Urban traffic congestion remains a critical challenge to mobility efficiency and environmental sustainability. This paper presents a Digital Twin framework for real-time urban traffic management in Issy-les-Moulineaux, France. The framework integrates heterogeneous traffic data sources, including historical, real-time, and predictive data, into a unified architecture for scenario-based analytics and decision support. For traffic forecasting, deep learning models, including Long Short-Term Memory (LSTM) and Transformer-based approaches, are evaluated alongside baseline models such as SARIMA and Neural Prophet. The LSTM model is selected based on its stable and consistent performance across heterogeneous traffic conditions, achieving mean absolute error (MAE) values ranging from approximately 2 to 33 vehicles/hour across different road segments. The system also supports dynamic event handling, including full and time-based road closures, with capacity-constrained and equal-allocation diversion strategies for first-order impact estimation. Quantitative evaluations demonstrate that the framework enables proactive congestion mitigation, comparative emission impact assessment, and improved interoperability with city platforms through NGSI-LD standardization. By combining predictive modeling, real-time monitoring, and scenario-driven analytics, the proposed Digital Twin delivers actionable insights for urban planners, reducing short-term disruptions and supporting long-term sustainable mobility management.

International audience

This paper presents a deep learning framework for energy-and bandwidth-aware time-series regression for IoT and wireless sensor networks. Leveraging cross-modality structural data dependencies, the approach uses a multivariate regression approach for predicting many different sensor modality time-series from a fewer number of sensor modality data. This reduces the communication bandwidth usage and energy consumption for resource-constrained sensor nodes. In addition, the approach can be leveraged for reducing number of sensors in a system, thus reducing the hardware and associated costs in IoT-based systems. This is done while ensuring successful reconstructions of all the original time-series for the necessary sensing modalities. One key attribute of the proposed framework is that the processing load is placed entirely at the receiver side, thus making it suitable for resource-constrained sensors and IoT based systems. The developed methodology is validated using data collected by a greenhouse sensor IoT system deployed over a period of three years. The results demonstrate the ability of the proposed approach for successful prediction of many sensor modality times series from only one time-series, representing the energy harvesting super-capacitor voltage of the sensor IoT system. The trade-offs between performance, bandwidth usage, number of sensing modalities, scalability, and computation cost are analyzed for providing design and implementation guidelines.

This paper introduces an Asymmetric Autoencoder (AAE)-driven data compression framework for efficient management of energy, bandwidth, and transmitter complexity in a Wireless Sensor Network (WSN). WSNs are often limited by their ability to process and transmit high-dimensional data due to various constraints, including available energy, processing cycles, and transmission capacity. Achieving an application-specific downstream task executed in a remote receiver under the influence of such sensor node constraints is the focus of the proposed methodology. It places a data compression encoder and decoder at the transmitter and the receiver, respectively. The architecture of the AAE's encoder and decoder can be asymmetric, and the degree of asymmetry can be adjusted based on the computation and processing abilities of the transmitting node, the available bandwidth, and the performance requirements of a specific downstream task. In the proposed framework, the encoder and decoder are jointly trained, enabling the system to extract downstream task-related information from one or more time series inputs. Verified for Human Activity Recognition (HAR), the framework demonstrates effective feature compression while maintaining efficient task performance.

The increasing demand for smart cities calls for advanced solutions to enhance urban sustainability. Digital twin technology offers transformative potential by synchronizing virtual and physical environments in real time. However, existing approaches struggle with scalability due to the reliance on numerous specialized prediction models for individual urban components, the lack of a unified framework for different use cases limits generalization, and high latencies in real-time synchronization. To address these, this paper presents a comprehensive software architecture for smart city DT and integrates correlation-aware model reduction and dynamic adaptive forecasting to support diverse urban applications to improve generalizability and scalability. This is done while adapting a smart distribution of DT software components between edge and core servers to ensure a low-latency performance. Validated using real-world traffic and air quality data, the system demonstrates significant improvements in traffic flow, emissions reduction, and public transportation efficiency, and enhances air quality monitoring, forecasting, and pollutant management. Key contributions include a scalable and generalizable DT architecture, AI-driven adaptability, edge-core deployment, and extensive validation through predictive analytics. This work establishes a replicable blueprint for metropolitan-scale DTs, balancing computational efficiency with responsive urban analytics.

