Work

Blockchain and RL-Based Secured Task Offloading Framework for Software-Defined 5G Edge Networks

Year: 2025

Type: article

Abstract: 5G (Fifth Generation) technology represents a significant advancement in telecommunications, facilitating industry innovation and advancement for applications across various sectors. It enhances high-speed, low-latency communication, making it ideal for task offloading in resource-constrained mobile devices. By leveraging task offloading, 5G networks maximize the efficiency of both computational and network resources, ensuring faster, more reliable data delivery and enabling high-performance requirements of modern applications. However, dynamic and secure task offloading remains a challenge due to fluctuating network conditions and trust concerns. This paper proposes SAGE (Secured Adaptive Generalized Edge), a reinforcement learning-based task offloading framework that leverages contextual bandits for adaptive decision-making in Multi-Access Edge Computing (MEC) environments. By integrating blockchain smart contracts for security and SDN-based orchestration for dynamic resource management, SAGE ensures robust, low-latency offloading. Experimental evaluations demonstrate that SAGE reduces task offloading delays by 36% and task durations by 30% compared to baseline methods under varying load and energy constraints.

Source: IEEE Access

DOI: 10.1109/access.2025.3554638

Authors: N. Sethu Subramanian, Prabhakar Krishnan, Kurunandan Jain, K. B. Aneesh Kumar, Tulika Pandey, Rajkumar Buyya

Institutions: Amrita Vishwa Vidyapeetham, Government of India, Ministry of Electronics and Information Technology, The University of Melbourne

Language: English

Topic: IoT and Edge/Fog Computing

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,075