Typical Wind-PV-Load Scenario Generation Based on Residual Convolutional Auto-encoders

doi:10.12204/j.issn.1000-7229.2021.08.002

Abstract

Abstract:

With the development of new energy sources, higher requirements are put forward for the regulation and operation of grids with PV and wind power. The typical scenario is one of the main ways to deal with this problem. The traditional method for generating typical scenarios is prone to data information loss and feature extraction inaccuracy. This paper proposes an uncertain wind-PV-load typical scenario generation method based on residual convolution auto-encoders. First, the residual convolution auto-encoders network is used to extract the characteristics of wind-PV-load data to reduce the data dimension while reducing the loss of data information and taking into account the coupling of wind and solar power. Then, reducing the influence of noise data on the experimental results, k-medoids is used for clustering to generate typical scenarios. The actual data collected from a power grid in northwest China is taken as the research object. Comparison with traditional clustering methods such as DBI (Davies-Bouldin Index), CHI (Calinski-Harabasz Index) and other indicators, the feasibility of the proposed method is verified.

Key words: residual neural network, multi-channel convolutional auto-encoder, wind-PV-load feature extraction, scenario generation

CLC Number:

TM715

PENG Yuzheng, LI Xiaolu, LI Congli, DING Yi. Typical Wind-PV-Load Scenario Generation Based on Residual Convolutional Auto-encoders[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(8): 10-17.

Figures/Tables 15

Fig.1 Structure of CAE model

Fig.2 Structure of residual module

Fig.3 Example of residual network architecture

Fig.4 Two structural forms of residuals blocks

Fig.5 Improved multi-channel convolutional encoder using residual network

Fig.6 The framework structure of wind-PV-load scenario generation based on RESCAE-kmedoids

