Abstract
Accurate and fast short-term traffic flow prediction plays a vital role in the construction of future smart cities. To address large bandwidth consumption and high delay in traditional cloud solutions, and improve the accuracy and timeliness of traffic prediction, this paper introduces a novel three-layer Cloud-Edge-IoT traffic flow edge computing architecture, and proposes a short-term Traffic Flow Prediction Method based on Spatial-Temporal Correlation (TFPM-STC), in which Principal Component Analysis (PCA) is adopted for analyzing the intersection correlation, and the Convolution-Gated Recurrent Unit (Conv-GRU) and Bidirectional GRU (Bi-GRU) are used for extracting the spatial-temporal and periodic features of the traffic flow. Experiment results show that compared with existing methods, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of TFPM-STC are reduced by about 16.5 points on average, and there is a significant reduction in training time and prediction time.
Original language | English |
---|---|
Article number | 107219 |
Pages (from-to) | 1-17 |
Number of pages | 17 |
Journal | Computers and Electrical Engineering |
Volume | 93 |
DOIs | |
Publication status | Published - Jul 2021 |
Keywords
- Short-term traffic flow prediction
- Edge computing
- Principal Component Analysis
- Convolution-Gated Recurrent Unit (Conv-GRU)
- Bi-directional GRU (Bi-GRU)
- Spatial-temporal features
- Spatial–temporal features