Transfer learning with seasonal and trend adjustment for cross-building energy forecasting

Ribeiro, Mauro C. C.; Grolinger, Katarina; ElYamany, Hany F.; Higashino, Wilson A.; Capretz, Miriam A. M.

doi:10.1016/j.enbuild.2018.01.034

Cited by 153 publications

(60 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The forecasting models in previous studies [19][20][21][22][23][24]26] could not predict the electric loads for various buildings. However, our forecasting model predicts the electric loads for 15 buildings; consequently, it can be considered as a generalized forecasting model.…”

Section: Related Workmentioning

confidence: 92%

“…and confirmed that their proposed method outperformed ARIMA by 19.5%, SVR by 13.1%, and RNN by 6.5% in terms of the root mean square error. Ribeiro et al [24] proposed a transfer-learning method, called Hephaestus, for cross-building electric energy consumption forecasting based on time-series multi-feature regression with seasonal and trend adjustments. Hephaestus was applied in the pre-and post-processing phases; then, standard machine learning algorithms such as ANN and SVR were used.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods

et al. 2020

View full text Add to dashboard Cite

An energy-management system requires accurate prediction of the electric load for optimal energy management. However, if the amount of electric load data is insufficient, it is challenging to perform an accurate prediction. To address this issue, we propose a novel electric load forecasting scheme using the electric load data of diverse buildings. We first divide the electric energy consumption data into training and test sets. Then, we construct multivariate random forest (MRF)-based forecasting models according to each building except the target building in the training set and a random forest (RF)-based forecasting model using the limited electric load data of the target building in the test set. In the test set, we compare the electric load of the target building with that of other buildings to select the MRF model that is the most similar to the target building. Then, we predict the electric load of the target building using its input variables via the selected MRF model. We combine the MRF and RF models by considering the different electric load patterns on weekdays and holidays. Experimental results demonstrate that combining the two models can achieve satisfactory prediction performance even if the electric data of only one day are available for the target building.

show abstract

Section: Related Workmentioning

confidence: 92%

Section: Related Workmentioning

confidence: 99%

Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In scenarios of little historical data it can also be possible to exploit the fact that vast quantities of data may be available for similar buildings which may display similar dynamics. A transfer learning method for energy prediction is proposed in [80] for example, using time-series multi-feature regression with an allowance for seasonal and trend adjustments. In [81], a Deep Belief Network (DBN) (for feature extraction) is incorporated into a reinforcement learning-based approach to enable knowledge transfer to buildings without historical data.…”

Section: Modelling the Thermal Behaviour Of Buildingsmentioning

confidence: 99%

Smart energy systems for sustainable smart cities: Current developments, trends and future directions

et al. 2019

View full text Add to dashboard Cite

Within the context of the Smart City, the need for intelligent approaches to manage and coordinate the diverse range of supply and conversion technologies and demand applications has been well established. The wide-scale proliferation of sensors coupled with the implementation of embedded computational intelligence algorithms can help to tackle many of the technical challenges associated with this energy systems integration problem. Nonetheless, barriers still exist, as suitable methods are needed to handle complex networks of actors, often with competing objectives, while determining design and operational decisions for systems across a wide spectrum of features and time-scales. This review looks at the current developments in the smart energy sector, focussing on techniques in the main application areas along with relevant implemented examples, while highlighting some of the key challenges currently faced and outlining future pathways for the sector. A detailed overview of a framework developed for the EU H2020 funded Sharing Cities project is also provided to illustrate the nature of the design stages encountered and control hierarchies required. The study aims to summarise the current state of computational intelligence in the field of smart energy management, providing insight into the ways in which current barriers can be overcome.

show abstract

“…Our experimental results show that the proposed method outperforms current techniques for load forecasting. Authors in [12] has also applied transfer learning to forecast building energy consumption. They leverage the consumption data of similar buildings, and augment it to limited data of target building for which the model is trained.…”

mentioning

confidence: 99%

Energy Predictive Models with Limited Data using Transfer Learning

Hooshmand

Sharma

2019

Proceedings of the Tenth ACM International Conference on Future Energy Systems

View full text Add to dashboard Cite

In this paper, we consider the problem of developing predictive models with limited data for energy assets such as electricity loads, PV power generations, etc. We specifically investigate the cases where the amount of historical data is not sufficient to effectively train the prediction model. We first develop an energy predictive model based on convolutional neural network (CNN) which is well suited to capture the interaday, daily, and weekly cyclostationary patterns, trends and seasonalities in energy assets time series. A transfer learning strategy is then proposed to address the challenge of limited training data. We demonstrate our approach on a usecase of daily electricity demand forecasting. we show practicing the transfer learning strategy on the CNN model results in significant improvement to existing forecasting methods.Various prediction models are utilized in power and energy systems such as electricity load forecasting, PV prediction, wind generation estimation, etc. Applying machine learning techniques to develop prediction models is a well-established and active research field attracting considerable researchers motivated by the new advances in computational technologies and machine learning techniques. Current algorithms require to have enough historical data of the energy assets and customers for training models. In [15], a recurrent neural network is designed to predict 24 hour ahead PV power generation.

show abstract

Transfer learning with seasonal and trend adjustment for cross-building energy forecasting

Cited by 153 publications

References 36 publications

Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods

Solving the Cold-Start Problem in Short-Term Load Forecasting Using Tree-Based Methods

Smart energy systems for sustainable smart cities: Current developments, trends and future directions

Energy Predictive Models with Limited Data using Transfer Learning

Contact Info

Product

Resources

About