Short-term Prediction Method of Maximum Power Load Based on KPCA-SVM Model

Yongwei ZHANG; Qiaobo PAN

doi:10.12096/j.2096-4528.pgt.19010

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Short-term Prediction Method of Maximum Power Load Based on KPCA-SVM Model

Energy Internet | 更新时间：2025-07-04

- Short-term Prediction Method of Maximum Power Load Based on KPCA-SVM Model
- Power Generation Technology Vol. 40, Issue 6, Pages: 521-526(2019)
- 作者机构：
  
  1.安徽邮电职业技术学院通信工程系, 安徽省合肥市 230000
  2.华电电力科学研究院有限公司, 浙江省杭州市 310030
- 作者简介：
- 基金信息：
  
  National Science and Technology Support Program of China(2015BAA06B02)
- DOI：10.12096/j.2096-4528.pgt.19010
  CLC：
- Received：16 January 2019，
  
  Published：30 December 2019
- 稿件说明：
移动端阅览
Yongwei ZHANG, Qiaobo PAN. Short-term Prediction Method of Maximum Power Load Based on KPCA-SVM Model[J]. Power Generation Technology, 2019, 40(6): 521-526.
DOI：

Yongwei ZHANG, Qiaobo PAN. Short-term Prediction Method of Maximum Power Load Based on KPCA-SVM Model[J]. Power Generation Technology, 2019, 40(6): 521-526. DOI： 10.12096/j.2096-4528.pgt.19010.

摘要

电力负荷最大值预测是电网企业调度工作的重要组成部分，其预测结果的准确度将对电能的配送、有效利用率、供电服务的质量以及电力系统的发展产生重要影响。以安徽某市81天的电力负荷最大值数据为基础，选取影响当天电力负荷最大值的10个因素，并采用核主成分分析（kernel principal component analysis，KPCA）算法将10维的影响因素降为5维，其累计贡献率可达93.70%。以降维后的5维数据为输入，以径向基函数为核函数，并采用交叉验证选择支持向量机（support vector machine，SVM）回归的最佳参数，随机选取54组数据训练SVM预测模型，最后进行27组数据的拟合预测，拟合预测的均方误差为0.004 1，相关系数为0.963 1。研究结果表明，应用KPCA结合的SVM预测模型对电力负荷最大值具有很好的预测能力。

Abstract

The maximum power load is an important part of power enterprise dispatching work. The accuracy of its prediction results will have an important impact on the distribution of power

the effective utilization rate of power

the quality of power supply service and the development of power system. Based on the 81-day maximum power load data of a city in Anhui province

10 factors influencing the maximum power load of that day were selected

and the influencing factors reduced from 10 dimensions to 5 dimensions by kernel principal component analysis(KPCA). The cumulative contribution rate can reach 93.70%. The best parameters of SVM regression were selected by cross validation. 54 groups of data were randomly selected to train SVM prediction model. Finally

27 groups of data were fitted and predicted. The mean square error of fitting prediction was 0.004 1

and the correlation coefficient was 0.963 1. The results show that the KPCA combining the SVM prediction model for maximum power load has good prediction ability.

关键词

Keywords

references

梁青艳, 孙彦广.钢铁企业电力负荷动态预测建模问题的应用研究[J].科学技术与工程, 2018, 18(16):44-54.

蔡秋娜, 张乔榆, 刘思捷, 等.市场环境下考虑多因素影响的母线负荷预测方法[J].广东电力, 2019, 32(8):65-72.

陈潇雅, 刘志坚, 刘晓欣, 等.基于长期负荷预测和联络分析的配电网规划[J].广东电力, 2019, 32(3):59-65.

杨博宇, 陈仕军.电力负荷预测研究综述及预测分析[J].四川电力技术, 2018, 41(3):56-60.

郭威, 巴秀玲.基于神经网络的电力系统负荷预测问题研究[J].自动化与仪器仪表, 2017(10):192-194.

肖白, 周潮, 穆钢.空间电力负荷预测方法综述与展望[J].中国电机工程学报, 2013, 33(25):78-79.

邹京希, 曹敏.基于总体测辨和人工神经网络的负荷建模及预测方法[J].电力系统及其自动化学报, 2018, 30(8):108-112.

周涛.基于改进神经网络的电力系统中长期负荷预测研究[J].电气应用, 2013, 32(4):26-29.

杨楠, 叶迪, 周峥.基于NACEMD-Elman神经网络的风功率组合预测[J].水电能源科学, 2018, 36(9):209-211.

胡朝举, 李云霞.关于电力负荷影响因素及智能预测方法的研究[J].通信电源技术, 2018, 35(2):231-232.

许杏花, 潘庭龙.基于KPCA-RF的风电场功率预测方法研究[J].可再生能源, 2018, 36(9):1323-1327.

刘剑, 刘丽华.基于KPCA与SVM的混合核交通流数据检测[J].沈阳建筑大学学报(自然科学版), 2018, 34(5):921-928.

李军, 王秋莉.KPCA-KELM在短期交通流量预测中的应用[J].江苏大学学报(自然科学版), 2018, 39(5):570-575.

胡伟, 张玮灵, 闵勇.基于支持向量机的电力系统紧急控制实时决策方法[J].中国电机工程学报, 2017, 37(16):4567-4576.

简献忠, 顾祎婷.一种基于全过程优化支持向量机的短期电力负荷预测方法[J].电力科学与工程, 2018, 34(11):45-51.

鞠建波, 胡胜林, 祝超.一种改进的支持向量机回归故障预测方法[J].电光与控制, 2018, 25(1):6-9.

吐松江·卡日, 高文胜, 张紫薇.基于支持向量机和遗传算法的变压器故障诊断[J].清华大学学报(自然科学版), 2018, 58(7):623-629.

许洪华, 李勇, 施恂山.基于振动噪声SC与SVM的变压器局部过热故障诊断[J].陕西电力, 2017, 45(6):11-17.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Three-Phase Imbalance in Distribution Networks Considering Coordinated Photovoltaic Phase Switching and Flexible Load

Detection Algorithm for Insulators and Foreign Objects on Transmission Lines Based on Unmanned Aerial Vehicle Inspection

Location Detection of False Data Injection Attacks in Power Grid Based on Improved Deep Extreme Learning Machine

Short-Term Wind Power Prediction Method Considering Wind Turbine Operation Status Clustering Under Low-Temperature Conditions

Optimal Operation Method of Electric-Hydrogen Hybrid Energy Storage Microgrid System Based on Typical Commercial Operation Mode

Related Author

GAO Shan

XING Jie

SHAN Yinghao

GU Yi

YU Zihan

WANG Heming

WANG Jiankai

ZHU Shengqiang

Related Institution

College of Information Science and Technology, Donghua University, Songjiang District

College of Automation and Electronic Engineering, Qingdao University of Science & Technology

Shandong Golden Electric Power Limited Company

College of Electrical Engineering and New Energy, China Three Gorges University

Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station (China Three Gorges University)

AI问答

⁰