![Ιδρυματικό Αποθετήριο [SANDBOX]](images/dias.logo.png "Ιδρυματικό Αποθετήριο [SANDBOX]"){kind=logo}
Ιδρυματικό Αποθετήριο [SANDBOX]
Πολυτεχνείο Κρήτης
Πολυτεχνείο Κρήτης
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/53066E80-3347-454A-AA29-97B0D36DEAB1 | ||
| Έτος | 2022 | ||
| Τύπος | Αφίσα σε Συνέδριο | ||
| Άδεια Χρήσης |
|
||
| Βιβλιογραφική Αναφορά | G. Charalambidis, C. Akasiadis, E. S. Rigas and G. Chalkiadakis, “A realistic dataset generator for smart grid ecosystems with electric vehicles,” in Proceedings of the 13th ACM International Conference on Future Energy Systems (e-Energy 2022), virtual event, 2022, pp. 432–433, June 2022, doi: 10.1145/3538637.3538755. https://doi.org/10.1145/3538637.3538755 | ||
| Εμφανίζεται στις Συλλογές |
Research on the deployment and employment of electric vehicles (EVs) in the emerging Smart Grid, typically requires access to large datasets containing data that is rich and reliable. Such datasets are hard to come by in the wild due to various privacy and sensitivity considerations. In this paper, we design a dataset generator for large-scale EVs charging management. The generator (i) takes as input anonymized real-world datasets describing different energy generation and demand types, as well as charging profiles of EVs and corresponding trip and type information; (ii) fits a variety of machine learning models using this data as training sets; and (iii) generates new synthetic data that adheres to the same principles and relationships as the input. The generator comes complete with data smoothing and dataset summarization, visualization, and comparison abilities that users can utilize via a web-based interface; and is offered as a free-to-use tool to the research community.
Copyright © DIAS 2013
