Accurate forecasting of building energy consumption via a novel ensembled deep learning method considering the cyclic feature

Abstract Short-term forecasting of building energy consumption (BEC) is significant for building energy reduction and real-time demand response. In this study, we propose a new method to realize half-hourly BEC prediction. In this new method, to fully utilize the existing data features and to further promote the forecasting performance, we divide the BEC data into the stable (cyclic) and stochastic components, and propose a novel hybrid model to model the stable and stochastic components respectively. The cyclic feature (CF) is extracted via the spectrum analysis, while the stochastic component is approximated by a novel Deep Belief Network (DBN) and Extreme Learning Machine (ELM) based ensembled model (DEEM). This novel hybrid model is named DEEM + CF. Furthermore, two real-world BEC experiments are performed to verify the proposed method. Also, to display the superiorities of the proposed DEEM + CF, this model is compared with the DBN, DBN + CF, ELM, ELM + CF, Support Vector Regression (SVR) and SVR + CF. Experimental results indicate that the CF has a great influence on the promotion of forecasting accuracy for approximately 20%, and DEEM + CF performance is the best among the comparative models, with at least 3%, 6%, 10% better accuracy than the DBN + CF, ELM + CF and SVR + CF respectively under the criteria of MAE.

[1]  Yongjun Sun,et al.  A collaborative control optimization of grid-connected net zero energy buildings for performance improvements at building group level , 2018, Energy.

[2]  Geoffrey E. Hinton,et al.  Using fast weights to improve persistent contrastive divergence , 2009, ICML '09.

[3]  Fang Liu,et al.  An Improved Fuzzy Neural Network for Traffic Speed Prediction Considering Periodic Characteristic , 2017, IEEE Transactions on Intelligent Transportation Systems.

[4]  Michael Wetter,et al.  Equation-based object-oriented modeling and simulation for data center cooling: A case study , 2019, Energy and Buildings.

[5]  Yanru Zhang,et al.  Hybrid short-term freeway speed prediction methods based on periodic analysis , 2015 .

[6]  Yan-Lin He,et al.  A novel prediction intervals method integrating an error & self-feedback extreme learning machine with particle swarm optimization for energy consumption robust prediction , 2018, Energy.

[7]  Chen Li,et al.  A novel hybrid forecasting scheme for electricity demand time series , 2020 .

[8]  Hong Liu,et al.  A path planning approach for crowd evacuation in buildings based on improved artificial bee colony algorithm , 2018, Appl. Soft Comput..

[9]  John Boland,et al.  Characterising Seasonality of Solar Radiation and Solar Farm Output , 2020, Energies.

[10]  Feras Al-Obeidat,et al.  Consistently accurate forecasts of temperature within buildings from sensor data using ridge and lasso regression , 2020, Future Gener. Comput. Syst..

[11]  Martin K. Patel,et al.  Evaluating the electricity saving potential of electrochromic glazing for cooling and lighting at the scale of the Swiss non-residential national building stock using a Monte Carlo model , 2019, Energy.

[12]  Aven Satre-Meloy,et al.  Investigating structural and occupant drivers of annual residential electricity consumption using regularization in regression models , 2019, Energy.

[13]  Yue Yuan,et al.  A novel energy demand prediction strategy for residential buildings based on ensemble learning , 2019, Energy Procedia.

[14]  Guoyin Fu,et al.  Deep belief network based ensemble approach for cooling load forecasting of air-conditioning system , 2018 .

[15]  Pei Huang,et al.  A collaborative demand control of nearly zero energy buildings in response to dynamic pricing for performance improvements at cluster level , 2019, Energy.

[16]  Li Bai,et al.  Performance predictions of ground source heat pump system based on random forest and back propagation neural network models , 2019, Energy Conversion and Management.

[17]  Konstantinos Gryllias,et al.  A semi-supervised Support Vector Data Description-based fault detection method for rolling element bearings based on cyclic spectral analysis , 2020, Mechanical Systems and Signal Processing.

[18]  Yisheng Lv,et al.  Data driven parallel prediction of building energy consumption using generative adversarial nets , 2019, Energy and Buildings.

[19]  Samuel Xavier de Souza,et al.  Spectrum sensing with a parallel algorithm for cyclostationary feature extraction , 2018, Comput. Electr. Eng..

[20]  Benjamin C. M. Fung,et al.  Systematic approach to provide building occupants with feedback to reduce energy consumption , 2020 .

[21]  Liyin Shen,et al.  The application of low-carbon city (LCC) indicators—A comparison between academia and practice , 2019, Sustainable Cities and Society.

[22]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[23]  Jan Kostrzewa.  Time series forecasting using clustering with periodic pattern , 2015, 2015 7th International Joint Conference on Computational Intelligence (IJCCI).

[24]  Wangda Zuo,et al.  A comprehensive review of energy-related data for U.S. commercial buildings , 2019, Energy and Buildings.

[25]  Guoqiang Zhang,et al.  Machine learning-based optimal design of a phase change material integrated renewable system with on-site PV, radiative cooling and hybrid ventilations—study of modelling and application in five climatic regions , 2020 .

[26]  Xiao Xue,et al.  Social Learning Evolution (SLE): Computational Experiment-Based Modeling Framework of Social Manufacturing , 2019, IEEE Transactions on Industrial Informatics.

[27]  Jinjun Tang,et al.  Short-term prediction of vehicle waiting queue at ferry terminal based on machine learning method , 2016 .

[28]  Jianqiang Yi,et al.  Deep Belief Network Based Hybrid Model for Building Energy Consumption Prediction , 2018 .

[29]  J. Boland,et al.  Nonparametric Conditional Heteroscedastic Hourly Probabilistic Forecasting of Solar Radiation , 2018, J.

[30]  Yunfei Ding,et al.  Cooling load prediction and optimal operation of HVAC systems using a multiple nonlinear regression model , 2019, Energy and Buildings.

[31]  Wangda Zuo,et al.  A methodology to create prototypical building energy models for existing buildings: A case study on U.S. religious worship buildings , 2019, Energy and Buildings.

[32]  Yang Zhao,et al.  Deep learning-based feature engineering methods for improved building energy prediction , 2019, Applied Energy.

[33]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[34]  Ozgur Kisi,et al.  A comparative study of several machine learning based non-linear regression methods in estimating solar radiation: Case studies of the USA and Turkey regions , 2020 .

[35]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[36]  John Boland.  Generation of Synthetic Sequences of Electricity Demand with Applications , 2009 .

[37]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[38]  Hoon Heo,et al.  Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach , 2015 .