基于多核模糊C均值聚类的配电网短期负荷预测Short-term Load Forecasting of Distribution Networks Based on Multiple Kernel Fuzzy C-means Clustering
孙景钌,胡长洪,项烨鋆,赵碚,刘津源,陈梦翔,蔡昌春
SUN Jingliao,HU Changhong,XIANG Yeyun,ZHAO Pei,LIU Jinyuan,CHEN Mengxiang,CAI Changchun
摘要(Abstract):
精准、高效的短期负荷预测是电力系统运行与调度的基础,负荷-气象因素的强耦合关系使得负荷预测过程中必须考虑气象因素。首先从影响电力负荷波动的气象因素出发,分析负荷样本数据的气象因素相关性,通过构造多核模糊C均值聚类函数实现负荷、气象数据的低维非线性至高维线性空间映射,完成基于负荷影响因素的聚类划分,获得强相关气象因素。接着,在传统LSTM(长短期记忆)神经网络中引入反馈环节,融合前向和反向计算机制消除LSTM训练过程的累计误差,构建基于深度学习的多层堆叠模式并应用于负荷预测中。然后,以历史负荷数据的聚类结果为训练样本,深度挖掘负荷-气象因素的耦合特征,从而提高负荷预测精度。最后,通过实际运行数据验证提出方法的合理性和准确性。
Accurate and efficient short-term load forecasting is the basis of power system dispatching and operation.It is necessary to consider the meteorological factors in the process of load forecasting since the strong coupling relationship between load and meteorological factors. Proceeding from meteorological factors that influence power load fluctuations,the correlation between load data samples and meteorological factors is analyzed;besides,the lowdimensional nonlinearity of meteorological data is mapped into the high-dimensional space based on multiple kernel fuzzy C-means(MKFCM) clustering algorithm. Furthermore,the meteorological factors are divided into several types. Based on the traditional LSTM(long and short-term memory)neural networks, a feedback mechanism integrating forward and reverse calculation is introduced to eliminate the cumulative error of the LSTM training process.The multi-layer stacking mode of LSTM based on deep learning is used in load forecasting. The clustering results of historical load data are used as training samples to deeply mine the coupling characteristics of load and meteorological factors and thus improve the accuracy of load forecasting. Finally,the rationality and accuracy of the proposed method are verified by using the actual operational data.
关键词(KeyWords):
短期负荷预测;多核模糊C均值;LSTM神经网络;气象因素
short-term load forecasting;multiple kernel fuzzy C-means;LSTM neural network;meteorological factor
基金项目(Foundation): 国网浙江省电力有限公司温州供电公司科技项目(521WZ210010)
作者(Author):
孙景钌,胡长洪,项烨鋆,赵碚,刘津源,陈梦翔,蔡昌春
SUN Jingliao,HU Changhong,XIANG Yeyun,ZHAO Pei,LIU Jinyuan,CHEN Mengxiang,CAI Changchun
DOI: 10.19585/j.zjdl.202203008
参考文献(References):
- [1]高亚静,孙永健,杨文海,等.基于新型人体舒适度的气象敏感负荷短期预测研究[J].中国电机工程学报,2017,37(7):1946-1955.
- [2]应张驰,陈淑萍,卢旭航.基于多源信息的短期负荷混合预测模型应用研究[J].浙江电力,2019,38(9):100-104.
- [3]张淑清,段晓宁,张立国,等.Tsne降维可视化分析及飞蛾火焰优化ELM算法在电力负荷预测中的应用[J].中国电机工程学报,2021,41(9):3120-3130.
- [4]蔡舒平,张保会,汤大海,等.短期负荷预测中气象因素处理的费歇信息方法[J].电力自动化设备,2020,40(3):141-146.
- [5]刘德旭,车权,黄炜斌,等.基于Copula-POME的负荷与气象因素相关性度量研究[J].水电能源科学,2020,38(11):203-206.
- [6]李博,门德月,严亚勤,等.基于数值天气预报的母线负荷预测[J].电力系统自动化,2015,39(1):137-140.
- [7]苏宜靖,谷炜,赵依,等.考虑气象因子的区域电网梅雨期负荷预测[J].浙江电力,2019,38(12):1-7.
- [8]李滨,覃芳璐,吴茵,等.基于模糊信息粒化与多策略灵敏度的短期日负荷曲线预测[J].电工技术学报,2017,32(9):149-159.
- [9]李滨,黄佳,吴茵,等.基于分形特性修正气象相似日的节假日短期负荷预测方法[J].电网技术,2017,41(6):1949-1955.
- [10]徐耀松,段彦强,王雨虹,等.基于相似日选择与改进Stacking集成学习的短期负荷预测[J].传感技术学报,2020,33(4):537-545.
- [11]DAVE R N.Generalized fuzzy c-shells clustering and detection of circular and elliptical boundaries[J].Pattern Recognition,1992,25(7):713-721.
- [12]GIROLAMI M.Mercer kernel-based clustering in feature space[J].IEEE Transactions on Neural Networks,2002,13(3):780-784.
- [13]SATHEESH K G,RAJ A N J.Medical image segmentation and classification using MKFCM and hybrid classifiers[J].International Journal of Intelligent Engineering and Systems,2017,10(6):9-19.
- [14]孔祥玉,胡启安,董旭柱,等.引入改进模糊C均值聚类的负荷数据辨识及修复方法[J].电力系统自动化,2017,41(9):90-95.
- [15]王增平,赵兵,纪维佳,等.基于GRU-NN模型的短期负荷预测方法[J].电力系统自动化,2019,43(5):53-58.
- [16]姚程文,杨萍,刘泽健.基于CNN-GRU混合神经网络的负荷预测方法[J].电网技术,2020,44(9):3416-3424.
- [17]马梦东,彭道刚,王丹豪.基于EEDM-LSTM的区域能源短期负荷预测[J].浙江电力,2020,39(4):29-35.
- [18]赵兵,王增平,纪维佳,等.基于注意力机制的CNN-GRU短期电力负荷预测方法[J].电网技术,2019,43(12):4370-4376.
- [19]史佳琪,张建华.基于多模型融合Stacking集成学习方式的负荷预测方法[J].中国电机工程学报,2019,39(14):4032-4042.
- [20]张淑清,要俊波,张立国,等.基于改进深度稀疏自编码器及FOA-ELM的电力负荷预测[J].仪器仪表学报,2020,41(4):49-57.
- [21]魏勇,李学军,李万伟,等.基于空间密度聚类和K-shape算法的城市综合体负荷模式聚类方法[J].电力系统保护与控制,2021,49(14):37-44.
- 短期负荷预测
- 多核模糊C均值
- LSTM神经网络
- 气象因素
short-term load forecasting - multiple kernel fuzzy C-means
- LSTM neural network
- meteorological factor
- 孙景钌
- 胡长洪
- 项烨鋆
- 赵碚
- 刘津源
- 陈梦翔
- 蔡昌春
SUN Jingliao - HU Changhong
- XIANG Yeyun
- ZHAO Pei
- LIU Jinyuan
- CHEN Mengxiang
- CAI Changchun
- 孙景钌
- 胡长洪
- 项烨鋆
- 赵碚
- 刘津源
- 陈梦翔
- 蔡昌春
SUN Jingliao - HU Changhong
- XIANG Yeyun
- ZHAO Pei
- LIU Jinyuan
- CHEN Mengxiang
- CAI Changchun