Online short-term traffic flow prediction method for road section

The invention provides an online short-time traffic flow prediction method for a road section. The method comprises the following steps: S1, obtaining floating vehicle speed data and traffic flow dataof a road section, and respectively processing the floating vehicle speed data and the traffic flow...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LI MENG, ZHANG ZHENGCHAO, JI CONGYUAN, HE FANG, WANG YINENG
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention provides an online short-time traffic flow prediction method for a road section. The method comprises the following steps: S1, obtaining floating vehicle speed data and traffic flow dataof a road section, and respectively processing the floating vehicle speed data and the traffic flow data into a time sequence form; S2, converting the floating vehicle speed data time sequence and the traffic flow data time sequence into the same time window granularity; S3, carrying out smooth noise reduction processing on the floating car speed data time sequence by utilizing wavelet transform;S4, constructing a space-time state vector; S5, optimizing parameters C and gamma of an SVR model by adopting a particle swarm algorithm according to the space-time state vector to obtain an optimalSVR prediction model; S6, inputting the test sample into the prediction model obtained in S5 to obtain a prediction result; and S7, optimizing S5 prediction model parameters according to real-time prediction error feedback. Flo