Novel deep supervised ML models with feature selection approach for large-scale utilities and buildings short and medium-term load requirement forecasts

Abstract Accurate energy analyses and forecasts not only impact a nation’s energy stability/security and environment but also provide policymakers with a reliable framework for decision-making. The load forecast of buildings and electricity companies for the arrangement of risk/low-cost demand and supply resources that fulfill future government commitments, plans consumer targets, and respond appropriately for stockholders. This study introduces two novels deep supervised machine learning models, including: (i) fit Gaussian Kernel regression model with random feature expansion (RFEM-GKR); and (ii) non-parametric based k-NN (NPK-NNM) models for buildings and the utility companies load demand forecasts with a higher predictive potential, speed, and accuracy. Five-fold cross-validation is used to reduce prediction errors and to improve network generalization. Real-load consumption data from two different locations (utility company and office building) are used to analyze and validate the proposed models. Each location data is further divided into six different feature selection (MFS) states. Each state is composed of various (16, 19, 17, 09, 16, and 13) types of real-time energy consumption and climatic feature variables. The energy consumption behaviors are then analyzed in terms of the feature significance applied with 5 min, 30 min, and 1-h of time-based on short-, and medium-term intervals. Eleven distance metrics used to measure the number of the neighboring object and the number of objective functions of the model network for accuracy. With less computational time, higher precision, and high penetration levels of multiple input feature variables, the method RFEM-GKR is proven superior. Therefore, because of its high accuracy and stability, the proposed model can be a successful tool to predict energy consumption.

[1]  Yang Fuhua,et al.  Research on the Impact of Wind Angles on the Residential Building Energy Consumption , 2014 .

[2]  Maurice Bluestein,et al.  The New Wind Chill Equivalent Temperature Chart. , 2005 .

[3]  Dongwei Yu,et al.  A two-step approach to forecasting city-wide building energy demand , 2018 .

[4]  D. Sailor.  Relating residential and commercial sector electricity loads to climate : evaluating state level sensitivities and vulnerabilities , 2001 .

[5]  O. Hyde,et al.  An adaptable automated procedure for short-term electricity load forecasting , 1997 .

[6]  Arash Ghanbari,et al.  A Cooperative Ant Colony Optimization-Genetic Algorithm approach for construction of energy demand forecasting knowledge-based expert systems , 2013, Knowl. Based Syst..

[7]  Adel Akbarimajd,et al.  Two stage forecast engine with feature selection technique and improved meta-heuristic algorithm for electricity load forecasting , 2018, Energy.

[8]  Yun Li,et al.  The Use of Extreme Value Theory for Forecasting Long-Term Substation Maximum Electricity Demand , 2020, IEEE Transactions on Power Systems.

[9]  Alagan Anpalagan,et al.  Joint bagged-boosted artificial neural networks: Using ensemble machine learning to improve short-term electricity load forecasting , 2020 .

[10]  Wai K. Chong,et al.  Analyzing the Impact of Outside Temperature on Energy Consumption and Production Patterns in High-Performance Research Buildings in Arizona , 2017 .

[11]  Robert G. Quayle,et al.  Heating Degree Day Data Applied to Residential Heating Energy Consumption , 1980 .

[12]  Marc A. Rosen,et al.  Sizing a stand-alone solar-wind-hydrogen energy system using weather forecasting and a hybrid search optimization algorithm , 2019, Energy Conversion and Management.

[13]  Mehdi Khashei,et al.  A seasonal direct optimal hybrid model of computational intelligence and soft computing techniques for electricity load forecasting , 2017 .

[14]  Yacine Rezgui,et al.  Electrical load forecasting models: A critical systematic review , 2017 .

[15]  W. Charytoniuk,et al.  Nonparametric regression based short-term load forecasting , 1998 .

[16]  Chengzhi Deng,et al.  Sequential grid approach based support vector regression for short-term electric load forecasting , 2019, Applied Energy.

[17]  Tai-Yue Wang,et al.  Applying optimized BPN to a chaotic time series problem , 2007, Expert Syst. Appl..

[18]  Jing Liu,et al.  Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms , 2019 .

[19]  Ying Chen,et al.  Short-Term Load Forecasting: Similar Day-Based Wavelet Neural Networks , 2010, IEEE Transactions on Power Systems.

[20]  Huanxin Chen,et al.  A review on machine learning forecasting growth trends and their real-time applications in different energy systems , 2020 .

[21]  Tanveer Ahmad,et al.  Utility companies strategy for short-term energy demand forecasting using machine learning based models , 2018 .

[22]  Ali Doustmohammadi,et al.  Modeling and estimation of the natural gas consumption for residential and commercial sectors in Iran , 2010 .

[23]  Wen-Chen Chu,et al.  Multi-region short-term load forecasting in consideration of Heat Index and load/weather diversity , 2009, Conference Record 2009 IEEE Industrial & Commercial Power Systems Technical Conference.

