Traffic Status Prediction of Arterial Roads Based on the Deep Recurrent Q-Learning

Abstract

With the exponential growth of traffic data and the complexity of traffic conditions, in order to effectively store and analyse data to feed back valid information, this paper proposed an urban road traffic status prediction model based on the optimized deep recurrent Q-Learning method. The model is based on the optimized Long Short-Term Memory (LSTM) algorithm to handle the explosive growth of Q-table data, which not only avoids the gradient explosion and disappearance but also has the efficient storage and analysis. The continuous training and memory storage of the training sets are used to improve the system sensitivity, and then, the test sets are predicted based on the accumulated experience pool to obtain high-precision prediction results. The traffic flow data from Wanjiali Road to Shuangtang Road in Changsha City are tested as a case. The research results show that the prediction of the traffic delay index is within a reasonable interval, and it is significantly better than traditional prediction methods such as the LSTM, K-Nearest Neighbor (KNN), Support Vector Machines (SVM), exponential smoothing method, and Back Propagation (BP) neural network, which shows that the model proposed in this paper has the feasibility of application.

Una revisión sistemática de literatura sobre implementaciones de sistemas de control de tráfico

“…Aunque principalmente se utiliza el aprendizaje guiado y supervisado para entrenar los modelos de predicción (Aqib et al, 2019), se han desarrollado propuestas para permitir que estos modelos aprendan mientras están en funcionamiento, utilizando datos en tiempo real (Hao, W. et al, 2020).…”

“…(Shin et al, 2019); (Chabchoub et al, 2021); (Wakkumbura et al, 2021); (Zhang et al, 2020); (Li, Y. et al, 2021) Image Processing Es un método que utiliza un conjunto de técnicas para manipular y analizar imágenes digitales. (Bao et al, 2023); (Cheng et al, 2023); (Hao, W. et al, 2020); (Islam et al, 2022); (Chahal et al, 2023) Long Short-Term Memory (LSTM)…”

Research on Vehicle Active Steering Stability Control Based on Variable Time Domain Input and State Information Prediction

“…In the actual offline data training process, the network input should not only consider the impact of historical data on current data, but also prevent excessive historical data from being obliterated and eliminate the impact of current data. Therefore, the network input data length needs to be dynamically adjusted in real time [36]. The operation cycle of the controller is T c , and the actual output of the network training is Y c = {y c1 , y c2 , .…”

“…dt , e δr (t) = δ tr (t) − δ r (t) (36) where, i pf , i pr , i if , i ir , i df, and i dr are the proportional, integral, and differential coefficients under the control of the front and rear wheel proportion integration differentiation (PID) controllers of the vehicle, respectively.…”

Road Traffic Status Prediction Approach Based on Kmeans-Decision Tree Model

“…Kumar and Sivanandan (2019) established a regression model to predict the congestion index (CI) of various types of vehicles by considering the bus congestion index, lane width, and signalized intersection as independent variables. Hao et al (2020) established an urban road traffic status prediction model based on a deep recursive Q-learning method, which was based on an optimized LSTM neural network. Ji and Hong (2019) used a deep learning method to predict the velocity of traffic flow based on real-time long-term evolution (LTE) data.…”