华南理工大学学报(自然科学版)
華南理工大學學報(自然科學版)
화남리공대학학보(자연과학판)
JOURNAL OF SOUTH CHINA UNIVERSITY OF TECHNOLOGY(NATURAL SCIENCE EDITION)
2014年
7期
49-54
,共6页
短时交通流预测%SARIMA模型%RBF神经网络%历史周期性%空间相关性
短時交通流預測%SARIMA模型%RBF神經網絡%歷史週期性%空間相關性
단시교통류예측%SARIMA모형%RBF신경망락%역사주기성%공간상관성
short-term traffic flow forecasting%SARIMA model%RBF networks%historical cycle%spatial correlation
根据交通流的历史周期性和空间相关性,文中综合SARIMA模型在历史周期性预测上的优势和RBF模型在空间相关性预测上的优势,提出了SARIMA-RBF模型。该模型采用SARIMA模型通过历史数据预测下一时刻的交通流,然后将预测值与该点上下游关联的交通流数据相结合,采用RBF神经网络模型得出输出值,并将该输出值作为SARIMA-RBF模型对下一时刻交通流的预测结果。实验结果表明,该模型因同时考虑了交通流的历史周期性和空间相关性,相比SARIMA模型和RBF模型具有更好的交通流预测效果。
根據交通流的歷史週期性和空間相關性,文中綜閤SARIMA模型在歷史週期性預測上的優勢和RBF模型在空間相關性預測上的優勢,提齣瞭SARIMA-RBF模型。該模型採用SARIMA模型通過歷史數據預測下一時刻的交通流,然後將預測值與該點上下遊關聯的交通流數據相結閤,採用RBF神經網絡模型得齣輸齣值,併將該輸齣值作為SARIMA-RBF模型對下一時刻交通流的預測結果。實驗結果錶明,該模型因同時攷慮瞭交通流的歷史週期性和空間相關性,相比SARIMA模型和RBF模型具有更好的交通流預測效果。
근거교통류적역사주기성화공간상관성,문중종합SARIMA모형재역사주기성예측상적우세화RBF모형재공간상관성예측상적우세,제출료SARIMA-RBF모형。해모형채용SARIMA모형통과역사수거예측하일시각적교통류,연후장예측치여해점상하유관련적교통류수거상결합,채용RBF신경망락모형득출수출치,병장해수출치작위SARIMA-RBF모형대하일시각교통류적예측결과。실험결과표명,해모형인동시고필료교통류적역사주기성화공간상관성,상비SARIMA모형화RBF모형구유경호적교통류예측효과。
According to the historical cycles and spatial correlation of traffic flows , a model named as SARIMA-RBF is proposed to forecast the short-term traffic flow , which integrates the advantage of the SARIMA model in making use of the historical cyclic data with that of the RBF model in making use of the spatial correlation data .In the proposed model , the SARIMA model is adopted to forecast the traffic flow at the next time by using historical data, and then the RBF model is employed to obtain the output value by combining the SARIMA-based forecast data with the relevant traffic flow data of the upstream and downstream of test point .The output value of the RBF model is exactly the prediction result of the SARIMA-RBF model .Experimental results show that , in comparison with the SARIMA model and the RBF model , the SARIMA-RBF model achieves better results in forecasting the short-term traffic flow, because it considers both the historical cycles and the spatial correlation .