Abstract
A non-standard method of forecasting load and power consumption using a regression model is considered. The training sample is taken as a basis, which is a set of values of the maximum annual load of the power system for the past ten years. The work is devoted to the issues of optimal design of the regression equation in the form of a time polynomial (polynomial) in order to ensure a high value of forecasting for the next five years and to estimate the confidence intervals of the forecast. A feature of this method of forecasting is the ability to find the values of the time series based on its historical values in energy. Which is the basis for planning, managing and optimizing energy production and control. Selection of informative indicators and determination of the type of model are considered separately. The statistical capacity of the model is being tested. However, the absence of autoregressive connections is checked. Calculation of interval estimates of the indicator and forecasting errors. Forecasting by regression model. In contrast to previous research, the authors have shown how to achieve a high rate of forecasting using the Python programming language and NumPy libraries. The results of the work will be useful for machine learning technologies, data science, statistics, energy companies and power systems and others.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tugay, D., Kotelevets, S., Korneliuk, S., Zhemerov, G.: Energy efficiency of microgrid implementation with solar photovoltaic power plants. In: 2018 IEEE 3rd International Conference on Intelligent Energy and Power Systems (IEPS), Kharkiv, pp. 275–279. IEEE (2018). https://doi.org/10.1109/IEPS.2018.8559579
Akbar, B., Amber, K.P., Kousar, A., et al.: Data-driven predictive models for daily electricity consumption of academic buildings. AIMS Energy 8(5), 783–801 (2020). https://doi.org/10.3934/energy.2020.5.783
Bedi, J., Toshniwal, D.: Deep learning framework to forecast electricity demand. Appl. Energy 238, 1312–1326 (2019). https://doi.org/10.1016/j.apenergy.2019.01.113
Kondratiev, A., PÃÅ¡tÄ›k, V., Purhina, S., et al.: Self-heating mould for composite manufacturing. Polymers 13(18), 3074 (2021). https://doi.org/10.3390/polym13183074
Aksonov, Y., Kombarov, V., Tsegelnyk, Y., et al.: Visualization and analysis of technological systems experimental operating results. In: 2021 IEEE 16th International Conference on Computer Sciences and Information Technologies (CSIT), Lviv, vol. 2, pp. 141–146. IEEE (2021). https://doi.org/10.1109/CSIT52700.2021.9648592
Deng, S., Yuan, C., Yang, L., Zhang, L.: Distributed electricity load forecasting model mining based on hybrid gene expression programming and cloud computing. Pattern Recogn. Lett. 109, 72–80 (2018). https://doi.org/10.1016/j.patrec.2017.10.004
Zahid, M., Ahmed, F., Javaid, N., et al.: Electricity price and load forecasting using enhanced convolutional neural network and enhanced support vector regression in smart grids. Electronics 8(2), 122 (2019). https://doi.org/10.3390/electronics8020122
Zhou, X., Gao, Y., Yao, W., Yu, N.: A robust segmented mixed effect regression model for baseline electricity consumption forecasting. J. Mod. Power Syst. Clean Energy 10(1), 71–80 (2020). https://doi.org/10.35833/MPCE.2020.000023
Hong, W.C., Fan, G.F.: Hybrid empirical mode decomposition with support vector regression model for short term load forecasting. Energies 12(6), 1093 (2019). https://doi.org/10.3390/en12061093
Lee, C.W., Lin, B.Y.: Applications of the chaotic quantum genetic algorithm with support vector regression in load forecasting. Energies 10(11), 1832 (2017). https://doi.org/10.3390/en10111832
