王玥;张宇帆;李昭昱;艾芊;吕天光;

• 1:电力传输与功率变换控制教育部重点实验室(上海交通大学)

摘要(Abstract)：

随着对利用新能源的迫切需求,分布式能源将以"能量细胞"的形式分布在用户侧,并具有即插即用的特点。受到利益的驱动或稳定性的要求,"能量细胞"将组成形态各异的"能量组织",而新形成的"能量组织"则存在历史数据较少的问题。针对"能量组织"中小样本日前负荷概率预测问题,提出基于pinball损失函数的深度长短时记忆(long short-term memory,LSTM)网络概率预测方法。为解决小样本下深度LSTM网络的过拟合问题,采用自底向上的层次聚类方法进行数据增强,并针对各个分位点进行并行预测。实验结果表明,所提方法能够获得较高的可靠性以及锐度较好的置信区间,可以为日前调度提供合理依据。

关键词(KeyWords)： 能源细胞-组织;即插即用;日前负荷概率预测;分位点;pinball损失函数;深度LSTM;数据增强

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学联合基金项目(U1866206)~~

作者(Author): 王玥;张宇帆;李昭昱;艾芊;吕天光;

Email:

DOI:

参考文献(References)：

• [1] Zhang N,Hu Z,Dai D,et al.Unit commitment model in smart grid environment considering carbon emissions trading[J]. IEEE Transactions on Smart Grid,2016,7(1):420-427.
• [2] Patrao I,Figueres E,GarceráG,et al.Microgrid architectures for low voltage distributed generation[J].Renewable and Sustainable Energy Reviews,2015(43):415-424.
• [3]茆美琴,丁勇,王杨洋,等.微网—未来能源互联网系统中的“有机细胞”[J].电力系统自动化,2017,41(19):1-11.Mao Meiqin,Ding Yong,Wang Yangyang,et al.Microgrid-an“organic cell” for future energy interconnection system[J].Automation of Electric Power Systems,2017,41(19):1-11(in Chinese).
• [4] Magdy G,Mohamed E A,Shabib G,et al.Microgrid dynamic security considering high penetration of renewable energy[J].Protection and Control of Modern Power Systems,2018,3(1):23.
• [5] Hu B,Wang H,Yao S.Optimal economic operation of isolated community microgrid incorporating temperature controlling devices[J].Protection and Control of Modern Power Systems,2017,2(2):70-80.
• [6]王皓,艾芊,吴俊宏,等.基于交替方向乘子法的微电网群双层分布式调度方法[J].电网技术,2018,42(6):1718-1725.Wang Hao,Ai Qian,Wu Junhong,et al.Bi-level distributed optimization for microgrid clusters based on alternating direction method of multipliers[J].Power System Technology,2018,42(6):1718-1725(in Chinese).
• [7] Jie Y U,Ming N I,Yiping J,et al.Plug-in and plug-out dispatch optimization in microgrid clusters based on flexible communication[J].Journal of Modern Power Systems and Clean Energy,2017,5(4):663-670.
• [8]江海啸,郑毅,李少远,等.微网优化控制研究现状及智能化即插即用趋势与策略[J].上海交通大学学报,2017,51(9):1097-1103.Jiang Haixiao,Zheng Yi,Li Shaoyuan,et al.Operational optimization of microgird control:a brief introduction and an intelligent plug-andplay control strategy[J].Journal of Shanghai Jiao Tong University,2017,51(9):1097-1103(in Chinese).
• [9]周晓倩,艾芊,王皓.即插即用微电网集群分布式优化调度[J].电力系统自动化,2018,42(1):106-113.Zhou Xiaoqian,Ai Qian,Wang Hao.Distributed optimal scheduling of microgird cluster with function of plug and play[J].Automation of Electric Power Systems,2018,42(1):106-113(in Chinese).
• [10] Shi H,Xu M,Li R.Deep learning for household load forecasting-a novel pooling deep RNN[J].IEEE Transactions on Smart Grid,2018,9(5):5271-5280.
• [11]史佳琪,谭涛,郭经,等.基于深度结构多任务学习的园区型综合能源系统多元负荷预测[J].电网技术,2018,42(3):698-706.Shi Jiaqi,Tan Tao,Guo Jing,et al.Multi-task learning based on deep architecture for various types of load forecasting in regional energy system integration[J].Power System Technology,2018,42(3):698-706(in Chinese).
• [12] Chen Y,Luh P B,Guan C,et al.Short-term load forecasting:similar day-based wavelet neural networks[J].IEEE Transactions on Power Systems,2010,25(1):322-330.
