基于多目标算法优化改进谱聚类和BiLSTM-MHA的光伏功率预测

唐晓乐; 卢浩; 康滟婷

doi:10.19912/j.0254-0096.tynxb.2025-0254

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于多目标算法优化改进谱聚类和BiLSTM-MHA的光伏功率预测

更新时间：2026-07-22

- 基于多目标算法优化改进谱聚类和BiLSTM-MHA的光伏功率预测
- Vol. 47, Issue 6, Pages: 782-791(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19912/j.0254-0096.tynxb.2025-0254
  CLC： TM615
- Online First：08 July 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
唐晓乐, 卢浩, 康滟婷. 基于多目标算法优化改进谱聚类和BiLSTM-MHA的光伏功率预测[J]. 2026, 47(6): 782-791.
DOI：

唐晓乐, 卢浩, 康滟婷. 基于多目标算法优化改进谱聚类和BiLSTM-MHA的光伏功率预测[J]. 2026, 47(6): 782-791. DOI： 10.19912/j.0254-0096.tynxb.2025-0254.

摘要

为提升典型天气下光伏功率预测的准确性与稳定性

提出一种基于多目标算法（NSGAⅡ）优化改进谱聚类和双向长短期记忆网络（BiLSTM）结合多头注意力机制（MHA）的光伏功率预测模型。首先

对气象及历史光伏数据进行异常值检测与处理并分析主要影响特征。其次

通过动态时间规整（DTW）对谱聚类中度矩阵的构建进行改进

并利用NSGAⅡ对相似性矩阵稀疏度与高斯核参数进行优化得到最优聚类模型

将天气划分为晴天、阴天与雨天。最后

建立典型天气下NSGAⅡ-BiLSTM-MHA最优参数模型

并与4种基准模型进行对比。结果表明

在3种天气条件下

所提模型的均方根误差（RMSE）与稳定性指标（SDEX）相比SVR分别降低50.74%~62.95%和55.85%~60.08%

决定系数（R²）指标提升8.99%~17.07%

表明该模型在多种气象条件下均具备更高的预测准确性与稳定性。

Abstract

To enhance the accuracy and stability of photovoltaic power forecasting under typical weather conditions

this paper proposes a forecasting model that integrates an improved spectral clustering method optimized by the NSGAⅡ multi-objective algorithm with a BiLSTM network enhanced by a multi-head attention mechanism （MHA）. Firstly

outlier detection and preprocessing are performed on meteorological and historical PV data

and key influencing features are identified. Then

the construction of the degree matrix in spectral clustering is improved using dynamic time warping （DTW）

and NSGAⅡ is employed to optimize the sparsity of the similarity matrix and the Gaussian kernel parameter

yielding an optimal clustering model that categorizes weather into sunny

cloudy

and rainy types. Finally

optimal NSGAⅡ-BiLSTM-MHA models are established for each weather type and compared with four baseline models. Results show that

under three weather conditions

the proposed model achieves 50.74%-62.95% lower RMSE and 55.85%-60.09% lower SDEX than that of SVR

while improving the ² by 8.99%-17.07%.

关键词

Keywords

references

ZHANG M Y, HAN Y, WANG C Y, et al.Ultra-short-term photovoltaic power prediction based on similar day clustering and temporal convolutional network with bidirectional long short-term memory model: a case study using DKASC data[J]. Applied energy, 2024, 375: 124085.

LI C S, TANG G, XUE X M, et al.The short-term interval prediction of wind power using the deep learning model with gradient descend optimization[J]. Renewable energy, 2020, 155: 197-211.

贺亦琛, 师长立, 郭小强, 等. 基于参数优化多核支持向量机的光伏功率预测算法[J]. 太阳能学报, 2024, 45(9): 394-404.

赖昌伟, 黎静华, 陈博, 等. 光伏发电出力预测技术研究综述[J]. 电工技术学报, 2019, 34(6): 1201-1217.

HENG J N, WANG J Z, XIAO L Y, et al.Research and application of a combined model based on frequent pattern growth algorithm and multi-objective optimization for solar radiation forecasting[J]. Applied energy, 2017, 208: 845-866.

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.

