Open AccessShort‐term power load fitting/forecasting based on composite modified fractal interpolation approaches
Author(s) -
Li Xiaolan,
Zhou Jun
Publication year - 2021
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/2050-7038.12709
Subject(s) - term (time) , interpolation (computer graphics) , fractal , composite number , computer science , mathematics , algorithm , artificial intelligence , mathematical analysis , physics , motion (physics) , quantum mechanics
Summary Fitting and forecasting of power load are difficult problems involving multiple aspects and factors about sources, grids and loads in power systems. Due to their key roles in power generation planning and distributing, fitting and forecasting are the essential topics in electrical engineering. In this study, fractal concepts and theories are reviewed briefly around fractal interpolation for function fitting; then fractal characteristics of power load are discussed, based on which their fitting and forecasting are improved. More precisely, a fractal interpolation approach with modified vertical scaling factors is developed for power load fitting that can accommodate for more time‐varying details. Also, short‐term power load forecasting under composite modified fractal interpolation with more parametric degrees of freedom for optimization are suggested and validated, whose performance and efficiency are compared with respect to some existing methods via numerical examples.