[24]  Rob J Hyndman,et al.  Short-Term Load Forecasting Based on a Semi-Parametric Additive Model , 2012, IEEE Transactions on Power Systems.

[25]  Xiuwen Cai,et al.  Clustering-based short-term load forecasting for residential electricity under the increasing-block pricing tariffs in China , 2018, Energy.

[26]  Alagan Anpalagan,et al.  Boosted neural networks for improved short-term electric load forecasting , 2017 .

[27]  Ram Rajagopal,et al.  Household Energy Consumption Segmentation Using Hourly Data , 2014, IEEE Transactions on Smart Grid.

[28]  Saifur Rahman,et al.  A generalized knowledge-based short-term load-forecasting technique , 1993 .

[29]  Monjur Mourshed,et al.  Forecasting methods in energy planning models , 2018 .

[30]  M. Janicki.  Methods of weather variables introduction into short-term electric load forecasting models - a review , 2017 .

[31]  José Ramón Cancelo,et al.  Forecasting the electricity load from one day to one week ahead for the Spanish system operator , 2008 .

[32]  Ioannis P. Panapakidis,et al.  Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model , 2017 .

[33]  Seyed Farid Ghaderi,et al.  Energy demand forecasting in Iranian metal industry using linear and nonlinear models based on evolutionary algorithms , 2012 .

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

[35]  Tanveer Ahmad,et al.  A review on renewable energy and electricity requirement forecasting models for smart grid and buildings , 2020 .

[36]  Kevin R. Gurney,et al.  The variation of climate change impact on building energy consumption to building type and spatiotemporal scale , 2016 .

[37]  Junwei Lu,et al.  Short-term load forecasting for microgrid energy management system using hybrid HHO-FNN model with best-basis stationary wavelet packet transform , 2020 .

[38]  Sahm Kim,et al.  Short term electricity load forecasting for institutional buildings , 2019, Energy Reports.

[39]  Yang Bai,et al.  A recursive ensemble model for forecasting the power output of photovoltaic systems , 2019, Solar Energy.

[40]  R. Buizza,et al.  Using weather ensemble predictions in electricity demand forecasting , 2003 .

[41]  Fazil Kaytez,et al.  A hybrid approach based on autoregressive integrated moving average and least-square support vector machine for long-term forecasting of net electricity consumption , 2020 .

[42]  Shoji Takechi,et al.  Knowledge Based Sales Forecasting Model for Non-linear Trend Products , 2009 .

[43]  Turaj Amraee,et al.  A hybrid data mining driven algorithm for long term electric peak load and energy demand forecasting , 2020 .

[44]  Carlo Cattani,et al.  Multifractional Brownian motion and quantum-behaved particle swarm optimization for short term power load forecasting: An integrated approach , 2020 .

[45]  Florian Ziel,et al.  Forecasting wind power – Modeling periodic and non-linear effects under conditional heteroscedasticity , 2016, 1606.00546.

[46]  C. Yoo,et al.  A deep learning-based forecasting model for renewable energy scenarios to guide sustainable energy policy: A case study of Korea , 2020 .

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

[48]  Ahmed Z. Al-Garni,et al.  Modelling and forecasting monthly electric energy consumption in eastern Saudi Arabia using abductive networks , 1997 .

[49]  Tai-Hsin Huang,et al.  Dynamic demand for residential electricity in Taiwan under seasonality and increasing-block pricing , 2015 .

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

[51]  Xiaofeng Guo,et al.  Modeling and forecasting building energy consumption: A review of data-driven techniques , 2019, Sustainable Cities and Society.

[52]  Sancho Salcedo-Sanz,et al.  Feature selection in machine learning prediction systems for renewable energy applications , 2018, Renewable and Sustainable Energy Reviews.

[53]  Zhongyi Hu,et al.  Comprehensive learning particle swarm optimization based memetic algorithm for model selection in short-term load forecasting using support vector regression , 2014, Appl. Soft Comput..

[54]  Robert G. Steadman,et al.  A Universal Scale of Apparent Temperature , 1984 .

[55]  Kwonsik Song,et al.  An energy-cyber-physical system for personalized normative messaging interventions: Identification and classification of behavioral reference groups , 2020 .

[56]  Werner Kristjanpoller,et al.  Forecasting based on an ensemble Autoregressive Moving Average - Adaptive neuro - Fuzzy inference system – Neural network - Genetic Algorithm Framework , 2020 .

[57]  D. K. Chaturvedi.  Soft Computing: Applications to Electrical Engineering Problem , 2007 .

[58]  Benjamin C. M. Fung,et al.  A review of the-state-of-the-art in data-driven approaches for building energy prediction , 2020 .

[59]  Qihao Weng,et al.  Modeling the effect of climate change on building energy demand in Los Angeles county by using a GIS-based high spatial- and temporal-resolution approach , 2019, Energy.

[60]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .