SMARTGREENS 2025 Abstracts

Area 1 - Energy Engineering

Short Papers

Paper Nr:	15
Title:	Belgian Energy Communities: Key Challenges and Opportunities
Authors:	Chadi Mahfoud, Rebecca Guglielmino, Gabriele Sapienza, Mohammed Qasem, Jon Teres-Zubiaga and Sesil Koutra
Abstract:	Being a ‘zoon politikon’, humankind develops its first ‘communities’ to harvest food, build shelter, and have socio-political interactions. Nowadays, the term has been configured as a challenging and promising concept for climate change mitigation and adaptation and advocates for the incorporation of various solutions within urban settings. In this contribution, a targeted and comprehensive understanding of the patterns of the ‘energy community’ (renewable/citizen) phenomenon is provided to provide clear observations unveiling the research gap. The work explores the spectrum of the ‘energy community’ according to the literature, as well as motivations and contextual factors in the Belgian context from different perspectives highlighting the necessity for sustainable development that harmonizes human activities with natural ecosystems. What is finally the energy community and what motivates its actions? What are the key factors that insight into the successful stories of energy communities in Belgium? What are the differences in the three areas of the Belgian territories? Building on this overview, this paper highlights the current research gap and provides insight into how the communities are emerging in three areas, the opportunities, and challenges they pose, and how their diffusion might be further facilitated despite their complexity and multi-dimensional nature.
Download

Area 2 - Smart and Digital Services

Short Papers

Paper Nr:	19
Title:	Towards a Green Digital Currency for Smart Communities: An AI-Powered Ecosystem for Citizen Green Stewardship
Authors:	Amira Kerkad and Rabah Gouri
Abstract:	This paper proposes a new ecosystem vision designed to measure and incentivize citizen and corporate engagement in environmental stewardship through circular economy (CE). The ecosystem uses a gamified platform where participants earn digital points for performing two types of operations: (1) recycling matters and (2) reusing items, within smart communities. We propose to consider these points as a new global digital currency redeemable for rewards and services offered by participating businesses worldwide. The businesses are mainly the polluters that aim to have green advertisement and engagement in the "polluter pays" principle. Consequently, these businesses will benefit simultaneously from green advertising and tax reductions. A suite of digital services and AI-powered tools are used to optimize operations and generate valuable data for improving both urban and rural sustainability initiatives. By making this new currency, we can assess environmental engagement, motivate citizens to adhere into CE, and impose hierarchical participation in sustainable practices. This paper outlines the ecosystem's components, discusses the feasibility of our proposal, and explores its potential benefits and challenges for various stakeholders.
Download

Area 3 - Smart Infrastructures and Smart Buildings

Full Papers

Paper Nr:	7
Title:	Topological Attention and Deep Learning Integration for Electricity Consumption Forecasting
Authors:	Ahmed Ben Salem and Manar Amayri
Abstract:	In this paper, we consider the problem of point-forecasting of univariate time series with a focus on electricity consumption forecasting. Most approaches, ranging from traditional statistical methods to recent learning-based techniques with neural networks, directly operate on raw time series observations. The main focus of this paper is to enhance forecasting accuracy by employing advanced deep learning models and integrating topological attention mechanisms. Specifically, N-Beats and N-BeatsX models are utilized, incorporating various time and additional features to capture complex nonlinear relationships and highlight significant aspects of the data. The incorporation of topological attention mechanisms enables the models to uncover intricate and persistent relationships within the data, such as complex feature interactions and data structure patterns, which are often missed by conventional deep learning methods. This approach highlights the potential of combining deep learning techniques with topological analysis for more accurate and insightful time series forecasting in the energy sector.
Download

Paper Nr:	17
Title:	Grid Interactive Smart Buildings Coordination in Multi-Area Power Systems: A Delay-Robustness Analysis
Authors:	Amedeo Andreotti, Bianca Caiazzo, Sara Leccese, Alberto Petrillo, Lorenzo Redi and Stefania Santini
Abstract:	This work focuses on the frequency support control problem for Grid-Interactive Smart Buildings (GISBs) with Thermostatically-Controlled Loads (TCLs). The problem is formalized by leveraging multi-agent systems paradigm and a distributed delayed PID-based controller is introduced in order to guarantee that each GISB provides a fast frequency support to the main grid while maintaining a desired comfort level. Compared to the technical literature, the main novelty relies in considering communication latencies from the beginning of control design phase, thus guaranteeing that the proposed control protocol is able to counteract the unavoidable presence of heterogeneous time-varying delays arising during information sharing among all the electrical entities. Extensive simulation results, exploiting also latin hypercube sampling technique, show the effectiveness and the resilience of the approach with respect to delays and parameters uncertainties, while also highlighting the delay stability margin of the entire network.
Download

Short Papers

Paper Nr:	18
Title:	Towards a Reference Model for Multimodal Transport Networks
Authors:	Daniel Zöttl, Alexander Granig, Benjamin Schwendinger and Sebastian Schlund
Abstract:	A multimodal transport network is a widely used form of transport infrastructure. The ability to describe different modes of transport, taking into account many different attributes, requires a structured model. This paper outlines the requirements for the description of a multimodal transport network in the form of a reference model. To this end, expert interviews were conducted with various expert groups from companies, researchers from the field of transport planning, traffic management system providers and internationally active logistics service providers to ensure that the reference model is suitable for practical applications. Furthermore, an approach to transform the attributes into a relational data model including entities and cardinalities is described and the challenges encountered are highlighted: different data formats, different stakeholders and insufficient data availability. Finally, the application of the reference model as data base in a practical real-world scenario is presented.
Download

Paper Nr:	12
Title:	Manglar Living Lab: Energy Management Through a Smart Microgrid with Artificial Intelligence
Authors:	Gustavo García, Alejandro Guerrero and Javier E. Sierra
Abstract:	Latin America, and Colombia in particular, are making strides in their energy transition by implementing innovative projects that prioritize sustainability and efficiency. This article presents a conceptual framework of the Manglar Living Lab pilot plant, detailing the microgrid architecture with the goal of overcoming energy challenges and focusing on efficient energy management. Central to this initiative is the development of a smart metering device, driven by artificial intelligence (AI), with a technological platform and real-time monitoring capabilities. This Living Lab not only bolsters Colombia’s energy transition strategy but also illustrates the potential of localized AI-powered solutions to enhance energy efficiency and grid reliability in the region.
Download

Area 4 - Sustainable Computing and Systems

Full Papers

Paper Nr:	9
Title:	Breaking Barriers: From Black Box to Intent-Driven, User-Friendly Power Management
Authors:	Thijs Metsch and Adrian Hoban
Abstract:	Power management in cloud and edge computing platforms is challenging due to the need for domain-specific knowledge to configure optimal settings. Additionally, the interfaces between application owners and resource providers often lack user-friendliness, leaving efficiency potentials unrealized. This abstraction also hinders the adoption of efficient power management practices, as users often deploy applications without optimization considerations. Efficient energy management works best when user intentions are clearly specified. Without this clarity, applications are treated as black boxes, complicating the process of setting appropriate throttling limits. This paper presents an application intent-driven orchestration model that simplifies power management by allowing users to specify their objectives. Based on these intentions, we have extended Kubernetes to autonomously configure system settings and activate power management features, enhancing ease of use. Our model demonstrates the potential to reduce power consumption in a server fleet within a range of ≈ 5-55% for a sample AI application. When applied broadly, the research offers promising potential to address both economic and environmental challenges. By adopting this model, applications can be more efficiently orchestrated, utilizing advanced resource management techniques to mitigate the power usage surge that is in part driven by applications such as AI and ML.
Download