The growing need for intelligent tools to support urban planning and resource management has positioned Digital Twin (DT) technology as a cornerstone of smart city development. DTs, as dynamic virtual replicas of physical systems, offer capabilities that extend beyond mere representation, enabling monitoring, diagnostics, forecasting, and optimization. In the context of urban traffic management, DTs provide a robust solution for real-time traffic monitoring and predictive analytics. However, existing approaches often lack a systematic design methodology, leading to challenges in scalability and adaptability, particularly in heterogeneous environments. This paper presents a novel methodology for developing scalable and adaptive smart city DT architectures, with a focus on real-time traffic management. A modular and unified software framework is proposed, leveraging AI-driven approaches to address the complexity of managing diverse traffic data sources. A sequential learning model is integrated into the architecture to enhance the DT's adaptability to evolving traffic conditions and congestion patterns. The proposed framework is validated using real-world traffic data from an IoT network deployed in Madrid, demonstrating its scalability and low-latency performance. Experimental results highlight the effectiveness of the framework in handling heterogeneous traffic scenarios and its ability to deliver accurate predictions while minimizing resource overhead.

Network Digital Twin (NDT) collects data from physical, virtual, and software components and supports real-time network performance analysis, emulation, and intelligent physical network control. This paper surveys the current state of NDT specifications and explores NDT benefits for Network Operators (NOs) and its possible roles in future network management. It discusses the NDT key components, architecture, and integration of Machine Learning and Artificial Intelligence models in the NDT. Further, it covers virtualization technology management, suitability of Software-Defined Networking capabilities, and simulation tools to empower NDT. Two perspectives make the position of this survey different from existing studies; first, it highlights NDT limitations regarding Edge–Cloud Continuum (ECC) contextualization. ECC is a purposeful trending integration of Edge and Cloud Computing , involving multiple stakeholders like Service Providers, Customers, and Platform or Infrastructure Providers. However, current NDT specifications have not mentioned the ways to benefit stakeholders other than NOs. We also discuss notable computing and communication technologies transformations necessary to consider during NDT modeling, the existing data models, and reusable vocabularies that can be extended to achieve a detailed ECC representation for all stakeholders, essentially for Service Providers and Customers. Secondly, a data model is proposed that covers descriptive and prescriptive features and aims to provide a granular representation of ECC components to meet stakeholders’ requirements and render particular user information views. Different explored NDT perspectives, and proposed data model reduces the impact of existing NDT limitations in ECC representation.

This article introduces an Unmanned Aerial Vehicle - enabled content management architecture that is suitable for critical content access in communities of users that are communication-isolated during diverse types of disaster scenarios. The proposed architecture leverages a hybrid network of stationary anchor UAVs and mobile Micro-UAVs for ubiquitous content dissemination. The anchor UAVs are equipped with both vertical and lateral communication links, and they serve local users, while the mobile micro-ferrying UAVs extend coverage across communities with increased mobility. The focus is on developing a content dissemination system that dynamically learns optimal caching policies to maximize content availability. The core innovation is an adaptive content dissemination framework based on distributed Federated Multi-Armed Bandit learning. The goal is to optimize UAV content caching decisions based on geo-temporal content popularity and user demand variations. A Selective Caching Algorithm is also introduced to reduce redundant content replication by incorporating inter-UAV information sharing. This method strategically preserves the uniqueness in user preferences while amalgamating the intelligence across a distributed learning system. This approach improves the learning algorithm's ability to adapt to diverse user preferences. Functional verification and performance evaluation confirm the proposed architecture's utility across different network sizes, UAV swarms, and content popularity patterns.

This paper presents a Micro-Unmanned Aerial Vehicle (UAV)-enhanced content management system for disaster scenarios where communication infrastructure is generally compromised. Utilizing a hybrid network of stationary and mobile Micro-UAVs, this system aims to provide crucial content access to isolated communities. In the developed architecture, stationary anchor UAVs, equipped with vertical and lateral links, serve users in individual disaster-affected communities. and mobile microferrying UAVs, with enhanced mobility, extend coverage across multiple such communities. The primary goal is to devise a content dissemination system that dynamically learns caching policies to maximize content accessibility to users left without communication infrastructure. The core contribution is an adaptive content dissemination framework that employs a decentralized Top-k Multi-Armed Bandit learning approach for efficient UAV caching decisions. This approach accounts for geo-temporal variations in content popularity and diverse user demands. Additionally, a Selective Caching Algorithm is proposed to minimize redundant content copies by leveraging inter-UAV information sharing. Through functional verification and performance evaluation, the proposed framework demonstrates improved system performance and adaptability across varying network sizes, micro-UAV swarms, and content popularity distributions.

