The time series prediction problem aimed at the implementation of a 'smart thermostat' is addressed. 'SARIMAX models' are compared with LSTM neural networks. We show that with a low amount of data used for training, SARIMAX models achieve significantly higher accuracy while maintaining high computational efficiency, so in a problem where it becomes necessary to implement the system on low-power embedded devices, these approaches have significant advantages over neural networks.
A Comparison of Time Series Prediction Techniques for the Realization of a Smart Thermostat / Lanciotti, A.; Lucadei, C.; Sernani, P.; Dragoni, A. F.. - (2023), pp. 301-305. (Intervento presentato al convegno 2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering, MetroXRAINE 2023 tenutosi a ita nel 2023) [10.1109/MetroXRAINE58569.2023.10405617].
A Comparison of Time Series Prediction Techniques for the Realization of a Smart Thermostat
Sernani P.;Dragoni A. F.
Primo
2023-01-01
Abstract
The time series prediction problem aimed at the implementation of a 'smart thermostat' is addressed. 'SARIMAX models' are compared with LSTM neural networks. We show that with a low amount of data used for training, SARIMAX models achieve significantly higher accuracy while maintaining high computational efficiency, so in a problem where it becomes necessary to implement the system on low-power embedded devices, these approaches have significant advantages over neural networks.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
