A Data-Driven Forecasting Strategy to Predict Continuous Hourly Energy Demand in Smart Buildings

Smart buildings seek to have a balance between energy consumption and occupant comfort. To make this possible, smart buildings need to be able to foresee sudden changes in the building’s energy consumption. With the help of forecasting models, building energy management systems, which are a fundamental part of smart buildings, know when sudden changes in the energy consumption pattern could occur. Currently, different forecasting methods use models that allow building energy management systems to forecast energy consumption. Due to this, it is increasingly necessary to have appropriate forecasting models to be able to maintain a balance between energy consumption and occupant comfort. The objective of this paper is to present an energy consumption forecasting strategy that allows hourly day-ahead predictions. The presented forecasting strategy is tested using real data from two buildings located in Valladolid, Spain. Different machine learning and deep learning models were used to analyze which could perform better with the proposed strategy. After establishing the performance of the models, a model was assembled using the mean of the prediction values of the top five models to obtain a model with better performance.

[1]  Krithi Ramamritham,et al.  A hybrid model for building energy consumption forecasting using long short term memory networks , 2020 .

[2]  Chang Soo Kim,et al.  Multi-Step Short-Term Power Consumption Forecasting Using Multi-Channel LSTM With Time Location Considering Customer Behavior , 2020, IEEE Access.

[3]  Yong Shi,et al.  A review of data-driven approaches for prediction and classification of building energy consumption , 2018 .

[4]  Dimitrios Tzovaras,et al.  Multi-Step Energy Demand and Generation Forecasting with Confidence Used for Specification-Free Aggregate Demand Optimization , 2021, Energies.

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

[6]  Junjing Yang,et al.  Building Energy Consumption Raw Data Forecasting Using Data Cleaning and Deep Recurrent Neural Networks , 2019 .

[7]  . Mustaqeem,et al.  Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach , 2021, IEEE Access.

[8]  Fan Zhang,et al.  A review on time series forecasting techniques for building energy consumption , 2017 .

[9]  Luis Hernández-Callejo,et al.  A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics , 2020, Applied Sciences.

[10]  Hazem Elzarka,et al.  Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold , 2019, Energy and Buildings.

[11]  Khalid Zine-Dine,et al.  Machine learning for energy consumption prediction and scheduling in smart buildings , 2020, SN Applied Sciences.

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

[13]  Lukumon O. Oyedele,et al.  Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings , 2020 .

[14]  Xianze Xu,et al.  A hybrid transfer learning model for short-term electric load forecasting , 2020, Electrical Engineering.

[15]  Xi Fang,et al.  A hybrid deep transfer learning strategy for short term cross-building energy prediction , 2021 .

[16]  Nadir Farah,et al.  Using deep learning for short-term load forecasting , 2020, Neural Computing and Applications.

[17]  Evangelos Spiliotis,et al.  The M4 Competition: 100,000 time series and 61 forecasting methods , 2020 .

[18]  Manuel Berenguel,et al.  A Comparison of Energy Consumption Prediction Models Based on Neural Networks of a Bioclimatic Building , 2016 .

[19]  Pedro Lara Benítez,et al.  Temporal convolutional networks applied to energy-related time series forecasting , 2020 .

[20]  Krithi Ramamritham,et al.  A deep learning framework for building energy consumption forecast , 2021 .

[21]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[22]  Yongjun Sun,et al.  Statistical investigations of transfer learning-based methodology for short-term building energy predictions , 2020 .

[23]  Eleni Mangina,et al.  A data-driven approach to optimize urban scale energy retrofit decisions for residential buildings , 2020, Applied Energy.

[24]  Nicolas Loeff,et al.  Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting , 2021, International Journal of Forecasting.

[25]  Eleni Mangina,et al.  Data-driven Predictive Control for Unlocking Building Energy Flexibility: A Review , 2020, ArXiv.

[26]  Namrye Son,et al.  Deep Neural Network and Long Short-Term Memory for Electric Power Load Forecasting , 2020, Applied Sciences.

[27]  Laurent L. Pauwels,et al.  Some Theoretical Results on Forecast Combinations , 2015 .

[28]  Yang Zhao,et al.  A hybrid deep learning-based method for short-term building energy load prediction combined with an interpretation process , 2020 .

[29]  Qiang Zhang,et al.  Research on short-term and ultra-short-term cooling load prediction models for office buildings , 2017 .

[30]  Seungmin Rho,et al.  Combination of short-term load forecasting models based on a stacking ensemble approach , 2020 .

[31]  Federico Divina,et al.  A Comparative Study of Time Series Forecasting Methods for Short Term Electric Energy Consumption Prediction in Smart Buildings , 2019, Energies.

[32]  Manuel Lopez-Martin,et al.  Novel Data-Driven Models Applied to Short-Term Electric Load Forecasting , 2021, Applied Sciences.

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

[34]  Huanling Hu,et al.  Forecasting energy consumption and wind power generation using deep echo state network , 2020 .

[35]  Michael I. Jordan,et al.  Machine learning: Trends, perspectives, and prospects , 2015, Science.

[36]  Xin Ma,et al.  Short-term prediction of building energy consumption employing an improved extreme gradient boosting model: A case study of an intake tower , 2020 .

[37]  De Xia,et al.  Effective energy consumption forecasting using empirical wavelet transform and long short-term memory , 2022 .

[38]  Jin Wen,et al.  A review of machine learning in building load prediction , 2021 .

[39]  R. Zmeureanu,et al.  A Review of Deep Learning Techniques for Forecasting Energy Use in Buildings , 2021, Energies.