基于LSTM-Transformer的分布式光伏违规扩容识别方法

魏梅芳; 李雄; 周文晴; 李彬; 苏盛

doi:10.19912/j.0254-0096.tynxb.2024-1146

PDF(5555 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (12) : 324-332. DOI: 10.19912/j.0254-0096.tynxb.2024-1146

基于LSTM-Transformer的分布式光伏违规扩容识别方法

魏梅芳¹, 李雄², 周文晴², 李彬², 苏盛²

作者信息 +

ILLEGAL EXPANDING CAPACITY IDENTIFICATION METHOD FOR DISTRIBUTED PHOTOVOLTAIC BASED ON LSTM-Transformer

Wei Meifang¹, Li Xiong², Zhou Wenqing², Li Bin², Su Sheng²

Author information +

文章历史 +

摘要

针对用户分布式光伏违规扩容威胁配电系统安全可靠运行的问题,提出一种基于长短期记忆网络（LSTM）-Transformer的分布式光伏违规扩容识别方法,首先进行时间序列数值和形态相似性预处理,筛选出与标杆电站气象情况一致的光伏电站;然后构建LSTM-Transformer模型,利用预处理后的数据进行训练和参数优化,预测光伏电站的理论出力;进而采用高斯核函数,基于实际发电功率与模型预测输出偏差计算违规扩容指数（IEI）,基于IEI的数值和突变时间检测光伏用户违规扩容严重程度和扩容时间。通过实际光伏用户数据验证了所提方法的有效性。

Abstract

With the wide application of distributed PV systems, the problem of users' illegal capacity expansion is gradually highlighted, which poses a threat to the stable operation of the power grid. In order to effectively identify the expansion behavior of distributed PV users, a distributed PV violation expansion identification method based on LSTM-Transformer is proposed. The method firstly screens out the PV power plants that are consistent with the meteorological conditions of the benchmark power plants through time series numerical and morphological similarity preprocessing, then constructs the LSTM-Transformer model, and uses the preprocessed data for training and parameter optimization to predict the theoretical output power of PV power plants. By comparing the actual power generation with the predicted output of the model, Gaussian kernel function is used to calculate the illegal expansion index （EVI）, detecting the severity of illegal expansion of PV users through the size of EVI, and determining the time of illegal expansion of users through the time of EVI mutation. The effectiveness of the proposed method was verified based on the actual data of photovoltaic users.

导出引用

魏梅芳, 李雄, 周文晴, 李彬, 苏盛. 基于LSTM-Transformer的分布式光伏违规扩容识别方法[J]. 太阳能学报. 2025, 46(12): 324-332 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1146

Wei Meifang, Li Xiong, Zhou Wenqing, Li Bin, Su Sheng. ILLEGAL EXPANDING CAPACITY IDENTIFICATION METHOD FOR DISTRIBUTED PHOTOVOLTAIC BASED ON LSTM-Transformer[J]. Acta Energiae Solaris Sinica. 2025, 46(12): 324-332 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1146