• [13] Al-Otaibi R,Jin N,Wilcox T,et al.Feature construction and calibration for clustering daily load curves from smart-meter data[J].IEEE Transactions on Industrial Informatics,2016,12(2):645-654.
• [14] Shi D,Li R,Shi R,et al.Analysis of the relationship between load profile and weather condition[C]//2014 IEEE PES General Meeting|Conference&Exposition.Maryland, USA:IEEE,2014:1-5.
• [15] Osowski S,Siwek K.Regularisation of neural networks for improved load forecasting in the power system[J]. IET Generation,Transmission and Distribution,2002,149(3):340-344.
• [16] Zhang Y,Luo G.Short term power load prediction with knowledge transfer[J].Information Systems,2015(53):161-169.
• [17]蒋宇,陈星莺,余昆,等.考虑风电功率预测不确定性的日前发电计划鲁棒优化方法[J].电力系统自动化,2018,42(19):57-63.Jiang Yu,Chen Xingying,Yu Kun,et al.Design and application of dynamic model for power system[J].Automation of Electric Power Systems,2018,42(19):57-63(in Chinese).
• [18]张宇帆,艾芊,郝然,等.基于机会约束规划的楼宇综合能源系统经济调度[J].电网技术,2019,43(1):108-115.Zhang Yufan,Ai Qian,Hao Ran,et al.Economic dispatch of integrated energy system at building level based on chance constrained programming[J].Power System Technology,2019,43(1):108-115(in Chinese).
• [19]范松丽,艾芊,贺兴.基于机会约束规划的虚拟电厂调度风险分析[J].中国电机工程学报,2015,35(16):4025-4034.Fan Songli,Ai Qian,He Xing.Risk analysis on dispatch of virtual power plant based on chance constrained programming[J].Proceedings of the CSEE,2015,35(16):4025-4034(in Chinese).
• [20]何耀耀,闻才喜,许启发.基于Epanechnikov核与最优窗宽组合的中期电力负荷概率密度预测方法[J].电力自动化设备,2016,36(11):120-126.He Yaoyao,Wen Caixi,Xu Qifa.Mid-term power load probability density forecast based on Epanechnikov kernel and optimal window bandwidth[J].Electric Power Automation Equipment,2016,36(11):120-126(in Chinese).
• [21] Yang Y,Li S,Li W,et al.Power load probability density forecasting using Gaussian process quantile regression[J].Applied Energy,2018(213):499-509.
• [22]彭虹桥,顾洁,宋柄兵,等.基于多维变量筛选-非参数组合回归的长期负荷概率预测模型[J].电网技术,2018, 42(6):1768-1775.Peng Hongqiao,Gu Jie,Song Bingbing,et al.Long term probabilistic load forecasting based on multivariate selection and nonparametric combination regression model[J].Power System Technology,2018,42(6):1768-1775(in Chinese).
• [23] Wang Y,Gan D,Sun M,et al.Probabilistic individual load forecasting using pinball loss guided LSTM[J].Applied Energy,2019(235):10-20.
• [24]彭虹桥,顾洁,胡玉,等.基于混沌粒子群—高斯过程回归的饱和负荷概率预测模型[J].电力系统自动化,2017,41(21):25-32.Peng Hongqiao,Gu Jie,Hu Yu,et al.Forecasting model for saturated load based on chaotic particle swarm optimization-Gaussian process regression[J].Automation of Electric Power Systems,2017,41(21):25-32(in Chinese).
• [25] Ward J J H. Hierarchical grouping to optimize an objective function[J].Journal of the American Statistical Association,1963,58(301):236-244.
• [26] Sideratos G,Hatziargyriou N D.Probabilistic wind power forecasting using radial basis function neural networks[J].IEEE Transactions on Power Systems,2012,27(4):1788-1796.
• [27] Pedregosa F,Varoquaux G,Gramfort A,et al.Scikit-learn:machine learning in Python[J]. Journal of Machine Learning Research,2011(12):2825-2830.