The variable-weight multi-model fusion PV forecasting method based on combined similar days

HUANG Yangjue; JIA Mengqi; SHEN Kaicheng; ZHU Yuanzhe; WANG Jinfeng; ZHANG Xiaoke

doi:10.14188/j.1671-8844.2023.0414

您当前的位置：

首页 >

文章列表页 >

The variable-weight multi-model fusion PV forecasting method based on combined similar days

更新时间：2026-10-15

- The variable-weight multi-model fusion PV forecasting method based on combined similar days
- Engineering Journal of Wuhan University Pages: 1-8(2026)
- 作者机构：
  
  1.广东电网有限责任公司电力科学研究院，广东广州 510080
  2.广东省电力装备可靠性企业重点实验室，广东广州 510080
  3.武汉大学电气与自动化学院，湖北武汉 430072
- 作者简介：
- 基金信息：
- DOI：10.14188/j.1671-8844.2023.0414
  CLC： TM 615
- Received：27 September 2024，
  
  Online First：15 October 2026，
- 稿件说明：
移动端阅览
HUANG Yangjue, JIA Mengqi, SHEN Kaicheng, et al. The variable-weight multi-model fusion PV forecasting method based on combined similar days[J/OL]. Engineering Journal of Wuhan University, 2026, 1-8.
DOI：

HUANG Yangjue, JIA Mengqi, SHEN Kaicheng, et al. The variable-weight multi-model fusion PV forecasting method based on combined similar days[J/OL]. Engineering Journal of Wuhan University, 2026, 1-8. DOI： 10.14188/j.1671-8844.2023.0414.

摘要

针对光伏功率预测，首先改进传统的相似日理论，计算不同时刻对应的相似时刻数据构成组合相似日数据，以保障每一时段的相似性；然后构建分位数回归-长短期记忆网络预测模型，将相似日数据和多步功率数据分别作为输入，获取2组不同分位数下的光伏功率预测值；最后利用核密度估计，并根据相似日与待预测日的相似程度赋予2组输出不同的权重，得到最终的光伏预测功率值和概率预测区间。仿真案例表明，该预测方法的均方根误差为0.017 0，90%概率预测覆盖率为97.08%，平均带宽为0.087 8，与传统模型相比兼顾了预测的可靠性和敏锐性。

Abstract

For photovoltaic (PV) power prediction

firstly

the traditional similar day theory is improved by calculating the similar day data corresponding to different moments to constitute the combined similar day data to guarantee the similarity of each moment; secondly

a quantile regression-long short-term memory prediction model is constructed

and the similar day data and multi-step power data are used as inputs respectively to obtain the PV power prediction values under two different quartiles; finally

using kernel density estimation and assigning different weights to the two sets of outputs according to the degree of similarity between the similar day and the day to be predicted

the final PV predicted power values and probabilistic prediction intervals are obtained. The simulation case shows that the root mean square error of the proposed prediction method is 0.017 0

the 90% probability prediction coverage is 97.08%

and the average bandwidth is 0.087 8. Compared with the traditional model

the prediction reliability and sensitivity are taken into account.

关键词

Keywords

references

丁明 , 王伟胜 , 王秀丽 , 等 . 大规模光伏发电对电力系统影响综述 [J ] . 中国电机工程学报 , 2014 , 34 ( 1 ): 1 - 14 .

DING Ming , WANG Weisheng , WANG Xiuli , et al . A review on the effect of large-scale PV generation on power systems [J ] . Proceedings of the CSEE , 2014 , 34 ( 1 ): 1 - 14 .

YAO T C , WANG J , WU H Y , et al . Intra-hour photovoltaic generation forecasting based on multi-source data and deep learning methods [J ] . IEEE Transactions on Sustainable Energy , 2022 , 13 ( 1 ): 607 - 618 .

王函 . 风光发电功率与用电负荷联合预测方法研究 [D ] . 北京 : 华北电力大学 , 2021 .

