Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data
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 o...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SDEWES Centre
2022-03-01
|
| Series: | Journal of Sustainable Development of Energy, Water and Environment Systems |
| Subjects: | |
| Online Access: |
http://www.sdewes.org/jsdewes/pid9.0388
|
| _version_ | 1798013996481118208 |
|---|---|
| author | Teo Čurčić Rajeev R. Kalloe Merel A. Kreszner Olivier van Luijk Santiago Puertas Puchol Emilio Caba Batuecas Tadeo B. Salcedo Rahola |
| author_facet | Teo Čurčić Rajeev R. Kalloe Merel A. Kreszner Olivier van Luijk Santiago Puertas Puchol Emilio Caba Batuecas Tadeo B. Salcedo Rahola |
| author_sort | Teo Čurčić |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-11T15:11:36Z |
| format | Article |
| id | doaj.art-3b3b1dc5716d46978dff82ef1c72d053 |
| institution | Directory Open Access Journal |
| issn | 1848-9257 |
| language | English |
| last_indexed | 2024-04-11T15:11:36Z |
| publishDate | 2022-03-01 |
| publisher | SDEWES Centre |
| record_format | Article |
| series | Journal of Sustainable Development of Energy, Water and Environment Systems |
| spelling | doaj.art-3b3b1dc5716d46978dff82ef1c72d0532022-12-22T04:16:39ZengSDEWES CentreJournal of Sustainable Development of Energy, Water and Environment Systems1848-92572022-03-0110111310.13044/j.sdewes.d9.03881090388Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather dataTeo Čurčić0Rajeev R. Kalloe1Merel A. Kreszner2Olivier van Luijk3Santiago Puertas Puchol4Emilio Caba Batuecas5Tadeo B. Salcedo Rahola6 Faculty of Technology, Innovation and Society, The Hague University of Applied Sciences, The Hague, The Netherlands Faculty of Technology, Innovation and Society, The Hague University of Applied Sciences, The Hague, The Netherlands Faculty of Engineering & ICT Avans University, Breda, The Netherlands Faculty of Technology, Innovation and Society, The Hague University of Applied Sciences, The Hague, The Netherlands Escuela Politécnica Superior University Francisco de Vitoria, Madrid, Spain Escuela Politécnica Superior University Francisco de Vitoria, Madrid, Spain Faculty of Technology, Innovation and Society, The Hague University of Applied Sciences, The Hague, The Netherlands 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. http://www.sdewes.org/jsdewes/pid9.0388 smart meternet-zero energy buildingsupervised machine learningclassificationlstm |
| spellingShingle | Teo Čurčić Rajeev R. Kalloe Merel A. Kreszner Olivier van Luijk Santiago Puertas Puchol Emilio Caba Batuecas Tadeo B. Salcedo Rahola Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data Journal of Sustainable Development of Energy, Water and Environment Systems smart meter net-zero energy building supervised machine learning classification lstm |
| title | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data |
| title_full | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data |
| title_fullStr | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data |
| title_full_unstemmed | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data |
| title_short | Gaining insights into dwelling characteristics using machine learning for policy making on nearly zero-energy buildings with the use of smart meter and weather data |
| title_sort | gaining insights into dwelling characteristics using machine learning for policy making on nearly zero energy buildings with the use of smart meter and weather data |
| topic | smart meter net-zero energy building supervised machine learning classification lstm |
| url |
http://www.sdewes.org/jsdewes/pid9.0388
|
| work_keys_str_mv | AT teocurcic gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT rajeevrkalloe gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT merelakreszner gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT oliviervanluijk gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT santiagopuertaspuchol gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT emiliocababatuecas gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata AT tadeobsalcedorahola gaininginsightsintodwellingcharacteristicsusingmachinelearningforpolicymakingonnearlyzeroenergybuildingswiththeuseofsmartmeterandweatherdata |