To enhance the accuracy of PV(photovoltaic) power output prediction by effectively capturing local temporal variations, we propose a PV generation forecasting model that integrates SSIM(structural similarity) algorithm with the Informer model for efficient long-term sequence prediction. As a case study, daily meteorological data from the Yanpeng PV Station in Yunnan Province were converted into vectors. These vectors were then transformed into Gram matrices and subsequently into daily meteorological pixel maps. SSIM algorithm was applied to identify and filter days exhibiting similarity to the target prediction day. On this basis, feature selection of meteorological elements influencing PV output was carried out. The Informer model was then employed to construct the PV output prediction model, enabling forecasts across multiple time intervals. The results show that the graph similarity day method effectively identifies similar days for the target prediction day, and the constructed Informer PV output prediction model demonstrates robust predictive performance under different weather conditions. Compared to traditional forecasting methods, the root mean square error on sunny days is reduced to 0.66, and the daily accuracy improves by 1.63% to 3.92%.
LIU Chen-chen, ZHOU Yu-ci, PAN Zhang-rong, LI Wei, SHEN Chun-ming, XUE Song, GUO Jun-hong.
Photovoltaic Output Forecasting with Coupled Graph Similarity Days and Informer[J].
Science Technology and Engineering, 2026, 26(2): 642-654 DOI:10.12404/j.issn.1671-1815.2500822
首先将采用K-means方法对异常数据进行剔除。K-means聚类算法的核心思想是以空间中K个点为中心进行聚类,对最靠近它们的对象进行归类,通过迭代的方法,逐次更新各聚类中心的值,直到得到最好的聚类结果。K-means聚类算法中K值确定的核心指标是误差平方和(sum of the squared errors,SSE)。
ChenWeixiong. Prediction of roadbed deformation of Qinghai-Tibet railway based on time series model[J]. Science Technology and Engineering, 2021, 21(35): 15203-15208.
HeHaibin, HuWentao, RuanXiaodong, et al. Optimization of motor controller’s heat dissipation fins based on regression analysis[J]. Science Technology and Engineering, 2022, 22(2): 828-834.
[7]
ChenB, LiJ H. Combined probabilistic forecasting method for photovoltaic power using an improved Markov chain[J]. IET Generation, Transmission & Distribution, 2019, 13(19): 4364-4373.
HouEnke, WuJiamei, YangFan, et al. Evaluation of water-richness of weathered bedrock based on the WOA-SVM discriminant model: take Zhangjiamao Coal Mine in Shenfu Coal Fieldas an example[J]. Science Technology and Engineering, 2025, 25(1): 119-127.
LiuYitong. Forecasting the size of digital economy as a share of GDP based on ARIMA and BP neural network models[J]. Econo-mic & Trade Update, 2024, 21(9): 15-17.
WangTao, WangXu, XuYe, et al. Study on LSTM photovoltaic output prediction model considering similar days[J]. Acta Energiae Solaris Sinica, 2023, 44(8): 316-323.
LiChangyun, LiTingli, HePinjie, et al. Fabric demand prediction based on association rule and combination model[J]. Science Technology and Engineering, 2022, 22(35): 15697-15707.
[16]
ZhouH Y, LiJ X, ZhangS H, et al. Expanding the prediction capacity in long sequence time-series forecasting[J]. Artificial Intelligence, 2023. DOI: 0.1016/j.artint.2023.103886.
LiZheng, ZhangJie, XuRuosi, 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.
YangKai, AnLina, ZhuTiansheng, et al. Research on LSTM short-term photovoltaic output prediction model based on similar-day correlation clustering[J]. Hydropower and Pumped Storage, 2024, 10(2): 86-92.
YanYixun, WangLijie, GuoHongwu, et al. Short-term photovoltaic power prediction based on multiple feature analysis and extraction[J]. High Voltage Engineering, 2022, 48(9): 3734-3743.
XueYang, LiJinxing, YangJiangtian, et al. Short-term prediction of photovoltaic power based on similar day analysis and improved whale algorithm for optimizing LSTM network model[J]. Southern Power System Technology, 2024, 18(11): 97-105.
WangRui, ZhangLuting, LuJing. Short-term photovoltaic power prediction based on novel similar day selection and VMD-NGO-BiGRU[J]. Journal of Hunan University(Natural Sciences Edition), 2024, 51(2): 68-80.
WuChunhua, DongAlong, LiZhihua, et al. Photovoltaic power prediction based on graph similarity day and PSO-XGBoost[J]. High Voltage Engineering, 2022, 48(8): 3250-3259.
ZhangRui, ZhangLihong. Research on optimization strategy of customer experience management based on K-means clustering algorithm[J]. Changjiang Information & Communications, 2024, 37(2): 217-219, 223.