Full Article: PDF
Scientific Object Identifier: http://s-o-i.org/1.1/TAS-03-107-36
DOI: https://dx.doi.org/10.15863/TAS.2022.03.107.36
Language: English
Citation: Jumanov, I. I., & Melieva, M. B. (2022). Mechanisms for forecasting time series of indicators of power supply systems based on soft calculations in non-stationary conditions. ISJ Theoretical & Applied Science, 03 (107), 587-591. Soi: http://s-o-i.org/1.1/TAS-03-107-36 Doi: https://dx.doi.org/10.15863/TAS.2022.03.107.36 |
Pages: 587-591
Published: 30.03.2022
Abstract: Scientific and methodological foundations for the application of methods and algorithms for data mining based on neural networks, fuzzy sets and fuzzy inferences, neuro-fuzzy networks, and genetic algorithms have been developed and implemented. As tools for the analysis and forecasting of time series of random processes, optimization mechanisms for determining and setting the parameters of genetic operators, dynamic identification models are proposed. The results of the study were obtained by solving forecasting problems in real conditions.
Key words: fuzzy inference, fuzzy logic, neural network, neuro-fuzzy network, genetic algorithms, forecast, time series.
|
