A Novel Energy Accounting Model Using Fuzzy Restricted Boltzmann Machine—Recurrent Neural Network

Energy accounting is a system for regularly measuring, analyzing, and reporting the energy use of various activities. This done to increase efficiency monitor impact usage on environment. Primary now by determining amount fossil fuel required generate it. However, if fuels become scarcer, this strategy becomes less viable. Instead, new approach will be required, one that takes into consideration intermittent character two most prevalent renewable sources, wind solar power. Furthermore, estimation consumption data collected from household surveys, whether using recall-based or meter-based one, remains difficult task. Hence, paper proposes novel model Fuzzy Restricted Boltzmann Machine-Recurrent Neural Network (FRBM-RNN). The dataset preprocessed linear-scaling normalization. proposed optimized Adaptive Adam Optimization Algorithm (AFAOA). performance metrics like Mean Square Error (MSE), Root (RMSE), Absolute (MAE), Percentage (MAPE) are estimated. estimated results our technique MSE (0.19), RMSE (0.44), MAE (0.2), MAPE (3.5).