Issue

Vol. 8, No. 2, May 2023

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Forecasting Model for Lighting Electricity Load with a Limited Dataset using XGBoost

https://doi.org/10.22219/kinetik.v8i2.1687
Maman Abdurohman
Telkom University
Aji Gautama Putrada
Telkom University

Corresponding Author(s) : Maman Abdurohman

abdurohman@telkomuniversity.ac.id

Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Vol. 8, No. 2, May 2023

Abstract

Energy forecasting is an important application of machine learning in renewable energy because it is used for operational, management, and planning purposes. However, using the electricity load dataset during COVID-19 is a research challenge in the forecasting model due to the limited dataset and non-stationarity. This paper proposes an extreme gradient boosting (XGBoost) forecasting model for a limited dataset. Forecasting models require large amounts of data to create high-accuracy models. We conduct research using the PT Biofarma office electricity usage dataset for eight months during the COVID-19 period. Because office activities were limited during the pandemic, the datasets obtained were few. Several methods are used for modeling limited datasets, namely XGBoost, multi-layer perceptron (MLP), autoregressive integrated moving average (ARIMA), and long short-term memory (LSTM). We have conducted several experiments using a limited dataset with these four methods. The test results with the t-test show that the electricity load data for work-from-office (WFO) and work-from-home (WFH) periods have a significant average difference. Then the test results with the augmented Dickey–Fuller (ADF) test show that our data is non-stationary. Compared to the benchmark method, the XGBoost method shows the best forecasting performance with mean absolute percentage error (MAPE), root mean squared error (RMSE), mean absolute error (MAE), and R2 of 0.48, 5.00, 3.09, and 0.61 respectively.

