A Short-Term Hybrid TCN-GRU Prediction Model of Bike-Sharing Demand Based on Travel Characteristics Mining

Abstract

This paper proposes an accurate short-term prediction model of bike-sharing demand with the hybrid TCN-GRU method. The emergence of shared bicycles has provided people with a low-carbon, green and healthy way of transportation. However, the explosive growth and free-form development of bike-sharing has also brought about a series of problems in the area of urban governance, creating a new opportunity and challenge in the use of a large amount of historical data for regional bike-sharing traffic flow predictions. In this study, we built an accurate short-term prediction model of bike-sharing demand with the bike-sharing dataset from 2015 to 2017 in London. First, we conducted a multidimensional bike-sharing travel characteristics analysis based on explanatory variables such as weather, temperature, and humidity. This will help us to understand the travel characteristics of local people, will facilitate traffic management and, to a certain extent, improve traffic congestion. Then, the explanatory variables that help predict the demand for bike-sharing were obtained using the Granger causality with the entropy theory-based MIC method to verify each other. The Multivariate Temporal Convolutional Network (TCN) and Gated Recurrent Unit (GRU) model were integrated to build the prediction model, and this is abbreviated as the TCN-GRU model. The fitted coefficient of determination R2 and explainable variance score (EVar) of the dataset reached 98.42% and 98.49%, respectively. Meanwhile, the mean absolute error (MAE) and root mean square error (RMSE) were at least 1.98% and 2.4% lower than those in other models. The results show that the TCN-GRU model has strong efficiency and robustness. The model can be used to make short-term accurate predictions of bike-sharing demand in the region, so as to provide decision support for intelligent dispatching and urban traffic safety improvement, which will help to promote the development of green and low-carbon mobility in the future.

A short-term forecasting method for photovoltaic power generation based on the TCN-ECANet-GRU hybrid model

“…In this paper, the model framework and parameters are set up mainly based on the literature [28][29][30] and adjusted through multiple experimental tests and personal experience. The TCN framework composed of 5 stacked TCN-ECA modules is used in this experiment.…”

Research on Shared Bicycle Prediction Using Gated Graph Convolutional Networks with Multi-Feature Edge Weights

“…In addition, predictive models like random forests or gradient boosting machines (GBM) are employed to classify demand levels based on the distinct attributes of each region 30 . Often, a combination approach is used where clustering techniques rst identify similar groups, and then speci c forecasting methods like time series analysis or regression are applied within these groups to re ne demand predictions 31,32 . This integrated method facilitates both extensive categorization and precise, localized forecasting.…”

A Hybrid Deep Learning Method Based on CEEMDAN and Attention Mechanism for Network Traffic Prediction

“…Different methods have different features and advantages, and the hidden features can be explored by using appropriate methods for training and learning. TCN uses convolutional networks, which can capture short-term local information of the data well, while the receptive field of the TCN can be flexibly adjusted and is suitable for network traffic prediction in most cases [46]. GRU has the characteristics of small parameters and fast convergence, which can better deal with the sudden and timely characteristics of network traffic.…”