A Multi-Step Prediction Method for Wind Power Based on Improved TCN to Correct Cumulative Error

Haifeng Luo,Rong Sun,Shengjun Wu,Xun Dou

doi:10.3389/fenrg.2021.723319

Haifeng Luo, Rong Sun + Show 2 more

Open Access

https://doi.org/10.3389/fenrg.2021.723319

Copy DOI

Abstract

Wind power generation is likely to hinder the safe and stable operations of power systems for its irregularity, intermittency, and non-smoothness. 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. Correcting the cumulative error to predict wind power in multi-step is an urgent problem that needs to be solved. In this study, a multi-step wind power prediction method was proposed by exploiting improved TCN to correct the cumulative error. 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. 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. 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 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. 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. An experimental comparative analysis was conducted based on the measured data from two wind farms in Shuangzitai, Liaoning, and Keqi, Inner Mongolia. 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. The MAE and RMSE metrics outperformed those of the VMD-AMS-TCN and MSC-SA-TCN models. 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 method is superior in terms of the accuracy and stability of wind power prediction.

Highlights

To solve the problem that the size of the convolution kernel of the conventional TCN model is fixed, in order to reduce the difficulty in extracting the multi-scale temporal and spatial features extracted from the input sequence, this study proposed an improved TCN model based on multi-scale convolution (MSC)-SA
Six metrics were adopted to assess the performance of the model, i.e., Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), MAE lift (PMAE), and RMSE lift (PRMSE) of the prediction results of the two models and MAE
To cope with the cumulative error in the wind power multi-step prediction, a wind power multi-step prediction method based on improved TCN to correct the cumulative error was proposed in this study

Summary

INTRODUCTION

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). Deep learning models comprise Neural Network Model (Zhou et al, 2018), Long Short-Term Memory (LSTM) (Li et al, 2018; Li et al, 2020; Liu and Liu, 2021), and Gated Recurrent Unit (GRU) (Hochreiter and Schmidhuber, 1997; Chung et al, 2014) They are capable of fully exploiting the temporal and spatial characteristics of the input sequence to improve further the accuracy of the single-step prediction of wind power. The combined prediction method refers to a wind power prediction method that maintains the advantages of all single prediction models to achieve more accurate and stable predictions It is generally used in wind power multi-step prediction. In Conclusion, relevant conclusions and subsequent research directions are given

Introduction to the TCN Model

Introduction

Evaluation Metrics

CONCLUSION