Short Papers

Paper Nr:	22
Title:	Digitalization Meets Climate Protection: Legal Framework for Energy-Efficient Data Centres
Authors:	Michael Denk and Marie-Theres Holzleitner-Senck
Abstract:	Data centres serve as a backbone of digitalization, yet consume vast amounts of electricity, particularly for server cooling and uninterrupted power supply. In response, recent EU directives – especially the recast Energy Efficiency Directive and the Renewable Energy Directive – push for transparency, reporting obligations, and reuse of server-generated waste heat. While exemptions (e.g., for economic infeasibility or technical constraints) currently soften mandatory requirements, Germany has adopted ambitious regulations, setting concrete efficiency and waste heat quotas. Still, implementation faces practical obstacles, such as the low-temperature nature of data centre heat, limited district heating infrastructure, and associated costs. As digital services expand, stricter regulations are expected to drive increased energy efficiency and decarbonization across the data centre sector.
Download

Paper Nr:	13
Title:	Application of XLPE Cables in Electric Networks Supplying DC Traction Loads
Authors:	Andrey Kryukov, Konstantin Suslov, Aleksandr Cherepanov, Quoc Hieu Nguyen and Ilya Shushpanov
Abstract:	The connection of railway traction substations (TS) to high-voltage networks of electric power systems relies on overhead power transmission lines. This approach has several downsides: considerable width of the protection zone; potential for damage during strong winds, and the accumulation of ice and frost deposits. Additionally, there is a risk of injury to both people and animals caused by step voltages resulting from wire breakage. The noted negative consequences can be forgotten when using 110 kV cable lines (CL) with cross-linked polyethylene (XLPE) insulation for connecting traction substations. The study presented in this paper aims to develop digital models for determining power flows in direct current traction power supply systems (DC TPSS) with power supply to converter substations via cable line. Multiphase modeling methods are used alongside the Fazonord software product, specifically version 5.3.5.0–2024. The obtained results allow us to draw the following conclusions: the use of cable lines leads to an increase in the minimum three-minute voltages of 2 to 3.5%, while active power losses in the main power transmission line decrease by 8 to 14%. DC traction substations do not create some noticeable levels of unbalance in the adjacent networks. However, any unbalance in a three-phase system has a negative effect on power consumers, especially on widely used induction electric motors. The use of XLPE cables allows reducing unbalance factors by 11-22 times. In the presence of overhead lines (OL), the levels of harmonic distortions on the 110 kV buses of traction substation (TS) 2 and TS 3 exceed the normally permissible values. Replacing the overhead lines with cable lines makes it possible to reduce the indicators by approximately 60%. The factors of certain harmonics are reduced by 37...100%. The developed digital models can be used to design and operate DC TPSS. The method for power flow determination is universal and can be used to make calculations for external power supply systems of any configuration and traction networks of various designs.
Download

Paper Nr:	14
Title:	Optimizing Morphological Design in High-Density Residences in Hong Kong to Enhance Mental Health
Authors:	Zijun Wang
Abstract:	This study addresses the challenges of enhancing mental well-being in high-density residential environments, with a specific focus on Hong Kong. Employing a 3D model in Rhino and parametric design in Grasshopper, we used the Wallacei plugin for multi-objective optimization to balance four critical factors—visual exposure, direct sun hours, Universal Thermal Climate Index (UTCI) standard deviation, and building volume—across four building typologies: East-West oriented dot-and-row forms, North-South oriented dot-and-row forms, crossing layouts, and loop-shaped layouts. This process generated six locally optimal configurations for each typology. We then examined how variations in building morphology and street configurations influenced these factors and, in turn, emotional responses. The results indicate that wider streets and a greater number of street intersections enhance visual emotional impact, while narrower streets yield a lower UTCI standard deviation, thereby improving thermal comfort. Typological differences underscore the need for context-specific design strategies to balance these factors. Our findings provide insights for optimizing building configurations to promote emotional well-being in high-density urban settings.
Download

