2026· International Journal of Computer Science and Engineering Innovations· 0 citations
TL;DR
This paper presents a comprehensive framework for artificial intelligence (AI)-enabled autonomous network slicing optimization in 6G systems and investigates the application of advanced machine learning paradigms specifically deep reinforcement learning, federated learning, and generative AI to orchestrate dynamic resource provisioning, cross-slice isolation, and proactive SLA (Service Level Agreement) enforcement.
Abstract
The advent of sixth-generation (6G) wireless communication networks introduces unprecedented demands for ultra-high data rates, near-zero latency, massive device connectivity, and hyper-reliability. To satisfy these heterogeneous service requirements simultaneously, network slicing has emerged as a foundational architectural paradigm. However, the static and reactive resource allocation strategies utilized in legacy generations are insufficient to cope with the highly dynamic, multi-dimensional, and time-varying nature of 6G traffic demands. This paper presents a comprehensive framework for artificial intelligence (AI)-enabled autonomous network slicing optimization in 6G systems. We investigate the application of advanced machine learning paradigms specifically deep reinforcement learning (DRL), federated learning (FL), and generative AI to orchestrate dynamic resource provisioning, cross-slice isolation, and proactive SLA (Service Level Agreement) enforcement. Through a robustly designed methodology combining centralized global coordination with decentralized edge execution, this study provides an optimized, self-healing, and intent-driven network orchestration architecture. The experimental evaluation illustrates that the proposed AI-driven framework outperforms conventional heuristics and static optimization models across critical performance metrics, including spectrum efficiency, SLA satisfaction rate, and computational overhead. The paper concludes by defining prominent research gaps and future directions toward standardizing fully autonomous, zero-touch 6G network management.
A QoE-aware framework for Multi-Access Edge Computing-enabled Open Radio Access Network (O-RAN) architectures, combining a graph attention network (GAT) encoder, distributed multi-agent DRL, and privacy-preserving FL, while transitioning control from Quality of Service (QoS) to QoE metrics is proposed.
Manoj Prasad Kunasegran, Wai Leong Pang, S. K. Phang· IEEE Access· 0 citations
Future 6G services will require strict performance guarantees, especially in terms of delay, end-to-end (e2e) across multiple network domains including packet and radio segments. While deterministic transport and slice-based capacity allocation can improve segment-level performance, ensuring e2e Network Service (NS) performance remains challenging as it requires making decisions Near–Real-Time (Near-RT) on a per-service basis, which does not fit well within the typical centralized control and orchestration hierarchy. Multi-agent systems (MAS), where a number of distributed agents collaborate, has demonstrated its capabilities for such Near-RT control. Agents equipped with Deep Reinforcement Learning (DRL) engines autonomously made traffic routing decisions based on e2e telemetry measurements. In this paper, we extend such MAS solutions for NS traffic routing focused on covering several issues that appear under frequent NS reconfiguration, e.g., caused by end device mobility. In addition, we define a lifecycle for NS operation that includes the initial MAS deployment, model reconfiguration during operation, and NS reconfiguration. The proposed lifecycle requires the definition of DRL training and validation procedures to produce models ready to be deployed with guaranteed performance under certain network conditions. In addition, model selection algorithms are defined for the lifecycle scenarios. In case of NS reconfiguration, a procedure for probe testing the actual network conditions is proposed to improve model selection. Evaluation across a meaningful set of network and traffic scenarios shows that the MAS is able to maintain e2e delay guarantees under all the lifecycle scenarios.
H. Shakespear-Miles, S. Barzegar, M. Ruiz et al.· IEEE Transactions on Network...· 0 citations
The impending advent of Sixth-Generation (6G) wireless networks promises unprecedented performance, including tera-bit-per-second data rates and ultra-low latency. However, the energy consumption required to support such massive connectivity and computational demands poses a significant threat to global sustainability goals. Consequently, the concept of "Green 6G" has emerged, aiming to minimize the carbon footprint of network operations. This paper provides a comprehensive review of energy-aware routing techniques that leverage Artificial Intelligence (AI) to optimize energy efficiency in 6G networks. We analyze key AI paradigms, including Deep Reinforcement Learning (DRL), Federated Learning (FL), and Graph Neural Networks (GNNs), and their applications in intelligent routing decisions. The review highlights how these AI-driven techniques can dynamically manage network resources, predict traffic loads, and select energy-optimal paths, thereby reducing overall power consumption without compromising Quality of Service (QoS). The challenges of computational overhead, data privacy, and integration with novel 6G architectures like terahertz communication and network slicing are also discussed. This survey concludes that AI is not merely an enabler but a cornerstone for realizing sustainable and intelligent 6G networks, paving the way for an eco-friendly digital future.
Joshna M, R. K.· Journal of Artificial Intell...· 0 citations
A constrained optimization model that supports different management goals through alternative objective functions (latency-aware or power-aware) while enforcing operational constraints, including node capacities, slice-specific latency bounds, and explicit limits on VNF migrations/relocations between scheduling periods is proposed.
R. Moreno-Vozmediano, E. Huedo, R. Montero et al.· Journal of Network and Syste...· 0 citations
Sixth-generation (6G) communication requires seamless integration of terrestrial networks (TN) and non-terrestrial networks (NTN) to deliver reliable, intelligent, and ubiquitous connectivity. This paper presents a Cognitive TN–NTN Service Orchestration framework that combines Digital Twins and Agentic Artificial Intelligence (AI) to achieve resilient network management. Digital Twins create real-time virtual replicas of terrestrial infrastructure, satellites, UAVs, and high-altitude platforms for continuous monitoring and prediction. Agentic AI employs autonomous agents to analyze network conditions, optimize routing, perform proactive fault detection, and coordinate service migration during failures or congestion. Reinforcement Learning and Graph Neural Networks support adaptive decision-making across heterogeneous 6G environments. Experimental evaluation indicates improved latency, packet delivery ratio, service availability, orchestration efficiency, and resilience compared with conventional orchestration methods. The proposed framework enables uninterrupted communication for smart cities, autonomous transportation, disaster recovery, industrial automation, maritime networks, and remote healthcare services.
Siva Sudheer Mahadasu, Dr. Nazila Safavi· International Journal of AI...· 0 citations
Efficient long-term network evolution is becoming increasingly critical in dense 5G-Advanced and beyond cellular systems, where persistent traffic imbalances and localized congestion pose significant challenges that conventional short-term radio resource management alone cannot fully mitigate. This paper proposes a digital twin (DT)-enabled non-real-time (NRT) network evolution framework integrated with a large language model (LLM). Within this architecture, the digital twin provides a high-fidelity, controllable environment for evaluating infrastructure actions, while the LLM serves as a strategic orchestration engine that recommends cost-efficient network upgrades based on observed network states. Unlike traditional optimization methods that require exhaustive mathematical reformulations for each specific scenario, the proposed framework leverages the reasoning capabilities of LLMs to interpret operator objectives and constraints in natural language, generating structured evolution plans. The considered NRT action space encompasses antenna upgrades, bandwidth expansion, and new base station (BS) deployment. A techno-economic formulation is introduced to jointly evaluate load reduction performance and overall economic expenditure. Numerical results in a dense cellular scenario demonstrate that the framework effectively reduces peak resource utilization and provides diverse, coordinated evolution strategies tailored to varying network conditions.
Yukai Wang, Janghee Woo, G. Hahm et al.· International Conference on...· 0 citations