网络首发:2026-10-10,
纸质出版:2026
移动端阅览
冯国会, 唐永源, 程昱茜, 等. 基于KFCM聚类和CPSC-LSTM的短期光伏功率预测研究[J]. 太阳能学报, 2026,47(9):192-202.
冯国会, 唐永源, 程昱茜, et al. 基于KFCM聚类和CPSC-LSTM的短期光伏功率预测研究[J]. 2026, 47(9): 192-202.
冯国会, 唐永源, 程昱茜, 等. 基于KFCM聚类和CPSC-LSTM的短期光伏功率预测研究[J]. 太阳能学报, 2026,47(9):192-202. DOI: 10.19912/j.0254-0096.tynxb.2025-0652.
冯国会, 唐永源, 程昱茜, et al. 基于KFCM聚类和CPSC-LSTM的短期光伏功率预测研究[J]. 2026, 47(9): 192-202. DOI: 10.19912/j.0254-0096.tynxb.2025-0652.
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。
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 -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 values across all weather conditions reach 0.6237
0.8854
and 0.9982
respectively
demonstrating the model’s effectiveness.
中国建筑能耗与碳排放研究报告(2023年)[J]. 建筑, 2024(2): 57-69.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Abdel-Basset M, Mohamed R, Abouhawwash M.Crested Porcupine Optimizer: a new nature-inspired metaheuristic[J]. Knowledge-based Systems, 2024, 284: 111257.
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.
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.
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.
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.
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.
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.
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.
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.
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621