Paper Nr:	21
Title:	Metaverse Technology for Public Services in Smart Cities: Opportunities and Challenges
Authors:	Hajra Rasmita Ngemba, Dian Indrayani Jambari and Kamsuriah Ahmad
Abstract:	This study investigates the viability of metaverse technology as a digital public service in smart cities and explores the prospects and challenges of implementing it in developed and developing countries. This study employs a conceptual exploration through a review of the contemporary literature concerning the deployment of metaverse technology, the construction of smart cities, and the revolutionization of public services. The analysis compares readiness factors of technology, infrastructure, and policy between developed and developing countries. Metaverse provides immense value to smart cities, including improved accessibility of public services, real-time interaction, and operational efficiency. However, key challenges in deploying such networks include limited infrastructure in the developing world, issues with data privacy, and high energy consumption in developed countries. Conceptual research needs further empirical studies focusing on implementing metaverse technology in smart cities. This research is beneficial for policymakers when designing smart-metaverse implementations.
Download

Area 5 - Energy-Aware Systems and Technologies

Full Papers

Paper Nr:	16
Title:	Understanding Intention to Adopt Smart Thermostats: The Role of Individual Predictors and Social Beliefs Across Five EU Countries
Authors:	Mona Bielig, Florian Kutzner, Sonja Klingert and Celina Kacperski
Abstract:	Heating of buildings represents a significant share of the energy consumption in Europe. Smart thermostats that capitalize on the data-driven analysis of heating patterns in order to optimize heat supply are a very promising part of building energy management technology. However, factors driving their acceptance by buildings’ inhabitants are poorly understood although being a prerequisite for fully tapping on their potential. In order to understand the driving forces of technology adoption in this use case, a large survey (N = 2250) was conducted in five EU countries (Austria, Belgium, Estonia, Germany, Greece). For the data analysis structural equation modelling based on the Unified Theory of Acceptance and Use of Technology (UTAUT) was employed, which was extended by adding social beliefs, including descriptive social norms, collective efficacy, social identity and trust. As a result, performance expectancy, price value, and effort expectancy proved to be the most important predictors overall, with variations across countries. In sum, the adoption of smart thermostats appears more strongly associated with individual beliefs about their functioning, potentially reducing their adoption. At the end of the paper, implications for policy making and marketing of smart heating technologies are discussed.
Download

Short Papers

Paper Nr:	8
Title:	Repurposing Alternators as Motors: Promoting Sustainability and Circular Economy in Low-Cost Mobility Systems
Authors:	Maximilian Dillitzer, Patrick Issle, Julian Schwarz, Tin Stribor Sohn, Michael Auerbach and Wolfgang Gruel
Abstract:	The automotive industry is undergoing a transformation driven by electric mobility, automated driving, and value creation. However, this shift often overlooks developing regions, where unique challenges restrict access to affordable, low-emission transportation. This paper explores how repurposing parts from end-of-life vehicles can promote sustainable mobility solutions in developing regions, where access to transportation is limited. We focus on converting alternators from internal combustion engines into electric motors, benefiting both the environment and resource-constrained populations. Our approach follows seven requirements for a sustainable mobility system, emphasizing affordability, sustainability, and circular economy principles over high-performance, costly solutions. By applying circular economy principles, we highlight the reuse of available alternators from scrap vehicles, providing a cost-effective and eco-friendly solution suited to the needs of developing regions. This approach addresses several Sustainable Development Goals, enhancing access to clean energy, economic growth, and responsible consumption. Engaging with local communities provided insights into specific needs and ensured practical applicability. To validate our approach, we conducted rig tests and field studies in Africa and Germany to assess the performance and viability of the repurposed alternators in real-world conditions. Successful testing in both regions demonstrates that this mobility system offers a practical solution to real-world challenges.
Download

