Open Access

ARTICLE

AI-Driven SDN and Blockchain-Based Routing Framework for Scalable and Trustworthy AIoT Networks

Mekhled Alharbi^1,*, Khalid Haseeb², Mamoona Humayun^3,*

1 Department of Software Engineering, College of Computer and Information Sciences, Jouf University, Sakaka, 72388, Al-Jouf, Saudi Arabia
2 Department of Computer Science, Islamia College Peshawar, Peshawar, 25120, Pakistan
3 School of Computing, Engineering and the Built Environment, University of Roehampton, London, SW155PJ, UK

* Corresponding Authors: Mekhled Alharbi. Email: ; Mamoona Humayun. Email:

(This article belongs to the Special Issue: Machine learning and Blockchain for AIoT: Robustness, Privacy, Trust and Security)

Computer Modeling in Engineering & Sciences 2025, 145(2), 2601-2616. https://doi.org/10.32604/cmes.2025.073039

Received 09 September 2025; Accepted 28 October 2025; Issue published 26 November 2025

Abstract

Emerging technologies and the Internet of Things (IoT) are integrating for the growth and development of heterogeneous networks. These systems are providing real-time devices to end users to deliver dynamic services and improve human lives. Most existing approaches have been proposed to improve energy efficiency and ensure reliable routing; however, trustworthiness and network scalability remain significant research challenges. In this research work, we introduce an AI-enabled Software-Defined Network (SDN)- driven framework to provide secure communication, trusted behavior, and effective route maintenance. By considering multiple parameters in the forwarder selection process, the proposed framework enhances network stability and optimizes decision-making. In addition, the involvement of the blockchain consensus algorithm and the intelligence of the SDN controller enables a proposed framework for robust authentication and a verifiable process of data blocks. Ultimately, only trusted devices are selected for routing, and malicious threats are prevented as data is forwarded to the cloud system. The extensive experimental analysis demonstrated that the proposed framework significantly improved energy consumption by 48%, packet loss by 49%, response time by 46%, and data transfer rate by 45% compared with existing techniques.

---

Keywords

---