现代电力2018，Vol.35Issue(2)：43-48,6.
基于深度学习的电网短期负荷预测方法研究
Research on Short-term Load Forecasting Method of Power Grid Based on Deep Learning
摘要
Abstract
The depth model achieves complex function ap-proximation by learning a deep nonlinear network structure, which has strong adaptive perception ability.In order to im-prove the prediction accuracy of power load,a deep learning prediction method based on stacked auto-encoder neural net-work is proposed in the paper.A multi-input single-output prediction model is built by combing the auto-encoder with the logic regression classifier,such data as the reconstructed historical load,meteorological elements and so on are all in-put into prediction model,and the load characteristics is ex-tracted through the hierarchical learning of the stacked auto-encoder.Finally,the short-term load prediction is realized by using the logical regression model at the top of the net-work.Case analysis shows that the proposed model can ef-fectively characterize the daily load change law with strong generalization performance,and its prediction accuracy can reach 9 6.2 %,which is higher than that of two shallow learning models based on support vector regression and fuzzy neural network respectively.关键词
负荷预测/深度学习/栈式自编码器/特征提取/神经网络Key words
load forecasting/deep learning/stacked auto-en-coder/feature extraction/neural network分类
信息技术与安全科学引用本文复制引用
吴润泽,包正睿,宋雪莹,邓伟..基于深度学习的电网短期负荷预测方法研究[J].现代电力,2018,35(2):43-48,6.基金项目
国家自然科学基金资助项目(51507063) （51507063）
国家电网公司科技项目(B34681150152) （B34681150152）
