| Title |
Tefnen: Transformer For Energy Forecasting In Natural Environment |
| ID_Doc |
54662 |
| Authors |
Domínguez-Cid S.; Larios D.F.; Barbancho J.; Salvador A.G.; Quintana-Ortí E.S.; León C. |
| Year |
2023 |
| Published |
International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2023 |
| DOI |
http://dx.doi.org/10.1109/ICECCME57830.2023.10253223 |
| Abstract |
Photovoltaic systems are being used in almost every field such as smart cities, Internet of Things paradigms or remote Wireless Sensor Networks. In Internet of things paradigms deployed in natural environments, energy harvesting technology is crucial to power the devices. For the energy management system, it is important to predict how much energy can be harvested from the environment. In this work we focus on creating a model for forecasting the total energy produced by a photovoltaic installation one day in advance. The model is based on the original Transformer architecture. This structure has minor modifications for time series applications. The dataset was created with weather forecasts and the energy and power production of a real photovoltaic installation. The model was trained and compared with state-of-art approaches. The results show that our approach could predict the total energy generated by the photovoltaic installation one day-ahead. © 2023 IEEE. |
| Author Keywords |
Energy harvesting; IoT; PV; Transformer |
