Combination of short-term load forecasting models based on a stacking ensemble approach

Abstract Building electric energy consumption forecasting is essential in establishing an energy operation strategy for building energy management systems. Because of recent developments of artificial intelligence hardware, deep neural network (DNN)-based electric energy consumption forecasting models yield excellent performances. However, constructing an optimal forecasting model using DNNs is difficult and time-consuming because several hyperparameters must be determined to obtain the best combination of neural networks. The determination of the number of hidden layers in the DNN model is challenging because it greatly affects the forecasting performance of the DNN models. In addition, the best number of hidden layers for one situation or domain is often not optimal for another domain. Hence, many efforts have been made to combine multiple DNN models with different numbers of hidden layers to achieve a better forecasting performance than that of an individual DNN model. In this study, we propose a novel scheme for the combination of short-term load forecasting models using a stacking ensemble approach (COSMOS), which enables the more accurate prediction of the building electric energy consumption. For this purpose, we first collected 15-min interval electric energy consumption data for a typical office building and split them into training, validation, and test datasets. We constructed diverse four-layer DNN-based forecasting models based on the training set and by considering the input variable configuration and training epochs. We selected optimal DNN parameters using the validation set and constructed four DNN-based forecasting models with various numbers of hidden layers. We developed a building electric energy consumption forecasting model using the test set and sliding window-based principal component regression for the calculation of the final forecasting value from the forecasting values of the four DNN models. To demonstrate the performance of our approach, we conducted several experiments using actual electric energy consumption data and verified that our model yields a better prediction performance than other forecasting methods.

[1]  Eenjun Hwang,et al.  Recurrent inception convolution neural network for multi short-term load forecasting , 2019, Energy and Buildings.

[2]  Yoshua Bengio,et al.  Practical Recommendations for Gradient-Based Training of Deep Architectures , 2012, Neural Networks: Tricks of the Trade.

[3]  Yi Song,et al.  Smart building energy management based on network occupancy sensing , 2018 .

[4]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[5]  Lino Guzzella,et al.  SHORT-TERM THERMAL AND ELECTRIC LOAD FORECASTING IN BUILDINGS , 2013 .

[6]  Seung-Il Moon,et al.  Very short-term load forecasting based on a pattern ratio in an office building , 2016 .

[7]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[8]  Eenjun Hwang,et al.  A short-term load forecasting scheme based on auto-encoder and random forest , 2018 .

[9]  Federico Silvestro,et al.  Electrical consumption forecasting in hospital facilities: An application case , 2015 .

[10]  Eenjun Hwang,et al.  2-Stage Electric Load Forecasting Scheme for Day-Ahead CCHP Scheduling , 2019, 2019 IEEE 13th International Conference on Power Electronics and Drive Systems (PEDS).

[11]  Eenjun Hwang,et al.  Forecasting power consumption for higher educational institutions based on machine learning , 2018, The Journal of Supercomputing.

[12]  Àngela Nebot,et al.  Hybrid methodologies for electricity load forecasting: Entropy-based feature selection with machine learning and soft computing techniques , 2015 .

[13]  Siddharth Suryanarayanan,et al.  An Artificial Neural Network in Short-Term Electrical Load Forecasting of a University Campus: A Case Study , 2013 .

[14]  J. Mikulik.  Energy Demand Patterns in an Office Building: A Case Study in Kraków (Southern Poland) , 2018, Sustainability.

[15]  Frank Hutter,et al.  Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves , 2015, IJCAI.

[16]  Michael J. Pazzani,et al.  A Principal Components Approach to Combining Regression Estimates , 1999, Machine Learning.

[17]  Saifur Rahman,et al.  Day-ahead building-level load forecasts using deep learning vs. traditional time-series techniques , 2019, Applied Energy.

[18]  Daniel L. Marino,et al.  Building energy load forecasting using Deep Neural Networks , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[19]  P. H. Nguyen,et al.  Agent-based control for building energy management in the smart grid framework , 2014, IEEE PES Innovative Smart Grid Technologies, Europe.