Paper Nr:	27
Title:	The Increasingly Critical Role of Communication Networks in Enhancing Power Grid Resilience Under Climate Change
Authors:	Oliver Jung
Abstract:	The increasing frequency and severity of extreme weather events, driven by climate change, pose significant challenges to the resilience of power grids worldwide. As critical infrastructure, power grids must adapt to these disruptions while meeting the growing demands of renewable energy integration, distributed energy resources (DERs), and energy system electrification. This position paper highlights the important role of communication networks in enhancing power grid resilience and the integration of renewable energy resources. Advanced communication technologies, such as 5G, IoT, and AI-driven analytics, enable real-time monitoring, fault detection, demand forecasting, and resource optimization, all of which are crucial for grid reliability under dynamic and extreme conditions. The paper analyses the vulnerability of electricity grids to climate-related disruptions, examines technical solutions to these challenges and provides strategic recommendations for the design of robust communication infrastructures. With a focus on redundancy, supporting technologies such as 5G and AI-powered analytics and decision support, this paper makes the argument for prioritising investment in resilient communication systems to future-proof power grids. By presenting communication networks as an essential part of grid modernisation, this paper underlines their crucial role in ensuring reliable, efficient and adaptable energy systems in the face of climate change.
Download

Area 6 - Smart Cities

Full Papers

Paper Nr:	24
Title:	Simulation Architecture for Electric Vehicle Charging Optimization in Dresden's Ostra District
Authors:	Shangqing Wang, Syed Irtaza Haider, Shiwei Shen, Faezeh Motazedian, Rico Radeke and Frank H. P. Fitzek
Abstract:	The integration of electric vehicles (EVs) into urban transportation systems presents significant challenges and opportunities for cities aiming to optimize energy usage and reduce emissions. This paper presents a simulation architecture to optimize EV charging in Dresden’s Ostra District as part of the Mobilities for EU project. The proposed architecture leverages the Simulation of Urban Mobility (SUMO) to model traffic patterns and vehicle movements, while a custom energy management system facilitates smart and bidirectional charging capabilities. By incorporating the Amitran methodology to evaluate CO2 emissions, the architecture aims to provide insights into the sustainability impacts of various charging strategies. The simulation environment allows for the exploration of ”what-if” scenarios, enabling city planners and fleet managers to assess the implications of different charging strategies on energy consumption and grid stability. Collaboration with the city of Dresden will be essential for validating the simulation with real data, enhancing model accuracy and supporting informed decision-making. Ultimately, this research aims to contribute to the growing body of knowledge on sustainable urban mobility and provide a valuable tool for optimizing EV integration in smart cities. Future work will focus on expanding the simulation framework to include additional variables such as renewable energy sources and user behavior patterns, further enhancing its applicability in real-world scenarios.
Download

Short Papers

Paper Nr:	11
Title:	Predicting Socio-Demographic Characteristics from Load Profiles with Varying Time Granularities
Authors:	Dejan Radovanovic, Maximilian Schirl, Andreas Unterweger and Günther Eibl
Abstract:	Energy consumption data from smart meters has been shown to infer socio-demographic characteristics, which impacts privacy. However, the impact of time granularity on the ability to classify such characteristics has not yet been investigated in existing literature. In this paper, we answer this question by analyzing a dataset of more than 1,000 households over one year. We obtain three main findings: (i) While a coarser time granularity leads to decreased classification performance, we find that, unexpectedly, classification performance only varies insignificantly within two relatively large granularity intervals. For example, one-hour granularity exhibits nearly the same classification performance as 15-minute granularity. This indicates that, depending on the use case, data collection can be minimized, as any resolution between 15 minutes and one hour can be used without significantly impacting prediction performance. (ii) We propose a new evaluation methodology where an interpretable classification algorithm can predict a household’s socio-demographic characteristics from a load profile of a single, arbitrary week of the year. Compared to existing methodologies, where training and testing data are sampled from a single known week, using arbitrary weeks as input makes classification harder, thus requiring more sophisticated classification algorithms. (iii) We present such an interpretable classification algorithm, which outperforms those that train and evaluate classifiers separately for each week. At the same time, our algorithm exhibits a comparable performance to approaches that require a load profile of the whole year instead of a single, arbitrary week.
Download