Dovgalyuk, O., Omelianenko, H., Pirotti, A., et al.: Reliability increase of the distribution electric networks operation in the implementation of the energy market in Ukraine. In: 2019 IEEE 6th International Conference on Energy Smart Systems (ESS), Kyiv, pp. 70–75. IEEE (2019). https://doi.org/10.1109/ESS.2019.8764243
Chen, Q., Balian, A., Kyzym, M., et al.: Electricity markets instability: causes of price dispersion. Sustainability 13(22), 12343 (2021). https://doi.org/10.3390/su132212343
Mohammed, N.A., Al-Bazi, A.: An adaptive backpropagation algorithm for long-term electricity load forecasting. Neural Comput. Appl. 34(1), 477–491 (2021). https://doi.org/10.1007/s00521-021-06384-x
Sayenko, Y., Baranenko, T., Kalyuzhniy, D.: Compensation of reactive power in electrical supply systems of large industrial enterprises. Przeglad Elektrotechniczny 91(11), 77–80 (2015). https://doi.org/10.15199/48.2015.11.22
Moon, J., Park, J., Hwang, E., Jun, S.: Forecasting power consumption for higher educational institutions based on machine learning. J. Supercomput. 74(8), 3778–3800 (2017). https://doi.org/10.1007/s11227-017-2022-x
El Sayed, M.A.E.A., Moustafa, H.M.M., Ziedan, I.E.S., Zamel, A.A.: A combined effective time series model based on clustering and whale optimization algorithm for forecasting smart meters electricity consumption. COMPEL 41(1), 209–237 (2021). https://doi.org/10.1108/COMPEL-04-2021-0150
Saxena, H., Aponte, O., McConky, K.T.: A hybrid machine learning model for forecasting a billing period’s peak electric load days. Int. J. Forecast. 35(4), 1288–1303 (2019). https://doi.org/10.1016/j.ijforecast.2019.03.025
Pliuhin, V., Korobka, V., Karyuk, A., et al.: Using Azure Machine Learning Studio with Python scripts for induction motors optimization web-deploy project. In: 2019 IEEE International Scientific-Practical Conference Problems of Infocommunications, Science and Technology (PIC S&T), Kyiv, pp. 631–634. IEEE (2019). https://doi.org/10.1109/PICST47496.2019.9061447
Pliuhin, V., Pan, M., Yesina, V., Sukhonos, M.:. Using Azure Maching Learning cloud technology for electric machines optimization. In: 2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T), Kharkiv, pp. 55–58. IEEE (2018). https://doi.org/10.1109/INFOCOMMST.2018.8632093
Pliuhin, V., Sukhonos, M., Bileckiy, I.: Object oriented mathematical modeling of electrical machines. In: 2020 IEEE 4th International Conference on Intelligent Energy and Power Systems (IEPS), Istanbul, pp. 267–272. IEEE (2020). https://doi.org/10.1109/IEPS51250.2020.9263158
Tajeuna, E.G., Bouguessa, M., Wang, S.: A network-based approach to enhance electricity load forecasting. In: 2018 IEEE International Conference on Data Mining Workshops (ICDMW), Singapore, pp. 266–275. IEEE (2018). https://doi.org/10.1109/ICDMW.2018.00046
Wang, D., Yue, C., ElAmraoui, A.: Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy. Chaos Solitons Fractals 152, 111453 (2021). https://doi.org/10.1016/j.chaos.2021.111453
Roubeyrie, L., Celles, S.: Windrose: a Python Matplotlib, Numpy library to manage wind and pollution data, draw windrose. J. Open Source Softw. 3(29), 268 (2018). https://doi.org/10.21105/joss.00268
Harris, C.R., Millman, K.J., Van Der Walt, S.J., et al.: Array programming with NumPy. Nature 585(7825), 357–362 (2020). https://doi.org/10.1038/s41586-020-2649-2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sukhonos, M., Babaiev, V., Pliuhin, V., Teterev, V., Khudiakov, I. (2023). Load Forecasting and Electricity Consumption by Regression Model. In: Arsenyeva, O., Romanova, T., Sukhonos, M., Tsegelnyk, Y. (eds) Smart Technologies in Urban Engineering. STUE 2022. Lecture Notes in Networks and Systems, vol 536. Springer, Cham. https://doi.org/10.1007/978-3-031-20141-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-20141-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20140-0
Online ISBN: 978-3-031-20141-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)