Electric Power Substitute End-use Energy Evaluation Model Based on Deep Learning

Because of low efficiency and accuracy in the domain in the’ oposed an evaluation model based on the method of deep learning and designed a optimal RBM training algorithm. The comparative experimental model in this paper mainly adopts naive Bayesian model algorithm, restricted Boltzmann machine model algorithm and perceptron model algorithm, respectively based on the training data of the algorithm model in this paper. The algorithm proposed in this paper can obtain high calculation accuracy under the condition of given training sample data, and also has good calculation accuracy in terms of running time. In the process of model training, the model proposed in this paper can obtain high accuracy in less training time, and the model has the least calculation time. The results have a good capacity of extracting features and can reflect the essential features by comparing the result with other different modern optimization algorithms.