Forecasting peak energy demand for smart buildings

Predicting energy consumption in buildings plays an important part in the process of digital transformation of the built environment, and for understanding the potential for energy savings. This also contributes to reducing the impact of climate change, where buildings need to increase their adaptability and resilience while reducing energy consumption and maintain user comfort. The use of Internet of Things devices for monitoring and control of energy consumption in buildings can take into account user preferences, event monitoring and building optimization. Detecting peak energy demand from historical building data can enable users to manage their energy use more efficiently, while also enabling real-time response strategies (including control and actuation) to known or future scenarios. Several statistical, time series, and machine learning techniques are proposed in this work to predict electricity consumption for five different building types, by using peak demand forecasting to achieve energy efficiency. We have used several indigenous and exogenous variables with a view to test different energy forecasting scenarios. The suggested techniques are evaluated for creating predictive models, including linear Regression, dynamic regression, ARIMA time series, exponential smoothing time series, artificial neural network, and deep neural network. We conduct the analysis on an energy consumption dataset of five buildings from 2014 until 2019. Our results show that for a day ahead prediction, the ARIMA model outperforms the other approaches with an accuracy of 98.91% when executed over a 168 h (1 week) of uninterrupted data for five government buildings.

[1]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[2]  Wontae Kim,et al.  Effect of length of measurement period on accuracy of predicted annual heating energy consumption of buildings , 2004 .

[3]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

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

[5]  Abdul Salam Shah,et al.  A Review on Energy Consumption Optimization Techniques in IoT Based Smart Building Environments , 2019, Inf..

[6]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[7]  Antonio F. Gómez-Skarmeta,et al.  Big data: the key to energy efficiency in smart buildings , 2015, Soft Computing.

[8]  Omer F. Rana,et al.  Predicting the energy demand of buildings during triad peaks in GB , 2017 .

[9]  Soniya Ghorbani.  Anomaly Detection in Electricity Consumption Data , 2017 .

[10]  Shahzad Muzaffar,et al.  Short-Term Load Forecasts Using LSTM Networks , 2019, Energy Procedia.

[11]  Song Chen,et al.  Research on neural network optimization algorithm for building energy consumption prediction , 2018, J. Comput. Methods Sci. Eng..

[12]  Shihab S Asfour,et al.  Short-Term Electrical Peak Demand Forecasting in a Large Government Building Using Artificial Neural Networks , 2014 .

[13]  M. Kottek,et al.  Comments on: The thermal zones of the Earth by Wladimir Köppen (1884) , 2011 .

[14]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[15]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..

[16]  Chunfeng Yang,et al.  Utilizing artificial neural network to predict energy consumption and thermal comfort level: an indoor swimming pool case study , 2014 .

[17]  B.M. Flax.  Intelligent buildings , 1991, IEEE Communications Magazine.

[18]  Aderemi Oluyinka Adewumi,et al.  Solving Dynamic Traveling Salesman Problem Using Dynamic Gaussian Process Regression , 2014, J. Appl. Math..

[19]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[20]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[21]  Saeed Ur Rehman,et al.  Prediction of Electricity Consumption for Residential Houses in New Zealand , 2018, SmartGIFT.

[22]  Marko Laine,et al.  Introduction to Dynamic Linear Models for Time Series Analysis , 2019, Geodetic Time Series Analysis in Earth Sciences.

[23]  George A Xydis,et al.  An R-based forecasting approach for efficient demand response strategies in autonomous micro-grids , 2018, Energy & Environment.

[24]  Atsushi Yamada,et al.  On-line prediction for load profile of an air-conditioning system , 1995 .

[25]  Kok Wai Wong,et al.  Predicting Electricity Consumption using Deep Recurrent Neural Networks , 2019, ArXiv.

[26]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[27]  Lars Nolting,et al.  How to model European electricity load profiles using artificial neural networks , 2020 .

[28]  Harshit Saxena,et al.  Forecasting Strategies for Predicting Peak Electric Load Days , 2017 .

[29]  J. A. White,et al.  Simplified method for predicting building energy consumption using average monthly temperatures , 1996, IECEC 96. Proceedings of the 31st Intersociety Energy Conversion Engineering Conference.

[30]  E. H. Barakat,et al.  New model for peak demand forecasting applied to highly complex load characteristics of a fast developing area , 1992 .

[31]  Yacine Rezgui,et al.  A modular optimisation model for reducing energy consumption in large scale building facilities , 2014 .

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

[33]  Kevin Kok Wai Wong,et al.  Language Modeling through Long-Term Memory Network , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[34]  Haisheng Chen,et al.  Progress in electrical energy storage system: A critical review , 2009 .

[35]  Kung-Sik Chan,et al.  Time Series Analysis: With Applications in R , 2010 .

[36]  Aderemi Oluyinka Adewumi,et al.  Comparison of ARIMA and Artificial Neural Networks Models for Stock Price Prediction , 2014, J. Appl. Math..

[37]  Maria del Carmen Pegalajar Jiménez,et al.  An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings , 2016 .

[38]  Roger H. French,et al.  Building electricity consumption: Data analytics of building operations with classical time series decomposition and case based subsetting , 2018, Energy and Buildings.

[39]  A. J. Hoffman.  Peak demand control in commercial buildings with target peak adjustment based on load forecasting , 1998, Proceedings of the 1998 IEEE International Conference on Control Applications (Cat. No.98CH36104).

[40]  Nadeem Javaid,et al.  Energy Efficiency Using Genetic and Crow Search Algorithms in Smart Grid , 2017, 3PGCIC.

[41]  Guy R. Newsham,et al.  Building-level occupancy data to improve ARIMA-based electricity use forecasts , 2010, BuildSys '10.

[42]  Yoseba K. Penya,et al.  Efficient building load forecasting , 2011, ETFA2011.

[43]  Rob J Hyndman,et al.  Automatic Time Series Forecasting: The forecast Package for R , 2008 .

[44]  James W. Taylor.  An evaluation of methods for very short-term load forecasting using minute-by-minute British data , 2008 .

[45]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[46]  Lei Wang,et al.  Study on Power Energy Consumption Model for Large-Scale Public Building , 2010, 2010 2nd International Workshop on Intelligent Systems and Applications.

[47]  Viktor Majer.  PREPARING AND ANALYSIS OF ELECTRICITY CONSUMPTION DATA FOR SHORT TERM PREDICTION , 2011 .

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

[49]  Jian LUO,et al.  Real-time anomaly detection for very short-term load forecasting , 2018 .

[50]  Kesheng Wang,et al.  LSTM Based Prediction and Time-Temperature Varying Rate Fusion for Hydropower Plant Anomaly Detection: A Case Study , 2018 .