Deep Recurrent Neural Network-Based Forecasting of Electricity Consumption and Anomalies Detection

Waqas Ahmed; Tayyab Ali; Bacha Hussain Bukhari; Amjad Khattak

Authors

Waqas Ahmed Department of Electrical and Power Engineering, University of Engineering & Technology, Peshawar
Tayyab Ali Department of Electrical and Power Engineering, Iqra National University, Peshawar
Bacha Hussain Bukhari Department of Mechatronics Engineering, University of Engineering & Technology, Peshawar
Amjad Khattak Department of Electrical and Power Engineering, University of Engineering & Technology, Peshawar

Keywords:

Forecasting, Energy Efficiency, Predictive Modeling, Building Energy Monitoring, Energy-saving Strategies, Anomaly Identification

Abstract

The construction industry is among the greatest fuel consumers of the world and a major source of carbon dioxide. Owing to this, the environmental effect can be minimized when focusing on conserving energy in buildings. Misuse of energy in the effort of equipment and errors of humans in the work is never considered budget. The use of smart buildings will address this problem since it will track the use of energy, detect abnormal behavior, and remind the managers that they are supposed to take energy-conservation actions. The current paper considers the issue of anomaly detection in the hourly electricity consumption level on a real basis and gives a two-step process with a Long Short-Term Memory (LSTM) network. In the first step, there will be forecasting of energy consumption, and, following this, the anomalies will be identified with the assistance of an LSTM Autoencoder. The article draws comparisons between highly complex time-dependent feature extraction algorithms like Rough Autoencoder (RAE), Deep Temporal Dictionary Learning (DTDL). The other algorithms could not perform better than the proposed method, the range of R-squared value was 95.11, MAE was 38.5, the MSE was 2448.94, and the RMSE was 49.49. Besides, the paper evaluates the means through which the AI-based anomaly detection solutions can provide forecasts of the electricity consumption, and the LSTM networks and autoencoders were tested to be more appropriate in forecasting the electricity consumption than the other deep learning algorithms.

References

V. K. Varun Chandola,Arindam Banerjee, “Anomaly detection: A survey,” ACM Comput. Surv., vol. 41, no. 3, pp. 1–58, 2009, doi: https://doi.org/10.1126/science.1235338.

P. P. B Peak, “Peak Electrical Energy Consumption Prediction by ARIMA, LSTM, GRU, ARIMA-LSTM and ARIMA-GRU Approaches,” Energies, vol. 16, no. 12, p. 4739, 2023, doi: https://doi.org/10.3390/en16124739.

H. Janetzko, F. Stoffel, S. Mittelstädt, and Daniel A. Keim, “Anomaly detection for visual analytics of power consumption data,” Comput. Graph., vol. 38, pp. 27–37, 2014, doi: https://doi.org/10.1016/j.cag.2013.10.006.

M. Wrinch, T. H. M. El-Fouly, and S. Wong, “Anomaly detection of building systems using energy demand frequency domain analysis,” IEEE Power Energy Soc. Gen. Meet., 2012, doi: 10.1109/PESGM.2012.6344790.

B. S. M. David J. Hill, “Anomaly detection in streaming environmental sensor data: A data-driven modeling approach,” Environ. Model. Softw., vol. 25, no. 9, pp. 1014–1022, 2010, doi: https://doi.org/10.1016/j.envsoft.2009.08.010.

O. D.-P. Angel L. Zorita, Miguel A. Fernández-Temprano, Luis-Angel García-Escudero, “A statistical modeling approach to detect anomalies in energetic efficiency of buildings,” Energy Build., vol. 110, pp. 377–386, 2016, doi: https://doi.org/10.1016/j.enbuild.2015.11.005.

J. Ploennigs, B. Chen, A. Schumann, and N. Brady, “Exploiting generalized additive models for diagnosing abnormal energy use in buildings,” BuildSys 2013 - Proc. 5th ACM Work. Embed. Syst. Energy-Efficient Build., Nov. 2013, doi: 10.1145/2528282.2528291.

and T. L. Y. Jiang, C. Zeng, J. Xu, “Real time contextual collective anomaly detection over multiple data streams,” Work. Outlier Detect. Descr. under Data Divers, 2014.

K. Hollingsworth et al., “Energy Anomaly Detection with Forecasting and Deep Learning,” Proc. - 2018 IEEE Int. Conf. Big Data, Big Data 2018, pp. 4921–4925, Jul. 2018, doi: 10.1109/BIGDATA.2018.8621948.

P. Malhotra, L. Vig, G. M. Shroff, and P. Agarwal, “Long Short Term Memory Networks for Anomaly Detection in Time Series,” Eur. Symp. Artif. Neural Networks, 2015.

N.-A. L.-K. Loic Bontemps, Van Loi Cao, James McDermott, “Collective Anomaly Detection based on Long Short Term Memory Recurrent Neural Network,” arXiv:1703.09752, 2017, doi: https://doi.org/10.48550/arXiv.1703.09752.

S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” Proc. - 17th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2018, pp. 1394–1401, Jul. 2018, doi: 10.1109/ICMLA.2018.00227.

Y. Himeur, A. Alsalemi, F. Bensaali, and A. Amira, “Smart power consumption abnormality detection in buildings using micromoments and improved K-nearest neighbors,” Int. J. Intell. Syst., vol. 36, no. 6, pp. 2865–2894, Jun. 2021, doi: 10.1002/INT.22404;JOURNAL:JOURNAL:1098111X;WGROUP:STRING:PUBLICATION.

C. L. Yun Bai, Jingjing Xie, Chao Liu, Ying Tao, Bo Zeng, “Regression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants,” Int. J. Electr. Power Energy Syst., vol. 126, p. 106612, 2021, doi: https://doi.org/10.1016/j.ijepes.2020.106612.

A. A. Yassine Himeur, “A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks,” Cognit. Comput., vol. 12, pp. 1381–1401, 2020, doi: https://doi.org/10.1007/s12559-020-09764-y.

M. I. Khawaja Moyeez Ullah Ghori, “Performance analysis of machine learning classifiers for non-technical loss detection,” J. Ambient Intell. Humaniz. Comput., vol. 14, no. 11, 2020, doi: 10.1007/s12652-019-01649-9.

J. Pereira and M. Silveira, “Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention,” Proc. - 17th IEEE Int. Conf. Mach. Learn. Appl. ICMLA 2018, pp. 1275–1282, Jul. 2018, doi: 10.1109/ICMLA.2018.00207.

S. Touzani, J. Granderson, and S. Fernandes, “Gradient boosting machine for modeling the energy consumption of commercial buildings,” Energy Build., vol. 158, pp. 1533–1543, 2018, doi: https://doi.org/10.1016/j.enbuild.2017.11.039.

J. W. Cheng Fan, Fu Xiao, Yang Zhao, “Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data,” Appl. Energy, vol. 211, pp. 1123–1135, 2018, doi: https://doi.org/10.1016/j.apenergy.2017.12.005.

M. W. Diederik P. Kingma, “An Introduction to Variational Autoencoders,” arXiv:1906.02691, 2019, doi: https://doi.org/10.48550/arXiv.1906.02691.