Predictive Modeling of Energy Consumption in Smart Grids using Artificial Neural Networks

Abstract

This study delves into the ground-breaking applications of optical fiber grids for material analysis. In it, we look at the correlation between light intensity and temperature, analyze the material composition, and conduct a comprehensive examination into sensor calibration. Optical fiber grids are quite accurate in detecting changes in temperature and refractive index, as shown by the calibration results, which showed an outstanding average accuracy of 98%. The grids were able to distinguish between different materials with an average accuracy of 96%, according to the material composition research. The correct identification of a polymer sample with 45% polyethylene and 55% polypropylene demonstrated this. Also, the grids were able to properly react to changing temperatures since there was a strong linear relationship between light intensity and temperature (92 percent explanatory power). Taken together, the findings highlight optical fiber grids’ versatility and reliability, showing how they might revolutionize material research across several industries.