Accurate latency computation is essential for the Internet of Things (IoT) since the connected devices generate a vast amount of data that is processed on cloud infrastructure. However, the cloud is not an optimal solution. To overcome this issue, fog computing is used to enable processing at the edge while still allowing communication with the cloud. Many applications rely on fog computing, including traffic management. In this paper, an Intelligent Traffic Congestion Mitigation System (ITCMS) is proposed to address traffic congestion in heavily populated smart cities. The proposed system is implemented using fog computing and tested in a crowded city. Its performance is evaluated based on multiple metrics, such as traffic efficiency, energy savings, reduced latency, average traffic flow rate, and waiting time. The obtained results are compared with similar techniques that tackle the same issue. The results obtained indicate that the execution time of the simulation is 4,538 seconds, and the delay in the application loop is 49.67 seconds. The paper addresses various issues, including CPU usage, heap memory usage, throughput, and the total average delay, which are essential for evaluating the performance of the ITCMS. Our system model is also compared with other models to assess its performance. A comparison is made using two parameters, namely throughput and the total average delay, between the ITCMS, IOV (Internet of Vehicle), and STL (Seasonal-Trend Decomposition Procedure based on LOESS). Consequently, the results confirm that the proposed system outperforms the others in terms of higher accuracy, lower latency, and improved traffic efficiency.

翻译：精确的延迟计算对于物联网（IoT）至关重要，因为互联设备会产生大量数据，这些数据需在云端基础设施上处理。然而，云端并非最优解决方案。为克服此问题，雾计算被用于在边缘端实现数据处理，同时仍保留与云端的通信能力。包括交通管理在内的众多应用均依赖于雾计算。本文提出了一种智能交通拥堵缓解系统（ITCMS），旨在解决人口密集的智慧城市中的交通拥堵问题。该系统基于雾计算实现，并在拥堵城市中进行了测试。其性能通过多个指标进行评估，包括交通效率、节能效果、延迟降低、平均交通流量及等待时间。将所得结果与解决相同问题的类似技术进行了对比。结果表明，仿真执行时间为4,538秒，应用环路延迟为49.67秒。本文探讨了CPU使用率、堆内存使用量、吞吐量及总平均延迟等关键问题，这些指标对于评估ITCMS性能至关重要。此外，还将本系统模型与其他模型进行了性能对比。通过ITCMS、车联网（IOV）和基于LOESS的季节性趋势分解过程（STL）三个模型的吞吐量与总平均延迟两个参数进行对比，结果证实本系统在更高精度、更低延迟及更优交通效率方面优于其他模型。