Article: Intelligent task offloading in vehicular edge computing using federated learning and Kolmogorov Arnold networks (FL-KAN) Journal: International Journal of Ad Hoc and Ubiquitous Computing (IJAHUC) 2026 Vol.51 No.1 pp.37 - 55 Abstract: In recent times, vehicular edge computing has risen to become a crucial paradigm to handle the increasing computational demands of smart transportation systems. However, multiple challenges exist including the dynamic nature of vehicular environments, resource constraints of edge servers, and high privacy for data. To address these challenges, an intelligent task offloading framework integrates Kolmogorov Arnold networks (KAN) and federated learning (FL) is proposed. The framework works within a multi-tier architecture, using two different modes vehicle-to-roadside unit and vehicle-to-infrastructure to offload tasks. The KAN is trained with historical task data allows efficient task offloading, while FL ensures privacy and scalability across the local and global model. The experimental simulations were performed to optimise parameters like service latency, energy consumption and transfer delay. The results depict the proposed approach exceeds the existing algorithms such as machine learning, selective model aggregation, reinforcement learning, deterministic policy gradient by 18%, 25%, 13% and 21%. Inderscience Publishers - linking academia, business and industry through research

Title: Intelligent task offloading in vehicular edge computing using federated learning and Kolmogorov Arnold networks (FL-KAN)

Authors: C.P. Shabariram; N. Shanthi; Alisha Shinaz; Lakshana Ranganathan

Addresses: Department of Computer Science and Engineering, University VOC College of Engineering, Thoothukudi, Tamil Nadu, India ' Department of Computer Science and Engineering, Kongu Engineering College, Erode, Tamil Nadu, India ' Caterpillar India Engineering Solutions Private Limited, Bengaluru, Karnataka, India ' SAP Labs India Private Limited, Bengaluru, Karnataka, India

Abstract: In recent times, vehicular edge computing has risen to become a crucial paradigm to handle the increasing computational demands of smart transportation systems. However, multiple challenges exist including the dynamic nature of vehicular environments, resource constraints of edge servers, and high privacy for data. To address these challenges, an intelligent task offloading framework integrates Kolmogorov Arnold networks (KAN) and federated learning (FL) is proposed. The framework works within a multi-tier architecture, using two different modes vehicle-to-roadside unit and vehicle-to-infrastructure to offload tasks. The KAN is trained with historical task data allows efficient task offloading, while FL ensures privacy and scalability across the local and global model. The experimental simulations were performed to optimise parameters like service latency, energy consumption and transfer delay. The results depict the proposed approach exceeds the existing algorithms such as machine learning, selective model aggregation, reinforcement learning, deterministic policy gradient by 18%, 25%, 13% and 21%.

Keywords: vehicular edge computing; VEC; task offloading; transport system; Kolmogorov Arnold networks; KAN; federated learning.

DOI: 10.1504/IJAHUC.2026.151264

International Journal of Ad Hoc and Ubiquitous Computing, 2026 Vol.51 No.1, pp.37 - 55

Received: 17 Jan 2025
Accepted: 11 Jun 2025
Published online: 20 Jan 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Intelligent task offloading in vehicular edge computing using federated learning and Kolmogorov Arnold networks (FL-KAN)

Keep up-to-date