Data Modeling for Energy Forecasting Using Machine Learning

The consumption of energy in enormous amounts is one of the prime areas of concern for the researchers globally. The focus is on buildings as they are the biggest consumers of energy. The analysis of energy consumption pattern of buildings diverts our attention toward the heating, ventilation, and air conditioning system which according to studies accounts for maximum energy consumption within buildings. This research employs several regression techniques to predict the energy consumption of HVAC plants. The algorithms from various families of machine learning like linear models, function-based learning models, lazy learning techniques, and tree-based techniques were applied on the dataset obtained from a commercial building and the results were evaluated and compared based on performance metrics—root mean square error, mean square error, mean absolute error, and coefficient of determination. The interpretation of results obtained shows that K-nearest neighbor model from lazy learning family outperforms other regression models with reduced errors and improved accuracy.

[1]  George A. F. Seber,et al.  Linear regression analysis , 1977 .

[2]  Sergio Gil-Lopez,et al.  An energy-efficient predictive control for HVAC systems applied to tertiary buildings based on regression techniques , 2017 .

[3]  Monika Goyal,et al.  A Systematic Analysis for Energy Performance Predictions in Residential Buildings Using Ensemble Learning , 2020, Arabian Journal for Science and Engineering.

[4]  Chirag Deb,et al.  Using artificial neural networks to assess HVAC related energy saving in retrofitted office buildings , 2018 .

[5]  Damien Picard,et al.  Approximate model predictive building control via machine learning , 2018 .

[6]  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 .

[7]  Tianzhen Hong,et al.  A data-mining approach to discover patterns of window opening and closing behavior in offices , 2014 .

[8]  Rahul Thakur,et al.  Exploratory Analysis of Machine Learning Techniques to predict Energy Efficiency in Buildings , 2020, 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO).

[9]  Constantine Kontokosta,et al.  Applications of machine learning methods to identifying and predicting building retrofit opportunities , 2016 .

[10]  Paulo Carreira,et al.  Can HVAC really learn from users? A simulation-based study on the effectiveness of voting for comfort and energy use optimization , 2018, Sustainable Cities and Society.

[11]  Rabindra Nath Shaw,et al.  Predictive Data Analysis for Energy Management of a Smart Factory Leading to Sustainability , 2021 .

[12]  Andrew Kusiak,et al.  Predictive modeling and optimization of a multi-zone HVAC system with data mining and firefly algorithms , 2015 .

[13]  Jie Zhao,et al.  Occupant behavior and schedule modeling for building energy simulation through office appliance power consumption data mining , 2014 .

[14]  Lluís A. Belanche Muñoz,et al.  Developments in kernel design , 2013, ESANN.

[15]  Luis M. Candanedo,et al.  Data driven prediction models of energy use of appliances in a low-energy house , 2017 .

[16]  Miao Sun,et al.  Data partitioning and association mining for identifying VRF energy consumption patterns under various part loads and refrigerant charge conditions , 2017 .

[17]  Saifur Rahman,et al.  Power disaggregation of combined HVAC loads using supervised machine learning algorithms , 2018, Energy and Buildings.

[18]  Andrew Kusiak,et al.  Modeling and optimization of HVAC energy consumption , 2010 .

[19]  Kim F. Nimon,et al.  Understanding the Results of Multiple Linear Regression , 2013 .

[20]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[21]  Zhe Chen,et al.  A simplified HVAC energy prediction method based on degree-day , 2019, Sustainable Cities and Society.

[22]  Wai Oswald Chong,et al.  Building energy modeling (BEM) using clustering algorithms and semi-supervised machine learning approaches , 2016 .

[23]  Jui-Sheng Chou,et al.  Modeling heating and cooling loads by artificial intelligence for energy-efficient building design , 2014 .

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

[25]  Rabindra Nath Shaw,et al.  IOT based MPPT for Performance Improvement of Solar PV Arrays Operating under Partial Shade Dispersion , 2020, 2020 IEEE 9th Power India International Conference (PIICON).

[26]  Ziwei Li,et al.  An ANN-based fast building energy consumption prediction method for complex architectural form at the early design stage , 2019, Building Simulation.

[27]  Monika Goyal,et al.  Towards Prediction of Energy Consumption of HVAC Plants Using Machine Learning , 2020 .

[28]  Monika Goyal,et al.  Extreme Gradient Boosting Algorithm for Energy Optimization in buildings pertaining to HVAC plants , 2018, EAI Endorsed Trans. Energy Web.

[29]  Dominic T. J. O'Sullivan,et al.  The suitability of machine learning to minimise uncertainty in the measurement and verification of energy savings , 2018 .

[30]  Fu Xiao,et al.  Data mining in building automation system for improving building operational performance , 2014 .

[31]  Hyo Seon Park,et al.  Development of a new energy benchmark for improving the operational rating system of office buildings using various data-mining techniques , 2016 .

[32]  Francisco Martínez,et al.  A methodology for applying k-nearest neighbor to time series forecasting , 2019, Artificial Intelligence Review.