Smart grid stability prediction using Adaptive Aquila Optimizer and ensemble stacked BiLSTM

Abstract

Background Smart grids, characterized by their ability to integrate renewable energy sources and manage the dynamic balance between supply and demand, require sophisticated prediction models to maintain stability. Traditional machine learning (ML) models often fall short in predicting the highly variable nature of smart grid operations. Methods This study introduces an ensemble stacked bidirectional Long Short-Term Memory model enhanced by a proposed Adaptive Aquila Optimizer (AAO). The AAO uses a Sigmoid Factor to balance exploration and exploitation, adapting the transition from broad searches to focused ones based on iteration progress. It is utilized for feature selection by identifying and excluding irrelevant and redundant features and methodically evaluates seven key hyperparameters to fine-tune the model's performance. Additionally, a weighted voting mechanism is employed to aggregate predictions in the ensemble model. Results Multiple rounds of empirical experiments using different sets of optimizers and configurations, supported by the visualization capabilities of TensorBoard, demonstrate significant improvements in the performance of the AAO-BiLSTM model. The results show profound potential with accuracy, precision, recall, and F1-score rates of 99.55%, surpassing both traditional ML algorithms and state-of-the-art approaches. • An Adaptive Aquila Optimizer (AAO) uses an adaptive Sigmoid Factor for effective hyperparameter tuning and feature selection. • An ensemble stacked BiLSTM enhanced by the proposed AAO, utilizing a weighted voting mechanism to aggregate predictions. • Multiple rounds of experiments visualized using TensorBoard provide interpretable insights into the model's effectiveness. • The AAO-BiLSTM outperforms state-of-the-art models, achieving accuracy, precision, recall, and F1-score of up to 99.55%.