Public bicycle flow variation volume forecasting method based on heap model fusion

Abstract

The invention discloses a public bicycle flow variation volume forecasting method based on heap model fusion. The public bicycle flow variation volume forecasting method comprises the steps of: 1, adopting a method of fusing public bicycle rental record data and meteorological data for extracting features, and constructing eigenvectors from several perspectives of time, space, meteorology, history, clustering and the like; 2, adopting a distance similarity matrix combining geological positions and a rental relation, clustering by utilizing a clustering algorithm, and configuring clustering features into the eigenvectors; 3, dividing the eigenvectors into five groups according to feature types, training five basic models by utilizing a machine learning system based on a gradient boosting tree algorithm, training features by adopting a cross validation method, and training a heap model by taking results of the five groups of basic models as features. The public bicycle flow variation volume forecasting method based on heap model fusion ensures that a certain difference exists among the basic models, constructs the heap model by adopting the cross validation method finally, improves the accuracy degree of the model, has good forecasting precision, and has small errors.

Description

technical field [0001] The invention belongs to the fields of intelligent transportation systems and data mining, and relates to a method for predicting the flow variation of public bicycles based on stack model fusion. Background technique [0002] In the face of deteriorating climate and environment, public bicycles, as a zero-pollution, zero-emission, low-carbon and environmentally friendly transportation method, must be vigorously promoted. Domestically, dozens of cities including Hangzhou, Shanghai, Beijing, Wuhan, and Nanjing have already operated public bicycle systems. On May 5, 2008, Hangzhou City began to operate the public bicycle system. The purpose is to solve the problem of "the last mile". The "bus-bicycle" method can reach the destination conveniently, thereby increasing the bus travel rate. However, after several years of practice, Hangzhou's public bicycle system has encountered some problems that need to be solved urgently. According to the satisfaction...

AI Technical Summary

Problems solved by technology

[0003] (1) Some rental points do not have bicycles at certain times, making it impossible for users to borrow bicycles in time;

[0004] (2) Some rental points do not have parking spaces at certain times, making it impossible for users to return bicycles in time

[0005] Except for Hangzhou, the public bicycle systems in other cities in China have the common problem of "difficulty in renting / returning bikes".

According to the results of the project team’s national survey, most cities in China that implement public bicycles use backward dispatching methods that cannot be dispatched in real time. Moreover, the current dispatching strategy is costly and requires a lot of labor costs and dispatching vehicle costs. At the same time, it lacks Certain predictability, lack of flow analysis of historical data and forecast of future flow, without considering factors such as weather and traffic conditions

Images