Accurate V2X Traffic Prediction with Deep Learning Architectures

Ali R. Abdellah ^1* Ahmed Abdelmoaty ^1* Abdelhamied Ateya ^2,3 Ahmed A Abd El-Latif ^2,4 Ammar Muthanna ^5,6 Andrey Koucheryavy ⁵

• ¹ Al-Azhar University, Cairo, Egypt
• ² Prince Sultan University, Riyadh, Riyadh, Saudi Arabia
• ³ Zagazig University, Zagazig, Al Sharqia, Egypt
• ⁴ University of Menoufia, Shibin Al Kawm, Al Minufiyah, Monufia, Egypt
• ⁵ Saint-Petersburg State University of Telecommunications, Saint Petersburg, Russia
• ⁶ Peoples' Friendship University of Russia, Moscow, Moscow Oblast, Russia

Vehicle-to-Everything (V2X) communication promises to revolutionize road safety and efficiency. However, challenges in data sharing and network reliability impede its full realization. This paper addresses these challenges by proposing a novel Deep Learning (DL) approach for traffic prediction in V2X environments. We employ Bidirectional Long Short-Term Memory (BiLSTM) networks and compare their performance against other prominent DL architectures, including unidirectional LSTM and Gated Recurrent Unit (GRU). Our findings demonstrate that the BiLSTM model exhibits superior accuracy in predicting traffic patterns. This enhanced prediction capability enables more efficient resource allocation, improved network performance, and enhanced safety for all road users, reducing fuel consumption, decreased emissions, and a more sustainable transportation system.