The invention belongs to the technical field of traffic flow prediction, and relates to a traffic flow prediction method based on a sliding window long-short term memory network, which comprises the following steps: preprocessing collected traffic flow data, constructing a topological structure chart of an urban road network, and constructing the input of a traffic flow prediction model; constructing a traffic flow prediction model based on a sliding window long-short term memory network, wherein the traffic flow prediction model is used for simultaneously obtaining space-time correlation of traffic flow; training the traffic flow prediction model, and evaluating the traffic flow prediction model based on the traffic data set to obtain a trained traffic flow prediction model; and performing traffic flow prediction based on the trained traffic flow prediction model. The invention provides a new traffic flow prediction model based on the sliding window long-short term memory network, and the traffic flow prediction model can better obtain the spatial and temporal correlation of the traffic flow, thereby obtaining a more accurate traffic flow prediction result.
本发明属于交通流量预测技术领域,涉及一种基于滑动窗口长短时记忆网络的交通流量预测方法,包括:对采集的交通流量数据进行预处理,构建城市路网的拓扑结构图和构建交通流量预测模型的输入;构建基于滑动窗口长短时记忆网络的交通流量预测模型,用于同时获取交通流量的时空相关性;对交通流量预测模型进行训练,并基于交通数据集评估交通流量预测模型,得到训练后的交通流量预测模型;基于训练后的交通流量预测模型进行交通流量预测。本发明提供了一种新的基于滑动窗口长短时记忆网络的交通流量预测模型,该交通流量预测模型能更好地获取交通流量的空间和时间相关性,从而获得更精准的交通流量预测结果。
Traffic flow prediction method based on a sliding window long-short term memory network
一种基于滑动窗口长短时记忆网络的交通流量预测方法
2021-07-13
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
A Short-Term Traffic Flow Prediction Method Based on Long Short-Term Memory Network
Springer Verlag | 2018
|A Short-Term Traffic Flow Prediction Method Based on Long Short-Term Memory Network
British Library Conference Proceedings | 2019
|