WANG Han . Research on integrated forecasting method for wind power, solar power, and system load [D ] . Beijing : North China Electric Power University , 2021 .

SANJARI M J , GOOI H B , NAIR N C . Power generation forecast of hybrid PV-wind system [J ] . IEEE Transactions on Sustainable Energy , 2020 , 11 ( 2 ): 703 - 712 .

李建林 , 方知进 , 谭宇良 , 等 . 电化学储能系统在整县制屋顶光伏中应用前景分析 [J ] . 太阳能学报 , 2022 , 43 ( 4 ): 1 - 12 .

LI Jianlin , FANG Zhijin , TAN Yuliang , et al . Application prospect analysis of electrochemical energy storage technology in county-wide rooftop photovoltaic system [J ] . Acta Energiae Solaris Sinica , 2022 , 43 ( 4 ): 1 - 12 .

吴鹏飞 , 刘博 , 杨鹏程 , 等 . 考虑天气和运行状态的光伏一次调频控制及评估 [J ] . 武汉大学学报(工学版) , 2022 , 55 ( 3 ): 275 - 282 .

WU Pengfei , LIU Bo , YANG Pengcheng , et al . PV primary frequency regulation and evaluation considering weather characteristics and operating conditions [J ] . Engineering Journal of Wuhan University , 2022 , 55 ( 3 ): 275 - 282 .

戚晓侠 . 基于深度学习的光伏/风电功率预测研究 [D ] . 哈尔滨 : 哈尔滨工程大学 , 2020 .

QI Xiaoxia . Research on photovoltaic/wind power forecasting based on deep learning [D ] . Harbin : Harbin Engineering University , 2020 .

ZHEN Z , LIU J M , ZHANG Z Y , et al . Deep learning based surface irradiance mapping model for solar PV power forecasting using sky image [J ] . IEEE Transactions on Industry Applications , 2020 , 56 ( 4 ): 3385 - 3396 .

张展耀 . 基于深度学习理论的光伏功率短期预测研究 [D ] . 北京 : 华北电力大学 , 2019 .

ZHANG Zhanyao . The short-term solar power forecasting research based on deep learning theory [D ] . Beijing : North China Electric Power University , 2019 .

ESEYE A T , ZHANG J H , ZHENG D H . Short-term photovoltaic solar power forecasting using a hybrid wavelet-PSO-SVM model based on SCADA and meteorological information [J ] . Renewable Energy , 2018 , 118 : 357 - 367 .

MELLIT A , PAVAN A M , LUGHI V . Deep learning neural networks for short-term photovoltaic power forecasting [J ] . Renewable Energy , 2021 , 172 ( C ): 276 - 288 .

OSPINA J , NEWAZ A , FARUQUE M O . Forecasting of PV plant output using hybrid wavelet-based LSTM-DNN structure model [J ] . IET Renewable Power Generation , 2019 , 13 ( 7 ): 1087 - 1095 .

SANJARI M J , GOOI H B . Probabilistic forecast of PV power generation based on higher order Markov chain [J ] . IEEE Transactions on Power Systems , 2017 , 32 ( 4 ): 2942 - 2952 .

YU Y X , WANG M X , YAN F Q , et al . Improved convolutional neural network-based quantile regression for regional photovoltaic generation probabilistic forecast [J ] . IET Renewable Power Generation , 2020 , 14 ( 14 ): 2712 - 2719 .

孟安波 , 陈嘉铭 , 黎湛联 , 等 . 基于相似日理论和CSO-WGPR的短期光伏发电功率预测 [J ] . 高电压技术 , 2021 , 47 ( 4 ): 1176 - 1184 .

MENG Anbo , CHEN Jiaming , LI Zhanlian , et al . Short-term photovoltaic power generation prediction based on similar day theory and CSO-WGPR [J ] . High Voltage Engineering , 2021 , 47 ( 4 ): 1176 - 1184 .

