An Intelligent Control Method for Urban Traffic using Fog Processing in the IoT Environment based on Cloud Data Processing of Big Data

Due to such disadvantages of current traffic light control methods as waste of time, waste of fuel and resources, increased air pollution, providing an intelligent traffic light control system that leads to the shortest waiting time for vehicles and pedestrians becomes so significant. Given the high priority of this issue, this paper presents an intelligent urban traffic system method based on IoT data and fog processing. Fog processing is a platform that is at the edge of the network and provides powerful services and applications for users. Compared to cloud computing, cloud computing is closer to users and therefore collects information faster and disseminates it over a network of sensors. It also helps cloud computing to perform tasks such as preprocessing and data collection. Cloud computing is a new type of distributed processing structure used for the Internet of Things. This paper proposed a method called GW-KNN. According to this method, we first collect data through the Internet of Things. Then, the preprocessing operation and extraction of effective fields in the cloud processing section are performed using the k-nearest neighbor improved machine learning algorithm. Traffic on each road is predicted in the next time slot and this information is sent for use in the fog processing layer to make traffic control decisions. The concept of Euclidean distance network with Gaussian weight was used to predict the future traffic situation and KNN model was included in the algorithm output to increase the forecasting accuracy and finally solve the problem of traffic light control. This idea was implemented and simulated using MATLAB. To get the results, the implementation was done on a computer with an i7-10750 processor and 16 GB of main memory and 1 TB of external memory. The results of the evaluations show that the proposed method has a much better performance than the previous two methods in terms of absolute mean error percentage, absolute mean error percentage of traffic forecast, and average waiting time of each vehicle.