DOI: 10.17587/prin.14.301-306

Method for Improving the Accuracy of Predictive Values of Time Series Based on the Imputation of Historical Data

E. V. Palchevsky, Lecturer, teelxp@inbox.ru, Faculty of Information Technology and Big Data Analysis, Financial University under the Government of the Russian Federation, Moscow, 109456, Russian Federation

Corresponding author: Evgeniy V. Palchevsky, Lecturer, Financial University under the Government of the Russian Federation, Moscow, 109456, Russian Federation, E-mail: teelxp@inbox.ru

The developed method for imputing retrospective data to improve the accuracy of long-term neural network fore­casting is considered. The peculiarity of the method is to increase the accuracy of the predictive values of the time series obtained at the output of the recurrent neural network by increasing the amount of historical data provided by the production department of the Kumertau Electric Networks. Using the example of forecasting the values of electricity consumption, an experiment was carried out on data imputation, which proves the effectiveness of using this method to improve accuracy in forecasting time series.

Keywords: data imputation, electricity consumption forecasting, neural networks, intelligent forecasting system

pp. 301–306

For citation:
Palchevsky E. V. Method for Improving the Accuracy of Predictive Values of Time Series Based on the Imputation of Historical Data, Programmnaya Ingeneria, 2023, vol. 14, no. 6, pp. 301—306. DOI: 10.17587/prin.14.301-306.

References:

1. Guo-Feng F., Xiao W., Ya-Ting L., Wei-Chiang H. Fore­casting electricity consumption using a novel hybrid model. Sustainable Cities and Society, 2020, vol. 61, pp. 102320. DOI: 10.1016/j. scs.2020.102320.
2. Wei-Chiang H. Hybrid Intelligent Technologies in Energy Demand Forecasting, Berlin, Springer, 2020, 192 p.
3. Losev A. S., Massel A. G. Prediction of solar radiation and data imputation for the digital twin of a solar power plant, Infor­mation and Mathematical Technologies in Science and Management, 2022, no. 1 (25), pp. 91—101. DOI: 10.38028/ESI.2022.25.1.008 (in Russian).
4. Kurapeev D. I., Lushnov M. S., Man T., Zhukova N. A. Imputation and system modeling of acid-base state parameters for different groups of patients, Scientific and technical journal of in­formation technologies, mechanics and optics, 2022, vol. 22, no. 1, pp. 155—166. DOI: 10.17586/2226-1494-2022-22-1-155-166.
5. Boseong S., Jaekyung S., Taejin K., Byeng D. Y. Missing data imputation using an iterative denoising autoencoder (IDAE) for dissolved gas analysis, Electric Power Systems Research, 2022, vol. 212, pp. 108642. DOI: 10.1016/j.epsr.2022.108642.
6. Yong C., Xiqun C. A novel reinforced dynamic graph convolutional network model with data imputation for network-wide traffic flow prediction, Transportation Research Part C: Emerging Technologies, 2022, vol. 143, pp. 103820. DOI:10.1016/j.trc.2022.103820.
7. Daoming W., Roozbeh R. F., Mehrdad S., Niloofar M. COLI: Collaborative clustering missing data imputation, Pattern Recognition Letters, 2021, vol. 152, pp. 420—427. DOI:10.1016/j.patrec.2021.11.011.
8. Shatha A., Hossam F., Hazem H. EvoImputer: An evolutionary approach for Missing Data Imputation and feature selection in the context of supervised learning, Knowledge-Based Systems, 2022, vol. 236, pp. 107734. DOI: 10.1016/j.knosys.2021.107734.
9. Gideon A. L., Mohd Z., Anoop Krishman N. M., Sumanta D. Prediction of concrete strengths enabled by missing data im­putation and interpretable machine learning, Cement and Concrete Composites, 2022. vol. 128, pp. 104414. DOI: 10.1016/j.cemcon-comp.2022.104414.
10. Palchevsky E. V., Antonov V. V. Decision Support System based on Application of the Second Generation Neural Network, Programmnaya Ingeneria, 2022, vol. 13, no. 6, pp. 301—308. DOI: 10.17587/prin.13.301-308.
11. Palchevsky E. V., Antonov V. V., Enikeev R. R., Breikin T. A system based on an artificial neural network of the second gen­eration for decision support in especially significant situations, Journal of Hydrology, 2023. vol. 616, pp. 128844. DOI: 10.1016/j.jhydrol.2022.128844.
12. Palchevsky E. V., Antonov V. V., Kromina L. A., Rodionova L. E., Fakhrullina A. R. Artificial Neural Network for Forecasting Electricity Consumption in Energy Enterprises, Programmnaya Ingeneria, 2023, vol. 14, no. 1, pp. 34—41. DOI: 10.17587/prin.14.34-41.