Artificial Intelligence Based Regression Models for Prediction of Smart Grid Stability

In parallel with the rapid increase in the world population and the rapid development of technology day by day, the need for electrical energy is increasing to this extent. However, today, due to the limited energy resources, electrical energy must be utilized efficiently and reach the users. Today, electrical smart grids play an important role in ensuring electrical grid stability. Artificial intelligence (AI) applications are used to ensure electricity grid stability. In this study, artificial intelligence based regression models (Gaussian Process Regression, Support Vector Machine Regression, Generalized Regression of Neural Network, Linear Regression and Decision Tree Regression) were employed to predict electricity grid stability. The coefficient of determination (R2) and error parameters Mean squared error (MSE), Mean Absolute Error (MAE) resulting from these models were analyzed. Finally, good results have been obtained to the proposed approach. The results show that with the proposed models, the energy demand-response balance can be department from these estimations, and the load and pricing can be made more effectively in the smart grid system. Also, for the Smart grid, a small estimation difference eliminates billions of dollars in investment and operating costs. Strong global growth in grid-integrated renewable energy deployment was supported by a variety of policies addressing energy security, local pollution issues and climate goals.