESSO), a novel technique for efficient task scheduling with reduced time consumption. User tasks are initially received, prioritized, and optimized. Cox proportional hazard regression is applied to establish relationships between task attributes (e.g., priority level, request arrival time, file size) and task prioritization. The great deluge elitist spiral search optimization identifies optimal virtual machines, considering factors like energy, memory, and CPU availability. The spiral search employs logarithmic spirals and Jenson Shannon divergence to find global optimal virtual machines. Finally, the task assigner schedules prioritized tasks onto the identified optimal virtual machines. Experimental evaluation is conducted with different metrics such as task scheduling efficiency, makespan, throughput and energy consumption. The quantitatively compared results exhibit the HRMESSO technique provides better scheduling efficiency, lesser makespan, throughput and energy consumption.