Towards Large-Scale Graph-Based Traffic Forecasting: A Data-Driven Network Partitioning Approach

Zhang，Chenhan1; Zhang，Shuyu2; Zou，Xiexin3; Yu，Shui1; Yu，James J.Q.2

2022

10.1109/JIOT.2022.3218780

IEEE Internet of Things Journal   Impact Factor & Quartile

2372-2541

2327-4662

Network partitioning is recognized as an effective auxiliary approach for solving transportation tasks on large-scale traffic networks in a domain-decomposition manner. Most of the existing related partitioning algorithms are explicitly designed to traffic management problems and merely focus on the implied topology of the networks. In this paper, towards the practical problems that happened to traffic forecasting tasks, we propose a network-partitioning-based domain-decomposition framework to improve GCN-based predictors’ performance on large-scale transportation networks. Particularly, we devise a data-driven network-partitioning approach, namely, Speed-Matching-Partitioning, which employs not only the topological features but also the traffic speed observations of traffic networks for partitioning. Additionally, we propose a data-parallel training strategy that feeds partitioned sub-networks into independent predictors for parallel training. The proposed approach is tested by comprehensive case studies on three real-world datasets to evaluate its effectiveness. The results indicate that the proposed approach can help improve GCN-based predictors’ accuracy and training efficiency on both small and relatively large traffic datasets. Furthermore, we investigate the model sensitivity to the selection of graph representations and framework parameters, and the learning efficiency of the data-parallel training strategy.

distributed computation domain decomposition Forecasting graph neural network Industrial Internet of Things Network partitioning Partitioning algorithms Roads Task analysis traffic forecasting Training Transportation

EI ; SCI

English

Others

Stable Support Plan Program of Shenzhen Natural Science Fund[20200925155105002] ; General Program of Guangdong Basic and Applied Basic Research Foundation[2019A1515011032] ; Guangdong Provincial Key Laboratory[2020B121201001] ; Australian Research Council (ARC)["DP200101374","LP190100676"]

Computer Science ; Engineering ; Telecommunications

Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications

WOS:000938278700057

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20224613110260

Efficiency ; Graph neural networks ; Graphic methods ; Internet of things ; Job analysis ; Large dataset ; Scalability ; Topology

Data Communication, Equipment and Techniques:722.3 ; Computer Software, Data Handling and Applications:723 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4 ; Production Engineering:913.1 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4 ; Systems Science:961

2-s2.0-85141555070

Scopus

1.Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia
2.Department of Computer Science and Engineering, Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Southern University of Science and Technology, Shenzhen, China
3.Department of Electrical Engineering, The Hong Kong Polytechnic University, Hong Kong, Hong Kong

Zhang，Chenhan,Zhang，Shuyu,Zou，Xiexin,et al. Towards Large-Scale Graph-Based Traffic Forecasting: A Data-Driven Network Partitioning Approach[J]. IEEE Internet of Things Journal,2022,PP(99):1-1.

Zhang，Chenhan,Zhang，Shuyu,Zou，Xiexin,Yu，Shui,&Yu，James J.Q..(2022).Towards Large-Scale Graph-Based Traffic Forecasting: A Data-Driven Network Partitioning Approach.IEEE Internet of Things Journal,PP(99),1-1.

Zhang，Chenhan,et al."Towards Large-Scale Graph-Based Traffic Forecasting: A Data-Driven Network Partitioning Approach".IEEE Internet of Things Journal PP.99(2022):1-1.