A Combined Forecasting Method of Short-term Traffic Flow

Abstract

Aiming at the problem that an existing short-time traffic flow forecasting model is low in forecasting precision, the invention provides a short-time traffic flow forecasting method on the basis of grey system and least square support vector machine combined forecasting. The method, on the basis of advantages of a grey model, the least square vector machine (LSSVM) and other artificial intelligence methods, establishes a grey system and least square support vector machine combined forecasting model, and carries out residual correction and background value correction on the grey model as well as parameter optimization on the least square vector machine, so as to improve forecasting precision and generalization ability of the combined forecasting model; as forecasting time extends, the grey system and least square support vector machine combined forecasting model is relatively high in forecasting precision and is high in forecasting precision stability; and the method, through empirical analysis, achieves a good improvement effect.

Description

technical field [0001] The invention belongs to the field of road network traffic planning system, and relates to a traffic flow prediction method, in particular to a short-term traffic flow prediction technology based on gray system and least square support vector machine combination prediction. Background technique [0002] Real-time and accurate traffic flow forecasting is the basis for intelligent traffic management. According to different time spans, traffic flow forecasting can be divided into long-term forecasting and short-term forecasting. Short-term traffic flow forecasting is sudden, time-varying and random. , it is difficult to make accurate mathematical models, and establishing a short-term traffic flow prediction model with high prediction accuracy and stable prediction results has always been a difficult problem in the field of traffic intelligent management research. [0003] In recent years, with the development of intelligent transportation system (ITS), in...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the problem that the prediction accuracy of the existing short-term traffic flow prediction model is not high, and provides a short-term traffic flow prediction method based on the combined prediction of the gray system and the least squares support vector machine, which can effectively improve the Prediction accuracy

Images