基于DE-BP神经网络的公共自行车站点需求量预测方法研究

Demand forecasting methods based on DE-BP neural network in public bicycle stations

通过对苏州高新区金狮大厦公共自行车站点历史借还数据进行周期相似性分析,选择工作日的数据作为样本数据,在此基础上构建基于BP神经网络公共自行车站点借还量预测模型,最后利用差分进化(DE)算法对BP神经网络模型进行优化,预测仿真结果表明,DE-BP神经网络模型精度较传统BP神经网络模型高。

By analyzing the cycle similarity of the historical borrowing and returning data of the public bicycle station at Golden Lion Building in Suzhou High-tech Zone, the working day data are selected as the sample data. On this basis, the paper constructs a predictive model of borrowing and returning amount of public bicycle stations based on BP neural network. Finally, the BP neural network model is optimized by the differential evolution (DE) algorithm. The simulation results show that the DE-BP neural network model is more accurate than the traditional BP neural network model.