M2TNet: Multi-modal multi-task Transformer network for ultra-short-term wind power multi-step forecasting

Wang, Lei; He, Yigang; Liu, Xiaoyan; Li, Lie; Shao, Kaixuan

doi:10.1016/j.egyr.2022.05.290

Cited by 34 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, deep learning methods have shown promising performance in the field of computer vision, natural language processing and speech recognition [10]. A number of deep learning-based methods have been proposed to predict wind power, such as long short-term memory (LSTM) [11], convolutional neural network (CNN) [12], graph neural network (GNN) [13] and transformer models [14], achieving outstanding prediction performance. neural network (ANN) model to consider both meteorological features and turbine-level signals [15], while Miele et al utilized two LSTM-based modules to combine local information from the turbine's internal operating conditions with future meteorological data from the surrounding area [16].…”

Section: Introductionmentioning

confidence: 99%

Multi-modal transformer-based wind power prediction by utilizing heterogeneous sources

Han,

Liang,

Zhu

2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

The increasing global energy shortage necessitates a swift transition to renewable energy sources, with wind power emerging as a cost-effective and environmentally friendly option. However, the non-stationary, random, and intermittent nature of wind poses challenges for power grid management, leading to inefficiency and energy supply-demand imbalances. To address these issues, various computational methods have been developed, including multi-modal machine learning methods. However, existing ANN or LSTM-based methods fail to learn complex patterns from heterogeneous features efficiently, especially when NWP forecast map data is considered. Thus, this paper presents a multi-modal transformer-based deep learning approach for wind power prediction, utilizing transformer model and vision transformer model to handle both historical turbine-level time-series data and NWP forecast map data. Extensive experiments demonstrate the model's ability to handle heterogeneous features effectively, outperforming benchmark algorithms in wind power prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-modal transformer-based wind power prediction by utilizing heterogeneous sources

Han,

Liang,

Zhu

2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

show abstract

“…As newer and more productive structures [23,24] arise, CLFormer [25] networks optimized by a linear attention mechanism and convolutional embedding have maximized the ability to efficiently extract global features for fault diagnosis. Some architectures, such as VIT [26], exhibit strong fault diagnosis capabilities as vision models.…”

Section: Introductionmentioning

confidence: 99%

“…The CSWin Transformer [28] proposes a cross-shaped window self-attention mechanism in both horizontal and vertical dimensions. Swin-T and MLP are combined in the SwinMLP [24] network, which employs Swin-T for image feature extraction and MLP for feature classification.…”

Section: Introductionmentioning

confidence: 99%

A multi-stream multi-scale lightweight SwinMLP network with an adaptive channel-spatial soft threshold for online fault diagnosis of power transformers

Liu

2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

The fault diagnosis of power equipment is extremely crucial to the stability of the power grid system. However, complex operating environments, high costs and limitations of single-modal signals are the biggest bottlenecks. To this end, a Multi-Stream Multi-Scale Lightweight SwinMLP Network (MLSNet) with adaptive channel-spatial soft threshold is proposed in this paper. First, a Res2net-based feature-enhanced method is used to learn the correlated features of vibration and voltage multi-modal signals. Second, a novel MLSNet isdesigned to combine the benefits of SwinMLP with lightweight CNN, and employs a staged model to extractvarious scale features. Third,module is intended an adaptive deep fusion approachto integrate employing a channel-spatial soft thresholdand recalibrate staged information at different scales. The overall accuracy ofthe proposed method can reach 99.20% by various experiments, aiming to make it an effective method for online fault diagnosis of power transformers.

show abstract

“…Wind speed prediction methods generally use machine learning or statistical approaches [11], without the need to establish physical models related to the actual environment, such as terrain, surface roughness, and meteorological conditions [12]. Statistical methods typically establish mapping relationships between data by learning the patterns of historical wind speed data, including Kalman filtering [13,14], exponential smoothing [15], and AutoRegressive Integrated Moving Average (ARIMA) models [16,17].…”

Section: Introductionmentioning

confidence: 99%

A Combined Wind Forecasting Model Based on SSA and WNN: Application on Real Case of Ningbo Zhoushan Port

Gu,

Xu,

Tang

et al. 2023

JMSE

View full text Add to dashboard Cite

Wind energy is an effective way to reduce emissions in ports. However, port wind power generation exhibits strong intermittency and randomness. Predicting port wind speed enables timely scheduling of port operations and improves wind energy utilization efficiency. To achieve high accuracy and rapid prediction of port wind speed, this paper proposes a wind speed prediction model based on the Sparrow Search Algorithm (SSA) optimized Wavelet Neural Network (WNN). Firstly, the SSA is used to optimize the Mean Squared Error (MSE) as the fitness function during the training process of the WNN model, obtaining the optimal fitness value corresponding to the network parameters. Then, the obtained parameters are used as the network model parameters of WNN for wind speed prediction. To validate the effectiveness of the proposed method, the model is validated using the measured wind speed data from the Chuanshan Port Area of Ningbo-Zhoushan Port throughout 2022, and its performance is compared with three other models: SSA–BP, SSA–LSTM, and WNN. The results demonstrate that the proposed prediction model exhibits good performance in port wind speed prediction and outperforms the other comparative models in terms of prediction accuracy and convergence speed.

show abstract

M2TNet: Multi-modal multi-task Transformer network for ultra-short-term wind power multi-step forecasting

Cited by 34 publications

References 24 publications

Multi-modal transformer-based wind power prediction by utilizing heterogeneous sources

Multi-modal transformer-based wind power prediction by utilizing heterogeneous sources

A multi-stream multi-scale lightweight SwinMLP network with an adaptive channel-spatial soft threshold for online fault diagnosis of power transformers

A Combined Wind Forecasting Model Based on SSA and WNN: Application on Real Case of Ningbo Zhoushan Port

Contact Info

Product

Resources

About