The increasing demand for privacy-preserving machine learning has spurred interest in federated unlearning, which enables the selective removal of data from models trained in federated systems. However, developing federated unlearning methods presents challenges, particularly in balancing three often conflicting objectives: privacy, accuracy, and efficiency. This paper provides a comprehensive analysis of existing federated unlearning approaches, examining their algorithmic efficiency, impact on model accuracy, and effectiveness in preserving privacy. We discuss key trade-offs among these dimensions and highlight their implications for practical applications across various domains. Additionally, we propose the OPENFEDERATE-DUNLEARNING framework, a unified benchmark for evaluating federated unlearning methods, incorporating classic baselines and diverse performance metrics. Our findings aim to guide practitioners in navigating the complex interplay of these objectives, offering insights to achieve effective and efficient federated unlearning. Finally, we outline directions for future research to further advance the state of federated unlearning techniques.

Generative AI (GenAI), exemplified by Large Language Models (LLMs), such as OpenAI’s ChatGPT, is revolutionizing various fields. Central to this transformation is Data Center Networking (DCN), which not only provides the infrastructure support for GenAI operation, but also provisions GenAI services to users. Hence, this article explores the interplay between GenAI and DCNs, analyzing their symbiotic relationship and mutual advances. We begin by reviewing the current challenges of DCNs and GenAI-based solutions, such as data augmentation, process automation, and domain transfer. We then discuss the distinctive characteristics of GenAI workloads on DCNs, gaining insights that catalyze the evolution of DCNs to more effectively support GenAI. Moreover, to illustrate the seamless integration of GenAI with DCNs, we present a case study on GenAI-empowered DCN digital twins. Specifically, we employ an LLM equipped with retrieval augmented generation to formulate optimization problems for DCNs (e.g., resource allocation and routing) and adopt diffusion-deep reinforcement learning to solve optimization. The experimental results on a representative DCN optimization problem, i.e., knowledge placement, demonstrate the validity and efficiency of our proposals. We anticipate that this article can promote further research to enhance the virtuous interaction between GenAI and DCNs.

The fog radio access network (F-RAN) is regarded as a promising architecture allowing distributed signal processing and edge intelligent, offering a synergistic paradigm of communication and computing. However, emerging services transcend this framework, necessitating additional support for advanced generalized computing and environmental sensing. In response, this paper presents an upgraded F-RAN enabled by integrated sensing, communication and computing (ISCC). Specifically, integrated sensing and communication is introduced for extended radio capabilities, with computing-first design concurrently employed as an advanced computational solution. The updated F-RAN architecture harmonizes these two emerging technical trends, underscoring their synergistic benefits. Then, key challenges in realizing this vision are identified, with corresponding solutions discussed as key technologies. Some simulation results are provided to demonstrate that incorporating ISCC design into F-RANs enhances the comprehensive performance encompassing communication, sensing, and computing. Finally, open issues are outlined to stimulate innovation in related fields.

The Scanning the Literature column provides concise summaries of selected papers that are recently published in the field of networking. Each summary describes the paper’s main idea, methodology and technical contributions. The purpose of the column is to bring the state-of-the-art of networking research to readers of IEEE Network magazine. Authors are also welcome to recommend their recently published work to the column, and papers with novel ideas, solid work, and significant contributions to the field are especially appreciated. Authors wishing to have their papers presented in the column should contact Xiaohua Tian at the email address below.

We are crossing in the big countries 51% IPv6 penetration in the big enterprise and some government network s. T herefore, it is the right time for the IPv6 Forum to call for a worldwide full transition to IPv6-Only for any enterprise and gover nment net work s for a number of reasons especially that the dual stack deployment is just a temporary solution wit h a lot of expenses, cost and massive time spent maintaining IPv4/ NAT while v6 Only is the vision for the new and real production Internet to cater for new technologies such as AI,6G, Blockchain, P2P IoT and all enterprise verticals (Supply chains, Industrial Internet) to name a few.

In this article, we propose an Intelligent-controlled Zero-Redundancy heterOgeneous Network Function (IzeRO-NF) framework, for achieving efficient security-endogenous 6G core networks. To ensure interoperability and standardization, the framework adheres to the 3GPP enhanced Service-Based Architecture (eSBA). Inspired by the hierarchical structure of the human central nervous system—comprising the effectors, the spinal cord and the brain—we design a three-tier intelligent perception-decision-action cycles for the framework. Particularly, the effector tier comprises resource-adaptive heterogeneous execution entities of NFs. The spinal-cord-like tier proactively schedules signaling flows to heterogeneous execution entities to disrupt the attacker’s ability to establish a stable, repeatable attack chain. The brain-like tier intelligently learns the optimal joint policies for heterogeneous execution entity scheduling and resource scaling. After highlighting key design aspects of the IZeRO-NF framework, we present simulation results from a case study that demonstrate its security and efficiency. Finally, we discuss open issues that warrant further exploration to advance and refine this novel framework.

As mobile networks evolve, we are witnessing a significant shift from traditional communication services to advanced network applications. This transformation calls for efficient and reliable Radio Access Network (RAN) operations. RAN Digital Twin (DT) is such an enabling technology. This paper delves into the AI-empowered RAN DT technology, analyzing the services that RAN DTs can provide to enhance the performance and operational efficiency of both current 5G networks and upcoming 6G networks. A comprehensive framework is proposed, which includes four subsystems: feature application, data repository, model repository, and RAN DT management. By integrating several key enabling technologies such as data management, AI-empowered RAN modeling techniques, multi-objective RAN performance optimization methods and RAN DT performance management which refers to the optimization of the RAN DT’s own model performance, the proposed RAN Digital Twin system can predict network conditions and fine-tune network configuration in a way that enhances network reliability and user satisfaction. To validate these improvements, practical tests are carried out within real mobile networks, focusing on the joint optimization of network energy efficiency and user data rates. The results demonstrate significant improvements in both network energy consumption and user data rates through RAN DT optimization. These findings underscore the potential of RAN Digital Twins in revolutionizing network operations and achieving high-level network automation.

Quantum Communications promise advances in cryptography, quantum computing and clock synchronisation, among other emerging applications. However, communication based on quantum phenomena requires an extreme level of isolation from external disturbances, complicating the co-propagation of quantum and classical signals. The challenge is greater when deploying networks that are both heterogeneous (e.g., multiple vendors) and installed in production facilities, given that this type of infrastructure already supports networks loaded with their own requirements. Moreover, to achieve a broad acceptance among network operators, the joint management and operation of quantum and classical resources, compliance with standards, and legal and quality assurance need to be addressed. This article presents solutions to the aforementioned challenges validated in the Madrid quantum network during the implementation of the projects CiViC and OpenQKD. This network was designed to integrate quantum communications in the telecommunications ecosystem by installing quantum-key-distribution modules from multiple providers in production nodes of two different operators. The modules were connected through an optically-switched network with more than 130 km of deployed optical fibre. The tests were done in compliance with strict service level agreements that protected the legacy traffic of the pre-existing classical network. The goal was to ensure full quantum-classical interoperability at all levels, while limiting the modifications to optical transport and encryption and complying with relevant standards. This effort is intended to lay the foundation for large-scale quantum network deployments.