Predicting Commercial Building Energy Consumption Using a Multivariate Multilayered Long-Short Term Memory Time-Series Model

The global demand for energy has been steadily increasing due to population growth, urbanization, and industrialization. Numerous researchers worldwide are striving to create precise forecasting models for predicting energy consumption to manage supply and demand effectively. In this research, a time-series forecasting model based on multivariate multilayered long short-term memory (LSTM) is proposed for forecasting energy consumption and tested using data obtained from commercial buildings in Melbourne, Australia: the Advanced Technologies Center, Advanced Manufacturing and Design Center, and Knox Innovation, Opportunity, and Sustainability Center buildings. This research specifically identifies the best forecasting method for subtropical conditions and evaluates its performance by comparing it with the most commonly used methods at present, including LSTM, bidirectional LSTM, and linear regression. The proposed multivariate, multilayered LSTM model was assessed by comparing mean average error (MAE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE) values with and without labeled time. Results indicate that the proposed model exhibits optimal performance with improved precision and accuracy. Specifically, the proposed LSTM model achieved a decrease in MAE of 30%, RMSE of 25%, and MAPE of 20% compared with the LSTM method. Moreover, it outperformed the bidirectional LSTM method with a reduction in MAE of 10%, RMSE of 20%, and MAPE of 18%. Furthermore, the proposed model surpassed linear regression with a decrease in MAE by 2%, RMSE by 7%, and MAPE by 10%.These findings highlight the significant performance increase achieved by the proposed multivariate multilayered LSTM model in energy consumption forecasting.

[1]  A. Ragauskas,et al.  Urban mining from biomass, brine, sewage sludge, phosphogypsum and e-waste for reducing the environmental pollution: Current status of availability, potential, and technologies with a focus on LCA and TEA. , 2023, Environmental research.

[2]  Mi Young Lee,et al.  Towards Intelligent Building Energy Management: AI-based Framework for Power Consumption and Generation Forecasting , 2022, Energy and Buildings.

[3]  M. R-Moreno,et al.  An Analysis of the Energy Consumption Forecasting Problem in Smart Buildings Using LSTM , 2022, Sustainability.

[4]  A. McGough,et al.  Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption - A systematic review , 2022, Eng. Appl. Artif. Intell..

[5]  L. Hernández-Callejo,et al.  Comparative study of continuous hourly energy consumption forecasting strategies with small data sets to support demand management decisions in buildings , 2022, Energy Science & Engineering.

[6]  Han-Gyun Woo,et al.  Energy Consumption Forecasting in Korea Using Machine Learning Algorithms , 2022, Energies.

[7]  Daniel Fernández-Martínez,et al.  Multi-Step Hourly Power Consumption Forecasting in a Healthcare Building with Recurrent Neural Networks and Empirical Mode Decomposition , 2022, Sensors.

[8]  S. Chou,et al.  A hybrid RF-LSTM based on CEEMDAN for improving the accuracy of building energy consumption prediction , 2022, Energy and Buildings.

[9]  E. Mangina,et al.  Forecast electricity demand in commercial building with machine learning models to enable demand response programs , 2021, Energy and AI.

[10]  Adem Dalcali,et al.  Effects of COVID-19 on electric energy consumption in Turkey and ANN-based short-term forecasting , 2021, Turkish J. Electr. Eng. Comput. Sci..

[11]  Zita Vale,et al.  Ensemble learning for electricity consumption forecasting in office buildings , 2021, Neurocomputing.

[12]  Manisa Pipattanasomporn,et al.  Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks , 2020 .

[13]  Junhwa Hwang,et al.  Forecasting Electricity Consumption in Commercial Buildings Using a Machine Learning Approach , 2020, Energies.

[14]  Elliott Skomski,et al.  Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings , 2020 .

[15]  Ke Yu,et al.  LSTM-Based VAE-GAN for Time-Series Anomaly Detection , 2020, Sensors.

[16]  Lin Li,et al.  Nonlinear Dynamic Soft Sensor Modeling With Supervised Long Short-Term Memory Network , 2020, IEEE Transactions on Industrial Informatics.

[17]  Srivatsa Krishnaswamy,et al.  A Comparative Study and Analysis of Time Series Forecasting Techniques , 2020, SN Computer Science.

[18]  Ruth L. Steiner,et al.  AI-Based Campus Energy Use Prediction for Assessing the Effects of Climate Change , 2020, Sustainability.

[19]  Sung Wook Baik,et al.  Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework , 2020, Sensors.

[20]  Hieu Le,et al.  Neural network model for short-term and very-short-term load forecasting in district buildings , 2019, Energy and Buildings.

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

[22]  Changjun Li,et al.  Conventional models and artificial intelligence-based models for energy consumption forecasting: A review , 2019, Journal of Petroleum Science and Engineering.

[23]  Sung Wook Baik,et al.  Improving Electric Energy Consumption Prediction Using CNN and Bi-LSTM , 2019, Applied Sciences.

[24]  Cesare Alippi,et al.  Deep Learning for Time Series Forecasting: The Electric Load Case , 2019, CAAI Trans. Intell. Technol..

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

[26]  Nils Jakob Johannesen,et al.  Relative evaluation of regression tools for urban area electrical energy demand forecasting , 2019, Journal of Cleaner Production.

[27]  Tao Zhang,et al.  Forecasting Electricity Consumption Using an Improved Grey Prediction Model , 2018, Inf..

[28]  Houshang Darabi,et al.  Multivariate LSTM-FCNs for Time Series Classification , 2018, Neural Networks.

[29]  Angela Lee,et al.  The impact of occupants’ behaviours on building energy analysis: A research review , 2017 .

[30]  Sanyogita Manu,et al.  Field studies of thermal comfort across multiple climate zones for the subcontinent: India Model for Adaptive Comfort (IMAC) , 2016 .

[31]  K. Lomas,et al.  Hybrid ventilation for low energy building design in south China , 2009 .

[32]  V. Bianco,et al.  Electricity consumption forecasting in Italy using linear regression models , 2009 .

[33]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[34]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[35]  Zhiwei Ji,et al.  Detecting Anomalies in Time Series Data via a Meta-Feature Based Approach , 2018, IEEE Access.

[36]  A. Ragauskas,et al.  Rice straw as a feedstock for biofuels: Availability, recalcitrance, and chemical properties , 2018 .

[37]  Samer S. Saab,et al.  Univariate modeling and forecasting of energy consumption: the case of electricity in Lebanon , 2001 .