Machine learning models have proven to be reliable methods in classification tasks. However, little research has been done on classifying dwelling characteristics based on smart meter & weather data before. Gaining insights into dwelling characteristics can be helpful to create/improve the policies for creating new dwellings at NZEB standard. This paper compares the different machine learning algorithms and the methods used to correctly implement the models. These methods include the data pre-processing, model validation and evaluation. Smart meter data was provided by Groene Mient, which was used to train several machine learning algorithms. The models that were generated by the algorithms were compared on their performance. The results showed that Recurrent Neural Network (RNN) 2performed the best with 96% of accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrices were used to produce classification reports, which can indicate which of the models work the best for this specific problem. The models were programmed in Python.
DOCUMENT
Machine learning models have proven to be reliable methods in classification tasks. However, little research has been conducted on the classification of dwelling characteristics based on smart meter and weather data before. Gaining insights into dwelling characteristics, which comprise of the type of heating system used, the number of inhabitants, and the number of solar panels installed, can be helpful in creating or improving the policies to create new dwellings at nearly zero-energy standard. This paper compares different supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Long-short term memory, and methods used to correctly implement these algorithms. These methods include data pre-processing, model validation, and evaluation. Smart meter data, which was used to train several machine learning algorithms, was provided by Groene Mient. The models that were generated by the algorithms were compared on their performance. The results showed that the Long-short term memory performed the best with 96% accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrics were used to produce classification reports, which indicates that the Long-short term memory outperforms the compared models on the evaluation metrics for this specific problem.
DOCUMENT
Uit het rapport: "In mei 2015 bestaat het Centre of Expertise Smart Sustainable Cities 1 jaar. De founding partners, Ballast Nedam, BJW, Hogeschool Utrecht, Movares, ROC Midden-Nederland, Royal HaskoningDHV, Uneto VNI en Utrecht Sustainability Institute, hebben in het afgelopen jaar hard gewerkt aan de organisatie en projecten. Medewerkers van bedrijven, studenten, docenten en onderzoekers werken samen in multidisciplinaire teams om met nieuwe kennis en inzichten concrete toepassingen te ontwikkelen. Dat is de kern van onze manier van werken. Vanuit een systeemperspectief verbinden we technologische oplossingen aan de vraagstukken van mens en maatschappij. Op de conferentie ‘Samen werken aan Smart Sustainable Cities: het Utrechtse model’ (hu-conferenties.nl) op 5 juni, laten we u graag zien hoe we dat in praktijk brengen. In deze uitgave vindt u een kleine greep uit de projecten van het Centre waarin u ziet wat de meerwaarde is van de verbinding beroepspraktijkonderzoek- onderwijs. Kijkt u voor alle projecten van het Centre of Expertise op onze website: www.smartsustainablecities.hu.nl/projecten. Nadia Verdeyen, Algemeen directeur Centre of Expertise Smart Sustainable Cities"
DOCUMENT
This study explores how households interact with smart systems for energy usage, providing insights into the field's trends, themes and evolution through a bibliometric analysis of 547 relevant literature from 2015 to 2025. Our findings discover: (1) Research activity has grown over the past decade, with leading journals recognizing several productive authors. Increased collaboration and interdisciplinary work are expected to expand; (2) Key research hotspots, identified through keyword co-occurrence, with two (exploration and development) stages, highlighting the interplay between technological, economic, environmental, and behavioral factors within the field; (3) Future research should place greater emphasis on understanding how emerging technologies interact with human, with a deeper understanding of users. Beyond the individual perspective, social dimensions also demand investigation. Finally, research should also aim to support policy development. To conclude, this study contributes to a broader perspective of this topic and highlights directions for future research development.
MULTIFILE
Uit voorwoord Anton Franken, lid CvB `Smart Sustainable Cities is een platform voor het bedrijfsleven, kennisinstellingen en Hogeschool Utrecht waar gezamenlijk vernieuwende producten en diensten worden ontwikkeld die de realisatie van slimme, duurzame en gezonde steden dichterbij brengt. Startende en ervaren professionals hebben hiermee de mogelijkheid om via het onderwijs of via bij- en nascholing de nieuwste toepasbare kennis en inzichten op dit gebied op te doen. Tevens verricht het platform onderzoek. In projecten werken studenten, bedrijven, docenten en onderzoekers samen om nieuwe kennis en inzichten tot toepassing te brengen. Drie inhoudelijke thema’s staan centraal: ‘Stedelijke gebieden energieneutraal’, ‘Gezonde gebieden gezond gebouwd’ en ‘Duurzaam gedrag: mens en organisatie’ .`
DOCUMENT
B4B is a multi-year, multi-stakeholder project focused on developing methods to harness big data from smart meters, building management systems and the Internet of Things devices, to reduce energy consumption, increase comfort, respond flexibly to user behaviour and local energy supply and demand, and save on installation maintenance costs. This will be done through the development of faster and more efficient Machine Learning and Artificial Intelligence models and algorithms. The project is geared to existing utility buildings such as commercial and institutional buildings.
DOCUMENT
The objective of this book ‘An introduction to Smart Dairy Farming’ is to provide insight in the development of the Smart Dairy Farming (SDF) concept and advise as to how to apply this knowledge in the field of activities of students from universities of applied science. The information in this book includes background information and comprehensive insight in the concept of SDF.
DOCUMENT
Installing photovoltaic panels (PV) on household rooftops can significantly contribute to mitigating anthropogenic climate change. The mitigation potential will be much higher when households would use PVs in a sustainable way, that is, if they match their electricity demand to their PVs electricity production, as to avoid using electricity from the grid. Whilst some have argued that owning PVs motivate households to use their PV in a sustainable way, others have argued that owning a PV does not result in load shifting, or that PV owners may even use more energy when their PV production is low. This paper addresses this critical issue, by examining to what extent PV owners are likely to shift their electricity demand to reduce the use of electricity from the grid. Extending previous studies, we analyse actual high frequency electricity use from the grid using smart meter data of households with and without PVs. Specifically, we employ generalized additive models to examine whether hourly net electricity use (i.e., the difference between electricity consumed from the grid and supplied back to the grid) of households with PVs is not only lower during times when PV production is high, but also when PV production low, compared to households without PVs. Results indicate that during times when PV production is high, net electricity use of households with PV is negative, suggesting they sent back excess electricity to the power grid. However, we found no difference in net electricity use during times when PV production is low. This suggests that installing PV does not promote sustainable PV use, and that the mitigation potential of PV installment can be enhanced by encouraging sustainable PV use
LINK
In this research, the experiences and behaviors of end-users in a smart grid project are explored. In PowerMatching City, the leading Dutch smart grid project, 40 households were equipped with various decentralized energy sources (PV and microCHP), hybrid heat pumps, smart appliances, smart meters and an in-home display. Stabilization and optimization of the network was realized by trading energy on the market. To reduce peak loads on the smart grid, several types of demand side management were tested. Households received feedback on their energy use either based on costs, or on the percentage of consumed energy that had been produced locally. Furthermore, devices could be controlled automatically, smartly or manually to optimize the energy use of the households. Results from quantitative and qualitative research showed that: (1) feedback on costs reduction is valued most; (2) end-users preferred to consume self-produced energy (this may even be the case when, from a cost or sustainability perspective, it is not the most efficient strategy to follow); (3) automatic and smart control are most popular, but manually controlling appliances is more rewarding; (4) experiences and behaviors of end-users depended on trust between community members, and on trust in both technology (ICT infrastructure and connected appliances) and the participating parties.
DOCUMENT
Het project PreciSIAlandbouw heeft precisielandbouwtechnieken ontwikkeld en gevalideerd op vijf thema's: sensortechnologie, kennis en advies, robotisering, digitalisering, en verdienmodellen. Dit rapport bevat de resultaten van robotisering. Er zijn modules ontwikkeld om gewas en onkruid te onderscheiden en locaties van plantdetails nauwkeurig te bepalen.Hogeschool Saxion, lectoraat Lectoraat Smart Mechatronics and Robotics
DOCUMENT
