This article argues that 6G should reverse that trajectory by reordering five priorities: control first; customer outcomes before peak rates; business guarantees before megabytes; software-driven operations with governed agentic artificial intelligence; and technology in service of those priorities.
Abstract
Sixth-generation mobile networks are approaching a structural inflection point. Five generations of vendor-led architecture have left operators dependent on platforms they cannot fully modify and artificial-intelligence inference layers they cannot audit. This article argues that 6G should reverse that trajectory by reordering five priorities: control first; customer outcomes before peak rates; business guarantees before megabytes; software-driven operations with governed agentic artificial intelligence; and technology in service of those priorities. Four contributions operationalize the thesis. The Control Compact is an own-federate-consume taxonomy that allocates architectural sovereignty by strategic value. The Guarantee Economy is a six-tier outcome-priced model aligned with IMT-2030 usage scenarios and converts operator control into enforceable service-level objectives. An operator-grade Network MCP Platform shows how autonomous agents could enter the service-based architecture through a governed tool plane with auditable hooks for identity, charging, lawful intercept, enforcement, and digital-twin validation. A standardization section states Rakuten Mobile's public position on AI-agent scope, radio access, migration, non-terrestrial networks, physical layer, core, and spectrum. The framework distinguishes operational evidence from national-scale cloud-native Open RAN and core network deployments, standards-grounded extrapolation, and forward-looking architecture and commercial proposals. A three-phase roadmap separates standards milestones from operator deployment targets and identifies validation gates and stakeholder implications.
Next-generation networks $(5 \mathrm{G} / 6 \mathrm{G})$ provide capabilities such as network slicing, enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communications (URLLC), and edge computing. However, configuring the related radio, core, slicing, and edge resources requires significant operational expertise. This work proposes an Intent-Based Networking (IBN) framework that combines Natural Language Processing, Large Language Models (LLMs), TMF921-compliant intent representation, and CAMARA APIs to simplify the definition and activation of network-sensitive vehicular services. In the proposed model, a Service Provider establishes a business agreement with a Network Operator, while the operator administrator defines service requirements through a conversational interface. These requirements are translated into machine-readable intents and mapped into network and edge orchestration actions. The framework is evaluated through a Teleoperated Driving (ToD) use case for autonomous vehicle repositioning. Results show that the intent translation and management pipeline introduces limited and repeatable overhead, while orchestration time is mainly affected by the underlying MANO/IaaS platform. The results indicate that combining IBN and CAMARA APIs can support flexible service preparation by operators and dynamic service consumption by applications.
Andrea Speranza, P. Giardina, Giacomo Bernini et al.· International Conference on...· 0 citations
This survey formally categorizes state-of-the-art DTN architectures into passive monitoring twins and active control twins, and provides an in-depth evaluation of their underlying enabling technologies, specifically ray-tracing, reconfigurable intelligent surfaces, artificial intelligence, and mobile edge computing.
Charalampos Oikonomidis, E. T. Michailidis, N. Miridakis· 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
This review systematically traces how mobile network technology has evolved from second-generation (2G) through fifth-generation (5G) systems, looks at how each generation has been applied in smart grid settings, and sets out what each generation could and could not do.
Musaab Abdelmageed Abdelraheem Abdalla· International Journal of Sci...· 0 citations
— The Kingdom of Saudi Arabia's ambition under Vision 2030 to rank among the world's top-ten logistics economies places its maritime gateways — principally Jeddah Islamic Port on the Red Sea and the adjacent King Abdullah Port — at the centre of a transformation toward autonomous, data-driven cargo handling. Legacy connectivity built on industrial Wi-Fi and best-effort 4G cannot guarantee the deterministic latency, mobility robustness, and device density that automated guided vehicles (AGVs), remotely operated ship-to-shore cranes, and real-time container tracking demand. This paper proposes the Hybrid Multi-Vendor Private 5G Blueprint (HMP-5G), an engineering and orchestration framework purpose-built for the topology, electromagnetic conditions, and procurement realities of Saudi industrial ports. The framework is organised across three coupled layers — a Radio Access layer mapped to port micro-zones, a Slicing layer that isolates safety-critical, automation, and enterprise traffic, and an Interoperability layer that allows heterogeneous Tier-1 vendor equipment (Huawei, Ericsson, Nokia) to coexist through standardised O-RAN O1/E2 and 3GPP service-based interfaces. The framework commits explicitly to a Standalone Non-Public Network (SNPN) model with on-site User Plane Function for data sovereignty, specifies hard slice isolation through dedicated physical resource block (PRB) allocation enforced by a Near-RT RIC xApp, and supports the isolation claim with a reserved-resource queueing model demonstrating that the URLLC control latency target is preserved under a one-million-device-per-square-kilometre telemetry surge. Performance targets are expressed against 3GPP TS 22.104 baselines rather than proprietary data, and every design choice is mapped to the National Transport and Logistics Strategy, the giga-project logistics layer, and the Saudi Green Initiative.
Siddiq Bin Salam, Sajjad Waqar Ahmad· Technium· 0 citations
This review examines how Ethernet Virtual Private Network and Virtual Extensible LAN overlays, operating across routed leaf-spine IP fabrics, can provide a resilient segmentation foundation for that requirement and concludes that EVPN-VXLAN should be treated as a programmable enforcement substrate rather than a security product.
Zakiuddin Mohammed· Global academic journal of e...· 0 citations
