引用本文:李若晨,朱帆,朱永利,等.结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测[J].电力系统保护与控制,2018,46(17):83-88.
LI Ruochen,ZHU Fan,ZHU Yongli,et al.Short-term power load forecasting using recurrent neural network with restricted Boltzmann machine[J].Power System Protection and Control,2018,46(17):83-88
【打印本页】   【下载PDF全文】   【查看/发表评论】  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被：浏览 5951次   下载 2596次 本文二维码信息
码上扫一扫！
分享到： 微信 更多
字体:加大+|默认|缩小-
结合受限玻尔兹曼机的递归神经网络电力系统短期负荷预测
李若晨1,朱 帆2,朱永利3,翟羽佳4
(1.国网河北省电力有限公司平山县供电分公司，河北 平山 050400;2.首都师范大学哲学系，北京 100037; 3.华北电力大学控制与计算机工程学院，河北 保定 071000;4.华北电力大学电力工程系，河北 保定 071000)
摘要:
短期负荷预测的重要性随着电力企业的发展不断提高。传统的负荷预测虽然已经发展相对成熟，但现阶段对负荷预测的准确性要求逐渐提高。为满足发展需要，则要对现有的方法进行改进或建立新的预测方法。通过分析负荷预测数据周期性及周期内的特征，结合递归神经网络在分析时间序列数据的独特优势和受限玻尔兹曼机的强大的无监督学习能力，对结合受限玻尔兹曼机的递归神经网络的工作原理及训练过程进行了阐述。利用该网络进行了电力负荷数据预测实验验证并与其他神经网络进行了比较性实验。结果表明，所提出的神经网络较其他网络在电力短期负荷预测实验中有更高的准确性。
关键词:  负荷预测  递归神经网络  受限玻尔兹曼机  时间序列
DOI：10.7667/PSPC171255
分类号:
基金项目:国家自然科学基金项目资助(51677072)
Short-term power load forecasting using recurrent neural network with restricted Boltzmann machine
LI Ruochen1,ZHU Fan2,ZHU Yongli3,ZHAI Yujia4
(1. State Grid Hebei Power Co., Ltd. Pingshan County Power Supply Branch, Pingshan 050400, China;2. Philosophy Department, Capital Normal University, Beijing 100037, China;3. School of Control and Computer Engineering, North China Electric Power University, Baoding 071000, China;4. Department of Electrical Engineering, North China Electric Power University, Baoding 071000, China)
Abstract:
The importance of short-term power load forecasting continues to improve with the development of power enterprises. Although the traditional load forecast has been developed relatively mature, the load forecast accuracy requirements gradually increase now. To meet the development needs, existing methods should be improved or new methods of prediction should be established. This paper analyzes the periodic load forecasting and periodic characteristics of load forecasting data. It also combines recursive neural networks with Limited Boltzmann machine's strong unsupervised learning ability in analyzing the unique advantages of time series data. The network principle and training process of the combination are described and the electric load data are predicted by experiment. The experiment compares the accuracy of the network and other networks in short-term load forecasting. The results show that the neural network proposed in this paper is more accurate than other networks in the power short-term load prediction experiment. This work is supported by National Natural Science Foundation of China (No. 51677072).
Key words:  power load forecasting  recurrent neural network  restricted Boltzmann machine  time series
  • 1
X关闭
  • 1
X关闭