Keywords

Extreme Gradient Boosting Electricity Load Forecasting COVID-19 Limited Dataset
Abdurohman, M. ., & Putrada, A. G. (2023). Forecasting Model for Lighting Electricity Load with a Limited Dataset using XGBoost. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 8(2). https://doi.org/10.22219/kinetik.v8i2.1687
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
References
  1. X. Wei, H. Ren, S. Ullah, and C. Bozkurt, “Does environmental entrepreneurship play a role in sustainable green development? Evidence from emerging Asian economies,” Econ. Res.-Ekon. Istraživanja, vol. 36, no. 1, pp. 73–85, 2023. https://doi.org/10.1080/1331677x.2022.2067887.
  2. L. Zhang et al., “A review of machine learning in building load prediction,” Appl. Energy, vol. 285, p. 116452, Mar. 2021. http://doi.org/10.1016/j.apenergy.2021.116452
  3. H. Wang, Z. Lei, X. Zhang, B. Zhou, and J. Peng, “A review of deep learning for renewable energy forecasting,” Energy Convers. Manag., vol. 198, p. 111799, 2019. https://doi.org/10.5958/2278-4853.2021.00832.6.
  4. Z. Shao, S. Yang, F. Gao, K. Zhou, and P. Lin, “A new electricity price prediction strategy using mutual information-based SVM-RFE classification,” Renew. Sustain. Energy Rev., vol. 70, pp. 330–341, Apr. 2017. http://doi.org/10.1016/j.rser.2016.11.155.
  5. C. Robinson et al., “Machine learning approaches for estimating commercial building energy consumption,” Appl. Energy, vol. 208, pp. 889–904, Dec. 2017. http://doi.org/10.1016/j.apenergy.2017.09.060.
  6. A. I. Arvanitidis, D. Bargiotas, D. Kontogiannis, A. Fevgas, and M. Alamaniotis, “Optimized Data-Driven Models for Short-Term Electricity Price Forecasting Based on Signal Decomposition and Clustering Techniques,” Energies, vol. 15, no. 21, Art. no. 21, Jan. 2022. https://doi.org/10.3390/en15217929.
  7. M. Askari and F. Keynia, “Mid-term electricity load forecasting by a new composite method based on optimal learning MLP algorithm,” IET Gener. Transm. Distrib., vol. 14, no. 5, pp. 845–852, 2020. https://doi.org/10.1049/iet-gtd.2019.0797.
  8. B. Nepal, M. Yamaha, A. Yokoe, and T. Yamaji, “Electricity load forecasting using clustering and ARIMA model for energy management in buildings,” Jpn. Archit. Rev., vol. 3, no. 1, pp. 62–76, 2020. https://doi.org/10.1002/2475-8876.12135.
  9. R. E. Alden, H. Gong, C. Ababei, and D. M. Ionel, “LSTM forecasts for smart home electricity usage,” in 2020 9th International conference on renewable energy research and application (ICRERA), 2020, pp. 434–438. https://doi.org/10.1109/icrera49962.2020.9242804.
  10. C. Donnat and S. Holmes, “Modeling the heterogeneity in COVID-19’s reproductive number and its impact on predictive scenarios,” J. Appl. Stat., pp. 1–29, 2021. https://doi.org/10.1080/02664763.2021.1941806.
  11. S. F. Pane, Heriyanto, A. G. Putrada, N. Alamsyah, and M. N. Fauzan, “The Influence of The COVID-19 Pandemics in Indonesia On Predicting Economic Sectors,” in 2022 Seventh International Conference on Informatics and Computing (ICIC), Dec. 2022, pp. 1–6. http://doi.org/10.1109/ICIC56845.2022.10006897.
  12. R. Chandra, A. Jain, and D. S. Chauhan, “Deep learning via LSTM models for COVID-19 infection forecasting in India,” PLOS ONE, vol. 17, no. 1, p. e0262708, Jan. 2022. http://doi.org/10.1371/journal.pone.0262708.
  13. M. H. A. Zamzuri, N. Sofian, and R. Hassan, “The Forecasting of Poverty using the Ensemble Learning Classification Methods,” Int. J. Perceptive Cogn. Comput., vol. 9, no. 1, pp. 24–32, 2023. https://doi.org/10.31436/ijpcc.v9i1.326.
  14. X. Zhao, Q. Li, W. Xue, Y. Zhao, H. Zhao, and S. Guo, “Research on Ultra-Short-Term Load Forecasting Based on Real-Time Electricity Price and Window-Based XGBoost Model,” Energies, vol. 15, no. 19, p. 7367, 2022. https://doi.org/10.3390/en15197367.
  15. C. Li et al., “Power load forecasting based on the combined model of LSTM and XGBoost,” in Proceedings of the 2019 the international conference on pattern recognition and artificial intelligence, 2019, pp. 46–51. https://doi.org/10.1145/3357777.3357792.
