Power load forecasting algorithm based on classified identification deep belief network

曹 敏; 李文云; 钱详华; 王 恩; 李 博; 李 坤; 唐 标; 李海铎; 练 雄

您当前的位置：

首页 >

文章列表页 >

Power load forecasting algorithm based on classified identification deep belief network

更新时间：2026-03-05

- Power load forecasting algorithm based on classified identification deep belief network
- Vol. 22, Issue 2, (2020)
- 作者机构：
  
  1. 云南电网有限责任公司电力科学研究院,昆明,650217
  2. 云南电网有限责任公司,昆明,650217
  3. 云南电网有限责任公司瑞丽供电局,云南瑞丽,678400
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2020
- 稿件说明：
移动端阅览
曹敏, 李文云, 钱详华, et al. Power load forecasting algorithm based on classified identification deep belief network[J]. 2020, 22(2).
DOI：

曹敏, 李文云, 钱详华, et al. Power load forecasting algorithm based on classified identification deep belief network[J]. 2020, 22(2). DOI：

摘要

针对传统神经网络负荷预测方法收敛速度慢、预测误差大的问题，提出一种基于分类识别的深度置信网络的负荷预测算法。对输入的历史负荷数据进行归一化预处理，并对深度置信网络采用层次无监督贪婪预训练方法分层预训练，将得到的结果作为监督学习训练概率模型的初始值。其深度置信网络由多层受限玻尔兹曼机构成，并采用分类识别机制和对比散度的方法训练预权值，来改善分类识别深度置信网络的学习性能。仿真结果显示，在基于200次负荷训练和温度训练的基础上，该负荷预测算法比自组织模糊神经网络和BP神经网络的收敛速度更快，预测精度更高。

Abstract

A load forecasting method based on classified identification deep belief network is proposed to solve the problem ofslow convergence and large prediction error of traditional neural network in load forecasting. In the proposed method

the input historicalload data is normalized firstly. Then

the layered pretraining of thedeep believe machine is implemented by hierarchical unsupervisedgreedy pre training method. Thirdly

the pre training results areused as the initial value of the supervised learning training model.Deep belief network is composed of multilayer restricted boltzmannmachine

and the pre weight of the restricted boltzmann machineand the classification recognition mechanism is trained by means of contrastive divergence. The learning performance of the classified identification deep belief network can be improved by this way. Simulation result shows that the load forecasting algorithm based on the200 times of load training and temperature training

the algorithm has faster convergence speed and higher prediction accuracy than the selforganizing fuzzy neural network and the BP neural network.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Power load dispatch optimization considering dynamic response reliability

Short-term power load forecasting based on parallel sequential convolutional neural network

Weighted load forecasting method based on change trend and meteorological factors

胶合成材（续三）

美国阔叶树材——可持续利用的木材资源记首届美国阔叶树材外销委员会东南亚区大会

Related Author

钱伟强

赵文会

张月

胡春光

赵罡

谭风雷

丁心志

张军

Related Institution

上海电力大学经济与管理学院

国网上海市电力公司浦东供电公司

国网江苏省电力有限公司镇江供电分公司

国网江苏省电力有限公司超高压分公司

云南电力试验研究院（集团）有限公司

AI问答

⁰