Key technologies of load forecasting in distribution network based on big data platform

张小斐; 耿俊成; 万迪明; 刘充许; 周双喜

您当前的位置：

首页 >

文章列表页 >

Key technologies of load forecasting in distribution network based on big data platform

更新时间：2026-03-05

- Key technologies of load forecasting in distribution network based on big data platform
- Vol. 22, Issue 4, (2020)
- 作者机构：
  
  1. 国网河南省电力公司电力科学研究院,郑州,450052
  2. 清华大学电机工程与应用电子技术系,北京,100084
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2020
- 稿件说明：
移动端阅览
张小斐, 耿俊成, 万迪明, et al. Key technologies of load forecasting in distribution network based on big data platform[J]. 2020, 22(4).
DOI：

张小斐, 耿俊成, 万迪明, et al. Key technologies of load forecasting in distribution network based on big data platform[J]. 2020, 22(4). DOI：

摘要

大规模配电网负荷预测需重点关注预测准确率及计算效率，由于规模大、关联因素复杂，采用传统集中式或简单分布式平台环境难以满足应用要求。提出了基于大数据平台的解决方案，方案结合大规模配电网负荷预测应用场景特点，提出了数据存储、数据预处理、特性分析、预测算法等关键环节的技术路线。应用多元化分布式存储方式，实现了多类型数据的分类存储；应用机器学习技术，实现了数据预处理、负荷特性分析等；应用Spark流计算技术，实现了基于滑动窗口操作的滚动短期预测和基于无状态操作的中长期预测。在某省的实际应用结果证明了解决方案在预测准确率和计算效率提升方面效果明显。

Abstract

Load forecasting of large scale distribution network needs to focus on the accuracy and calculation efficiency. Because of the large scale and complex correlation factors

the traditional centralized or simple distributed platform environment is difficult to meet the application requirements. A solution based on the big data platform is proposed. Combined with the characteristics of large-scale distribution network load forecasting application scenario

the technical route of key links such as data storage

data preprocessing

characteristic analysis

forecasting algorithm

etc. is proposed in the scheme. The classified storage of multiple types of data is realized by the application of diversified distributed storage mode；data preprocessing

load characteristic analysis

etc. is realized by the application of machine learning technology；rolling shortterm forecasting based on sliding window operation and medium and long-term forecasting based on stateless operation is realized by the application of spark stream computing technology. The practical application results in a province prove that the solution is effective in improving the forecasting accuracy and calculation efficiency.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Deep convolutional neural network online identification method for detailed topological operating states of distribution network

Design and implementation of virtual power plant system supporting dynamic aggregation of equipment

Research on the planning method of distribution system with distributed generations considering the impact of short-term peak load

Enhancement optimization model for distributed photovoltaic hosting capacity considering multiple adjustment methods

Short-term power load forecasting based on load decomposition and identification

Related Author

蒋帅

李德志

廖霈之

吴啸

田长航

徐哲男

刘泽三

诸葛雪迎

Related Institution

中南民族大学计算机科学学院

东南大学能源热转换及其过程测控教育部重点实验室

深圳市中电电力技术股份有限公司

国网信息通信产业集团有限公司

国网四川省电力公司成都供电公司

AI问答

⁰