LSTM Short-Term Wind Power Prediction Method Based on Data Preprocessing and Variational Modal Decomposition for Soft Sensors

Abstract

Soft sensors have been extensively utilized to approximate real-time power prediction in wind power generation, which is challenging to measure instantaneously. The short-term forecast of wind power aims at providing a reference for the dispatch of the intraday power grid. This study proposes a soft sensor model based on the Long Short-Term Memory (LSTM) network by combining data preprocessing with Variational Modal Decomposition (VMD) to improve wind power prediction accuracy. It does so by adopting the isolation forest algorithm for anomaly detection of the original wind power series and processing the missing data by multiple imputation. Based on the process data samples, VMD technology is used to achieve power data decomposition and noise reduction. The LSTM network is introduced to predict each modal component separately, and further sum reconstructs the prediction results of each component to complete the wind power prediction. From the experimental results, it can be seen that the LSTM network which uses an Adam optimizing algorithm has better convergence accuracy. The VMD method exhibited superior decomposition outcomes due to its inherent Wiener filter capabilities, which effectively mitigate noise and forestall modal aliasing. The Mean Absolute Percentage Error (MAPE) was reduced by 9.3508%, which indicates that the LSTM network combined with the VMD method has better prediction accuracy.

A Soft Sensor for Flow Estimation and Uncertainty Analysis Based on Artificial Intelligence: A Case Study of Water Supply Systems

“…A recent application of LSTM networks was made by Lei et al [22], which predicted each modal component of energy produced from wind sources. One of the contributions of that work consists of the application of variational modal decomposition (VMD) to decompose the already processed data into K modal components in order to improve the quality of the soft sensor estimate.…”

“…In this work, LSTM was chosen due to the advantages mentioned in the previous section, and the works cited here reinforce the trend towards its adoption. Some of the differences of this work, when compared to those mentioned above, are the incorporation of outlier detection (observed only in [22,23]) and the use of Monte Carlo dropout in addition to the tests carried out in a real water distribution environment. In this article, we propose an LSTM-based model with Monte Carlo dropout to be used in soft flow sensors with outliers treatment based on TEDA, and the results obtained in field tests are shown in order to demonstrate the validity of the proposed approach in real scenarios.…”