Prognozowanie z wykorzystaniem architektury sieci typu Transformer
[Transformers-based forecasters]

André Novaes (Department of Electrical & Computer Engineering, Univ. Coimbra, Portugal)


Meter-level load forecasting is crucial for efficient energy management and power system 
planning for Smart Grids (SGs), in tasks associated with regulation, dispatching, 
scheduling, and unit commitment of power grids. Although a variety of algorithms have been 
proposed and applied on the field, more accurate and robust models are still required: the 
overall utility cost of operations in SGs increases 10 million currency units if the load 
forecasting error increases 1%, and the mean absolute percentage error (MAPE) in 
forecasting is still much higher than 1%. Transformers have become the new state-of- 
the-art in a variety of tasks, including the ones in computer vision, natural language 
processing and time series forecasting, surpassing well established models such as 
convolutional and recurrent neural networks. In this talk, a new state-of-the-art 
Transformer-based algorithm for the meter-level load forecasting is presented. Results show 
that the Transformer surpassed the former state-of-the-art, LSTM, and the traditional 
benchmark, vanilla RNN, in all experiments by a margin of at least 13% in MAPE.

Based on: A.Novaes. R.Araújo, J.Figueiredo, L.Pavanelli, F.Roosevelt (2021) 
Transformers-based smart grid load forecasting: a new state-of-the-art on the smart meters 
in London dataset, ETFA-2021, forthcoming.