  16. M. Xue, L. Wu, Q. P. Zhang, J. X. Lu, X. Mao, and Y. Pan, “Research on load forecasting of charging station based on XGBoost and LSTM model,” in Journal of Physics: Conference Series, 2021, vol. 1757, no. 1, p. 012145. https://doi.org/10.1088/1742-6596/1757/1/012145.
  17. T. U. Wiganarto, A. Asenar, and E. Gultom, “Legal Aspects of Business Competition in the Procurement of Covid-19 Vaccine by Bio Farma Ltd,” Kanun J. Ilmu Huk., vol. 23, no. 2, pp. 193–209, 2021. https://doi.org/10.24815/kanun.v23i2.20416.
  18. A. G. Putrada, N. G. Ramadhan, and M. A. Makky, “An evaluation of activity recognition with hierarchical hidden Markov model and other methods for smart lighting in office buildings,” ICIC Int., 2022. http://doi.org/10.24507/icicel.16.01.91.
  19. S. Midesia, “Dampak Covid-19 Pada Pasar Saham Syariah Di Indonesia,” J. Penelit. Ekon. Akunt. JENSI, vol. 4, no. 1, pp. 68–79, 2020. https://doi.org/10.33059/jensi.v4i1.2663.
  20. F. Nataliia, H. Yevgen, K. Artem, S. Denys, and H. Iryna, “Electric Meters Monitoring System for Residential Buildings,” Adv. Intell. Syst. Comput. Sci. Digit. Econ. IV, pp. 173–185, 2023. https://doi.org/10.1007/978-3-031-24475-9_15.
  21. M. Abdurohman, A. G. Putrada, S. Prabowo, C. W. Wijiutomo, and A. Elmangoush, “M2M device connectivity framework,” Int. J. Electr. Eng. Inform., vol. 9, no. 3, pp. 441–454, 2017. https://doi.org/10.15676/ijeei.2017.9.3.2.
  22. M. Abdurohman, A. G. Putrada, S. Prabowo, C. W. Wijiutomo, and A. Elmangoush, “Integrated lighting enabler system using M2M platforms for enhancing energy efficiency,” J. Inf. Process. Syst., vol. 14, no. 4, pp. 1033–1048, 2018. http://dx.doi.org/10.3745/JIPS.03.0103.
  23. J. Wu, M. Yunus, P. K. Streatfield, and M. Emch, “Association of climate variability and childhood diarrhoeal disease in rural Bangladesh, 2000–2006,” Epidemiol. Infect., vol. 142, no. 9, pp. 1859–1868, 2014. https://doi.org/10.1017/s095026881300277x.
  24. R. B. Cleveland, W. S. Cleveland, J. E. McRae, and I. Terpenning, “STL: A seasonal-trend decomposition,” J Stat, vol. 6, no. 1, pp. 3–73, 1990.
  25. Z. Shen, G. Qin, P. Zuo, F. Wei, and X. Xu, “A Study of Variations of Galactic Cosmic-Ray Intensity Based on a Hybrid Data-processing Method,” Astrophys. J., vol. 900, no. 2, p. 143, 2020. https://doi.org/10.3847/1538-4357/abac60.
  26. A. G. Putrada, M. Abdurohman, D. Perdana, and H. H. Nuha, “CIMA: A Novel Classification-Integrated Moving Average Model for Smart Lighting Intelligent Control Based on Human Presence,” Complexity, vol. 2022, pp. 1–19, Sep. 2022. http://doi.org/10.1155/2022/4989344.
  27. M. H. Ferdous, U. Hasan, and M. O. Gani, “CDANs: Temporal Causal Discovery from Autocorrelated and Non-Stationary Time Series Data,” ArXiv Prepr. ArXiv230203246, 2023. https://doi.org/10.48550/arXiv.2302.03246.
  28. S. Pasari and A. Shah, “Time series auto-regressive integrated moving average model for renewable energy forecasting,” in Enhancing Future Skills and Entrepreneurship: 3rd Indo-German Conference on Sustainability in Engineering, 2020, pp. 71–77. https://doi.org/10.1007/978-3-030-44248-4_7.
  29. N. Abu Bakar and S. Rosbi, “Autoregressive integrated moving average (ARIMA) model for forecasting cryptocurrency exchange rate in high volatility environment: A new insight of bitcoin transaction,” Int. J. Adv. Eng. Res. Sci., vol. 4, no. 11, pp. 130–137, 2017. https://doi.org/10.22161/ijaers.4.11.20
  30. N. Maleki, A. Nikoubin, M. Rabbani, and Y. Zeinali, “Bitcoin price prediction based on other cryptocurrencies using machine learning and time series analysis,” Sci. Iran., 2020. https://doi.org/10.24200/sci.2020.55034.4040.
  31. A. G. Putrada, N. Alamsyah, S. F. Pane, and M. N. Fauzan, “XGBoost for IDS on WSN Cyber Attacks with Imbalanced Data,” in 2022 International Symposium on Electronics and Smart Devices (ISESD), Nov. 2022, pp. 1–7. http://doi.org/10.1109/ISESD56103.2022.9980630.
