Forecasting Energy Demand Using Conditional Random Field and Convolution Neural Network

Electric load forecasting has been identified as an effective strategy to increase output and revenues in electrical manufacturing distribution organizations. Several strategies for power consumption have suggested; however, they all fail account small variations demand throughout the prediction. Therefore, aim of this study was develop a CRF-based prediction technique (CRF-PCP) meet difficulty estimating energy (EC). The EC regions area is forecasted using convolution neural networks (CNNs) conditional random fields (CRFs). Then, cloud, predicted results are delivered electricity system. To our knowledge, first attempt forecast CNN CRF algorithms. In comparison state-of-the-art algorithms, proposed achieves 98.9 % accuracy. This recommended work also obtained minimum values root mean square error (RMSE), (MSE), absolute (MAE), percentage (MAPE), bias (MBE) by 10-fold cross-validation (CV) hold-out methodology.