Intelligent voltage prediction of active distribution network with high proportion of distributed photovoltaics

Abstract

The access of high proportion of zero carbon energy, such as distributed photovoltaics (DPVs), makes the voltage time series of the new active distribution network (ADN) show a high degree of volatility and randomness, which brings great difficulties to voltage prediction. Hence, a voltage prediction method named VMD-XGBTCN that combining variable modal decomposition (VMD), extreme gradient boosting (XGBoost) and temporal convolutional network (TCN) to achieve an accurate voltage prediction. Primarily, it uses three spline interpolation functions to fill the historical voltage and power data with missing values to obtain a reliable sample data set and breaks down the voltage time series into multiple sub-signal modes by VMD to reduce data non-stability. It also uses the XGBoost to extract multiple characteristic features affecting voltage, avoiding the limitations of single feature importance measurement. Finally, it improves overall prediction accuracy by using optimization of the data input of TCN and overlay of the prediction outputs. Simulation results show that the proposed voltage intelligent prediction method fully integrates data feature extraction, combined prediction and residual correction compared with the traditional methods, and has better application effect on the accuracy and efficiency of voltage prediction.

Keywords

• Extreme gradient boosting
• Three spline interpolation
• Time convolution network
• Variable mode decomposition