Electrical Load Forecasting using Improved Feature Selection and Hybrid Deep Learning Algorithms for Power System Situational Awareness

Accurate electrical load prediction is imperative for effective energy management, grid stability, and resource planning. This research endeavours to enhance forecasting precision by developing an advanced electrical load forecasting model that integrates improved feature selection and hybrid deep learning algorithms. In this study, a novel Electrical Load Forecasting model is meticulously crafted, encompassing phases of pre-processing, feature extraction, feature selection, and the prediction phase. The process initiates with the pre-processing of raw data, employing data cleaning and normalization techniques for ensuring data quality and consistency. Relevant features for load forecasting, including Improved Principal Component Analysis, Skewness, Kurtosis, and Variance-based features, are subsequently extracted. The research introduces a novel Improved Information Gain approach for feature selection, aiming to discern the most informative and discriminative features crucial for precise load forecasting. Additionally, a hybrid classifier model is implemented in the load forecasting phase, synergizing the strengths of deep learning classifiers - the Artificial Neural Network and Long Short-Term Memory. The ANN and LSTM models are adeptly trained using the selected features acquired from the Improved Information Gain approach. The predictions from both LSTM and ANN models are intelligently fused to yield the final load forecasting outcome. This comprehensive approach contributes to the advancement of electrical load forecasting models, providing a robust framework for accurate predictions and informed decision-making in the realm of energy management and planning.