A novel hybrid ensemble approach for wind speed forecasting with dual-stage decomposition strategy using optimized GRU and transformer models
Authors:
- Sajid UllahSUSajid Ullah
- Xi ChenXCXi Chen
- Han HanHHHan Han
- Junhao WuJWJunhao Wu
- Jinghan DongJDJinghan Dong
- Ruiqing LiuRLRuiqing Liu
- Weijie DingWDWeijie Ding
- Min LiuMLMin Liu
- Qingli LiQingli Li
- Honggang QiHQHonggang Qi
- Yonggui HuangYHYonggui Huang
- Philip Lh YuPYPhilip Lh Yu
Abstract
No abstract availableFunding Information
- Fundamental Research Funds for the Central Universities (22002400300)
- Croucher Foundation
- Science and Technology Commission of Shanghai Municipality (23692123900)
This publication has 52 references indexed in Scilit:
- Explainable machine learning techniques based on attention gate recurrent unit and local interpretable model‐agnostic explanations for multivariate wind speed forecastingJournal of Forecasting, 2024
- Applicability analysis of transformer to wind speed forecasting by a novel deep learning framework with multiple atmospheric variablesApplied Energy, 2023
- A convolutional Transformer-based truncated Gaussian density network with data denoising for wind speed forecastingApplied Energy, 2023
- A compositive architecture coupling outlier correction, EWT, nonlinear Volterra multi-model fusion with multi-objective optimization for short-term wind speed forecastingApplied Energy, 2022
- Multi-step wind speed forecasting based on secondary decomposition algorithm and optimized back propagation neural networkApplied Soft Computing, 2021
- Wind speed forecasting system based on gated recurrent units and convolutional spiking neural networksApplied Energy, 2021
- A self-adaptive kernel extreme learning machine for short-term wind speed forecastingApplied Soft Computing, 2021
- A permutation entropy-based EMD–ANN forecasting ensemble approach for wind speed predictionNeural Computing and Applications, 2020
- Multi-step wind speed and power forecasts based on a WRF simulation and an optimized association methodApplied Energy, 2017
- Comparison of two new ARIMA-ANN and ARIMA-Kalman hybrid methods for wind speed predictionApplied Energy, 2012