An Innovative Method for Electricity Load Forecasting in the Agriculture Sector Using a Restricted Boltzmann Machine (RBM) Model

While a large percentage of Indians work in agriculture, the sector's impact on the country's GDP is minimal. Therefore, in order to enhance and boost productivity, energy forecasting is essential. Diesel engines, power plants, and coal mines supply much of the energy that farms require. One of these essential energy needs is watering crops. Power projections are also crucial to demand response management. Preprocessing and training the model make up the suggested approach. In this case, feature selection, SVD, and normalizing make up the preprocessing. Prior to evaluating the electrical demand in the agricultural sector, we catalogued the several elements impacting the power load. The preprocessing steps gather data on the amount of electricity consumed by farms. The results demonstrate that the incorporation of external features leads to improved predicting accuracy. The RBM was used for training the model. This cutting-edge method outperforms DNN and SVR, averaging a 92.69% accuracy rate.