Sustainability · 2023 · 171 citations · 59 references
ComputingAutonomous SystemsCloud ComputingAutonomous VehiclesInternet Of ThingsTransportationIntelligent Transportation SystemsIot Cloud PlatformsSmart CitiesSmart City SystemsSustainable TransportationTraffic EngineeringMachine Learning For Traffic AnalysisReal-time Traffic MonitoringSmart City ApplicationsSmart City Internet Of ThingsTraffic ManagementTraffic Management ApplicationsTraffic Management SystemsTraffic Monitoring Systems
Smart cities have addressed many urban challenges, yet sustainable traffic management remains under‑researched because of its complex, heterogeneous nature. This study proposes a sustainable traffic framework grounded in IoT and ITS to tackle smart‑city traffic issues. The framework combines modeling‑based and decision‑making approaches, leveraging real‑time data from AI sensors and ITS devices processed by machine learning and cloud computing for traffic control and policy generation. Deploying the framework enables traffic prediction, forecasting, decongestion, route optimization, and pollution reduction through public transport promotion and low‑carbon zones, thereby achieving sustainable, low‑carbon urban mobility.
The emergence of smart cities has addressed many critical challenges associated with conventional urbanization worldwide. However, sustainable traffic management in smart cities has received less attention from researchers due to its complex and heterogeneous nature, which directly affects smart cities’ transportation systems. The study aimed at addressing traffic-related issues in smart cities by focusing on establishing a sustainable framework based on the Internet of Things (IoT) and Intelligent Transportation System (ITS) applications. To sustain the management of traffic in smart cities, which is composed of a hybridized stream of human-driven vehicles (HDV) and connected automated vehicles (CAV), a dual approach was employed by considering traffic as either modeling- and analysis-based, or/and the decision-making issues of previous research works. Moreover, the two techniques utilized real-time traffic data, and collected vehicle and road users’ information using AI sensors and ITS-based devices. These data can be processed and transmitted using machine learning algorithms and cloud computing for traffic management, traffic decision-making policies, and documentation for future use. The proposed framework suggests that deploying such systems in smart cities’ transportation could play a significant role in predicting traffic outcomes, traffic forecasting, traffic decongestion, minimizing road users’ lost hours, suggesting alternative routes, and simplifying urban transportation activities for urban dwellers. Also, the proposed integrated framework adopted can address issues related to pollution in smart cities by promoting public transportation and advocating low-carbon emission zones. By implementing these solutions, smart cities can achieve sustainable traffic management and reduce their carbon footprint, making them livable and environmentally friendly.
59