Enhancement of SmartGrid Stability by Optimal Energy Management System (EMS) through Deep Learning

Electrical power networks depend on power system stability to provide dependable and continuous operation. It speaks to a power system's capacity to continue operating in a balanced and steady manner after minor and major disruptions. The stability of the electricity system is necessary to avoid large-scale blackouts and guarantee that customers will always have access to energy. The most momentous obstacle to generating a steady flow of electricity at a low cost is the fluctuating pattern of generation, load, and demand. To address this problem, a day-ahead energy management system (EMS) based on deep learning has been proposed; it offers the necessary functionality to guarantee that the energy production systems balance stability levels at the lowest possible operational costs. A Convolutional Neural Network (CNN) and CNN-Multilayer Perceptron (CNN-MLP) approach has been created for forecasting the accuracy level of electricity balance stability with the use of demand-side management (DSM). To improve outcomes, the dataset has been subjected to data analysis and feature scaling. The customer response time regarding the electricity production dataset, established statistical parameters, and minimum price elasticity coefficients (0.05–1) were examined in addition to the time-domain simulation findings to verify the stability of the power network. A score of 93.75% accuracy is offered by the proposed CNN-MLP model, whereas CNN delivers 93.55% accuracy. The outcome of this suggested optimized deep learning CNN-MLP predictive model, which uses the Adam optimizer, indicates that it is much more beneficial than the CNN predictive model in terms of properly monitoring the balance of power and providing it to clients at a reasonable price.