An electricity load forecasting model for Integrated Energy System based on BiGAN and transfer learning

Abstract Integrated Energy System (IES) is able to collaborate various energy systems and boost energy supply efficiency. To further facilitate the energy scheduling in IES, load forecasting model of the system is required to describe the conditions continuously on a future time span. While the IES is a service model with frequent in-and-out users which are always dynamically changed, thus the dataset for some new users is always not enough sufficient to build the predicting model. Most of present researches focus on model refinement and accuracy boosting but rarely consider such data lack problem in IES. To tackle this issue, an integrated load forecasting model based on Bidirectional Generative Adversarial Networks (BiGAN) data augmentation and transfer learning techniques is proposed in this paper. Ten different types of data-driven models including the proposed model have been compared on two cases, resident and commercial users, in order to carry out the ablation and contrast experiment. Accuracy with the presented model is 2.08% and 1.50% higher than the original model averagely on resident and commercial users respectively, proving the effectiveness of the new model. And impact of sample size is analyzed and disclosed the effect patterns of the two modules. Result shows that the two modules can flexibly couple with different predictive models and boost their efficiency on both resident and commercial cases on data missing problem. And load forecasting becomes feasible for users with fewer samples or even zero samples when adopting the proposed framework.

[1]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

[2]  Tao Yu,et al.  Deep transfer Q-learning with virtual leader-follower for supply-demand Stackelberg game of smart grid , 2017 .

[3]  Wei-Chiang Hong,et al.  Application of SVR with chaotic GASA algorithm in cyclic electric load forecasting , 2012 .

[4]  Jian Liu,et al.  Comparative study of posteriori decision-making methods when designing building integrated energy systems with multi-objectives , 2019, Energy and Buildings.

[5]  Fuad E. Alsaadi,et al.  A switching delayed PSO optimized extreme learning machine for short-term load forecasting , 2017, Neurocomputing.

[6]  Lelitha Vanajakshi,et al.  Short-term traffic flow prediction using seasonal ARIMA model with limited input data , 2015, European Transport Research Review.

[7]  Shanlin Yang,et al.  A deep learning model for short-term power load and probability density forecasting , 2018, Energy.

[8]  Qiang Wang,et al.  A novel hybridization of nonlinear grey model and linear ARIMA residual correction for forecasting U.S. shale oil production , 2018, Energy.

[9]  Hayit Greenspan,et al.  Synthetic data augmentation using GAN for improved liver lesion classification , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[10]  Derong Liu,et al.  Energy consumption prediction of office buildings based on echo state networks , 2016, Neurocomputing.

[11]  Mohd Tahir Ismail,et al.  Selecting Wavelet Transforms Model in Forecasting Financial Time Series Data Based on ARIMA Model , 2011 .

[12]  Constantine Bekas,et al.  BAGAN: Data Augmentation with Balancing GAN , 2018, ArXiv.

[13]  David Cox,et al.  Conditional Infilling GANs for Data Augmentation in Mammogram Classification , 2018, RAMBO+BIA+TIA@MICCAI.

[14]  P. Damrongkulkamjorn,et al.  Monthly energy forecasting using decomposition method with application of seasonal ARIMA , 2005, 2005 International Power Engineering Conference.

[15]  Zhe Chen,et al.  Optimal Operation of the Integrated Electrical and Heating Systems to Accommodate the Intermittent Renewable Sources , 2016 .

[16]  Ruzhu Wang,et al.  Performance analysis of an integrated energy storage and energy upgrade thermochemical solid–gas sorption system for seasonal storage of solar thermal energy , 2013 .

[17]  Wenbo Chen,et al.  Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform , 2019, Energy.

[18]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[19]  A. D'Amico,et al.  Building energy performance forecasting: A multiple linear regression approach , 2019, Applied Energy.

[20]  Luisa F. Cabeza,et al.  Modeling global and regional potentials for building-integrated solar energy generation , 2019, Energy and Buildings.

[21]  Yuexing Peng,et al.  An ensemble deep learning model for short-term load forecasting based on ARIMA and LSTM , 2019, 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm).

[22]  Weilin Li,et al.  Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildings , 2017 .

[23]  Yuval Elovici,et al.  DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[24]  Christopher Leckie,et al.  Robust and Accurate Short-Term Load Forecasting: A Cluster Oriented Ensemble Learning Approach , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[25]  Lu Zhao,et al.  Forecasting of global horizontal irradiance by exponential smoothing, using decompositions , 2015 .

[26]  Khaled Galal,et al.  A charging control strategy for active building-integrated thermal energy storage systems using frequency domain modeling , 2014 .

[27]  Qinghua Hu,et al.  Transfer learning for short-term wind speed prediction with deep neural networks , 2016 .

[28]  Chia-Nan Ko,et al.  Short-term load forecasting using lifting scheme and ARIMA models , 2011, Expert Syst. Appl..

[29]  G. Ahmadi,et al.  Multi-objective linear regression based optimization of full repowering a single pressure steam power plant , 2019, Energy.

[30]  Madeleine Gibescu,et al.  Deep learning for estimating building energy consumption , 2016 .

[31]  Ning Zhang,et al.  Probabilistic individual load forecasting using pinball loss guided LSTM , 2019, Applied Energy.

[32]  Miriam A. M. Capretz,et al.  Transfer learning with seasonal and trend adjustment for cross-building energy forecasting , 2018 .

[33]  Yi-Ming Wei,et al.  Short term electricity load forecasting using a hybrid model , 2018, Energy.

[34]  Qian Ai,et al.  Data augmentation strategy for small sample short‐term load forecasting of distribution transformer , 2020, International Transactions on Electrical Energy Systems.

[35]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[36]  Zhenhao Tang,et al.  The multi-objective optimization of combustion system operations based on deep data-driven models , 2019, Energy.

[37]  Hongzhan Nie,et al.  Hybrid of ARIMA and SVMs for Short-Term Load Forecasting , 2012 .

[38]  David J. Hill,et al.  Short-Term Residential Load Forecasting Based on Resident Behaviour Learning , 2018, IEEE Transactions on Power Systems.

[39]  I. Dincer,et al.  Life cycle assessment of integrated thermal energy storage systems in buildings: A case study in Canada , 2020 .

[40]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[41]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[42]  A. Prasad,et al.  Newer Classification and Regression Tree Techniques: Bagging and Random Forests for Ecological Prediction , 2006, Ecosystems.

[43]  Liwen Hu,et al.  Research of an integrated cooling system consisted of compression refrigeration and pump-driven heat pipe for data centers , 2019, Energy and Buildings.

[44]  Jun Wang,et al.  Crude oil price prediction model with long short term memory deep learning based on prior knowledge data transfer , 2019, Energy.

[45]  David J. Parsons,et al.  An improved wavelet–ARIMA approach for forecasting metal prices , 2014 .

[46]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[47]  Jaehee Lee,et al.  Short-Term Load Forecasting for a Single Household Based on Convolution Neural Networks Using Data Augmentation , 2019, Energies.

[48]  Yuan Zhang,et al.  Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network , 2019, IEEE Transactions on Smart Grid.