Evaluating Energy Efficiency in IoT Systems: A Comparative Analysis of Cloud and Hybrid Edge-Cloud Processing Models Towards Green Computing

This study investigates the optimization strategies and green computing approaches for energy efficient data processing in IoT-cloud systems. The purpose of this investigation is to enhance the sustainability of IoT-cloud ecosystems by exploring existing methodologies and evaluating their effectiveness. Internet of Things (IoT) has been facing increased energy consumption concerns, especially in cloud-based data processing systems with its rapid expansion. This paper examines energy-efficient data handling in IoT-cloud ecosystems by comparing traditional cloud-based processing with hybrid edge-cloud computing to seek the optimal model for reducing energy consumption and environmental impact. A weather monitoring system, with ESP32 microcontrollers and environmental sensors, is used as a testbed simulating data intensive IoT operations. Research has focused and researched on three main areas: energy efficiency, the carbon footprint and the performance of systems, particularly how hybrid processing can reduce the energy and carbon footprint related to cloud computing. Within the analysis, the estimation of energy and carbon consumption, system responsiveness and the efficiency of task allocation on the kWh consumed was evaluated. Furthermore, scalability simulations of hybrid IoT networks with up to 10,000 devices illustrate the practicality of large-scale systems. The outcomes show substantial improvements to energy efficiency, especially at scale, offered by hybrid edge-cloud models, aiming to the promise for designing sustainable IoT systems. These findings provide empirical evidence confirming hybrid processing as a sustainable substitute to standard cloud architectures. The research concludes by giving recommendations for designing energy-efficient IoT systems and integrating hybrid edge-cloud processing models into future IoT infrastructure towards greener computing solutions.