SHADAB A, AHMAD S, SAID S.Spatial forecasting of solar radiation using ARIMA model[J]. Remote Sensing Applications: Society and Environment, 2020, 20: 100427.

ALRASHIDI M, RAHMAN S.Short-term photovoltaic power production forecasting based on novel hybrid data-driven models[J]. Journal of big data, 2023, 10(1): 26.

MARKOVICS D, MAYER M J.Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction[J]. Renewable and sustainable energy reviews, 2022, 161: 112364.

卢俊杰, 蔡涛, 郎建勋, 等. 基于集群划分的光伏电站集群发电功率短期预测方法[J]. 高电压技术, 2022, 48(5): 1943-1951.

吐松江·卡日, 雷柯松, 马小晶, 等. 基于LSTM-Attention和CNN-BiGRU误差修正的光伏功率预测[J]. 太阳能学报,2024, 45(12): 85-93.

赵如意, 王晓辉, 郑碧煌, 等. 基于特征优化和混合改进灰狼算法优化BiLSTM网络的短期光伏功率预测[J]. 电网技术, 2025, 49(1): 209-222.

董俊, 刘瑞, 束洪春, 等. 基于BIRCH聚类的L-Transformer分布式光伏短期发电功率预测[J]. 高电压技术, 2024, 50(9): 3883-3893.

杨国华, 张鸿皓, 郑豪丰, 等. 基于相似日聚类和IHGWO-WNN-AdaBoost模型的短期光伏功率预测[J]. 高电压技术, 2021, 47(4): 1185-1194.

吴春华, 董阿龙, 李智华, 等. 基于图相似日和PSO-XGBoost的光伏功率预测[J]. 高电压技术, 2022, 48(8): 3250-3259.

方朝雄, 郑洁云, 张章煌, 等. 基于相似日与VMD-DBO-KELM的分布式光伏发电功率预测方法[J]. 高电压技术, 2025, 51(7): 3477-3487.

郭雯博. 基于相似日理论和Tent-SSA-BP模型的光伏发电功率预测研究[D]. 淮南: 安徽理工大学, 2024.

李东颖. 基于Bi-LSTM负荷预测的光储充电站优化配置与控制研究[D]. 天津: 河北工业大学, 2022.

YUSUF A, BAYHAN N, TIRYAKI H, et al.Multi-objective optimization of concentrated Photovoltaic-Thermoelectric hybrid system via non-dominated sorting genetic algorithm (NSGAⅡ)[J]. Energy conversion and management, 2021, 236: 114065.

时培明, 郭轩宇, 杜清灿, 等. 基于TCN-BiLSTM-Attention-ESN的光伏功率预测[J]. 太阳能学报, 2024, 45(9): 304-316.

YU M, NIU D X, WANG K K, et al.Short-term photovoltaic power point-interval forecasting based on double-layer decomposition and WOA-BiLSTM-Attention and considering weather classification[J]. Energy, 2023, 275: 127348.

MARTÍNEZ-OTZETA J M, RODRÍGUEZ-MORENO I, MENDIALDUA I, et al. RANSAC for robotic applications: a survey[J]. Sensors, 2023, 23(1): 327.

DE WINTER J C F, GOSLING S D, POTTER J. Comparing the pearson and spearman correlation coefficients across distributions and sample sizes: a tutorial using simulations and empirical data[J]. Psychological methods, 2016, 21(3): 273-290.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于双层分解和改进多目标浣熊优化算法的BiLSTM光伏功率预测

不同风况特性对风力机叶片载荷的影响及预测研究

计及风险偏好的风光氢储醇耦合系统多目标运行优化及效益均衡模型

基于聚合模态分解和TCN-BiGRU的光伏功率预测模型

考虑配电网净负荷时空分布特性的储能优化配置

Related Author

张晓涛

马剑龙

苏宏杰

李秋燕

赵明博

高志鹰

徐甜甜

杜易达

Related Institution

State Grid Tianjin Electric Power Company

School of Energy Power and Mechanical Engineering, North China Electric Power University

Hubei Energy Group Ezhou Power Generation Co., Ltd.

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

China Center for Information Industry Development

AI问答

⁰