This paper proposes a learning-driven approach for medium access slot allocation in the presence of malicious nodes. Learning policies are developed with the goal of defending against several forms of quasi-random slot-scheduling attack models used by the malicious nodes. The primary learning objective for the non-malicious nodes is to minimize the degradation in network performance caused by the malicious nodes. This is accomplished while minimizing the bandwidth share of the malicious nodes. These objectives are achieved using a Multi-Armed Bandit (MAB) learning architecture that allows the nodes to learn transmission schedule on-the-fly, and without the need for any central arbitrator. Two different scheduling policies are introduced: robust and reactive policies. Following the design, a detailed characterization of these policies and their use in different application-specific scenarios are presented. An analytical model of the system is developed to find the benchmark throughput for different malicious attack models. It is demonstrated that the proposed framework allows network nodes to learn close-to -benchmark slot scheduling, while thwarting attacks from the malicious nodes. The proposed architecture is validated for various mesh networks and traffic conditions in the presence of different attack models enacted by the malicious nodes.

This paper presents a modular Digital Twin software architecture designed for smart cities, leveraging Edge-Cloud Continuum to enable the development of flexible and scalable DT-based solutions. Digital Twin technology provides a powerful framework for simulating, analyzing, and optimizing urban environments by integrating real-time and historical data from various city sensors through IoT, AI, and cloud computing. The proposed architecture addresses the limitations of existing DT frameworks by focusing on smart city-specific requirements such as dynamic resource management, real-time data processing, and autonomous decision-making. The viability of the proposed framework is demonstrated through a case study on autonomous traffic management in the city of Issy-les-Moulineaux. It shows how the proposed framework predicts traffic patterns and manages network resource allocation by adjusting the data sampling frequency to balance prediction accuracy and communication costs. The architecture’s modular design supports seamless integration and adaptability, making it suitable for various smart city applications, thereby advancing the development of more efficient, sustainable, and resilient urban environments.

Specifications for Network Digital Twin (NDT) from Standardization Development Organizations (SDOs), such as the Internet Engineering Task Force (IETF), and academic contributions focus primarily on benefiting network operators. However, they often overlook the needs of stakeholders in the Edge-Cloud Continuum (ECC), such as Service Providers, customers, and Platform or Infrastructure Providers. In ECC, resource heterogeneity, agile software component integration, and quality of service requirements are challenges. To address these challenges, continuous and granular monitoring of software and physical resources is required. In this paper, we present the design and ongoing implementation of a data model. It captures and characterizes the physical and software properties, i.e., Key Performance Indicators (KPIs), of Kubernetes-managed components in the ECC. Collected data is structured in NGSI-LD-compliant format and managed through interoperable context brokers for authenticating the requests of various stakeholder applications. We also demonstrate sample data curation from a lab-configured platform, its integration into the context broker, and how it responds to the queries concerning a particular component information, thereby representing a partial implementation of proposed data model to render the views for particular stakeholders.

This paper proposes an unmanned aerial vehicle (UAV) aided content management system in communication-challenged disaster scenarios. Without cellular infrastructure in such scenarios, community of stranded users can be provided access to situation-critical contents using a hybrid network of static and traveling UAVs. A set of relatively static anchor UAVs can download content from central servers and provide content access to its local users. A set of ferrying UAVs with wider mobility can provision content to users by shuffling them across different anchor UAVs while visiting different communities of users. The objective is to design a content dissemination system that on-the-fly learns content caching policies for maximizing content availability to the stranded users. This paper proposes a decentralized Top-k Multi-Armed Bandit Learning model for UAV-caching decision-making that takes geo-temporal differences in content popularity and heterogeneity in content demands into consideration. The proposed paradigm is able to combine the expected reward maximization attribute and a proposed multidimensional reward structure of Top-k Multi-Armed Bandit, for caching decision at the UAVs. This study is done for different user-specified tolerable access delay, heterogeneous popularity distributions, and inter-community geographical characteristics. Functional verification and performance evaluation of the proposed caching framework is done for a wide range of network size, UAV distribution, and content popularity.

