Short-Term Intersection Traffic Flow Forecasting

Details

• Creators:
  Qi, Yi ; Qun, Zhao ; Qu, Wenrui ; Azimi, Mehdi
• Corporate Creators:
  Texas Southern University. Dept. of Transportation Studies ; Qilu University of Technology (Shandong Academy of Sciences) ; University of North Carolina at Charlotte. Center for Advanced Multimodal Mobility Solutions and Education
• Corporate Contributors:
  United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Data Mining Dispatching Forecasting Mathematical Prediction Routing Scheduling Signalized Intersections Traffic Congestion Traffic Flow Truck Traffic
• Publication/ Report Number:
  69A3551747133
• Resource Type:
  Tech Report
• Geographical Coverage:
  China
• Edition:
  Final Report
• Corporate Publisher:
  University of North Carolina at Charlotte. Center for Advanced Multimodal Mobility Solutions and Education
• Abstract:
  The intersection is a bottleneck in an urban roadway network. As traffic demand increases, there is a growing congestion problem at urban intersections. Short-term traffic flow forecasting is crucial for advanced trip planning and traffic management. However, there are only a handful of existing models for forecasting intersection traffic flow. In addition, previous short-term traffic flow forecasting models usually were for predicting roadway conditions in a very short period, such as one minute or five minutes, which is often too late given that a driver may well be approaching the bottleneck already. Being able to accurately predict traffic congestion in about half-hour advance is very critical for advanced trip planning and traffic management. To fill this gap, this research evaluated different methods used for short-term traffic flow forecasting. 24-h cycle by cycle traffic data collected at a signalized intersection in Jinan, China is used to develop models. First, single models are developed, including clustering, k-nearest neighbors (KNN), backpropagation neural network (BP), and Elman models. Next, an improved KNN model was developed to improve the prediction accuracy of the original KNN model. In addition, entropy-weight-method based integrated models are also developed. Three different types of entropy weight methods (EWMs), i.e., EWM-A, EWM-B, and EWM-C, have been used by previous studies for integrating prediction models. These three methods use very different ideas for determining the weights of individual models for integration. To compare the performances of these three EWMs, this study also applied them to develop integrated short-term traffic flow prediction models for the same selected signalized intersections by combining the improved KNN and Elman models. These two models were selected because they have been widely used for traffic flow prediction and have been approved to be able to achieve good performance. After that, three integrated models were developed by using the three different types of EWMs. The performances of the three integrated models were compared with improved KNN and Elman models. The developed models are evaluated by applying them to the same intersection for forecasting the short-term traffic conditions on a different set of days. The prediction performance of these models was compared. We found that for the four single models, KNN outperforms other models. For EWMs based integrated models, the traffic flow predicted with the EWM-C model is the most accurate prediction for most of the days. Based on the model evaluation results, the advantages of using the EWM-C method were deliberated and the problems with the EWM-A and EWM-B methods were also discussed. The objectives of this project are to (1) introduce different methods to predict short-term traffic flow at signalized intersections; (2) develop models with filed collected data; and (3) evaluate the performance of the different models.
• Format:
  PDF
• Funding:
  CAMMSE-UNCC-2021-UTC-Project-08
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:3996ef41b533a181402112addd9aca653fcf5b5254b679bb7611995f6c3e78d0a2354d7ab97e0a2304cd7af01c26a216ecc5459dc4f63d4b09585a950b42cc93
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/64497/dot_64497_DS1.pdf
• File Type:
  [PDF - 1.41 MB ]