Forecasting the Short-Term Electricity Consumption of Building Using a Novel Ensemble Model

The accurate prediction approach of urban buildings’ electricity consumption is an important foundation for smart urban energy management. It provides a decision basis for reasonable electricity deployments upon different scenarios. Usually, a single model cannot solve linear and nonlinear problems that may occur in electricity consumption prediction effectively and may produce predictions with unsatisfactory accuracy and stability. Moreover, some prediction models are also poorly interpretable and generalized, which makes them difficult to be applied in practice. To overcome these problems, this paper proposes an ensemble prediction model called gravity gated recurrent unit electricity consumption model which integrates the gated recurrent unit model and the proposed logarithmic electricity consumption gravity model. The weights are derived from average mutual information and weighted entropy. We use two years (17 520 hours) electricity consumption of a five-star hotel building in Shanghai, China, as the study case to illustrate our approach, and apply nine common prediction models as the benchmarks to conduct the computational experiments and comparisons. Furthermore, we also employ the electricity consumption data of another type of building (office building) to evaluate the generalization capability of the proposed ensemble model. Our approach outperforms all benchmarks in terms of accuracy, stability, and generalization.

[1]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[2]  Bumshik Lee,et al.  Combining LSTM Network Ensemble via Adaptive Weighting for Improved Time Series Forecasting , 2018, Mathematical Problems in Engineering.

[3]  M. A. Rafe Biswas,et al.  Regression analysis for prediction of residential energy consumption , 2015 .

[4]  José Humberto Ablanedo-Rosas,et al.  Surrogate constraint normalization for the set covering problem , 2010, Eur. J. Oper. Res..

[5]  Danijela Nikolić,et al.  The impact of the mean daily air temperature change on electricity consumption , 2015 .

[6]  Shanlin Yang,et al.  A review of the decomposition methodology for extracting and identifying the fluctuation characteristics in electricity demand forecasting , 2017 .

[7]  Bing Dong,et al.  A hybrid model approach for forecasting future residential electricity consumption , 2016 .

[8]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[9]  Lior Rokach,et al.  Ensemble learning: A survey , 2018, WIREs Data Mining Knowl. Discov..

[10]  Lei Wu,et al.  Applying Machine Learning to Study the Relationship Between Electricity Consumption and Weather Variables Using Open Data , 2018, 2018 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[11]  Mohammad Yusri Hassan,et al.  Building electrical energy consumption forecasting analysis using conventional and artificial intelligence methods: A review , 2017 .

[12]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[13]  Mohamed A. Meguid,et al.  Robust ensemble learning framework for day-ahead forecasting of household based energy consumption , 2018 .

[14]  Tao Lu,et al.  Modeling and forecasting energy consumption for heterogeneous buildings using a physical -statistical approach , 2015 .

[15]  Md Maksudur Rahman,et al.  Understanding Dhaka city traffic intensity and traffic expansion using gravity model , 2017, 2017 20th International Conference of Computer and Information Technology (ICCIT).

[16]  Irena Koprinska,et al.  Multi-step forecasting for big data time series based on ensemble learning , 2019, Knowl. Based Syst..

[17]  Ronald L. Moy,et al.  Study guide for statistics for business and financial economics, second edition, Cheng F. Lee, John C. Lee & Alice C. Lee , 1999 .

[18]  Sachin Ahuja,et al.  Time Series Analysis and Prediction of Electricity Consumption of Health Care Institution Using ARIMA Model , 2016, SocProS.

[19]  Stphane Tuffry,et al.  Data Mining and Statistics for Decision Making , 2011 .

[20]  Shanlin Yang,et al.  Multivariate statistical and similarity measure based semiparametric modeling of the probability distribution: A novel approach to the case study of mid-long term electricity consumption forecasting in China , 2015 .

[21]  Milan Prodanovic,et al.  Estimation and Analysis of Building Energy Demand and Supply Costs , 2015 .

[22]  C. Giannakopoulos,et al.  Modelling the energy demand projection of the building sector in Greece in the 21st century , 2012 .

[23]  R. Ramos,et al.  A Gravity Model of Migration between Enc and EU , 2013, SSRN Electronic Journal.

[24]  Flora D. Salim,et al.  Multi-resolution Selective Ensemble Extreme Learning Machine for Electricity Consumption Prediction , 2017, ICONIP.

[25]  Volker Gollnick,et al.  A global gravity model for air passenger demand between city pairs and future interurban air mobility markets identification. , 2018, 2018 Aviation Technology, Integration, and Operations Conference.

[26]  Fangdan Zheng,et al.  A novel data-driven approach for residential electricity consumption prediction based on ensemble learning , 2018 .

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

[28]  Meng Shen,et al.  Household Electricity Consumption Prediction Under Multiple Behavioural Intervention Strategies Using Support Vector Regression , 2017 .

[29]  Evangelos Spiliotis,et al.  Statistical and Machine Learning forecasting methods: Concerns and ways forward , 2018, PloS one.

[30]  Airfares 2002Q,et al.  MULTIPLE LINEAR REGRESSION , 2006, Statistical Methods for Biomedical Research.

[31]  V. R. Dehkordi,et al.  Hourly prediction of a building's electricity consumption using case-based reasoning, artificial neural networks and principal component analysis , 2015 .

[32]  Terri L. Moore,et al.  Regression Analysis by Example , 2001, Technometrics.

[33]  Yousef Mohammadi,et al.  A hybrid Genetic Algorithm and Monte Carlo simulation approach to predict hourly energy consumption and generation by a cluster of Net Zero Energy Buildings , 2016 .

[34]  Yueren Wang,et al.  A novel ensemble learning approach to support building energy use prediction , 2018 .

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

[36]  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.

[37]  S. Diestel,et al.  The Detection of Heteroscedasticity in Regression Models for Psychological Data , 2016 .

[38]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[39]  R. Gray.  Entropy and Information Theory , 1990, Springer New York.

[40]  Karen Kafadar,et al.  Letter-Value Plots: Boxplots for Large Data , 2017 .

[41]  Zeyu Wang,et al.  A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models , 2017 .

[42]  James A. Dirks,et al.  Impacts of climate change on energy consumption and peak demand in buildings: A detailed regional approach , 2015 .

[43]  Miguel Molina-Solana,et al.  Data science for building energy management: A review , 2017 .

[44]  S. Saeedeh Sadegh,et al.  Forecasting energy consumption using ensemble ARIMA-ANFIS hybrid algorithm , 2016 .

[45]  R. Stott,et al.  The World Bank , 2008, Annals of tropical medicine and parasitology.

[46]  Carlos Rubio-Bellido,et al.  Comparison of linear regression and artificial neural networks models to predict heating and cooling energy demand, energy consumption and CO2 emissions , 2017 .

[47]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.