Search

One of the major challenges in grid-connected wind farms is the flicker emission caused by the reactive power extremely short time variations. A general used solution is installing a static volt-ampere reactive (VAR) compensator (SVC) as the most cost-saving device, which still holds the risk of incomplete reactive power compensation subject to the operating delay time. To this end, an accurate extreme short-term reactive power forecasting structure is essential. Although there are many studies related to the forecasting of wind power in long, medium, and short terms, however, the extremely short-term reactive power prediction of the wind farms is only addressed in few studies. The main aim in this article is to develop a method based on the convolutional neural network (CNN) to directly learn nonstationary and complex features from the raw wind farm reactive power time series and to contribute a predictive controller to mitigate the voltage flicker through an SVC connected to the wind farm. However, high sensitivity of typical mean-squared-based loss functions might lead to considerable errors in the forecasting. To resolve this issue, a modified loss function is proposed to enhance the performance and, consequently, an improved CNN is presented. The evaluation of the proposed method is based on the actual recorded data of a wind farm in Manjil, Iran. The data are directly used in the modeling of the wind farm. A current source, which is based on the actual records its amplitude and phase angle change every 0.01 s, is utilized to model the wind farm. The numerical results in terms of flicker sensation and short-term flicker perceptibility (Pst) measurement are used to verify the performance of the proposed method through comparison with the wind farm performance without SVC and SVC with a common control system. [ABSTRACT FROM AUTHOR]

One of the prominent problems in wind farms is voltage flicker emission. To prevent flicker emission or mitigate the impact as best as possible, a static VAr compensator (SVC) is a great candidate both economically and technically. However, SVCs cannot completely compensate the fast-changing reactive power due to delays caused by the reactive power calculation unit and the triggering fire angle of the SVC. This paper proposes a predictive control system for SVCs, by merging an additional predictive control block into the conventional control system. It is constructed based on deep neural networks, namely adaptive one-dimensional convolutional neural network (1D-CNN). The training process is conducted based on the adaptive learning weights process to enhance the prediction accuracy and training computational complexity of the 1D-CNN. Numerical results on the actual dataset in a wind farm in Manjil, Iran, have verified the forecasting accuracy and flicker mitigation of the proposed controller. [ABSTRACT FROM AUTHOR]