Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning

A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective d...

Full description

Bibliographic Details
Main Authors: V.G. Kurbatsky, P. Leahy, V.A. Spiryaev, N.V. Tomin, D.N. Sidorov, A.V. Zhukov
Format: Article
Language:English
Published: Irkutsk State University 2014-09-01
Series:Известия Иркутского государственного университета: Серия "Математика"
Subjects:
Online Access:http://isu.ru/journal/downloadArticle?article=_9a0762f6e2fd4db7a22a9c79dd5b23dc&lang=eng
_version_ 1818114047052087296
author V.G. Kurbatsky
P. Leahy
V.A. Spiryaev
N.V. Tomin
D.N. Sidorov
A.V. Zhukov
author_facet V.G. Kurbatsky
P. Leahy
V.A. Spiryaev
N.V. Tomin
D.N. Sidorov
A.V. Zhukov
author_sort V.G. Kurbatsky
collection DOAJ
description A novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.
first_indexed 2024-12-11T03:44:30Z
format Article
id doaj.art-aa555f76ef6c47a3bd04e1c5e09813f6
institution Directory Open Access Journal
issn 1997-7670
2541-8785
language English
last_indexed 2024-12-11T03:44:30Z
publishDate 2014-09-01
publisher Irkutsk State University
record_format Article
series Известия Иркутского государственного университета: Серия "Математика"
spelling doaj.art-aa555f76ef6c47a3bd04e1c5e09813f62022-12-22T01:22:04ZengIrkutsk State UniversityИзвестия Иркутского государственного университета: Серия "Математика"1997-76702541-87852014-09-01917590Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine LearningV.G. KurbatskyP. LeahyV.A. SpiryaevN.V. TominD.N. SidorovA.V. ZhukovA novel hybrid data-driven approach is developed for forecasting power system parameters with the goal of increasing the efficiency of short-term forecasting studies for non-stationary time-series. The proposed approach is based on mode decomposition and a feature analysis of initial retrospective data using the Hilbert-Huang transform and machine learning algorithms. The random forests and gradient boosting trees learning techniques were examined. The decision tree techniques were used to rank the importance of variables employed in the forecasting models. The Mean Decrease Gini index is employed as an impurity function. The resulting hybrid forecasting models employ the radial basis function neural network and support vector regression. A part from introduction and references the paper is organized as follows. The second section presents the background and the review of several approaches for short-term forecasting of power system parameters. In the third section a hybrid machine learningbased algorithm using Hilbert-Huang transform is developed for short-term forecasting of power system parameters. Fourth section describes the decision tree learning algorithms used for the issue of variables importance. Finally in section six the experimental results in the following electric power problems are presented: active power flow forecasting, electricity price forecasting and for the wind speed and direction forecasting.http://isu.ru/journal/downloadArticle?article=_9a0762f6e2fd4db7a22a9c79dd5b23dc&lang=engtime seriesforecastingintegral transformsANNSVM machine learningboostingsingular integralfeature analysis
spellingShingle V.G. Kurbatsky
P. Leahy
V.A. Spiryaev
N.V. Tomin
D.N. Sidorov
A.V. Zhukov
Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
Известия Иркутского государственного университета: Серия "Математика"
time series
forecasting
integral transforms
ANN
SVM
machine learning
boosting
singular integral
feature analysis
title Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
title_full Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
title_fullStr Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
title_full_unstemmed Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
title_short Power System Parameters Forecasting Using Hilbert-Huang Transform and Machine Learning
title_sort power system parameters forecasting using hilbert huang transform and machine learning
topic time series
forecasting
integral transforms
ANN
SVM
machine learning
boosting
singular integral
feature analysis
url http://isu.ru/journal/downloadArticle?article=_9a0762f6e2fd4db7a22a9c79dd5b23dc&lang=eng
work_keys_str_mv AT vgkurbatsky powersystemparametersforecastingusinghilberthuangtransformandmachinelearning
AT pleahy powersystemparametersforecastingusinghilberthuangtransformandmachinelearning
AT vaspiryaev powersystemparametersforecastingusinghilberthuangtransformandmachinelearning
AT nvtomin powersystemparametersforecastingusinghilberthuangtransformandmachinelearning
AT dnsidorov powersystemparametersforecastingusinghilberthuangtransformandmachinelearning
AT avzhukov powersystemparametersforecastingusinghilberthuangtransformandmachinelearning