针对传统预测模型输入气象参数过多造成预测精度不高的问题,提出一种融合核模糊C聚类算法（KFCM）、冠豪猪优化算法（CPO）以及SE通道注意力机制的卷积长短期记忆网络的光伏功率组合预测模型。首先综合考虑皮尔逊相关系数和最大信息系数筛选出主要影响特征,其次使用核模糊C聚类算法（KFCM）将样本灵活划分为晴天、少云、晴转多云以及阴雨天4类。然后通过加入SE机制的卷积神经网络（CNN）对主要气象参数和历史功率的时空特征进行特征提取;最后通过CPO对长短期记忆网络的超参数进行寻优,并选择超参数最优的组合模型进行预测。算例结果表明：在4种天气条件下,相比其他对比模型,所提模型平均绝对误差（MAE）平均降低2.6700、1.9054、1.6192、2.1716 kW;均方根误差（RMSE）平均降低3.1462、2.1492、1.7318、2.3303 kW。4种天气下平均MAE、RMSE和决定系数（R2）分别为0.6237、0.8854、0.9982,验证了该模型的有效性。
Abstract
Aiming at the problem that excessive meteorological parameters in traditional forecasting models lead to reduced prediction accuracy, a combined prediction model integrating kernel-based fuzzy C-means clustering（KFCM）similarity-day theory, crested porcupine optimizer （CPO）, and squeeze-and-excitation （SE） channel attention mechanism with a convolutional long short-term memory （CNN-LSTM） network is proposed. Firstly, primary meteorological features are identified through Pearson correlation coefficient and maximal information coefficient. Secondly, the kernel-based fuzzy C-means clustering algorithm is applied to flexibly categorize samples into four weather types： sunny days, partly cloudy days, sunny to cloudy days, and rainy days. Subsequently, a CNN integrated with the SE mechanism extracts spatiotemporal features from key meteorological parameters and historical power data. Finally, CPO is utilized to optimize the hyperparameters of the long short-term memory （LSTM） network, and the optimal hyperparameter combination is selected for prediction. The comparative experiment and simulation results show that under the four weather conditions, compared to baseline models, the proposed model reduces the mean absolute error （MAE） by 2.67, 1.9054 kW, 1.6192, and 2.1716 kW on average, respectively; decreases the root mean square error （RMSE） by 3.1462, 2.1492, 1.7318, and 2.3303 on average. The average MAE, RMSE, and R2 values across all weather conditions reach 0.6237, 0.8854, and 0.9982, respectively, demonstrating the model’s effectiveness.
关键词
光伏发电 /
预测 /
神经网络 /
模糊聚类 /
注意力机制 /
优化算法
Key words
photovoltaic power /
forecasting /
neural networks /
fuzzy clustering /
attention mechanism /
optimization algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 中国建筑能耗与碳排放研究报告(2023年)[J]. 建筑, 2024(2): 57-69.
Research report on building energy consumption and carbon emissions in China (2023)[J]. Construction and Architecture, 2024(2): 57-69.
[2] 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.
[3] Mayer M J, YAng D Z.Pairing ensemble numerical weather prediction with ensemble physical model chain for probabilistic photovoltaic power forecasting[J]. Renewable and Sustainable Energy Reviews, 2023, 175(C): 113171.
[4] Mayer M J, Yang D Z, Szintai B.Comparing global and regional downscaled NWP models for irradiance and photovoltaic Power forecasting: ECMWF versus AROME[J]. Applied Energy, 2023, 352(C): 121958.
[5] Belmahdi B, Louzazni M, El Bouardi A.One month-ahead forecasting of mean daily global solar radiation using time series models[J]. Optik, 2020, 219: 165207.
[6] Rosen K, Angeles-Camacho C, Elvira V, et al.Intra-hour photovoltaic forecasting through a time-varying Markov switching model[J]. Energy, 2023, 278: 127952.
[7] 梁宏涛, 王莹, 刘国柱, 等. 光伏出力预测理论与方法综述[J]. 青岛科技大学学报(自然科学版), 2024, 45(2): 147-158.
Liang H T, Wang Y, Liu G Z, et al.Review on the theory and methods of photovoltaic output forecasting[J]. Journal of Qingdao University of Science and Technology (Natural Science Edition), 2024, 45(2): 147-158.
[8] 李争, 张杰, 徐若思, 等. 基于相似日聚类和PCC-VMD-SSA-KELM模型的短期光伏功率预测[J]. 太阳能学报, 2024, 45(2): 460-468.
Li Z, Zhang J, Xu R S, et al.Short term photovoltaic power prediction based on similar day clustering and PCC-VMD-SSA-KELM model[J]. Acta Energiae Solaris Sinica, 2024, 45(2): 460-468.
[9] 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.
Long X H, Qin J Y, Zhang Q L, et al.Short-term photovoltaic power prediction study based on similar day clustering and modal decomposition[J]. Power System Technology, 2024, 48(7): 2948-2957.
[10] 邹港, 赵斌, 罗强, 等. 基于PCA-VMD-MVO-SVM的短期光伏输出功率预测方法[J]. 电力科学与技术学报, 2024, 39(5): 163-171.
