A Multi-Scale Component Feature Learning Framework Based on Cnn-Bigru and Online Sequential Regularized Extreme Learning Machine for Wind Speed Prediction DOI
Xuedong Zhang, Huanyu Zhao, Zheng Wang

и другие.

Опубликована: Янв. 1, 2024

Язык: Английский

Research and application of a novel graph convolutional RVFL and evolutionary equilibrium optimizer algorithm considering spatial factors in ultra-short-term solar power prediction DOI
Peng Tian,

Shihao Song,

Leiming Suo

и другие.

Energy, Год журнала: 2024, Номер 308, С. 132928 - 132928

Опубликована: Авг. 23, 2024

Язык: Английский

Процитировано

11
A multi-scale component feature learning framework based on CNN-BiGRU and online sequential regularized extreme learning machine for wind speed prediction DOI
Xuedong Zhang, Huanyu Zhao,

Junhao Yao

и другие.

Renewable Energy, Год журнала: 2025, Номер unknown, С. 122427 - 122427

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

1
Research and application of a novel weight-based evolutionary ensemble model using principal component analysis for wind power prediction DOI
Chu Zhang,

Zihan Tao,

Jinlin Xiong

и другие.

Renewable Energy, Год журнала: 2024, Номер 232, С. 121085 - 121085

Опубликована: Июль 30, 2024

Язык: Английский

Процитировано

6
A novel hybrid model based on multiple influencing factors and temporal convolutional network coupling ReOSELM for wind power prediction DOI

Yida Ge,

Chu Zhang, Yiwei Wang

и другие.

Energy Conversion and Management, Год журнала: 2024, Номер 313, С. 118632 - 118632

Опубликована: Июнь 4, 2024

Язык: Английский

Процитировано

4
A Hybrid Dual Stream ProbSparse Self-Attention Network for spatial–temporal photovoltaic power forecasting DOI
Jingyin Pei, Yunxuan Dong,

Peiting Guo

и другие.

Energy, Год журнала: 2024, Номер 305, С. 132152 - 132152

Опубликована: Июнь 21, 2024

Язык: Английский

Процитировано

4
Nuclear Power Systems Unsupervised Anomaly Localization Considering Spatiotemporal Information and Influence Mechanism between Devices DOI
Haotong Wang, Jianxin Shi,

Chaojing Lin

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 136204 - 136204

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
Short-term wind speed prediction method based on prior wind direction knowledge and multi-period decoupling DOI
Zewen Shang, Xuewei Li, Zhiqiang Liu

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 153, С. 110596 - 110596

Опубликована: Апрель 22, 2025

Язык: Английский

Процитировано

0
Enhancement of wind speed forecasting using optimized decomposition technique, entropy-based reconstruction, and evolutionary PatchTST DOI

Changwen Ma,

Chu Zhang,

Junhao Yao

и другие.

Energy Conversion and Management, Год журнала: 2025, Номер 333, С. 119819 - 119819

Опубликована: Апрель 23, 2025

Язык: Английский

Процитировано

0
A probabilistic load forecasting method for multi-energy loads based on inflection point optimization and integrated feature screening DOI
Xiaoyu Zhao, Pengfei Duan, Xiaodong Cao

и другие.

Energy, Год журнала: 2025, Номер unknown, С. 136391 - 136391

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning DOI
Rafael Ayllón-Gavilán, Antonio M. Gómez-Orellana, Víctor Manuel Vargas

и другие.

Integrated Computer-Aided Engineering, Год журнала: 2025, Номер unknown

Опубликована: Май 15, 2025

In this paper, we present the MUSONet model, which leverages information from different sources (in case, wind farms) to perform a multi-step speed prediction. The main goal of approach is improving global prediction accuracy, specifically at longer horizons. Thus, proposed model able simultaneously predict three horizons ( 6 h, 12 and 24 h), across farms located in Spain. We also evaluate performance presented methodology by considering activation functions for hidden neurons neural network: Sigmoid, ReLU, ELUs+2L. results show that multi-source improves single-source counterpart h h). addition, method reduces over 30 % number parameters compared models one per farm), resulting simpler solution problem addressed requiring much lower computational resources.

Язык: Английский

Процитировано

0