Building Energy Load Forecasting using Deep Neural Networks
This work addresses energy management for sustainability by improving load forecasting accuracy, but it is incremental as it applies known deep learning techniques to a specific domain.
The paper tackled building energy load forecasting by applying LSTM and sequence-to-sequence deep neural networks to residential electricity data, finding that the S2S architecture performed well at both one-hour and one-minute resolutions while standard LSTM failed at the finer resolution, with results comparable to existing deep learning methods.
Ensuring sustainability demands more efficient energy management with minimized energy wastage. Therefore, the power grid of the future should provide an unprecedented level of flexibility in energy management. To that end, intelligent decision making requires accurate predictions of future energy demand/load, both at aggregate and individual site level. Thus, energy load forecasting have received increased attention in the recent past, however has proven to be a difficult problem. This paper presents a novel energy load forecasting methodology based on Deep Neural Networks, specifically Long Short Term Memory (LSTM) algorithms. The presented work investigates two variants of the LSTM: 1) standard LSTM and 2) LSTM-based Sequence to Sequence (S2S) architecture. Both methods were implemented on a benchmark data set of electricity consumption data from one residential customer. Both architectures where trained and tested on one hour and one-minute time-step resolution datasets. Experimental results showed that the standard LSTM failed at one-minute resolution data while performing well in one-hour resolution data. It was shown that S2S architecture performed well on both datasets. Further, it was shown that the presented methods produced comparable results with the other deep learning methods for energy forecasting in literature.