顾德文 , 李文博 , 徐箭 , 等 . 基于相似日特征的雷电天气下辐照度预测 [J ] . 武汉大学学报(工学版) , 2021 , 54 ( 10 ): 952 - 957 .

GU Dewen , LI Wenbo , XU Jian , et al . Forecast of irradiance under lightning weather based on similar day characteristics [J ] . Engineering Journal of Wuhan University , 2021 , 54 ( 10 ): 952 - 957 .

WENG P Y , TIAN Y , LIU Y F , et al . Time-series generative adversarial networks for flood forecasting [J ] . Journal of Hydrology , 2023 , 622 : 129702 .

张航 , 张竞宇 , 吕能超 , 等 . 基于可靠度的公路隧道进出口段行车安全分析 [J ] . 公路 , 2023 , 68 ( 4 ): 238 - 245 .

ZHANG Hang , ZHANG Jingyu , LÜ Nengchao , et al . Analysis on driving safety at entrance and exit of the highway tunnel based on reliability [J ] . Highway , 2023 , 68 ( 4 ): 238 - 245 .

李昱瑾 . 分位数回归在办公建筑节能潜力评估上的应用研究 [D ] . 武汉 : 华中科技大学 , 2021 .

LI Yujin . Office building energy efficiency benchmarking method based on quantile regression [D ] . Wuhan : Huazhong University of Science and Technology , 2021 .

ZHANG N , REN Q , LIU G C , et al . Short-term PV output power forecasting based on CEEMDAN-AE-GRU [J ] . Journal of Electrical Engineering & Technology , 2022 , 17 ( 2 ): 1183 - 1194 .

葛乐 , 陆文伟 , 袁晓冬 , 等 . 基于改进相似日和ABC-SVM的光伏电站功率预测 [J ] . 太阳能学报 , 2018 , 39 ( 3 ): 775 - 782 .

GE Le , LU Wenwei , YUAN Xiaodong , et al . Power forecasting of photovoltaic plant based on improved similar day and ABC-SVM [J ] . Acta Energiae Solaris Sinica , 2018 , 39 ( 3 ): 775 - 782 .

杨皓然 , 杨茂 , 苏欣 . 计及预测误差时空-条件相依特性的日内光伏出力区间预测方法 [J ] . 南方电网技术 , 2023 , 17 ( 2 ): 128 - 136 .

YANG Haoran , YANG Mao , SU Xin . Intraday photovoltaic output interval prediction method considering the spatiotemporal-conditional dependence of prediction error [J ] . Southern Power System Technology , 2023 , 17 ( 2 ): 128 - 136 .

万灿 , 宋永华 . 新能源电力系统概率预测理论与方法及其应用 [J ] . 电力系统自动化 , 2021 , 45 ( 1 ): 2 - 16 .

WAN Can , SONG Yonghua . Theories, methodologies and applications of probabilistic forecasting for power systems with renewable energy sources [J ] . Automation of Electric Power Systems , 2021 , 45 ( 1 ): 2 - 16 .

羲和能源气象大数据平台 [N/OL ] . https://www.xihe-energy.com https://www.xihe-energy.com .

Xihe energy meteorological big data platform [N/OL ] . https://www.xihe-energy.com https://www.xihe-energy.com .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on optimal scheduling method of wind‐photovoltaic‐hydroelectric storage joint power generation system

A prediction method for dissolved gas concentrations in transformer oil based on VMD-SSA-LSSVM

Analysis on the geological adaptability of the TBM selection for the water conveyance tunnels of the Yangtze River to Han River Water Diversion Project

Deformation behavior of the Maerdang extra‐high concrete‐faced rockfill dam during impoundment period

Multi-dialect speech recognition based on lightweight Conformer and dialect embedding

Related Author

CHEN Zihang

ZHU Yanqing

SONG Ningfeng

Related Institution

School of Electrical and Information Engineering， Hunan University

State Grid Ezhou Power Supply Company

School of Electrical and Electronic Engineering， Hubei University of Technology

AI问答

⁰