Testing AI
in Smart Cities and

Local Digital Twins & Electromobility: Towards informed decision making

LDT electromobility in city small

Author: German Castignani 

The deployment of electromobility in urban areas is crucial for sustainable development. Local Digital Twins (LDTs) are emerging as the most suitable tools to facilitate informed decision-making for city planners. This article explores the transformative impact of LDTs on electromobility, in a concrete pilot experimentation in the City of Differdange in south Luxembourg, highlighting CitCom.ai's pioneering contributions to testing and experimenting AI and Digital Twins for urban sustainability and technological advancement.

LDTs create dynamic, real-time virtual replicas of cities, enabling precise planning and management of electric vehicle (EV) infrastructure, renewable power generation, and other relevant entities the cities manage. By integrating diverse data sources, including built-up environments and real-time telemetries, incorporating relevant demand and supply models for electromobility and smart visualization components we support cities in monitoring, predicting, and simulating potential electromobility and renewable energy deployment scenarios, fostering greener, even net-zero, smarter cities.

LDT illustration1

Understanding Local Digital Twins

LDTs are virtual representations of specific urban areas, reflecting real-time data to simulate and manage city infrastructure and operations. Utilizing sensors, IoT devices, and AI, LDTs capture data on various city aspects, such as traffic, energy usage, and environmental conditions. This dynamic model enables city planners to analyze, predict, and optimize urban systems efficiently. In smart cities, LDTs support decision-making for infrastructure development, resource allocation, and emergency responses, enhancing urban resilience and sustainability. 

By providing a comprehensive and interactive view of city operations, LDTs drive smarter, data-driven urban management and planning. Several initiatives are being conducted with the support of the EU Commission, including the role of CitCom.ai as a Testing and Experimentation Facility (TEF) for AI-powered LDTs, the procurement of an LDT toolbox, and the creation of a new European Digital Infrastructure Consortium (EDIC) for networked LDTs towards the itiverse.

Electromobility for urban sustainability

Cities and communities face significant challenges in deploying electromobility, particularly in the strategic placement of charging stations and ensuring adequate energy capacity. Locating chargers requires careful consideration of accessibility, demand patterns, and grid infrastructure, balancing convenience for users with minimal urban disruption. Inadequate or poorly positioned chargers can lead to range anxiety and underutilization. 

Additionally, providing sufficient renewable energy capacity involves direct or indirect investment into renewable infrastructure, including photovoltaic generation and energy storage, or liaising with the energy operator to upgrade the electrical grid to handle increased loads, managing peak demand, and integrating renewable energy sources. These challenges necessitate comprehensive planning and collaboration among city planners, energy providers, and stakeholders to create an efficient and resilient electromobility network.

LDT illustration2

Case study: Implementing a Local Digital Twin for Electromobility in Differdange

The city of Differdange, in south Luxembourg, is a vibrant city known for its industrial heritage and green spaces. Committed to sustainability, Differdange actively pursues net-zero carbon emissions through innovative urban planning, renewable energy initiatives, and promoting eco-friendly transportation solutions.

Working in collaboration with the city experts in energy and mobility, we have created a first LDT architecture including the relevant entities modeling the electromobility challenges, including charging points, buildings and solar patches, among others. In this architecture, different components, including data collection and telemetry emulators, spatio-temporal and graph databases, DT cloud solutions, and smart maps and dashboard visualization are put together to create a lean toolbox to model different city problems.

We have considered relevant data from the city, including current charging positions and metadata, load curves, energy consumption, and generation telemetries from different city infrastructures. Several models have been inferred from this data and connected to the LDT as telemetry emulators.

Results and success

Through this first experimentation, we have been able to advance in multiple senses: (i) testing and experimenting with state-of-the-art technologies to build a lean and modular LDT architecture to solve city problems in a relatively short time, (ii) inferring models from real data to emulate telemetries in the Digital Twin and enable simulation capacities, (iii) working in collaboration with cities, understanding their problems and needs and leveraging their data to solve them.

This pilot case stands as a first milestone to prove that fast experimentation in city-wide LDTs is possible. Our goal is to continue exploring new technologies in an incremental way, covering more topics beyond electromobility and iteratively build a multi-purpose tools for cities to connect data, models and services, following from close the technological advances on LDTs, AI and data analytics technologies.