中图分类号： TM615

参考文献

[1] 李鑫, 高伟, 杨耿杰. 基于动态时间规整的光伏系统直流串联电弧故障特征提取[J]. 太阳能学报, 2023, 44(12): 82-89.
LI X, GAO W, YANG G J.DC series arc fault feature extraction for photovoltaic system based on dynamic time warping[J]. Acta energiae solaris sinica, 2023, 44(12): 82-89.
[2] 汤渊, 吴裕宙, 苏盛, 等. 基于改进深度极限学习机的光伏扩容用户识别方法[J]. 电力系统及其自动化学报, 2024, 36(5): 59-68.
TANG Y, WU Y Z, SU S, et al.Identification method for photovoltaic capacity expansion users based on improved deep extreme learning machine[J]. Proceedings of the CSU-EPSA, 2024, 36(5): 59-68.
[3] 魏梅芳, 阳靖, 黄頔, 等. 基于对比预测编码SVDD的窃电检测方法[J/OL]. 中国测试, 1-8[2025-08-01].
WEI M F, YANG J, HUANG D, et al.Electricity theft detection method based on contrast predictive coding-SVDD[J/OL]. China measurement & test, 1-8[2025-08-01].
[4] 白文伦, 李文丹, 李若, 等. 基于多端数据融合的绕表窃电检测方法[J]. 大众用电, 2023, 38(12): 52-53.
BAI W L, LI W D, LI R, et al.Detection method of electricity stealing based on multi-terminal data fusion[J]. Popular utilization of electricity, 2023, 38(12): 52-53.
[5] 孔祥玉, 马玉莹, 赵鑫, 等. 基于多阶段递推数据分析的低压台区窃电检测方法[J]. 中国电机工程学报, 2024, 44(15): 5921-5934.
KONG X Y, MA Y Y, ZHAO X, et al.Detection method of electric theft in low voltage station area based on multi-stage recursive data analysis[J]. Proceedings of the CSEE, 2024, 44(15): 5921-5934.
[6] 殷涛, 薛阳, 杨艺宁, 等. 基于向量自回归模型的高损线路窃电检测[J]. 中国电机工程学报, 2022, 42(3): 1015-1024.
YIN T, XUE Y, YANG Y N, et al.Electricity theft detection of high-loss line with vector autoregression[J]. Proceedings of the CSEE, 2022, 42(3): 1015-1024.
[7] 刘康, 李彬, 薛阳, 等. 基于传递熵密度聚类的用户窃电识别方法[J]. 中国电机工程学报, 2022, 42(20): 7535-7546.
LIU K, LI B, XUE Y, et al.User electric theft detection method based on transfer entropy density clustering[J]. Proceedings of the CSEE, 2022, 42(20): 7535-7546.
[8] 李景歌, 荣娜, 陈庆超. 基于生成对抗网络的分布式光伏窃电数据增强方法[J]. 电力科学与技术学报, 2022, 37(5): 181-190.
LI J G, RONG N, CHEN Q C.A data augmentation method for distributed photovoltaic electricity theft using generative adversarial network[J]. Journal of electric power science and technology, 2022, 37(5): 181-190.
[9] 薛阳, 杨艺宁, 廖文龙, 等. 基于非线性独立成分估计的分布式光伏窃电数据增强方法[J]. 电力系统自动化, 2022, 46(2): 171-179.
XUE Y, YANG Y N, LIAO W L, et al.Data augmentation method for distributed photovoltaic electricity theft based on non-linear independent components estimation[J]. Automation of electric power systems, 2022, 46(2): 171-179.
[10] 张娜, 葛磊蛟. 基于SOA优化的光伏短期出力区间组合预测[J]. 太阳能学报, 2021, 42(5): 252-259.
ZHANG N, GE L J.Photovoltaic system short-term power interval hybrid forecasting method based on seeker optimization algorithm[J]. Acta energiae solaris sinica, 2021, 42(5): 252-259.
[11] HAN Y T, WANG N B, MA M, et al.A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm[J]. Solar energy, 2019, 184: 515-526.
[12] 王海军, 居蓉蓉, 董颖华. 基于时空关联特征与B-LSTM模型的分布式光伏功率区间预测[J]. 中国电力, 2024, 57(7): 74-80.
WANG H J, JU R R, DONG Y H.Distributed photovoltaic power interval prediction based on spatio-temporal correlation feature and B-LSTM model[J]. Electric power, 2024, 57(7): 74-80.
[13] 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.
DONG J, LIU R, SHU H C, et al.Short-term distributed photovoltaic power generation prediction based on BIRCH clustering and L-Transformer[J]. High voltage engineering, 2024, 50(9): 3883-3893.
[14] 周海, 李登宣, 尹万思, 等. 基于极限学习机的光伏发电短期预测校正方法[J]. 电网与清洁能源, 2020, 36(6): 64-69, 77.
