SHORT-TERM TRAFFIC FLOW FORECASTING MODELS AND COMBINATORIAL OPTIMIZATION ALGORITHM

Accurate and real-time short-term traffic flow prediction is the foundation for urban traffic control, and also an important part of intelligent transportation system. We made research and improvement for several major forecasting models based on the analysis of the traditional methods of traffic flow forecasting. According to the idea of data fusion, the comprehensive results of the various models, and the dynamic weight distribution, we establish a prediction model combinatorial optimization. The idea of data fusion in accordance with the comprehensive results of the various models, the dynamic weight distribution, the establishment of a prediction model combinatorial optimization. Finally, Validation and comparison have been taken through concrete examples. The result shows that the combinatorial optimization algorithm has the best forecasting for it has the smallest average relative error and mean square error.