Open AccessApplication of Deep Learning in Power load Analysis
Author(s) -
Xinhua Duan
Publication year - 2020
Publication title -
international journal of circuits, systems and signal processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.156
H-Index - 13
ISSN - 1998-4464
DOI - 10.46300/9106.2020.14.92
Subject(s) - computer science , artificial intelligence , value (mathematics) , power (physics) , training (meteorology) , sample (material) , deep learning , mean squared error , electric power system , machine learning , data mining , statistics , mathematics , chemistry , physics , chromatography , quantum mechanics , meteorology
Aiming at the problems of slow model training speed and poor prediction effect of traditional power load prediction algorithm, a parallel load prediction method based on deep learning is proposed. The method is based on the MapReduce parallel calculating framework, and the deep belief network model, which is used to parallel training the sample data with the historical load and the weather information, and the model of the training model to predict the load value. The experimental results show that the average root-mean-square error between the predicted power load value and the actual value of the prediction method in this paper is 2.86%. The prediction accuracy is higher than the traditional method, and the training and prediction time are effectively reduced, which can adapt to the prediction requirements of large-scale power data.