ZHOU H, LI D X, YIN W S, et al.Short-term forecasting correction method of photovoltaic power based on extreme learning machine[J]. Power system and clean energy, 2020, 36(6): 64-69, 77.
[15] 李宝, 孙树敏, 王士柏, 等. 基于空间相关性的区域分布式光伏预测[J]. 电源技术, 2021, 45(8): 1048-1051.
LI B, SUN S M, WANG S B, et al.Research on prediction of regional distributed photovoltaic output considering spatial relevance[J]. Chinese journal of power sources, 2021, 45(8): 1048-1051.
[16] 栗峰, 丁杰, 周才期, 等. 新型电力系统下分布式光伏规模化并网运行关键技术探讨[J]. 电网技术, 2024, 48(1): 184-199.
LI F, DING J, ZHOU C Q, et al.Key technologies of large-scale grid-connected operation of distributed photovoltaic under new-type power system[J]. Power system technology, 2024, 48(1): 184-199.
[17] 陆双, 彭曙蓉, 杨云皓, 等. 基于平均影响值-启发式前向搜索的异常光伏用户识别方法[J]. 电力自动化设备, 2022, 42(2): 106-111.
LU S, PENG S R, YANG Y H, et al.Identification method of abnormal photovoltaic users based on mean impact value and heuristic forward searching[J]. Electric power automation equipment, 2022, 42(2): 106-111.
[18] 唐冬来, 倪平波, 李玉, 等. 基于互信共识标识的县域屋顶光伏消纳交易策略[J]. 电力系统自动化, 2022, 46(22): 41-50.
TANG D L, NI P B, LI Y, et al.Transaction strategy of roof-mounted photovoltaic accommodation for county area based on mutual trust and consensus identification[J]. Automation of electric power systems, 2022, 46(22): 41-50.
[19] MOSIER B R, BANTIS L E.Combining multiple biomarkers linearly to minimize the Euclidean distance of the closest point on the receiver operating characteristic surface to the perfection corner in trichotomous settings[J]. Statistical methods in medical research, 2024, 33(4): 647-668.
[20] BARONA LÓPEZ L I, FERRI F M, ZEA J, et al. CNN-LSTM and post-processing for EMG-based hand gesture recognition[J]. Intelligent systems with applications, 2024, 22: 200352.
[21] 臧海祥, 张越, 程礼临, 等. 基于ICEEMDAN-LSTM和残差注意力的短期太阳辐照度预测[J]. 太阳能学报, 2023, 44(12): 175-181.
ZANG H X, ZHANG Y, CHENG L L, et al.Short term solar radiation forecasting based on ICEEMDAN-LSTM and residual attention[J]. Acta energiae solaris sinica, 2023, 44(12): 175-181.
[22] 陈巧红, 孙佳锦, 漏杨波, 等. 基于多任务学习与层叠Transformer的多模态情感分析模型[J]. 浙江大学学报(工学版), 2023, 57(12): 2421-2429.
CHEN Q H, SUN J J, LOU Y B, et al.Multimodal sentiment analysis model based on multi-task learning and stacked cross-modal Transformer[J]. Journal of Zhejiang University (engineering science), 2023, 57(12): 2421-2429.
[23] 侯志强, 杨晓麟, 马素刚, 等. 基于特征增强和历史帧选择的Transformer视觉跟踪算法[J]. 控制与决策, 2024, 39(10): 3506-3512.
HOU Z Q, YANG X L, MA S G, et al.Feature enhancement and history frame selection based Transformer visual tracking[J]. Control and decision, 2024, 39(10): 3506-3512.
[24] 李贝奥, 李开成, 肖贤贵, 等. 基于多尺度卷积融合时间序列Transformer的复合电能质量扰动识别[J]. 电网技术, 2025, 49(6): 2511-2520.
LI B A, LI K C, XIAO X G, et al.Compound power quality disturbances identification based on multi-scale convolution fusion time series Transformer[J]. Power system technology, 2025, 49(6): 2511-2520.
[25] PRECUP R E, DAVID R C, PETRIU E M.Grey wolf optimizer algorithm-based tuning of fuzzy control systems with reduced parametric sensitivity[J]. IEEE transactions on industrial electronics, 2017, 64(1): 527-534.
[26] 张雪松, 李鹏, 周亦尧, 等. 基于贝叶斯概率的光伏出力组合预测方法[J]. 太阳能学报, 2021, 42(10): 80-86.
ZHANG X S, LI P, ZHOU Y Y, et al.Photovoltaic output combination forecasting method based on Bayesian probability[J]. Acta energiae solaris sinica, 2021, 42(10): 80-86.