3/2/2024 0 Comments Vmd modelThe physical methods generally apply to the single-step prediction. The physical method refers to a wind power prediction method based solely on the historical wind power data and the Numerical Weather Prediction (NWP) data ( Louka et al., 2008 De Giorgi et al., 2011 Cassola and Burlando, 2012 Liu et al., 2020a). The mentioned methods can fall into three main categories, i.e., statistical methods, physical methods ( Wu et al., 2017), and combined prediction methods ( Han et al., 2019). Relevant researchers have adopted a range of methods for the single-step and multi-step predictions of wind power. On the whole, the existing multi-step prediction of wind power has been conducted based on the single-step prediction. Accordingly, correcting the cumulative error to conduct the multi-step prediction of wind power should be solved urgently. The phenomenon will increase the difficulty of the multi-step prediction of wind power. The cumulative error of wind power will increase as the number of prediction steps rises continuously ( Chen et al., 2017). However, the conventional multi-step rolling prediction model should exploit the wind power predicted at the previous moment to predict the wind power at the subsequent moment and the prediction result at the subsequent moment will accumulate the prediction error of the previous moment. Since wind power is continuously connected to the power system, the requirements for step length of its prediction are gradually increasing and the accuracy requirements are gradually becoming higher. Because wind power output is found to be intermittent and stochastic, an accurate wind power prediction method acts as a vital technical tool to ensure the safe, stable, and economic operation of the power system ( Ye and Zhao, 2014). The global installed wind power capacity is expected to reach nearly 800 GW by 2021 ( Global Wind Energy Council, 2021). Wind energy will become the most promising clean energy source for its inexhaustible and renewable characteristics ( Du et al., 2017). The increasing depletion of traditional energy sources (e.g., fossil fuels and natural gas) has greatly challenged the development of power systems ( Wu et al., 2020). The method is superior in terms of the accuracy and stability of wind power prediction. It can be seen that the wind power prediction method proposed in this study could improve the feature extraction ability of TCN for input sequences and the ability of mining the mapping relationship between multiple inputs and multiple outputs. The MAE and RMSE metrics outperformed those of the VMD-AMS-TCN and MSC-SA-TCN models. As revealed from the results, the MAE and RMSE of the MMED-TCN-based multi-step prediction model achieved the cumulative mean values of 0.0737 and 0.1018. An experimental comparative analysis was conducted based on the measured data from two wind farms in Shuangzitai, Liaoning, and Keqi, Inner Mongolia. The MMED-TCN multi-step wind power prediction model was developed to separate linearity and nonlinearity between input and output to reduce the multi-step prediction error. The method improved the problem that a single TCN is difficult to tap the different nonlinear relationships between the multi-step prediction output and the fixed input. On that basis, the multi-channel time convolutional network with multiple input and multiple output codec technologies was adopted to build the nonlinear mapping between the output and input of the TCN multi-step prediction. The MSC-SA-TCN model was built to recognize and extract different features exhibited by the input sequence to improve the accuracy and stability of the single-step prediction of wind power. First, multi-scale convolution (MSC) and self-attentiveness (SA) were adopted to optimize the problem that a single-scale convolution kernel of TCN is difficult to extract temporal and spatial features at different scales of the input sequence. In this study, a multi-step wind power prediction method was proposed by exploiting improved TCN to correct the cumulative error. Correcting the cumulative error to predict wind power in multi-step is an urgent problem that needs to be solved. Since wind power is continuously connected to power systems, the step length required for predicting wind power is increasingly extended, thereby causing an increasing cumulative error. Wind power generation is likely to hinder the safe and stable operations of power systems for its irregularity, intermittency, and non-smoothness. 2State Grid Jiangsu Electric Power Co.1Nanjing Tech University, Nanjing, China.Haifeng Luo 1 Xun Dou 1* Rong Sun 2 Shengjun Wu 2
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |