Czasopismo
Tytuł artykułu
Warianty tytułu
Języki publikacji
Abstrakty
Purpose: The key element of effective electricity management is to improve the accuracy of forecasting its consumption. To create a forecast, data on customers' energy consumption in previous periods is required, and the accuracy of the forecasts depends on the quality and availability of data. The acquired historical data is often incomplete and contains missing values. The aim of the article is therefore to choose an appropriate method of imputation of missing values for one-dimensional time series of energy consumption.
Design/methodology/approach: The aim of the article was achieved by using the Known Substring Algorithm (KSSA) to verify the imputation precision. The KSSA algorithm allowed to test of eleven imputation methods, most of which are implemented in the 'ImputeTS' package in R. Based on the RMSE error, the best imputation method was selected for the analyzed series.
Findings: As a result of the analyzes carried out, it was shown that the KSSA algorithm is a good tool for selecting the appropriate imputation method in the case of one-dimensional series of electricity consumption series. Based on the RMSE error, 'auto.arima' turned out to be the best imputation method for the analyzed objects.
Research limitations/implications: Future research will concern the use of the KSSA algorithm for a larger number of energy consumption series and with greater variation.
Originality/value: The article presents an important problem of the imputation of missing values in the electricity consumption series. Increasing the accuracy of electricity consumption forecasting depends on the quality of the collected data, which are often incomplete and contain missing values. Therefore, the selection of the appropriate imputation method is so important.(original abstract)
Design/methodology/approach: The aim of the article was achieved by using the Known Substring Algorithm (KSSA) to verify the imputation precision. The KSSA algorithm allowed to test of eleven imputation methods, most of which are implemented in the 'ImputeTS' package in R. Based on the RMSE error, the best imputation method was selected for the analyzed series.
Findings: As a result of the analyzes carried out, it was shown that the KSSA algorithm is a good tool for selecting the appropriate imputation method in the case of one-dimensional series of electricity consumption series. Based on the RMSE error, 'auto.arima' turned out to be the best imputation method for the analyzed objects.
Research limitations/implications: Future research will concern the use of the KSSA algorithm for a larger number of energy consumption series and with greater variation.
Originality/value: The article presents an important problem of the imputation of missing values in the electricity consumption series. Increasing the accuracy of electricity consumption forecasting depends on the quality of the collected data, which are often incomplete and contain missing values. Therefore, the selection of the appropriate imputation method is so important.(original abstract)
Rocznik
Strony
325--337
Opis fizyczny
Twórcy
- Silesian University of Technology
autor
- Silesian University of Technology
autor
- Silesian University of Technology
Bibliografia
- 1. Aravkin, A., Burke, J.V., Ljung, L., Lozano, A., Pillonetto, G. (2017). Generalized Kalman smoothing: Modeling and algorithms. Automatica, 86, 63-86.
- 2. Benavides, I.F., Santacruz, M., Romero-Leiton, J.P., Barreto, C., Selvaraj, J.J. (2021). Assessing methods for multiple imputation of systematic missing data in arine fisheries time series with a new validation algorithm. Aquaculture and Fisheries, https://doi.org/10.1016/j.aaf.2021.12.013.
- 3. Bokde, N., Beck, M.W., Álvarez, F.M., Kulat, K. (2018). A novel imputation methodology for time series based on pattern sequence forecasting. Pattern recognition letters, 116, 88-96.
- 4. Chen, W., Zhou, K., Yang, S., Wu, C. (2017). Data quality of electricity consumption data in a smart grid environment. Renew. Sust. Energy Rev., 75, 98-105.
- 5. Cleveland, R.B., Cleveland, W.S., McRae, J.E., and Terpenning, I. (1990). STL: A seasonal-trend decomposition. J. Off. Stat, 6(1), 3-73.
- 6. Demirhan, H., Renwick, Z. (20180). Missing value imputation for short to mid-term horizontal solar irradiance data. Appl. Energy, 225(9), 98-1012.
- 7. Durbin, J., Koopman, S.J. (2001). Time Series Analysis by State Space Methods. Oxford University Press.
- 8. García-Laencina, P.J., Sancho-Gómez, J.L., Figueiras-Vidal, A.R. (2010). Pattern classification with missing data: a review. Neural Computing and Applications, 19, 263- 282.
- 9. Golyandina, N., Korobeynikov, A. (2014). Basic singular spectrum analysis and forecasting with R. Computational Statistics & Data Analysis, 71, 934-954.
- 10. Hall, C.A., Meyer, W.W. (1976). Optimal error bounds for cubic spline interpolation. Journal of Approximation Theory, 16(2), 105-122.
- 11. Harvey, A.C. (1990) Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge University Press.
- 12. Hyndman, R.J., Khandakar, Y. (2008). Automatic time series forecasting: the forecast package for R. Journal of statistical software, 27, 1-22.
- 13. Kim, T., Ko, W., Kim, J. (2019). Analysis and impact evaluation of missing data imputation in day-ahead PV generation forecasting. Appl. Sci., 9, 204.
- 14. Kowalska-Styczeń, A., Owczarek, T., Siwy, J., Sojda, A., Wolny, M. (2022). Analysis of Business Customers' Energy Consumption Data Registered by Trading Companies in Poland. Energies, 15(14), 5129.
- 15. Li, H., Li, M., Lin, X., He, F., Wang, Y. (2020). A spatiotemporal approach for traffic data imputation with complicated missing patterns. Transportation Research, Part C, 119, 102730.
- 16. Liu, C.-H., Tsai, C.-F., Sue, K.-L., Huang, M.-W. (2020). The Feature Selection Effect on Missing Value Imputation of Medical Datasets. Appl. Sci., 10, 2344.
- 17. Makonin, S. (2019). HUE: The hourly usage of energy dataset for buildings in British Columbia. Data in brief, 23.
- 18. Moritz, S., Bartz-Beielstein, T. (2017). "imputeTS: Time Series Missing Value Imputation in R. " _The R Journal_, *9*(1), 207-218. doi:10.32614/RJ-2017-009.
- 19. Moritz, S., Sardá, A., Bartz-Beielstein, T., Zaefferer, M., Stork, J. (2015). Comparison of different Methods for Univariate Time Series Imputation in R, arXiv:physics/1510.03924
- 20. Sefidian, A.M., Daneshpour, N. (2019). Missing value imputation using a novel grey based fuzzy c-means, mutual information based feature selection, and regression model. Expert Systems with Applications, 115, 68-94.
- 21. Stineman, R.W. (1980). A consistently well-behaved method of interpolation. Creative Computing, 6(7), 54-57.
- 22. Wang, M.-C., Tsai, C.-F., Lin, W.-C. (2021). Towards missing electric power data imputation for energy management systems. Expert Syst. Appl., 174, 14743
Typ dokumentu
Bibliografia
Identyfikatory
Identyfikator YADDA
bwmeta1.element.ekon-element-000171678669
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.