Paper Nr:	20
Title:	Incorporating Animals as Stakeholders in ICT: Towards Truly Inclusive Digital Sustainability
Authors:	Roberto Vergallo and Luca Mainetti
Abstract:	The digital revolution has driven unprecedented technological advancements, transforming modern life and addressing global challenges. However, while sustainability efforts in Information and Communication Technology (ICT) are addressing environmental issues like energy consumption and carbon footprints, the ethical implications for non-human animals remain largely unexplored. This position paper calls for a redefinition of sustainability in ICT to include animal welfare as a core principle. We argue that animals should be recognized not only as indirect stakeholders impacted by technological progress but as direct beneficiaries of ethical digital practices. For the first time, we propose the concept of vegan digital product, also introducing an interdisciplinary methodological framework that prioritize animal welfare in digital design and policy-making. Particularly, the framework incorporates animal welfare as a scope-based non-functional requirement in ICT projects, including a draft for quantitative metrics based on the Value of Statistical Life (VSL).
Download

Paper Nr:	26
Title:	Building Smarter Cities Through AI-Driven Digitization: A Case Study
Authors:	Zuzana Schwarzová, Leonard Walletzký, Mouzhi Ge and Patrik Procházka
Abstract:	The concept of Smart (or Smarter) Cities is widely recognized in contemporary society. The integral relationship between Smart Cities and digitization has been extensively researched, establishing it as a fundamental condition for developing modern, effective, and sustainable services within the intricate environment of a Smart City. This paper focuses on the implementation methods of digitization. Numerous cities are transitioning their agendas from traditional (analogue or paper-based) to digital platforms. However, the impact of such digitization can vary significantly. In many instances, cities develop a one-to-one digital replica of an analogue or paper service, neglecting to explore the potential for improved service utilization or integration with other services. This often overlooks the opportunity to leverage synergistic effects that could enhance value for all stakeholders, including citizens, administration, and business entities. We aim to investigate the digitization process at the Official Board of a municipality, using the results from a Hackathon organized in Brno, Czech Republic, as an example of an innovative approach to such solutions. We intend to discuss the methods of digitization provision and based on the case study suggest a best practice approach to avoid common mistakes and issues arising from an incorrect approach to digitizing public services.
Download

Paper Nr:	6
Title:	Unsupervised Partial Domain Adaptation for Occupants Behavior Modeling in Smart Buildings
Authors:	Jawher Dridi, Manar Amayri and Nizar Bouguila
Abstract:	Smart buildings rely on activity recognition (AR) and occupancy estimation (OE) tasks to provide residents with several services such as optimal energy management, HVAC (Heating, ventilation, and air conditioning) systems optimization, and security. Estimating the number of occupants and recognizing their activities is performed using sensor data which is scarce. The collection and labeling of smart building data are tedious, costly, and time-consuming, pushing researchers to consider solutions based on domain adaptation (DA) to transfer knowledge from source domains where data is abundant to target domains where data is scarce. In particular, unsupervised domain adaptation (UDA) has been considered to solve the unavailability of labeled data in target domains. Previous research has focused on standard UDA methods where label space is identical between source and target domains which is not the case for real-world datasets. This work considers unsupervised partial domain adaptation (UPDA) methods where target classes are a subset of source classes. We adapt and evaluate two UPDA techniques called Adversarial Re-weighting for Partial Domain Adaptation (ARPDA) and Selective Adversarial Networks for Partial Domain Adaptation (SAN w PDA). We have compared their performance to Adversarial Re-weighting for Standard Domain Adaptation (ARSDA) and Selective Adversarial Networks for Standard Domain Adaptation (SAN w SDA) as well as several previous UDA methods. The impressive results with scores up to 98% prove the efficiency of the adapted UPDA techniques. We provide the code in the following repository: https://github.com/JawDri/UPDA-for-OE-and-AR.git.
Download