WIND: A Wireless Intelligent Network Digital Twin for Federated Learning and Multi-Layer Optimization

Background The 6G network provides on-demand services and efficient governance, which is an important capability of the 6G network in the future. Providing more flexibility, availability, and dynamicity in services and network function enablement face many challenges in the 6G network due to the system complexity. To fulfill the requirement of the new generation of a digital and intelligent network, the 6G architecture with digital twin as a new enabler technology, is expected to evolve in the network autonomy and generative intelligence properties, which could optimize and adapt the network and services themselves to a variety of scenarios and deployments. Methods To achieve 6G network autonomy and generative intelligence, we propose an architecture based on digital twin technology. This architecture integrates the digital twin network with the minimalist network and supports single-domain autonomous and cross-domain collaboration via centralized-distributed digital twin deployment, and defines the interactions between the digital twin and the service layer as well as the physical network. Results Based on the analysis of the architecture, we put forward the following design principles for the 6G digital twin network architecture: decoupling, interactions, endogenous Artificial Intelligence (AI), distribution, heterogeneity, autonomous, and closed-loop. In addition, we get the key technologies achieving collaboration efficiently between the network autonomy domain and generative intelligence domain in the distributed digital twin system. Important application directions of the 6G digital twin network architecture are also analyzed. Conclusions In this paper, the new digital-twin-enabled 6G architecture and 6G digital twin network architecture design principles are proposed. The key technologies and important application of digital-twin-enabled 6G architecture are provided.

Background: The 6G network provides on-demand services and efficient governance, which is an important capability of the 6G network in the future. Providing more flexibility, availability, and dynamicity in services and network function enablement face many challenges in the 6G network due to the system complexity. To fulfill the requirement of the new generation of a digital and intelligent network, the 6G architecture with digital twin as a new enabler technology, is expected to evolve in the network autonomy and generative intelligence properties, which could optimize and adapt the network and services themselves to a variety of scenarios and deployments. Methods: To achieve 6G network autonomy and generative intelligence, we propose an architecture based on digital twin technology. This architecture integrates the digital twin network with the minimalist network and supports single-domain autonomous and cross-domain collaboration via centralized-distributed digital twin deployment, and defines the interactions between the digital twin and the service layer as well as the physical network. Results: Based on the analysis of the architecture, we put forward the following design principles for the 6G digital twin network architecture: decoupling, interactions, endogenous AI, distribution, heterogeneity, autonomous, and closed-loop. In addition, we get the key technologies achieving collaboration efficiently between the network autonomy domain and generative intelligence domain in the distributed digital twin system. Important application directions of the 6G digital twin network architecture are also analyzed. Conclusions: In this paper, the new digital-twin-enabled 6G architecture and 6G digital twin network architecture design principles are proposed. The key technologies and important application of digital-twin-enabled 6G architecture are provided.

Digital twins and the Internet of Things (IoT) have gained significant research attention in recent years due to their potential advantages in various domains, and vehicular ad hoc networks (VANETs) are one such application. VANETs can provide a wide range of services for passengers and drivers, including safety, convenience, and information. The dynamic nature of these environments poses several challenges, including intermittent connectivity, quality of service (QoS), and heterogeneous applications. Combining intelligent technologies and software-defined networking (SDN) with VANETs (termed intelligent software-defined vehicular networks (iSDVNs)) meets these challenges. In this context, several types of research have been published, and we summarize their benefits and limitations. We also aim to survey stochastic modeling and performance analysis for iSDVNs and the uses of machine-learning algorithms through digital twin networks (DTNs), which are also part of iSDVNs. We first present a taxonomy of SDVN architectures based on their modes of operation. Next, we survey and classify the state-of-the-art iSDVN routing protocols, stochastic computations, and resource allocations. The evolution of SDN causes its complexity to increase, posing a significant challenge to efficient network management. Digital twins offer a promising solution to address these challenges. This paper explores the relationship between digital twins and SDN and also proposes a novel approach to improve network management in SDN environments by increasing digital twin capabilities. We analyze the pitfalls of these state-of-the-art iSDVN protocols and compare them using tables. Finally, we summarize several challenges faced by current iSDVNs and possible future directions to make iSDVNs autonomous.

In today's highly competitive wireless marketplace, carriers have to offer user-friendly innovative services to gain a competitive advantage. Furthermore, subscribers desire services that are easily or automatically customized to their specific needs and environment. This presentation examines how this can be achieved by synergistically leveraging the capabilities inherent in emerging technologies such as the wireless application protocol (WAP) and the wireless intelligent network (WIN).

Perhaps you have heard ofartificial intelligence (AI) or artificial neural networks (ANN) lately? An artificial neural network can be used to analyze all the simulated data from a digital twin and predict new outcomes. Sometimes they can respond faster than the digital twin itself. They can also be used to describe the complicated behavior of complex systems. We will revisit the topic of combining our digital twins with neural networks for control and automation. We will look at the rules used to define a simple example of a neural network and how it can be used as an alternative to the twin.

