基于相似日理论和IPOA-ELM的短期光伏发电预测

doi:doi:10.19912/j.0254-0096.tynxb.2024-0743

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

基于相似日理论和IPOA-ELM的短期光伏发电预测

更新时间：2025-10-22

- 基于相似日理论和IPOA-ELM的短期光伏发电预测
- Vol. 46, Issue 9, Pages: 463-473(2025)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：doi:10.19912/j.0254-0096.tynxb.2024-0743
  CLC： TK615
- Published Online：14 October 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
[J]. 2025, 46(9): 463-473.
DOI：

[J]. 2025, 46(9): 463-473. DOI： doi:10.19912/j.0254-0096.tynxb.2024-0743.

摘要

针对规模化光伏发电系统在非理想天气条件下预测精度不足

进而引发电力系统调度计划实施困难的问题

提出基于相似日理论和改进鹈鹕算法（IPOA）优化极限学习机（ELM）的光伏功率预测方法。首先利用皮尔逊相关系数方法

筛选出与光伏发电相关的主要气象因素;然后结合欧氏距离与马氏距离的综合评价指标对各时间点的历史数据与待预测日之间的综合距离进行比较

以求得相似日;接着将相似日样本集输入构建好的IPOA-ELM功率预测模型进行训练

并基于实际测量数据

对比研究IPOA-ELM模型与POA-ELM、SCSO-ELM、GJO-ELM模型在预测精度方面的表现。经比较分析后得出：加权综合指标选取相似日能更加准确地反映每个时刻点之间的距离和分布特性;IPOA算法对比POA、SCSO和GJO

在收敛速度和适应度表现上均为最优;同时在不同天气条件下作光伏预测时

IPOA-ELM模型的预测均方根误差均低于其他对比模型。值得注意的是

在阴雨天气等出力波动较强的情况下

该模型仍展现出良好的稳定性。充分证明所应用的IPOA-ELM预测模型具有较强的适应能力和预测准确性。

Abstract

Aiming at the problem of insufficient prediction accuracy of large-scale photovoltaic power generation system under non-ideal weather conditions

which in turn triggers the difficulties in the implementation of the power system dispatch plan

a prediction method of photovoltaic power generation is proposed based on the similar day theory and the improved pelican optimization algorithm （IPOA） extreme learning machine （ELM）. First

the Pearson correlation coefficient method filters out meteorological factors that exhibit a significant correlation with PV power generation; then the combined Euclidean distance and Mahalanobis distance evaluation indexes are used to calculate the combined distance between the historical days and the days to be predicted at each time point to determine the similar days. Then

the sample set of similar days is input into the constructed IPOA-ELM power prediction model for training

and based on the actual measurement data

the performance of the IPOA-ELM model is compared with that of the POA-ELM

SCSO-ELM

and GJO-ELM models in terms of prediction accuracy. After comparative analysis

it is concluded that the selection of similar days for the weighted composite index can more accurately reflect the distance and distribution characteristics between each moment point; the IPOA algorithm is optimal in terms of convergence speed and adaptability compared with POA

SCSO and GJO; and the root-mean-square errors of the IPOA-ELM model are lower than the other comparative models in the prediction of photovoltaic power generation under different weather conditions. It is worth noting that the model still shows good stability under rainy weather. It is fully proved that the applied IPOA-ELM prediction model has strong adaptive ability and prediction accuracy.

关键词

Keywords

references

KALAIR A, ABAS N, SALEEM M S, et al.Role of energy storage systems in energy transition from fossil fuels to renewables[J]. Energy storage, 2021, 3(1): e135.

KABIR E, KUMAR P, KUMAR S, et al.Solar energy: potential and future prospects[J]. Renewable and sustainable energy reviews, 2018, 82: 894-900.

LI W, REN H, CHEN P, et al.Key operational issues on the integration of large-scale solar power generation: a literature review[J]. Energies, 2020, 13(22): 5951.

董存, 王铮, 白捷予, 等. 光伏发电功率超短期预测方法综述[J]. 高电压技术, 2023, 49(7): 2938-2951.

王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45(2): 443-450.

DAS U K, TEY K S, SEYEDMAHMOUDIAN M, et al.Forecasting of photovoltaic power generation and model optimization: a review[J]. Renewable and sustainable energy reviews, 2018, 81: 912-928.

耿博, 高贞彦, 白恒远, 等. 结合相似日GA-BP神经网络的光伏发电预测[J]. 电力系统及其自动化学报, 2017, 29(6): 118-123.

