An Efficient Bio-Inspired Optimization Framework for Scalable Task Scheduling in Cloud Computing Environments

The need for sharing and using resources is growing at a fast pace, which poses several issues for cloud computing (CC) as the number of users increases. For this reason, job scheduling with load balancing across resources is a crucial area for improving performance. High energy usage and underutilised resources are two of the major obstacles to effective task scheduling. To address this, propose a bio-inspired optimization framework utilizing the Lyrebird Falcon Optimization (LFO) algorithm, which mimics lyrebird behavior through two key phases: escaping (exploration) and hiding (exploitation). This population-based metaheuristic dynamically updates task assignments to minimize makespan and energy usage while enhancing CPU and resource utilization. The algorithm was implemented in CloudSim and evaluated across various task loads (1000–5000 tasks). Experimental results demonstrate that LFO consistently achieves lower makespan (from 22.13s to 18.78s) and energy consumption (from 21.67 kW to 23.70 kW) compared to the traditional Fruit Fly Optimization Algorithm (FOA), highlighting its efficiency. The key advantages of this work include its ability to minimize energy consumption while optimizing resource utilization, scalability to large-scale cloud environments, and improved performance, making it a promising solution for sustainable and efficient task scheduling in cloud computing.