SMARTGREENS 2024 Abstracts

Area 1 - Smart Infrastructures and Smart Buildings
Full Papers Short Papers
Area 2 - Sustainable Computing and Systems
Short Papers
Area 3 - Energy-Aware Systems and Technologies
Full Papers Short Papers
Area 4 - Smart Cities
Full Papers Short Papers

Area 1 - Smart Infrastructures and Smart Buildings

Full Papers
Paper Nr: 22
Title:

Modeling the Operation of Traction Power Systems Incorporating Wind Turbines
Authors:

Andrey Kryukov, Konstantin Suslov, Aleksandr Cherepanov and Alexander Kryukov
Abstract: The paper presents the outcomes of the research aimed at developing digital models for calculating the operating conditions of railway power supply systems (RPSS) incorporating wind turbines. The implementation of the models relies on the methods of phase coordinates, which enable a systems, universal, and comprehensive approach. The systems dimension is achieved by considering all the significant properties of a complex RPSS and a supply network. The versatility is ensured by modeling traction networks, power lines, and transformers of various designs. The comprehensiveness lies in the possibility of calculating the normal, emergency, and special operating conditions in the RPSS. The study highlights a variety of applications of the wind turbines: to power the facilities located in regions with unstable energy supply; to enhance the reliability of power supply to the consumer whose disconnection could lead to serious consequences; to supply energy to relatively low-power facilities. The creation of the calculation model for the RPSS requires the implementation of an algorithm for the interaction of models of individual components and includes the following stages: modeling the rolling stock traffic schedule; developing instantaneous diagrams corresponding to specific time instants and calculating their operating parameters; determining integrated modeling indices. The results obtained using the Fazonord software indicate that the use of wind turbines can bring about the following benefits: cutting down energy supply costs; reducing unbalance on the busbars of traction substations, stabilizing voltage levels on the current collectors of electric locomotives.
Download
Short Papers
Paper Nr: 25
Title:

NILM-Based Solutions for the Automation of Energy Services in Residential Buildings
Authors:

Pierre Ferrez, Dominique Gabioud and Pierre Roduit
Abstract: In Switzerland, about 40 % (90 TWh) of the energy needs are due to buildings and about 70 % of these needs come from heating. Therefore, improving the efficiency of buildings has a high potential for energy savings. This paper presents innovative solutions for the automation of energy services in residential buildings, based solely on the disaggregation of the centralized electricity consumption measurement of the household. The developed method was successfully used on electricity consumption data recorded in 14 households over a year to (1) extract the heat pump consumption from the aggregated consumption, (2) split the heat pump consumption into space heating and domestic hot water consumption and (3) split the remaining consumption into four categories: base load, low power, medium power, and high power. With a daily average error on the prediction of the heat pump consumption below 3.5 % and daily average errors on the prediction of the number of cycles and the operating time of the heat pump both around 1 %, the described method can be used for the development of energy service prototypes allowing to better understand and optimize the energy functioning of residential buildings with potential savings for the residents.
Download

Area 2 - Sustainable Computing and Systems

Short Papers
Paper Nr: 24
Title:

Integrating Legal Considerations into Model-Based Cyber-Physical-Systems Development
Authors:

Katharina Polanec, Dominik Vereno, Erich Fritzenwallner and Christian Neureiter
Abstract: Developing complex cyber-physical systems (CPS) demands a variety of disciplines like engineering, software development, economics and legislation to effectively communicate with each other. Enabling this interdisciplinary communication is a challenge that can be tackled with the use of a model-based systems engineering approach in combination with domain-specific modeling languages. In domain-specific modeling frameworks that implement these approaches, however, research reveals an oversight: an insufficient consideration of legislation disciplines. Since regulations have a significant impact on CPS, omitting their incorporation early on during development can significantly delay deployment and lead to exponentially rising development costs. This position paper advocates for a compliance-by-design approach through the early integration of legal requirements into domain-specific architecture frameworks. By bridging the gap between technical and legislative disciplines, the interdisciplinary development of CPS is enhanced, not only ensuring the technical robustness of the systems but also regulatory compliance. This results in mitigating development risks, especially avoiding pitfalls of costly adaptions to the system due to late-stage integration of legal considerations.
Download

Area 3 - Energy-Aware Systems and Technologies

Full Papers
Paper Nr: 27
Title:

Assessing the Suitability of Architectural Models for Generating Smart Grid Co-Simulations
Authors:

Markus Peter, Dominik Vereno, Jounes-Alexander Gross and Christian Neureiter
Abstract: Ensuring the reliability of critical infrastructure, such as a smart grid, is of utmost importance. The verification of this reliability needs to occur early in the systems engineering process. An effective method to accomplish this verification is to simulate a model of a smart grid. Given the complexity of such a system with diverse subsystems, co-simulation has emerged as a leading approach due to its capability to engage various independently developed simulators. This paper explores the interoperability between architectural models and co-simulation. The evaluation relies on a case study implemented both as a simulation and an architectural model, with the goal of identifying similarities and differences. The conclusion drawn is that the two tools do not achieve full interoperability to generate a comprehensive simulation out of an architectural model. This limitation stems from co-simulations requiring precise information at an entity level, which type-based architectural models cannot provide. However, a proposal is put forth to use architectural models as a starting point for generating co-simulation code skeletons. The research provides an analysis of the interoperability challenges and suggests a practical combination of the two concepts.
Download
Short Papers
Paper Nr: 15
Title:

Sustainable Energy Management System for AIoT Solutions Using Multivariate and Multi-Step Battery State of Charge Forecasting
Authors:

