| Title |
A Comparison of Automated Time Series Forecasting Tools for Smart Cities |
| ID_Doc |
43846 |
| Authors |
Pereira, PJ; Costa, N; Barros, M; Cortez, P; Duraes, D; Silva, A; Machado, J |
| Title |
A Comparison of Automated Time Series Forecasting Tools for Smart Cities |
| Year |
2022 |
| Published |
|
| DOI |
10.1007/978-3-031-16474-3_45 |
| Abstract |
Most smart city sensors generate time series records and forecasting such data can provide valuable insights for citizens and city managers. Within this context, the adoption of Automated Time Series Forecasting (AutoTSF) tools is a key issue, since it facilitates the design and deployment of multiple TSF models. In this work, we adapt and compare eight recent AutoTSF tools (Pmdarima, Prophet, Ludwig, DeepAR, TFT, FEDOT, AutoTs and Sktime) using nine freely available time series that can be related with the smart city concept (e.g., temperature, energy consumption, city traffic). An extensive experimentation was carried out by using a realistic rolling window with several training and testing iterations. Also, the AutoTSF tools were evaluated by considering both the predictive performances and required computational effort. Overall, the FEDOT tool presented the best overall performance. |
| Author Keywords |
Automated machine learning; Time Series Forecasting; Smart cities |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Conference Proceedings Citation Index - Science (CPCI-S) |
| EID |
WOS:000869745400045 |
| WoS Category |
Computer Science, Artificial Intelligence |
| Research Area |
Computer Science |
| PDF |
|