Transformer Based Traffic Flow Forecasting in SDN-VANET

• Main Authors: Hossen, M.S (Author), Hussain, F. (Author), Khan, M.S (Author), Moniruzzaman, M. (Author), Rahman, M. (Author), Shuvro, A.A (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Subjects: Attention; Computer architecture; Data models; Encoder; Encoders; Forecasting; Information management; Intelligent systems; Intelligent vehicle highway systems; Long short-term memory; Network architecture; Predictive models; Sequence length; Sequence lengths; Software defined networking; Software-defined Network; Software-defined networkings; Software-defined networks; Time series; Traffic flow; Transformer; Transformers; Vehicles; Vehicular ad hoc networks; Vehicular Ad-hoc Network; Vehicular Adhoc Networks (VANETs); Wireless sensor networks
• Online Access: View Fulltext in Publisher; View in Scopus

 Intelligent Transportation System (ITS) provides services for proper traffic assistance. ITS helps in creating a transportation system that is smart, safe and efficient. Vehicular Ad-hoc Network supplies internet connectivity to vehicles and helps in traffic guidance. This paper uses a modified transformer architecture for time-series vehicular data to predict traffic flow. Time-series sequences are generated from the dataset for capturing temporal dependencies. Our proposed transformer-based model has been engineered to capture inter-feature correlations along with inter-sample correlations. The 2D-Transformers model has a significant decrease in error compared with Transformers and LSTM-based models. The prediction generated from the model can be transmitted throughout a network of vehicles. So, a holistic networking model is proposed where the vehicles will be connected to Road-side Units (RSUs) and the backbone network will be Software Defined Network (SDN). The traditional design principles, that incorporate data, control and management planes together in a network device, are incapable to adapt with this much data growth, bandwidth, speed, security, and scalability compared to SDN as it provides with centralized programmable mechanism reliably. The trained parameters learned using the transformer model can be passed throughout the network for traffic guidance. Author