Distribution System Nodal Voltage Forecasting Based on GCN-LSTM

초록

Amid evolving energy policies and increasingly diversified electricity consumption patterns, the operational complexity of distribution systems has intensified, leading to amplified voltage variability and heightened operational uncertainty. Time-varying load characteristics and dynamic network operating conditions contribute to inefficient system operation and pose challenges to voltage stability. As voltage directly influences the dynamic stability of a system, accurate voltage forecasting is essential for improving the reliability of system operation. Traditionally, voltage forecasting of individual buses relies primarily on load forecasting followed by power flow calculations. However, more efficient voltage forecasting methods are needed to account for the dynamic nature of voltage variations. In this study, we propose a voltage-forecasting model that integrates load forecasting based on graph convolutional network-long short-term memory (GCN-LSTM) with power-flow calculations. By considering the spatial characteristics derived from the physical configuration of the distribution system and the temporal characteristics, we predict the voltage magnitude and phase angle of each bus. A case study of a distribution system using real data from South Korea is conducted to evaluate the prediction accuracy and computational efficiency of the proposed method. When evaluated on a dataset characterized by seasonal variability, the proposed model reduced prediction errors by 7.8% to 29.9% compared with the benchmark models. These results demonstrate that, in scenarios where conventional approaches suffer from error propagation-originating from load forecasting and subsequently amplified through the power flow calculation stage-the proposed unified framework plays a significant role in enhancing the reliability of voltage forecasting.

키워드