Conference Program

Session chair:

Pr. Nédra MELLOULI
Ecole Supérieure d'Ingénieurs Léonard de Vinci, Paris, France.

13:30:00	Performance of Smart Contract-based Digital Twins for the Internet of Things
	Chalima Dimitra Nassar Kyriakidou, Athens University of Economics and Business, Greece Iakovos Pittaras, Athens University of Economics and Business, Greece Athanasia Maria Papathanasiou, Athens University of Economics and Business, Greece George Xylomenos, Athens University of Economics and Business, Greece George C. Polyzos, The Chinese University of Hong Kong, Shenzhen
	Despite its rapid growth, the Internet of Things (IoT) still faces significant challenges related to interoperability, transparency and security. To address these issues, we propose the utilization of smart contract-based Digital Twins (DTs) “hosted”intheHyperledgerFabricblockchainnetwork,while leveraging the Web of Things paradigm for interoperability. Thus, our solution includes several notable features, such as decentralization, auditability and security. However, implementing DTs using Distributed Ledger Technologies (DLTs) introduces certain overheads. In this paper, we assess the feasibility and evaluate the performance of smart contractbased DTs using a set of Key Performance Indicators (KPIs). Our results demonstrate that, although DLT-induced overheads, such as latency, are present, they remain manageable for IoT use cases.

14:00	Urban Digital-Twin Planning for Sustainable Smart Cities: System Architecture, Preliminary Experiments, and Open Challenges
	"Cheng-Chia Lai (National Tsing Hua University), Agnibha Sarkar (Vishwakarma Institute of Technology), Phuong Anh Dinh (SP Jain School of Global Management), Suyash Gaikwad (Vishwakarma Institute of Technology), Cheng-Hsin Hsu (National Tsing Hua University)" Cheng-Chia Lai, National Tsing Hua University, Taïwan Agnibha Sarkar, Vishwakarma Institute of Technology, India Phuong Anh Dinh, SP Jain School of Global Management, Sydney, New South Wales, Australia Suyash Gaikwad, Vishwakarma Institute of Technology, India Cheng-Hsin Hsu, National Tsing Hua University, Taïwan
	A Digital Twin (DT) is a digital representation of a physical object, offering unique features such as object mirroring, object relation, data availability, and user interaction. In this paper, we discuss the challenges of deploying urban infrastructure for DT-enabled smart city applications, such as air-quality-aware navigation and traffic management, which aim to improve citizens’ quality of life and assist policymakers' decision-making. We refer to this research problem as urban DT planning, with the core objective of enhancing the interoperability and scalability of geolocation- and capability-diverse hardware and software by leveraging modern middleware approaches. Our explorations consist of the following three steps. First, we present our perspective on urban DT planning and propose a general, layered DT architecture. Second, we share our preliminary experiments involving a micro wind turbine using commercial (Microsoft Azure) and open-source (Eclipse) DT platforms. Finally, we conclude the paper with open challenges that need to be studied to achieve the ultimate goal of sustainable smart cities. These challenges are intended to inspire future research on sustainable urban DT planning and encourage the broader adoption of DT-enabled smart city applications.

14:30	Smart Agriculture Framework with Digital Twin: A monitoring Model Based on Clustering and prediction of Multivariate Time Series
	Mellouli Nedra, University Paris 8, France Yahjeb Bouha Khatraty, University Paris 8, France Mamadou Tourad Diallo, University of Nouakchott Al Aasriya, Mauritania Mohamedade Farouk Nanne, University of Nouakchott Al Aasriya, Mauritania
	The current trend in agricultural field management research emphasizes the use of the digital twin due to its importance in digital resource management. Our paper proposes a digital twin architecture for intelligent rice field control by combining IoT sensors, satellite data, and deep learning models to predict yield, weather, and soil conditions to achieve a predefined yield. This approach enables a more comprehensive management of agricultural resources, helping farmers make informed decisions to improve yields while reducing costs and environmental impact.