Hybrid Optimal Ensemble SVM Forest Classifier for Task Offloading in Mobile Cloud Computing.

The article focuses on a novel task offloading framework for mobile devices (MDs) that enhances energy efficiency and system performance by employing a Hybrid Red Fox Flow Direction-based Ensemble Support Vector Machine Random Forest Classifier (HRFFD-ESVMF) algorithm. This multi-objective scheduling approach aims to minimize energy consumption and latency while maximizing resource utilization in cloud computing environments, particularly for smartphones offloading tasks to cloudlets and remote servers. Simulated using the Cloudsim tool, the HRFFD-ESVMF method demonstrated superior performance compared to existing techniques such as RL-SARSA, DRL-DTPG, and DQN across metrics including latency, energy cost, makespan, CPU utilization, execution time, and energy consumption. The study highlights the algorithm's potential to improve battery life and user satisfaction in mobile cloud computing by optimizing task scheduling under communication and computational constraints.