Article
Engineering, Ocean
Bharat Kumar Saxena, Sanjeev Mishra, Komaragiri Venkata Subba Rao
Summary: This paper compares six different variants of deep learning models for offshore wind speed forecasting, and finds that EEMD can reduce forecasting error, while the superiority of deep learning models is site specific.
APPLIED OCEAN RESEARCH
(2021)
Article
Mathematics, Interdisciplinary Applications
Yaoyao He, Yun Wang, Shuo Wang, Xin Yao
Summary: This article develops a wind speed probabilistic forecasting model based on the complete ensemble empirical mode decomposition, adaptive noise-least absolute shrinkage and selection operator, and quantile regression neural network, achieving high accuracy and robustness through multi-step prediction and probability density function fitting.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Computer Science, Artificial Intelligence
Zhihao Shang, Yao Chen, Yanhua Chen, Zhiyu Guo, Yi Yang
Summary: With the increase in global energy demand, the proportion of installed wind capacity continues to rise. However, accurately forecasting wind speed is challenging due to the nonlinearity, fluctuation, and intermittence of wind speed time series data. This paper proposes a novel wind speed forecasting model that can capture all implicit information of wind speed data and achieve accurate prediction results.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Thermodynamics
Zheyong Jiang, Jinxing Che, Lina Wang
Summary: This study proposes a novel EMD-VAR wind speed forecasting model based on high-correlation wind speed data from multiple adjacent measuring points. By utilizing multiple adjacent spatial sites to balance information and variance, the model achieves better experimental results with high accuracy and strong stability. The method effectively improves the accuracy and reliability of wind speed forecasting in each season.
ENERGY CONVERSION AND MANAGEMENT
(2021)
Article
Thermodynamics
Dan Li, Fuxin Jiang, Min Chen, Tao Qian
Summary: This paper presents a hybrid decomposition method combining EPT and CEEMDAN for wind speed prediction, integrated with TCN for individual component forecasting. Experimental results demonstrate the significant advantages of this approach in accuracy and stability.
Article
Green & Sustainable Science & Technology
Xue-Jun Chen, Jing Zhao, Xiao-Zhong Jia, Zhong-Long Li
Summary: The study introduces a multi-step forecasting method called ECKIE, which effectively predicts very-short-term wind speed at specific stations. This method reduces forecasting errors through data filtering, clustering, and model construction processes, and outperforms comparable models in simulations.
Article
Thermodynamics
Wendong Yang, Zhirui Tian, Yan Hao
Summary: Wind speed forecasting is crucial for wind power generation, but previous studies focused on model combination and overlooked the opportunities of big data. A novel ensemble model that incorporates mixed-frequency data was developed, achieving excellent forecasting results and making use of the advantages of both mixed-frequency models and artificial intelligence methods.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Thermodynamics
Lean Yu, Yueming Ma, Mengyao Ma
Summary: This paper proposes an effective rolling decomposition-ensemble model for quarterly gasoline consumption forecasting in China, involving data decomposition, component prediction, and ensemble output. By utilizing wavelet decomposition and support vector regression, the model addresses data scarcity issue and improves prediction accuracy.
Article
Thermodynamics
Zhuoyi Liu, Ryoichi Hara, Hiroyuki Kita
Summary: Wind speed forecasting is crucial for power grid dispatch, controllability, and stability, with accuracy being essential for efficient wind resource utilization. A novel hybrid wind speed forecasting system utilizing data area division and deep learning neural network is developed, showing good stability and generalizability in short-term wind speed forecasts. The system effectively improves forecast accuracy compared to conventional methods, demonstrating practicality in area-wide short-term wind power forecasting.
ENERGY CONVERSION AND MANAGEMENT
(2021)
Article
Computer Science, Artificial Intelligence
Rashmi P. Shetty, A. Sathyabhama, P. Srinivasa Pai
Summary: This study proposed a multi-step hybrid online wind speed forecasting (WSF) model, combining different algorithms and technologies for more accurate wind speed prediction. The model, validated with real-world data, is able to better capture the nonlinear characteristics of wind speed, providing accurate wind speed forecasts and helping wind farms efficiently estimate wind power.
Article
Computer Science, Artificial Intelligence
J. J. Ruiz-Aguilar, I Turias, J. Gonzalez-Enrique, D. Urda, D. Elizondo
Summary: Accurate wind speed prediction is crucial for various tasks, especially air pollution modeling. A hybrid wind speed forecasting approach was proposed in this study, combining different methods to achieve higher prediction performance. Experimental results showed that the EMD-PE-ANN model outperformed single ANN models in all tested prediction horizons, indicating that it could be a powerful tool for wind speed forecasting.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Tao Wang
Summary: The study proposed a new wind speed forecasting model that combines multiple techniques, with experimental results showing better performance in multi-step wind speed forecasting.
PEERJ COMPUTER SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Thermodynamics
Rui Yang, Hui Liu, Nikolaos Nikitas, Zhu Duan, Yanfei Li, Ye Li
Summary: The article introduces a novel hybrid model for wind speed prediction, which shows good performance in experiments, accurately capturing changes in wind data and having the best prediction performance compared to state-of-the-art models.
Article
Engineering, Electrical & Electronic
Ping Jiang, Zhenkun Liu, Jianzhou Wang, Lifang Zhang
Summary: In this study, a novel wind speed prediction system is proposed, which can conduct point and interval prediction simultaneously. The system successfully integrates the merits of component models and effectively overcomes the disadvantages of traditional prediction methods. Simulation results demonstrate its important application value in the scheduling and management of power systems.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Energy & Fuels
Yuyang Gao, Chao Qu, Kequan Zhang
Article
Energy & Fuels
Jiyang Wang, Yuyang Gao, Xuejun Chen
Article
Energy & Fuels
Tongxiang Liu, Yu Jin, Yuyang Gao
Article
Energy & Fuels
Ping Jiang, Ranran Li, Ningning Liu, Yuyang Gao
Article
Green & Sustainable Science & Technology
Yuyang Gao, Jianzhou Wang, Hufang Yang
Summary: This study proposes a multi-component hybrid onshore wind speed forecasting system based on predictability recognition framework, k point modified multi-objective golden eagle optimizer, and weight hybrid kernel extreme learning machine. The system shows superior performances on one-step ahead and multi-step ahead forecast and outperforms some typical methods. It can offer a more reliable forecast for onshore wind speed.
Article
Computer Science, Artificial Intelligence
Yuyang Gao, Jianzhou Wang, Xiaobo Zhang, Ranran Li
Summary: This article proposes a novel wind speed prediction system (DRIPS) that improves the accuracy of wind speed prediction by integrating complexity, chaos, and long-term dependence indicators (PDI). Experimental results show that DRIPS performs significantly better than common prediction models and that the integration strategy based on PDI significantly improves prediction accuracy.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Jianzhou Wang, Yuyang Gao
Summary: This study aims to establish an integrated interval forecasting system for solar radiation, using feature extraction and a hybrid kernel relevance vector machine. The proposed system achieves higher coverage rate and narrower interval width in solar radiation forecasting.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Economics
Xiaobo Zhang, Jianzhou Wang, Yuyang Gao