Zou G, Zhao B, Luo Q, et al.Prediction method of short-term PV output power based on PCA-VMD-MVO-SVM[J]. Journal of Electric Power Science and Technology, 2024, 39(5): 163-171.
[11] 干逸飞, 吕品, 郑树泉. 面向光伏功率预测的残差深度学习模型[J]. 计算机应用与软件, 2024, 41(11): 101-107.
Gan Y F, Lyu P, Zheng S Q.Residual deep learning model for photovoltaic power prediction[J]. Computer Applications and Software, 2024, 41(11): 101-107.
[12] Pires S, Mascarenhas C.Cyber threat analysis using Pearson and spearman correlation via exploratory data analysis[C]//2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC). Jalandhar, India, 2023: 257-262.
[13] 彭曙蓉, 陈慧霞, 孙万通, 等. 基于改进LSTM的光伏发电功率预测方法研究[J]. 太阳能学报, 2024, 45(11): 296-302.
Peng S R, Chen H X, Sun W T, et al.Research on photovoltaic power prediction method based on improved LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(11): 296-302.
[14] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
Wang X X, Yu M, Ji M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta Energiae Solaris Sinica, 2023, 44(6): 275-283.
[15] 杜立, 李振华, 李振兴, 等. 基于特征优选的DBO-CNN-BiLSTM-AM短期光伏发电预测[J]. 可再生能源, 2025, 43(11): 1458-1468.
Du L, Li Z H, Li Z X, et al.DBO-CNN-BiLSTM-AM short-term photovoltaic power generation prediction based on feature optimization[J]. Renewable Energy Resources, 2025, 43(11): 1458-1468.
[16] 周育才, 肖添, 谢七月, 等. 基于聚类的HPO-BILSTM光伏功率短期预测[J]. 太阳能学报, 2024, 45(4): 512-518.
Zhou Y C, Xiao T, Xie Q Y, et al.Clustering-based HPO-BILSTM short-term prediction of PV power[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 512-518.
[17] Abdel-Basset M, Mohamed R, Abouhawwash M.Crested Porcupine Optimizer: a new nature-inspired metaheuristic[J]. Knowledge-based Systems, 2024, 284: 111257.
[18] 查航伟, 成燕, 黄瑞承. 基于K均值聚类和VMD-COA-BiLSTM的光伏功率预测[J]. 热能动力工程, 2025, 40(5): 157-165.
Zha H W, Cheng Y, Huang R C.Photovoltaic power prediction based on K-means clustering and VMD-COA-BiLSTM[J]. Journal of Engineering for Thermal Energy and Power, 2025, 40(5): 157-165.
[19] 冯建铭, 希望·阿不都瓦依提, 蔺红. 基于聚类SABO-VMD和组合神经网络的短期光伏发电功率预测[J]. 太阳能学报, 2025, 46(2): 357-366.
Feng J M, Xiwang A, Lin H.Short-term PV power forecasting based on clustering SABO-VMD and ensemble neural networks[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 357-366.
[20] 王开艳, 杜浩东, 贾嵘, 等. 基于相似日聚类和QR-CNN-BiLSTM模型的光伏功率短期区间概率预测[J]. 高电压技术, 2022, 48(11): 4372-4384.
Wang K Y, Du H D, Jia R, et al.Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J]. High Voltage Engineering, 2022, 48(11): 4372-4384.
[21] 温廷新, 郭晓赛. 基于特征组合的ECA-TCN光伏发电功率预测模型[J]. 太阳能学报, 2024, 45(12): 94-100.
Wen T X, Guo X S.ECA-TCN photovoltaic power prediction model based on feature combination[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 94-100.
[22] 张赟宁, 魏广军. 考虑特征选择的短期光伏功率组合预测模型[J]. 电力系统及其自动化学报, 2024, 36(8): 122-132.
Zhang Y N, Wei G J.Combined prediction model for short-term photovoltaic power considering feature selection[J]. Proceedings of the CSU-EPSA, 2024, 36(8): 122-132.
[23] Luo Y, Xiang Y X, Zhong S Y.A study on intelligent diagnosis model of shortwave receiving system based on improved KFCM and LapSVM[J]. Pattern Analysis and Applications, 2021, 24(3): 1377-1386.
[24] 林文婷, 李培强, 荆志宇, 等. 基于多级特征提取的BiLSTM短期光伏出力预测[J]. 太阳能学报, 2024, 45(10): 284-297.
Lin W T, Li P Q, Jing Z Y, et al.Short-term photovoltaic output prediction based on multi-level feature extraction using BiLSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(10): 284-297.
[25] 陈庆斌, 杨耿煌, 耿丽清, 等. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
Chen Q B, Yang G H, Geng L Q, et al.Short term photovoltaic power combination prediction method based on similar day selection and data reconstruction[J]. Electric Power, 2024, 57(12): 71-81.
基金
国家自然科学基金区域联合基金（U23A20657）; 辽宁省教育厅青年项目（LJ212410153009）; 辽宁省科技厅博士科研启动基金计划（2024-BS-120）
PDF(1944 KB)
