Short-term traffic flow forecasting is crucial for intelligent traffic management. In view of the non-linear and random nature of short-term traffic flow, a prediction model based on BAS-VMD-CEEMDAN and IWOA-RF is proposed. Firstly, the parameters of the VMD, namely the modal number (K) and the value of the quadratic penalty term (α), are optimized using the BAS algorithm, and then the traffic flow is decomposed to obtain several VMF components and one RES component, which extracts the smooth information of the traffic flow. Subsequently, the RES component is decomposed using the decomposition completeness of CEEMDAN to obtain several IMF components, refining the complex information of the RES component. Then, the RF model is constructed according to the characteristics of each component, and then the parameters of RF models are optimized using IWOA. Finally, overlay the predictions of each component superimposed to obtain the final predictions. Experimental results show that the short-term traffic flow forecasting model basedon BAS-VMD-CEEMDAN-IWOA-RF has a high accuracy compared to other decomposition models.
Short-term traffic flow prediction based on BAS-VMD-CEEMDAN and IWOA-RF
30.07.2023
1276234 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
CEEMDAN-RF-LSTM-based traffic flow time sequence data prediction method and system
Europäisches Patentamt | 2024
|Short-term Wind Power Forecasting Based on CEEMDAN-FE-KELM Method
British Library Online Contents | 2016
|Prediction of Bus Passenger Flow Based on CEEMDAN-BP Model
SAE Technical Papers | 2020
|