Life cycle monitoring of civil infrastructure such as bridges and buildings is critical to the long-term operational cost and safety of aging structures. The widespread use of Structural Health Monitoring (SHM) systems is limited due to unavailability of specialized data acquisition equipment, high cost of generic equipment, and absence of fully automatic decision support systems. The goals of the presented project include: first, design of a Wireless Intelligent Sensor and Actuator Network (WISAN) and creation of an inexpensive set of instrumentation for the tasks of structural health monitoring; second, development of a SHM method, which is suitable for autonomous structural health monitoring. The design of the wireless sensor network is aimed at applications of structural health monitoring, addressing the issues of achieving a low cost per sensor, higher reliability, sources of energy for the network nodes, energy-efficient distribution of the computational load, security and coexistence in the ISM radio bands. The practical applicability of the sensor network is increased through utilization of computational intelligence and support of signal generation capabilities. The automated SHM method is based on the method of modal strain energy, though other SHM methods will be supported as well. The automation tasks include automation of the modal identification through ambient vibrations, classification of the acquired mode shapes, and automatic evaluation of the structural health.

Abstract: The transition from Beyond 5G (B5G) to 6G is a sea change in wireless communication technology, which is expected to upend industries such as transportation, healthcare, and manufacturing. By expanding upon the 5G network's current capabilities, B5G boosts mobile broadband, reduces power consumption, and maximizes spectrum usage. Advanced Internet of Things (IoT) devices and real-time applications are made possible by essential features like massive machine-type communications (mMTC) and ultra-low latency. The advent of 6G in the 2030s heralds revolutionary improvements such as intelligent surfaces, AI-driven network automation, and terahertz transmission frequencies. Thanks to this development, previously unimaginable speeds and bandwidth will be available, allowing for a proliferation of networked devices with latency reduced to microseconds. While resolving issues with present networks, these advancements will provide state-of-the-art solutions for smart cities and digital twins and enhance existing networks' capacities.

The advancement of Industry 4.0 has spurred the integration of Internet of Things (IoT) technologies into predictive maintenance systems, particularly in industrial machinery management. Traditional maintenance models—reactive and time-based—have proven insufficient in addressing operational uncertainties and unexpected equipment failures. This study aims to explore how IoT applications in predictive maintenance can enhance the operational reliability of industrial machines. Utilizing a qualitative literature review method, the research synthesizes findings from 10 scholarly articles published between 2023 and 2025, focusing on various IoT applications such as digital twins, intelligent networks, and energy-optimized communication protocols. The data collection involved systematic searches through major academic databases using targeted keywords, and data analysis was conducted using thematic analysis to extract key themes such as architecture, machine learning integration, and infrastructure readiness. The findings reveal that IoT significantly contributes to predictive maintenance through real-time data collection, anomaly detection using AI models, and automated decision-making processes. The use of digital twins, fog computing, and sensor-integrated systems has demonstrated measurable improvements in equipment uptime, fault detection accuracy, and cost efficiency. The integration of IoT with Enterprise Asset Management (EAM) platforms has further enabled organizations to transform their maintenance strategies into data-driven, proactive systems. In conclusion, the study confirms that IoT is not merely a supporting technology but a foundational enabler of operational resilience in modern industries. This research provides a framework for sustainable implementation and highlights critical success factors such as sensor quality, model precision, and infrastructure scalability.

The metaverse, powered by the convergence of augmented and virtual reality (AR/VR), artificial intelligence (AI), blockchain, digital twins, and next-generation networks (5G/6G), represents the next evolutionary phase of the internet (Web 4.0). The chapter conducts a comparative analysis of global and Turkish brand strategies in the metaverse, discusses the changes it brings to business processes, value-chain analysis, and organizational models, and identifies AI and explores the metaverse newly emerging professions at their point of intersection. This paper is mainly based on a qualitative content analysis of academic literature, industry reports and corporate case studies reveals a significant gap between comprehensive global implementations and market-oriented Turkish initiatives. The suggested AI & Metaverse Integration Model (five dimensions: Technology Layer, Integration, Value-Chain, Performance, Regulatory Factors) offers a strategic framework for the sustainable adoption. Policy recommendations for Turkey are provided to close the global-local divide.