[20]  Le Zhang,et al.  Ensemble deep learning for regression and time series forecasting , 2014, 2014 IEEE Symposium on Computational Intelligence in Ensemble Learning (CIEL).

[21]  A. Ożadowicz,et al.  A New Concept of Active Demand Side Management for Energy Efficient Prosumer Microgrids with Smart Building Technologies , 2017 .

[22]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[23]  Jaime Lloret,et al.  A Survey on Electric Power Demand Forecasting: Future Trends in Smart Grids, Microgrids and Smart Buildings , 2014, IEEE Communications Surveys & Tutorials.

[24]  Olatunji Ruwase,et al.  Performance Modeling and Scalability Optimization of Distributed Deep Learning Systems , 2015, KDD.

[25]  Erin LeDell,et al.  Scalable Ensemble Learning and Computationally Efficient Variance Estimation , 2015 .

[26]  Zafar A. Khan,et al.  Load forecasting, dynamic pricing and DSM in smart grid: A review , 2016 .

[27]  Khuram Pervez Amber,et al.  Electricity consumption forecasting models for administration buildings of the UK higher education sector , 2015 .

[28]  Milos Manic,et al.  Building Energy Management Systems: The Age of Intelligent and Adaptive Buildings , 2016, IEEE Industrial Electronics Magazine.

[29]  S. Chatterjee,et al.  Regression Analysis by Example , 1979 .

[30]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[31]  Eenjun Hwang,et al.  A Short-Term Electric Load Forecasting Scheme Using 2-Stage Predictive Analytics , 2018, 2018 IEEE International Conference on Big Data and Smart Computing (BigComp).

[32]  Nashat T. AL-Jallad,et al.  Short-Term Forecasting for Energy Consumption through Stacking Heterogeneous Ensemble Learning Model , 2018, Energies.

[33]  A. Ferrer,et al.  PCA model building with missing data: New proposals and a comparative study , 2015 .

[34]  Eenjun Hwang,et al.  Hybrid Short-Term Load Forecasting Scheme Using Random Forest and Multilayer Perceptron , 2018, Energies.

[35]  Jose I. Bilbao,et al.  A review and analysis of regression and machine learning models on commercial building electricity load forecasting , 2017 .

[36]  Gaurav Pandey,et al.  A Comparative Analysis of Ensemble Classifiers: Case Studies in Genomics , 2013, 2013 IEEE 13th International Conference on Data Mining.

[37]  Kevin M. Smith,et al.  Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on performance accuracy , 2014 .

[38]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[39]  Fu Xiao,et al.  A short-term building cooling load prediction method using deep learning algorithms , 2017 .

[40]  George Edwards,et al.  A Review of Deep Learning Methods Applied on Load Forecasting , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[41]  Miriam A. M. Capretz,et al.  Energy Forecasting for Event Venues: Big Data and Prediction Accuracy , 2016 .

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

[43]  Ran Li,et al.  Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN , 2018, IEEE Transactions on Smart Grid.

[44]  Lachlan L. H. Andrew,et al.  Short-term residential load forecasting: Impact of calendar effects and forecast granularity , 2017 .

[45]  Heaton T. Jeff,et al.  Introduction to Neural Networks with Java , 2005 .

[46]  Michael J. Crawley,et al.  The R book , 2022 .

[47]  Leandro dos Santos Coelho,et al.  Enhanced ensemble structures using wavelet neural networks applied to short-term load forecasting , 2019, Eng. Appl. Artif. Intell..

[48]  Ashok K. Bhateja,et al.  ANN Based Distinguishing Attack on RC4 Stream Cipher , 2012, BIC-TA.

[49]  Guohai Liu,et al.  Building's electricity consumption prediction using optimized artificial neural networks and principal component analysis , 2015 .

[50]  Yibo Chen,et al.  Short-term prediction of electric demand in building sector via hybrid support vector regression , 2017 .

[51]  Hongseok Kim,et al.  Deep Neural Network Based Demand Side Short Term Load Forecasting , 2016 .

[52]  Ping Wang,et al.  Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose , 2018, PloS one.

[53]  Federico Divina,et al.  Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting , 2018 .