Farnaz Kashefinishabouri, Nizar Bouguila and Zachary Patterson
Abstract: The convergence of Artificial Intelligence (AI) with Internet of Things (IoT) technologies, known as AIoT, is revolutionizing industries, including smart cities. However, this transformation introduces challenges in energy management. Addressing this issue while upholding responsible AI principles requires prioritizing the sustainability of AIoT solutions through using renewable energy sources. While renewable energy offers numerous advantages, its intermittent nature necessitates an effective power management system. Developing a power management system serving as a decision-making platform for AIoT-driven solutions is the goal of this study. This platform contains two critical components: accurate forecasts of battery “State of Charge” (SoC), and the implementation of appropriate control strategies, including energy consumption adjustments. This study focuses on accurate battery SoC forecasts, to this end, an experiment has been designed, and a data logging system has been developed to produce suitable data since publicly available datasets do not match the specific characteristics of this research. The SoC forecasting in this paper has been addressed as a multivariate and multi-step time series forecasting problem, benchmarking various models. Comprehensive evaluations on datasets with varying time intervals showed the Bi-GRU model outperforming others based on MAE and RMSE metrics.
Download
Paper Nr: 17
Title:

Pareto-Optimal Execution of Parallel Applications with Respect to Time and Energy
Authors:

Thomas Rauber and Gudula Rünger
Abstract: Compute-Bound numerical solution methods have a high demand for computational power and, thus, for energy. Both depend strongly on the numerical accuracy required for the approximation solution. A higher numerical accuracy often requires more execution time and energy. However, this dependence is more subtle and diverse. That means for a given numerical problem, different settings of the solution process, such as the use of different solvers, different implementation variants, different numbers of cores, or different operational frequencies result in a large number of different possibilities for the solution process, each of which may lead to a potentially different execution time and energy consumption. The best combination also depends on the specific execution platform used. Using different tolerance values for the time steps in the solution process adds another degree of complexity with a potentially different accuracy of the resulting approximation solution. The goal of this article is to investigate the selection process of performance-optimal variants of all these computation possibilities when solving a given numerical problem. In particular, a selection process is proposed determining Pareto-optimal computation variants of the numerical method. As representative numerical solution method, explicit solution methods for ordinary differential equations are considered.
Download

Area 4 - Smart Cities

Full Papers
Paper Nr: 18
Title:

Automatic Identification and Classification of Map-Matching Anomalies in Cycling Routes
Authors:

Carlos Carvalho, Moisés Ramires and Rui José
Abstract: Road network data models are a key element for many cycling services. However, cyclists often ride unconventional paths that may not be properly represented in those models. This may cause various types of map-matching anomalies, where the map-matched route does not correspond to the real route. In this work, we assess a set of classification models to automatically detect and classify these map-matching anomalies. Using OpenStreetMap road network, we generated the map-matched routes for a dataset of 98 cycling GPS traces. To produce ground-truth data, we visually inspected each result to identify and classify every map-matching anomaly, and computed several similarity measures between each GPS trace and the respective map-matched segment. Based on this data, we trained several classification models with different feature engineering approaches to perform binary and multi-class classification. The results show that binary classifiers can be very effective in the identification of map-matching anomalies. The best model, a XGBoost classifier, obtained an F1 Score of 0.906 and an accuracy of 0.893, which outperform other methods. However, the multi-class classifiers had lower performance. This ability to automatically detect and classify map-matching anomalies may help to systematically improve road network models and consequently improve information provided to cyclists and decision-makers.
Download
Short Papers
Paper Nr: 16
Title:

AI-Powered Urban Mobility Analysis for Advanced Traffic Flow Forecasting
Authors:

Sarah Di Grande, Mariaelena Berlotti and Salvatore Cavalieri
Abstract: Rapid global urbanization has resulted in burgeoning metropolitan populations, posing significant challenges for managing transportation infrastructure. Despite various attempts to address these issues, persistent challenges hinder urban growth. This study emphasizes the crucial need for effective traffic flow forecasting in city traffic management systems, with Catania serving as a case study due to its notable traffic congestion. Predicting traffic flow encounters obstacles, such as the cost and feasibility of deploying sensors across all roads. To overcome this, the authors suggest an innovative two-level machine learning approach, involving an unsupervised clustering model to extract patterns from extensive sensor-generated big data, followed by supervised machine learning models forecasting traffic within individual clusters. Notably, this method allows predictions for roads without sensor data by leveraging a small subset of alternative data sources.
Download
Paper Nr: 23
Title:

Customizing Trust Systems: Personalized Communication to Address AI Adoption in Smart Cities
Authors:

Jessica Ohnesorg, Nazek Fakhoury, Noura Eltahawi and Mouzhi Ge
Abstract: Since it is challenging to tailor trust management systems to accommodate diverse individual preferences due to the evolving adoption of artificial intelligence (AI) in smart cities, through a comprehensive review of internal and external factors influencing trust levels, including personal values, personality traits, and cultural background, the paper highlights the crucial role of communications in human-machine interactions by emphasizing AI technologies. Based on the review, this paper proposes a Framework for AI Trust enHancement (FAITH). The FAITH framework integrates personalized communication strategies with individual preferences to enhance trust in smart city systems. To validate the proposed framework, the FAITH framework is applied in a use case scenario to demonstrate its potential effectiveness in fostering trust, collaboration, and innovation. The research results contribute not only to understand trust management systems in smart cities, but also offer practical insights for addressing the diverse preferences of individuals in smart cities.
Download