Fig.7 Change of SIL evaluation index

Fig.8 Typical annual wind-PV-load scenarios

Fig.9 Typical seasonal wind-PV-load scenarios

Table 1 Typical annual wind-PV-load scenario probability

Table 2 Typical seasonal wind-PV-load scenario probability

Fig.10 The computation result of CHI index

Fig.11 The computation result of DBI index

Fig.12 CHI calculation index result of auto-encoded clustering

Fig.13 DBI calculation index result of auto-encoded clustering

References 20

[1]	WANG T, BI T S, WANG H F, et al. Decision tree based online stability assessment scheme for power systems with renewable generations[J]. CSEE Journal of Power and Energy Systems, 2015, 1(2): 53-61. doi: 10.17775/CSEEJPES.2015.00019 URL
[2]	王洪涛, 刘旭, 陈之栩, 等. 低碳背景下基于改进通用生成函数法的随机生产模拟[J]. 电网技术, 2013, 37(3): 597-603.
	WANG Hongtao, LIU Xu, CHEN Zhixu, et al. Power system probabilistic production simulation based on improved universal generating function methods in low-carbon context[J]. Power System Technology, 2013, 37(3): 597-603.
[3]	罗庆, 晁勤, 王一波, 等. 基于场景划分方法的风光出力耦合特性机理[J]. 电力自动化设备, 2014, 34(8): 42-46.
	LUO Qing, CHAO Qin, WANG Yibo, et al. Characteristics of wind-photovoltaic power output coupling based on scenario classification[J]. Electric Power Automation Equipment, 2014, 34(8): 42-46.
[4]	NOTARISTEFANO A, CHICCO G, PIGLIONE F. Data size reduction with symbolic aggregate approximation for electrical load pattern grouping[J]. IET Generation, Transmission & Distribution, 2013, 7(2): 108-117. doi: 10.1049/iet-gtd.2012.0383 URL
[5]	林顺富, 田二伟, 符杨, 等. 基于信息熵分段聚合近似和谱聚类的负荷分类方法[J]. 中国电机工程学报, 2017, 37(8): 2242-2253.
	LIN Shunfu, TIAN Erwei, FU Yang, et al. Power load classification method based on information entropy piecewise aggregate approximation and spectral clustering[J]. Proceedings of the CSEE, 2017, 37(8): 2242-2253.
[6]	LASUE J, WIENS R C, STEPINSKI T F, et al. Nonlinear mapping technique for data visualization and clustering assessment of LIBS data: Application to ChemCam data[J]. Analytical and Bioanalytical Chemistry, 2011, 400(10): 3247-3260. doi: 10.1007/s00216-011-4747-3 URL
[7]	BOLOGNA G, HAYASHI Y. Characterization of symbolic rules embedded in deep DIMLP networks: A challenge to transparency of deep learning[J]. Journal of Artificial Intelligence and Soft Computing Research, 2017, 7(4): 265-286. doi: 10.1515/jaiscr-2017-0019 URL
[8]	石亮缘, 周任军, 张武军, 等. 采用深度学习和多维模糊C均值聚类的负荷分类方法[J]. 电力系统及其自动化学报, 2019, 31(7): 43-50.
	SHI Liangyuan, ZHOU Renjun, ZHANG Wujun, et al. Load classification method using deep learning and multi-dimensional fuzzy C-means clustering[J]. Proceedings of the CSU-EPSA, 2019, 31(7): 43-50.
[9]	杨晶显, 刘俊勇, 韩晓言, 等. 基于深度嵌入聚类的水光荷不确定性源场景生成方法[J]. 中国电机工程学报, 2020, 40(22): 7296-7306.
	YANG Jingxian, LIU Junyong, HAN Xiaoyan, et al. An uncertain hydro/PV/load typical scenarios generation method based on deep embedding for clustering[J]. Proceedings of the CSEE, 2020, 40(22): 7296-7306.
[10]	申昌, 冀俊忠. 基于双通道卷积神经网络的文本情感分类算法[J]. 模式识别与人工智能, 2018, 31(2): 158-166. doi: 10.16451/j.cnki.issn1003-6059.201802007
	SHEN Chang, JI Junzhong. Text sentiment classification algorithm based on double channel convolutional neural network[J]. Pattern Recognition and Artificial Intelligence, 2018, 31(2): 158-166. doi: 10.16451/j.cnki.issn1003-6059.201802007
[11]	栗然, 孙帆, 丁星, 等. 考虑多能时空耦合的用户级综合能源系统超短期负荷预测方法[J]. 电网技术, 2020, 44(11): 4121-4134.
	LI Ran, SUN Fan, DING Xing, et al. Ultra short-term load forecasting for User-level integrated energy system considering multi-energy spatio-temporal coupling[J]. Power System Technology, 2020, 44(11): 4121-4134.
[12]	LAINA I, RUPPRECHT C, BELAGIANNIS V, et al. Deeper depth prediction with fully convolutional residual networks[C]// 2016 Fourth International Conference on 3D Vision (3DV). Stanford, CA, USA: IEEE, 2016: 239-248.
[13]	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016: 770-778.
[14]	SHI T, MEI F, LU J X, et al. Phase space reconstruction algorithm and deep learning-based very short-term bus load forecasting[J]. Energies, 2019, 12(22): 4349.
[15]	贾瑞明, 李阳, 李彤, 等. 多层级特征融合结构的单目图像深度估计网络[J]. 计算机工程, 2020, 46(12): 207-214.
	JIA Ruiming, LI Yang, LI Tong, et al. Monocular image depth estimation network with multiple level feature fusion structure[J]. Computer Engineering, 2020, 46(12): 207-214.
[16]	张斌, 庄池杰, 胡军, 等. 结合降维技术的电力负荷曲线集成聚类算法[J]. 中国电机工程学报, 2015, 35(15): 3741-3749.
	ZHANG Bin, ZHUANG Chijie, HU Jun, et al. Ensemble clustering algorithm combined with dimension reduction techniques for power load profiles[J]. Proceedings of the CSEE, 2015, 35(15): 3741-3749.
[17]	丁明, 解蛟龙, 刘新宇, 等. 面向风电接纳能力评价的风资源/负荷典型场景集生成方法与应用[J]. 中国电机工程学报, 2016, 36(15): 4064-4072.
	DING Ming, XIE Jiaolong, LIU Xinyu, et al. The generation method and application of wind resources/load typical scenario set for evaluation of wind power grid integration[J]. Proceedings of the CSEE, 2016, 36(15): 4064-4072.
[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.
	ZHAO Bing, WANG Zengping, JI Weijia, et al. A short-term power load forecasting method based on attention mechanism of CNN-GRU[J]. Power System Technology, 2019, 43(12): 4370-4376.
[19]	XU Q Y, KANG C Q, ZHANG N, et al. A probabilistic method for determining grid-accommodable wind power capacity based on multiscenario system operation simulation[J]. IEEE Transactions on Smart Grid, 2016, 7(1): 400-409. doi: 10.1109/TSG.2014.2381271 URL
[20]	潘尔生, 宋毅, 原凯, 等. 考虑可再生能源接入的综合能源系统规划评述与展望[J]. 电力建设, 2020, 41(12): 1-13.
	PAN Ersheng, SONG Yi, YUAN Kai, et al. Review and prospect of integrated energy system planning considering the integration of renewable energy[J]. Electric Power Construction, 2020, 41(12): 1-13.