1 J. Warren McClure School of Emerging Communication & Technology, Ohio University, USA.
2 Information and Telecommunication System, Ohio University, USA.
3 Computer Science Dept, University of Texas Permian Basin, Texas, USA.
International Journal of Science and Research Archive, 2025, 15(02), 1953-1967
Article DOI: 10.30574/ijsra.2025.15.2.1349
Received on 21 March 2025; revised on 22 May 2025; accepted on 28 May 2025
The transition to 6G networks necessitates a shift toward AI-native ecosystems capable of supporting Critical Network Infrastructure (CNI), such as autonomous transport and remote surgery. These applications require deterministic performance, specifically sub-millisecond latency and 99.99999% reliability, which exceed the capabilities of manual 5G orchestration. This paper proposes a decentralized, self-optimizing framework that integrates Deep Reinforcement Learning (DRL) for real-time resource allocation with Blockchain-based Smart Contracts for automated Service Level Agreement (SLA) enforcement.
By deploying Soft Actor-Critic (SAC) agents at the network edge, the system proactively optimizes bandwidth and beamforming in volatile Terahertz environments. Simultaneously, a Smart Contract layer enables "zero-touch" governance, utilizing an immutable ledger for resource trading and penalty execution. Results from a co-simulation using NS-3 and Hyperledger Fabric show a 38% increase in throughput and a 55% reduction in SLA violations over traditional methods. This hybrid architecture provides a scalable, secure, and autonomous management plane for future 6G critical infrastructures.
6G Communication; Critical Network Infrastructure (CNI); Network Slicing; Deep Reinforcement Learning (DRL); Smart Contracts; Blockchain; Zero-Touch Network Management (ZSM); Quality of Service (QoS)
Get Your e Certificate of Publication using below link
Preview Article PDF
Joy Selasi Agbesi, Justin Njimgou Zeyeum, Osorachukwu Maurice Ayozie, Damilola Hannah Titilayo and Halimat Popoola Oluwabukola. Self-optimizing resource management: Utilizing deep reinforcement learning and smart contracts for scalable and efficient network slicing in 6G CNI. International Journal of Science and Research Archive, 2025, 15(02), 1953-1967. Article DOI: https://doi.org/10.30574/ijsra.2025.15.2.1349.
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0
