摘要
当前停车位资源需求预测方法对城市潜力地段停车位资源分布均匀性差,导致共享停车位资源需求预测误差较大、可信度较低等问题。针对上述问题提出一种基于灰色算法的共享停车位资源需求预测方法,计算共享停车时间转变参数、出行吸引参数、区位因子参数和出行方式调节参数。利用灰度灰色算法构建非畸形模型,将参数结果代入最小二乘法中获取指标矩阵,利用该矩阵计算拟合值,得到城市潜力地段共享停车位资源需求的预测结果。实验结果证明,所提方法能够提高共享停车位资源需求预测准确率,保证了方法的可信度。
Currently,the distribution of parking space resources in urban potential location is not uniform,leading to large prediction error and low reliability of resource demand for shared parking space.Therefore,a method to fore-cast resource demand for shared parking space based on grey algorithm was proposed.This method calculated the time transformation parameters of sharing parking,the trip attraction parameters,the location factor parameters and the travel mode adjustment parameters.Then,our method used grayscale algorithm to construct a non-deformed model,and then took the parameter result into the least square method to obtain the index matrix.In addition,the method used this matrix to calculate the fitting value.Finally,we obtained the prediction result of resource demand for shared parking space in urban potential location.Simulation results show that the proposed method can improve the accuracy of resource demand predication for shared parking space and ensure the credibility.
作者
秦亚莘
吴海燕
QIN Ya-xin;WU Hai-yan(Beijing University of Civil Engineering and Architecture,Beijing 100044,China)
出处
《计算机仿真》
北大核心
2020年第1期421-424,共4页
Computer Simulation
基金
北京建筑大学研究生创新项目(PG2018005)。
关键词
城市
共享停车位
需求预测
准确率
误差率
Share parking space
Demand predication
Accuracy rate
Error rate
