Application of GSA-SVR in Short-term Traffic State Prediction Model of Urban Roads

To improve the accuracy of short-term traffic state prediction, this paper proposes a short-term traffic state prediction method based on the fusion of Gravitational search algorithm (GSA) and Support Vector Regression (SVR) to predict the average speed and traffic on urban roads. The average speed is predicted. This method combines the working mechanism of SVR in prediction and uses the GSA algorithm to optimize the relevant parameters in the SVR kernel function to improve the accuracy of the SVR kernel function, thereby obtaining more accurate prediction accuracy. Taking 4 road sections in a road network in Xuanwu District of Nanjing City as an example, using the measured traffic flow and speed data of urban roads to test the performance of the GSA-SVR model. Using 12 historical average data from 17:00-17:55 are recorded as training sample to predict road traffic flow and speed data from 18:00-18:25, the analysis results show that from the overall prediction rate, the GSA-SVR algorithm reduces the prediction error to less than 40% of the SVM algorithm, which verifies the GSA-SVR mentioned in this article. The effectiveness and practicality of the algorithm can provide a reliable basis for decision-making for the good management of urban roads.