  32. A. G. Putrada, M. Abdurohman, D. Perdana, and H. H. Nuha, “Machine Learning Methods in Smart Lighting Toward Achieving User Comfort: A Survey,” IEEE Access, vol. 10, pp. 45137–45178, 2022. http://doi.org/10.1109/ACCESS.2022.3169765.
  33. N. Engelke Infante, K. Murphy, C. Glenn, and V. Sealey, “How concept images affect students’ interpretations of Newton’s method,” Int. J. Math. Educ. Sci. Technol., vol. 49, no. 5, pp. 643–659, 2018. https://doi.org/10.1080/0020739x.2017.1410737.
  34. R. R. Pamungkas, A. G. Putrada, and M. Abdurohman, “Performance improvement of non invasive blood glucose measuring system with near infra red using artificial neural networks,” Kinet. Game Technol. Inf. Syst. Comput. Netw. Comput. Electron. Control, pp. 315–324, 2019. https://doi.org/10.22219/kinetik.v4i4.844.
  35. M. F. Akbar, A. G. Putrada, and M. Abdurohman, “Smart light recommending system using artificial neural network algorithm,” in 2019 7th International Conference on Information and Communication Technology (ICoICT), 2019, pp. 1–5. https://doi.org/10.1109/icoict.2019.8835192.
  36. R. Irvan, M. Abdurohman, and A. G. Putrada, “Designing a monitoring and prediction system of water quality pollution using artificial neural networks for freshwater fish cultivation in reservoirs,” in Proceedings of Sixth International Congress on Information and Communication Technology, 2022, pp. 469–476. https://doi.org/10.1007/978-981-16-2380-6_41.
  37. A. M. Syukur, A. G. Putrada, and M. Abdurohman, “Increasing accuracy of power consumption using artificial neural network,” in 2019 7th International Conference on Information and Communication Technology (ICoICT), 2019, pp. 1–6. https://doi.org/10.1109/icoict.2019.8835371.
  38. M. A. G. Putrada, M. Abdurohman, D. D. Perdana, and D. H. H. Nuha, “Recurrent Neural Network Architectures Comparison in Time-Series Binary Classification on IoT-Based Smart Lighting Control,” p. 6. https://doi.org/10.1109/icoict55009.2022.9914831.
  39. H. C. Kilinc, “Daily streamflow forecasting based on the hybrid Particle Swarm Optimization and Long Short-Term Memory model in the Orontes Basin,” Water, vol. 14, no. 3, p. 490, 2022. https://doi.org/10.3390/w14030490
  40. A. G. Putrada, N. Alamsyah, S. F. Pane, and M. N. Fauzan, “GRU-MF: A Novel Appliance Classification Method for Non-Intrusive Load Monitoring Data,” in 2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), 2022, pp. 200–205. https://doi.org/10.1109/comnetsat56033.2022.9994409.
  41. A. G. Putrada, “Gated Recurrent Unit for Fall Detection on Motorcycle Smart Helmet with Accelerometer Sensor,” Indones. J. Comput. Indo-JC, vol. 7, no. 3, Art. no. 3, Dec. 2022. http://doi.org/10.34818/INDOJC.2022.7.3.672.
  42. E. Sener and I. Demir, “Wavelet-Denoised ARIMA and LSTM Method to Predict Cryptocurrency Price,” in 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), 2022, pp. 577–582. https://doi.org/10.1109/ismsit56059.2022.9932727.
  43. A. Narotama, “The Effect of Service Quality on Customer Loyalty with Brand Images and Customer Satisfaction as Mediation,” J. Manaj. DAN KEWIRAUSAHAAN, vol. 7, no. 1, p. 86, Jun. 2019. http://doi.org/10.26905/jmdk.v7i1.2692.
  44. D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, 2021. https://doi.org/10.7717/peerj-cs.623.
  45. Q. Lhoest et al., “Datasets: A community library for natural language processing,” ArXiv Prepr. ArXiv210902846, 2021. https://doi.org/10.48550/arXiv.2109.02846.
  46. J. Cong, M. Ren, S. Xie, and P. Wang, “Predicting Seasonal Influenza Based on SARIMA Model, in Mainland China from 2005 to 2018,” Int. J. Environ. Res. Public. Health, vol. 16, no. 23, Art. no. 23, Jan. 2019. http://doi.org/10.3390/ijerph16234760.
Read More
Author biographies is not available.
Download this PDF file
PDF
Statistic
Read Counter : 8 Download : 10

Downloads

Download data is not yet available.