Green, Sustainable, and Energy-Efficient System for Transportation Applications in IoT Edge-Cloud Networks

Abstract

In recent years, the concepts of sustainability and green computing have gained significant attention, particularly in the context of smart cities and their various transportation applications. The primary goal is to shift transportation from fuel-based systems to electric alternatives, reducing overall CO 2 emissions. Motivated by this objective, this paper proposes a Green, Sustainable, and Energy-Efficient System for Transportation Applications in IoT Edge Cloud Networks. The focus is on designing an IoT edge cloud infrastructure to support sustainable and green transportation within smart cities. The system addresses various transportation-related tasks, including energy consumption monitoring, traffic and object detection, and optimal route planning, all while leveraging green edge cloud networks. To optimize performance, we propose a workload partitioning method based on a min-cut scheme that categorizes tasks into IoT-local, edge, and cloud-based workloads. This partitioning aims to reduce computational energy consumption and lower CO 2 emissions, fostering a more eco-friendly environment. Additionally, we introduce the Energy-Efficient Application Partitioning and Task Scheduling (EAPTS) scheme, which efficiently divides and schedules tasks across different nodes. To validate the system, we implemented testbeds based on Oslo’s public transport scenario, used training data from the given dataset, and developed a simulator for a green, sustainable transport environment. Simulation results demonstrate that the proposed system effectively reduces CO 2 emissions, energy consumption, and execution time for all operational tasks.