Akademik Veri Yönetim Sistemi
IEEE INTERNET OF THINGS JOURNAL, cilt.12, sa.17, ss.34644-34652, 2025 (SCI-Expanded, Scopus)
Integrating advanced artificial intelligence (AI), the Internet of Things (IoT) and cutting-edge cloud computing epitomizes the transformative potential of Industry 5.0 technologies, enabling unprecedented automation and efficiency. However, this technological surge also brings serious environmental challenges, significantly increasing energy consumption and carbon emissions. This article introduces EcoCloud, a robust task scheduling mechanism based on ant colony optimization (ACO) principles that aims to improve energy and carbon efficiency in Industrial IoT-enabled cloud environments. EcoCloud dynamically schedules MapReduce jobs on Hadoop clusters in IoT-based cloud systems by leveraging real-time resource consumption metrics through a comprehensive energy model deployed via a multilayer perceptron (MLP) neural network. As a result, the model accurately predicts power consumption and distributes workloads to underutilized nodes to optimize energy usage and reduce carbon emissions. Extensive evaluations show that EcoCloud significantly outperforms traditional scheduling methods, improving energy consumption and overall system performance.