,
Department of Electronics and Communication Engineering, KGiSL Institute of Technology , Coimbatore, Tamil Nadu , India
Department of Computer Science and Engineering, PSG Institute of Technology and Applied Research , Coimbatore, Tamil Nadu , India
The stability of smart grids (SG) plays a critical role in improving the stability of power supply, particularly when system failures or sensor breakdowns could occur and result in a lack of input data. This paper provides a new method of prediction of smart grid consistency by using a Gradient Policy prediction model, which is based on reinforcement learning to tackle the problem of incomplete input features. With the help of deep neural networks, the model predicts the stability of the four-node star network even in the case of incomplete information. The suggested model is assessed based on the statistical measures of R-values and Mean Squared Error (MSE), and the findings show considerable improvement in the prediction of stability. Precisely, the model attained an R-value of 0.97 and an MSE value of 125, which is higher in predictive accuracy and stability than conventional methods. Also, an ablation study was done to evaluate how the absence of data affected the performance of the prediction. The results indicate that the model is capable of detecting and offsetting the lost input variables, which is why it is a valid instrument in predicting smart grid stability. The subsequent study will aim at expanding this approach to include other, more nonlinear variables, such as price elasticity and consumer response time, to improve the level of prediction.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.