邱实, 张琨, 程嵩晴, 等. 基于数据更新长短期记忆网络的多能源微网集群优化调度方法[J]. 太阳能学报, 2024, 46(4): 193-199.

张姗, 冬雷, 纪德洋, 等. 基于NWP相似性分析的超短期光伏发电功率预测[J]. 太阳能学报, 2022, 43(4): 142-147.

张程, 林谷青, 匡宇. 基于MEEMD-QUATRE-BILSTM的短期光伏出力区间预测[J]. 太阳能学报, 2023, 44(11): 40-54.

龙小慧, 秦际赟, 张青雷, 等. 基于相似日聚类及模态分解的短期光伏发电功率组合预测研究[J]. 电网技术, 2024, 48(7): 2948-2957.

王瑞, 张璐婷, 逯静. 基于新型相似日选取和VMD-NGO-BiGRU的短期光伏功率预测[J]. 湖南大学学报(自然科学版), 2024, 51(2): 68-80.

王涛, 王旭, 许野, 等. 计及相似日的LSTM光伏出力预测模型研究[J]. 太阳能学报, 2023, 44(8): 316-323.

李超然, 潘鹏程, 杨伟荣, 等. 基于改进相似日优化HBA-BiLSTM-KELM的光伏发电功率预测[J]. 太阳能学报, 2024, 45(5): 508-516.

吴汉斌, 时珉, 郑焕坤, 等. 基于EEMD-ALOCO-SVM模型的光伏功率短期区间预测[J]. 太阳能学报, 2023, 44(11): 64-71.

杨锡运, 王诗晨, 张艳峰, 等. 基于相似日的Grey-Markov与BP_Adaboost的短期光伏功率预测[J]. 电源技术, 2023, 47(6): 790-794.

周新茂, 郑焮元, 于正鑫, 等. 基于相似日理论和LCSSA-BP的短期光伏发电功率预测[J]. 电网与清洁能源, 2022, 38(11): 88-97.

HU W, ZHANG X Y, ZHU L J, et al.Short-term photovoltaic power prediction based on similar days and improved SOA-DBN model[J]. IEEE access, 2020, 9: 1958-1971.

SHENG H M, XIAO J, CHENG Y H, et al.Short-term solar power forecasting based on weighted Gaussian process regression[J]. IEEE transactions on industrial electronics, 2018, 65(1): 300-308.

郝丽春, 孟庆岩, 葛小三, 等. 一种基于八分位法的工业热污染区提取方法[J]. 遥感技术与应用, 2020, 35(2): 469-477.

DENG J X, DENG Y, CHEONG K H.Combining conflicting evidence based on Pearson correlation coefficient and weighted graph[J]. International journal of intelligent systems, 2021, 36(12): 7443-7460.

BENAVIDES D, ARÉVALO P, VILLA-ÁVILA E, et al. Predictive power fluctuation mitigation in grid-connected PV systems with rapid response to EV charging stations[J]. Journal of energy storage, 2024, 86: 111230.

左锋琴, 张达敏, 何庆, 等. 融合无迹sigma点变异和交叉反向的鹈鹕优化算法[J]. 计算机科学与探索, 2024, 18(11): 2954-2968.

吴艳娟, 刘振朝, 王云亮. 基于IPOA的太阳电池模型参数辨识[J]. 太阳能学报, 2024, 45(1): 1-10.

任志玲, 毛奕栋. 基于改进黏菌算法的光伏多峰值MPPT控制[J]. 太阳能学报, 2024, 45(2): 421-428.

ZHONG C T, LI G, MENG Z.Beluga whale optimization: a novel nature-inspired metaheuristic algorithm[J]. Knowledge-based systems, 2022, 251: 109215.

麻吕斌, 潘国兵, 蒋群, 等. 基于EOF-DBSCAN-GRU的分布式光伏集群出力预测方法研究[J]. 太阳能学报, 2024, 45(1): 39-46.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于注意力机制的Bi-LSTM光伏发电超短期功率预测方法研究与实施

计及光伏渗透率的光伏发电系统并网模型稳定性分析

基于P-V特性曲线的光伏系统MPPT控制方法

面向PEMFC系统的多输入单输出ELM-Hammerstein建模与参数辨识

Related Author

归一数

霍勇

徐亦淳

李晨曦

沈赋

李施伟

单节杉

韩劲苗

Related Institution

State Key Laboratory of Power Transmission Equipment Technology, School of Electrical Engineering, Chongqing University, Chongqing 400044, China

美国大自然保护协会

农业部农村可再生能源重点开放实验室

中原工学院

School of Electrical Engineering, Shenyang University of Technology

AI问答

⁰