Advanced machine learning algorithms for reactive power forecasting in electric distribution systems

Due to the rising penetration of distributed generators to the current microgrids, reactive power management has become a crucial concern in terms of voltage stability and resilience of smart grids. In this regard, reactive power forecasting (RPF) is an essential tool for maintaining the reactive power management and planning of active electric distribution systems in which power flow is bidirectional. Machine learning (ML)-based algorithms are frequently applied to electric load forecasting owing to the fact that these methods achieve more accurate results in the short-term horizon. One challenging implementation of electric load forecasting, RPF which can be characterised as a nonlinear problem with a variety of explanatory variables such as active and lagging reactive power values. In this paper, a real-time short-term RPF using ML-based algorithms including long short-term memory (LSTM), random forest (RF), and extreme gradient boosting decision trees (XGBoost) will be employed for an electric distribution system located in the North of England, UK. The study also incorporates convolutional neural network (CNN), gated recurrent unit (GRU), and light gradient boosting machine (LightGBM) for benchmarking and efficient comparison of the main selected methods. The experimental results demonstrate that LightGBM outperforms other models which achieves the highest accuracy with an R 2 of 95.37% and the lowest root mean squared scaled error (RMSSE) of 0.541 while maintaining the shortest computation time of 0.396 s. These findings highlight the potential of ML-based RPF techniques for improving voltage stability, optimising reactive power compensation, and enhancing energy efficiency in modern smart grids. To the best of our knowledge, there is a lack in the current literature for real-time applications of RPF and this paper is considered to fill this deficiency along with aspiring researchers in the field. • Smart grid advancements highlight the role of reactive power forecasting (RPF). • Short-term RPF is vital for voltage stability, power tracking, and demand planning. • LSTM, RF, XGBoost, CNN, GRU & LightGBM were applied to RPF at Liversedge, UK. • LightGBM outperformed all models achieving the highest accuracy across metrics. • This study addresses a gap emphasizing RPF over active power forecasting.