Open Access

ARTICLE

Mobility-Aware Federated Learning for Energy and Threat Optimization in Intelligent Transportation Systems

Hamad Ali Abosaq¹, Jarallah Alqahtani^1,*, Fahad Masood², Alanoud Al Mazroa³, Muhammad Asad Khan⁴, Akm Bahalul Haque⁵

1 Computer Science Department, College of Computer Science and Information Systems, Najran University, Najran, 61441, Saudi Arabia
2 Department of Computer Science, CECOS University of IT and Emerging Sciences, Peshawar, 25000, Pakistan
3 Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, 11671, Saudi Arabia
4 Department of Telecommunication, Hazara University, Mansehra, 21120, Pakistan
5 The Faculty of Science and Engineering, Abo Akademi University, Turku, 20520, Finland

* Corresponding Author: Jarallah Alqahtani. Email:

Computers, Materials & Continua 2026, 87(2), 47 https://doi.org/10.32604/cmc.2026.075250

Received 28 October 2025; Accepted 26 December 2025; Issue published 12 March 2026

Abstract

The technological advancement of the vehicular Internet of Things (IoT) has revolutionized Intelligent Transportation Systems (ITS) into next-generation ITS. The connectivity of IoT nodes enables improved data availability and facilitates automatic control in the ITS environment. The exponential increase in IoT nodes has significantly increased the demand for an energy-efficient, mobility-aware, and secure system for distributed intelligence. This article presents a mobility-aware Deep Reinforcement Learning based Federated Learning (DRL-FL) approach to design an energy-efficient and threat-resilient ITS. In this approach, a Policy Proximal Optimization (PPO)-based DRL agent is first employed for adaptive client selection. Second, an autoencoder-based anomaly detection module is considered for malicious node detection. Results reveal that the proposed framework achieved an 8% higher accuracy increase, and 15% lower energy consumption. The model also demonstrates greater resilience under adversarial conditions compared to the state of the art in federated learning. The adaptability of the proposed approach makes it a compelling choice for next-generation vehicular networks.

---

Keywords

---