A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting
Wind speed and streamflow series always are nonlinear and unstable because the effects of chaotic weather systems. These inherent features make them difficult to forecast, especially in a changing environment. To improve forecasting accuracy, an innovation uncertainty forecasting architecture is dev...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9244167/ |
id |
doaj-8d7a9d147983458a975c012fa1a94443 |
---|---|
record_format |
Article |
spelling |
doaj-8d7a9d147983458a975c012fa1a944432021-03-30T03:34:53ZengIEEEIEEE Access2169-35362020-01-01820925120926610.1109/ACCESS.2020.30341279244167A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow ForecastingNa Sun0https://orcid.org/0000-0001-9671-2536Shuai Zhang1Tian Peng2Jianzhong Zhou3https://orcid.org/0000-0003-4435-3118Xinguo Sun4College of Automation, Huaiyin Institute of Technology, Huai’an, ChinaKey Laboratory of Thermo-Fluid Science and Engineering, Ministry of Education, School of Energy and Power Engineering, Xi’an Jiaotong University, Xi’an, ChinaCollege of Automation, Huaiyin Institute of Technology, Huai’an, ChinaSchool of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan, ChinaJiangsu Smart Factory Engineering Research Centre, College of Management and Engineering, Huaiyin Institute of Technology, Huai’an, ChinaWind speed and streamflow series always are nonlinear and unstable because the effects of chaotic weather systems. These inherent features make them difficult to forecast, especially in a changing environment. To improve forecasting accuracy, an innovation uncertainty forecasting architecture is developed by coupling data decomposition method, feature selection, multiple artificial intelligence (AI) techniques and composite strategy to do unstable time series forecasting. In the designed architecture, the AVMD (adaptive variational mode decomposition) is first applied to excavate implicit information from the original time series. Then, the random forest is utilized to select the suitable inputs for each mode. After that, the GPR (Gaussian Process Regression), a very famous probabilistic AI technique, is driven by various neural networks (ELM (Extreme Learning Machine), BP (Back Propagation Neural Networks), GRNN(Generalized Regression Neural Networks) and RBF (Radial Basis Function Neural Networks)) to produce both deterministic and probabilistic forecasting results in a nonlinear manner to play strengths of each other. The effectiveness and applicability of the proposed approach is verified by unstable wind speed data and streamflow data, and also compared with eleven related models. Results indicate that the proposed model not only improves the forecasting accuracy for deterministic predictions, but also provides more probabilistic information for decision making. The proposed method achieves significantly better performance than the traditional forecasting models both on wind speed forecasting and streamflow forecasting with at least 50% average performance promotion over all the eleven competitors. Comprehensive comparisons demonstrate the superior performance of the proposed method than the involved models as a powerful tool for unstable series forecasting.https://ieeexplore.ieee.org/document/9244167/Unstable time series predictionhybrid modelGPRartificial intelligencecombination forecasting |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Na Sun Shuai Zhang Tian Peng Jianzhong Zhou Xinguo Sun |
spellingShingle |
Na Sun Shuai Zhang Tian Peng Jianzhong Zhou Xinguo Sun A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting IEEE Access Unstable time series prediction hybrid model GPR artificial intelligence combination forecasting |
author_facet |
Na Sun Shuai Zhang Tian Peng Jianzhong Zhou Xinguo Sun |
author_sort |
Na Sun |
title |
A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting |
title_short |
A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting |
title_full |
A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting |
title_fullStr |
A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting |
title_full_unstemmed |
A Composite Uncertainty Forecasting Model for Unstable Time Series: Application of Wind Speed and Streamflow Forecasting |
title_sort |
composite uncertainty forecasting model for unstable time series: application of wind speed and streamflow forecasting |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Wind speed and streamflow series always are nonlinear and unstable because the effects of chaotic weather systems. These inherent features make them difficult to forecast, especially in a changing environment. To improve forecasting accuracy, an innovation uncertainty forecasting architecture is developed by coupling data decomposition method, feature selection, multiple artificial intelligence (AI) techniques and composite strategy to do unstable time series forecasting. In the designed architecture, the AVMD (adaptive variational mode decomposition) is first applied to excavate implicit information from the original time series. Then, the random forest is utilized to select the suitable inputs for each mode. After that, the GPR (Gaussian Process Regression), a very famous probabilistic AI technique, is driven by various neural networks (ELM (Extreme Learning Machine), BP (Back Propagation Neural Networks), GRNN(Generalized Regression Neural Networks) and RBF (Radial Basis Function Neural Networks)) to produce both deterministic and probabilistic forecasting results in a nonlinear manner to play strengths of each other. The effectiveness and applicability of the proposed approach is verified by unstable wind speed data and streamflow data, and also compared with eleven related models. Results indicate that the proposed model not only improves the forecasting accuracy for deterministic predictions, but also provides more probabilistic information for decision making. The proposed method achieves significantly better performance than the traditional forecasting models both on wind speed forecasting and streamflow forecasting with at least 50% average performance promotion over all the eleven competitors. Comprehensive comparisons demonstrate the superior performance of the proposed method than the involved models as a powerful tool for unstable series forecasting. |
topic |
Unstable time series prediction hybrid model GPR artificial intelligence combination forecasting |
url |
https://ieeexplore.ieee.org/document/9244167/ |
work_keys_str_mv |
AT nasun acompositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT shuaizhang acompositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT tianpeng acompositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT jianzhongzhou acompositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT xinguosun acompositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT nasun compositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT shuaizhang compositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT tianpeng compositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT jianzhongzhou compositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting AT xinguosun compositeuncertaintyforecastingmodelforunstabletimeseriesapplicationofwindspeedandstreamflowforecasting |
_version_ |
1724183199879266304 |