Hybrid Monarch Butterfly Optimization-DenseNet framework for energy-aware task scheduling in cloud environments.

Cloud computing provides scalable processing capabilities for handling large-scale datasets across healthcare and other industries. Efficient task scheduling is essential to optimize resource utilization, reduce execution time, and minimize energy consumption. The authors of this study suggest a hybrid task scheduling strategy that uses DenseNet and Monarch Butterfly Optimization to enhance cloud computing settings. With Model-Based Optimization (MBO), the model aims to achieve task scheduling that not only reduces make span and energy consumption but also improves task prioritization through DenseNet deep learning techniques, which leverage resource availability for efficient learning. The model aims to address multiple optimization metrics, including CPU and resource utilization. The hybrid method, as the experiments show, achieves superior results compared to the existing techniques, including a make span of 406 ms and lower energy consumption with 200 tasks, and is equally effective with 1000 tasks. The proposed approach demonstrates strong performance under healthcare-representative workload abstractions modeled through task priority, latency sensitivity, and resource intensity characteristics. While the evaluation is conducted using generalized cloud workload traces, the framework is designed to support energy-conscious scheduling in healthcare-oriented cloud environments. Validation using healthcare-specific operational traces is identified as future work.