Novel machine learning approach for enhanced smart grid power use and price prediction using advanced shark Smell-Tuned flexible support vector machine

Abstract Energy management has enhanced sustainability, dependability, and efficiency in smart grids. Urbanisation, technology, and consumer behaviour have boosted need for innovative power use and price control systems. The paper intends to construct ML for smart grid power use and price prediction. This work used an advanced shark smell-tuned flexible support vector machine (ASS-FSVM) to forecast smart grid price and power use. Weather stations, smart meters, and market price databases document power use and pricing. The quality and consistency of data are enhanced via the processes of cleaning and normalizing inputs. PCA reduces dimensionality by extracting pre-processed data characteristics. Optimized and tested FSVM models can anticipate smart grid power use and pricing. ASS may identify the most important dataset properties. The research evaluates electricity consumption forecasting using accuracy (98.05%), recall (98.93%), precision (97.10%), and F1-score (98.04%), and electricity price predicting using MAPE (4.32%), RMSE (5.80%), MSE (8.50%), and MAE (2.95%). The recommended strategy greatly increases forecast accuracy, helping utilities improve grid stability, demand responsiveness, and customer pricing.