关键词: 时间序列, 交通流预测, 回声状态网络, 主成分分析降维

Abstract:

ing at the problem of low precision of multi-step traffic flow prediction, a cycle prediction model for traffic flow forecasting is presented. First, the time series is reconstructed by considering the periodicity of traffic flow in our model, and Principal Component Analysis (PCA) is explored as a dimensionality reduction method. Then the Echo State Network (ESN) model is used to predict the traffic flow time series. Meanwhile, an adaptive disturbance particle swarm optimization algorithm is used to optimize the parameters of the model. The availability of the proposed model is proved by predicting the time series of real traffic flow. The Mean Absolute Percentage Error (MAPE) of the prediction results is 9.8%, which is 12.7% lower than that of the traditional ESN multi-step prediction model. Experiments demonstrate that the proposed model can effectively prevent the delay of prediction results and greatly improve the precision of multi-step prediction.

Key words: time-series, traffic flow prediction, echo state network, principal component analysis dimensionality reduction