The level of education, training of researchers and technologists and international scientific, technological and technological development allows the world community to gradually move to the formation and management of the industry 5.0 through the cognitive technological mind with the help of ensembles of intelligent agents and digital twins and automated systems with artificial intelligence. The cognitive technological mind on the speech mission of a person forms a design implementation for ensembles of intellectual agents. The ensembles of intelligent agents for the project implementation of a human task activate the work of digital twins with artificial intelligence, corresponding to the industry, for the production implementation of a human task. Cognitive technological intelligence, intelligent agent ensembles, and digital doubles make decisions based on representative data. Their representativeness is reflected by the similarity of the data in terms of the qualitative properties and characteristics of a certain production. Through cognitive technological mind with the help of ensembles of intellectual agents it is also possible to manage financial, ecological and other activities of enterprises of industry 5.0. Cognitive technological mind, ensembles of intellectual agents and digital doubles are a very effective tool of automation of management in all spheres of life of society and the state. The international scientific engineering community can begin the formation and technical implementation of industry control automation systems 5.0 based on cognitive virtual mind with artificial intelligence, additive technologies and 5G network. Sensitive safe robots with cognitive artificial mind will perform high-tech professional work in various fields of industry 5.0. A person will teach robots with a cognitive mind to increase professionalism by recursive self-improvement to technological singularity. Artificial intelligence with technological singularity will be controlled by the results of self-improvement in simulation mode in virtual space. He can become a good assistant to humanity in the safe development of living spaces.

In this tutorial paper, we look into the evolution and prospect of network architecture and propose a novel conceptual architecture for the 6th generation (6G) networks. The proposed architecture has two key elements, i.e., holistic network virtualization and pervasive artificial intelligence (AI). The holistic network virtualization consists of network slicing and digital twin, from the aspects of service provision and service demand, respectively, to incorporate service-centric and user-centric networking. The pervasive network intelligence integrates AI into future networks from the perspectives of networking for AI and AI for networking, respectively. Building on holistic network virtualization and pervasive network intelligence, the proposed architecture can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI, to maximize the flexibility, scalability, adaptivity, and intelligence for 6G networks. We also identify challenges and open issues related to the proposed architecture. By providing our vision, we aim to inspire further discussions and developments on the potential architecture of 6G.

The increasing complexity and capacity demands of modern optical communication networks require advanced tools for predictive maintenance and fault prevention. This study presents a systematic methodology for generating a comprehensive network failure database using Digital Twins (DTs) based on the open-source optical network simulation framework GNPy (Gaussian Noise model in Python). GNPy enables the generation of synthetic datasets to support the development of Machine Learning (ML) models for proactive fault detection and network performance optimization. By modeling a wide range of failure scenarios such as amplifier degradation, span loss variation, and component misconfigurations, GNPy enables detailed analysis of their impact on critical transmission parameters including Generalized Signal-to-Noise Ratio (GSNR), Optical Signal-to-Noise Ratio (OSNR), and channel power. The proposed methodology allows the generation of a diverse and scalable database that reflects both normal and degraded network operating conditions. This synthetic dataset provides valuable input for training ML algorithms to detect subtle performance degradations and predict potential failures before they impact running services. By leveraging this simulation-based data generation approach, network operators can significantly enhance the reliability and resilience of their transport networks. Furthermore, the integration of GNPy with data-driven ML models lays the foundation for intelligent network management systems capable of automated fault prediction and proactive maintenance strategies in future high-capacity optical networks.

As a pivotal virtualization technology, the network digital twin (DT) is expected to accurately reflect real-time status and abstract features in the ongoing sixth generation (6G) networks. In this article, we propose an artificial intelligence (AI)-native network DT framework for 6G networks to enable the synergy of AI and network DT, thereby facilitating intelligent network management. In the proposed framework, AI models are utilized to establish network DT models to support network status prediction, network pattern abstraction, and network management decision-making. Furthermore, potential solutions are proposed to enhance the performance of network DT. Finally, a case study is presented, followed by a discussion of open research issues that are essential for the AI-native network DT in 6G networks.

The high-paced development of wireless communication technologies brought about the growing need of smart, autonomous, and ultra-high-performance network structures, and the combination of Artificial Intelligence and Machine Learning in the 6G wireless communication networks is a major research issue. The conventional network management techniques cannot support the new demands that include ultra-low latency communications, intelligent spectrum management, mass connectivity, and real-time dynamic resource provision. This paper is a systematically-conducted literature review on the recent research on AI-driven networks, edge AI, federated learning, intelligent radio access network design, and AI-native architecture in next-generation networks based on PRISMA. The review focuses on the possibilities of self-organizing networks, digital twin networks, and smart connectivity that machine learning, deep learning, and autonomous wireless systems provide to the next generation of wireless networks working in terahertz communication ranges and integrated sensing and communication landscape. The findings indicate that AI based resource allocation, intelligent surfaces of reconfigurability, massive mimo optimization and network automation are all effective towards improving spectral efficiency, reliability and energy efficiency of 6G wireless communication. Moreover, the paper has also noted the increased importance of smart security mechanisms, distributed learning, and edge computing in enabling scalable and secure AI-native architectures. The results also indicate that the next generation wireless networks will be based upon intelligent spectrum management, autonomous control, and real-time data analytics to accommodate the new applications in holographic communication, smart cities, extended reality, and connected autonomous systems.

Bridging the gap: A comprehensive survey on AI-driven digital twin networks for future wireless systems