This paper presents a lightweight on-device liquid consumption tracking system based on a semi-supervised learning paradigm. The online learning framework caters to scenarios where a hydration tracking bottle/device has no prior knowledge of a user's consumption gesture patterns. The proposed iterative semi-supervised learning (ISSL) framework uses sparsely labelled user gesture events acquired from the IMU sensors installed on a bottle, such that it can learn to differentiate between sip and non-sip gestures by specific individuals. Two different strategies, namely, population-based, and distance-based, are employed to achieve the desired clustering performance. A comparative study between these strategies has been presented in terms of clustering accuracies for classifying sip and non-sip gestures. The proposed architecture is shown to be lightweight in terms of computation complexity and memory usage of the bottle-embedded hardware. The trade-off between classification accuracy and computation complexity is analyzed for different algorithmic hyper-parameters and it is shown how to manage this trade-off. Extensive experimentation and simulation study has been conducted for multiple users' drinking patterns to validate the proposed learning paradigm.

This article proposes an unmanned aerial vehicle (UAV) aided content provisioning system in communication-challenged disaster scenarios. In such scenarios, without the availability of static base stations and their wireline backhauls, community of stranded users can access contents from a network of static and traveling UAVs. A set of relatively static anchor UAVs with vertical as well as lateral links can provide content access to its local users. A set of ferrying UAVs with only lateral links, but with wider mobility, can provision content to users while visiting different communities of users. The objective is to design a content dissemination system that handles user demand heterogeneity while maximizing content availability to the requesting users. This work proposes a popularity-based caching policy which tackles heterogeneity in content popularity across a disaster region. A novel value-based caching policy is developed which considers the popularity and the tolerable access delay of the content requests from the users to make caching decisions. The paper develops a novel approach called Joint Deployment of Ferrying UAVs (JDFU) Algorithm to exploit the collective storage of ferrying UAVs which boosts content distribution for users. Through analytical modeling and simulation experiments it is demonstrated that content availability can be maximized by choosing an optimal cache storage segmentation factor, JDFU configuration and hover time of ferrying UAVs. This analysis is done for different user-specified tolerable access delay, heterogeneous popularity distributions and intercommunity geographical characteristics. The paper does functional verification and performance evaluation of the proposed caching framework under a wide range of network size, UAV distribution, content popularity, and ferrying UAV trajectories.

This article presents an unmanned aerial vehicle (UAV) based caching framework for content provisioning in disaster scenarios. In a disaster scenario without the availability of static base stations and their wireline backhauls, community of stranded users can access contents from a network of static and traveling UAVs. A set of relatively static anchor UAVs with vertical as well as lateral links provide content access to its local users. A set of ferrying UAVs with only lateral links, but with wider mobility, can also provision content to users while visiting different communities of users. The algorithmic objective is to intelligently cache contents in the storage-constrained UAVs in order to maximize content availability for the users affected by such disasters. The paper develops a novel approach of content duplication within the anchor UAVs along with a mechanism to distribute non-duplicated contents across the ferrying UAVs. Through analytical modeling and simulation experiments it is demonstrated that content availability in such an arrangement can be maximized by choosing an optimal level of duplication for content with specific popularity distributions. The paper does functional verification and performance evaluation of the proposed caching framework under a wide range of network size, UAV distribution, content popularity, and ferrying UAV trajectories.

This paper presents a distributed framework for Medium Access Control (MAC) slot allocation in time-asynchronous wireless networks using Multi-Armed Bandits (MAB) based learning. MAC slot allocation is formulated as an MAB problem where the nodes act as independent learning agents and learn transmission policies that ensure collision free transmissions. A novel concept of Hysteretic MAB has been introduced to speed up learning convergence. In order to reduce the bandwidth overhead while maintaining a desired MAB learning speed, a novel slot defragmentation mechanism is introduced. Not relying on network time synchronization makes the proposed mechanism feasible for low-complexity and low-cost transceivers for wireless sensor and loT networks. The proposed mechanism is tested and evaluated on both fully connected and arbitrary mesh network topologies and is shown to be scalable with network size and topological degree. It is also shown that in partially connected topologies, the mechanism learns spatial channel reuse, thus leading to better spectral usage efficiency.