Abstract
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.
Highlights
static VAr compensator (SVC) suffers from an inherent time delay problem, which adversely affects the performance of reactive power compensation in the wind farms
An adaptive 1D-CNN based structure is designed as an extreme short-term forecasting engine and applied as an additional block to compensate for the inherent delay by SVC
The results demonstrate the superiority of the proposed method based on four different accuracy metrics and computational complexity, more than 12% improvement in terms of accuracy, and lower computational time in comparison with deep CNN-based networks
Summary
Wind speed variation could cause voltage fluctuation in terms of flicker phenomenon in connection point of wind turbine and electric grid. Flicker emission is significantly increased in the grid-connected wind farm due to the variation in metrological data such as wind speed and failures of electronic and mechanical components of the wind turbines. This section briefly introduces the principle of the proposed extremely short-term forecasting control system for the SVCs in largescale wind farms. The amplitude of voltage and corresponding angles are highly influenced by inherent intermittency of wind speed, voltage at PCC is obtained as: VPCC = Vgrid + I(R + j X) (1). According to reference value of voltage at the PCC, VPreCfC, VPCC is obtained based on line power flow P and Q can be rewritten as: P − jQ. The voltage angle between the voltage at the PCC and voltage at the MV/HV substation is typically small, while voltage amplitude is adversely changing, which is determined by the first term in (3),
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call