
浏览全部资源
扫码关注微信
1.新能源电力系统国家重点实验室(华北电力大学),河北省保定市 071003
2.国网上海市电力公司,上海市 200437
华回春(1980—),男,博士,副教授,主要研究方向:电能质量、电力市场。E-mail:huahuichun@126.com
邓彬(1996—),男,通信作者,硕士研究生,主要研究方向:电力市场、深度学习。E-mail:dengbin13992@126.com
刘哲(1992—),男,硕士,高级工程师,主要研究方向:能源互联网、电能质量。E-mail:liuzheacyy@163.com
收稿:2020-11-18,
修回:2021-10-18,
网络出版:2021-12-01,
纸质出版:2022-02-25
移动端阅览
华回春,邓彬,刘哲等.基于变分自编码高斯混合模型的发电企业串谋智能预警[J].电力系统自动化,2022,46(4):188-196.
HUA Huichun,DENG Bin,LIU Zhe,et al.Intelligent Early-warning of Collusion Between Power Generation Enterprises Based on Variational Autoencoding Gaussian Mixture Model[J].Automation of Electric Power Systems,2022,46(4):188-196.
华回春,邓彬,刘哲等.基于变分自编码高斯混合模型的发电企业串谋智能预警[J].电力系统自动化,2022,46(4):188-196. DOI: 10.7500/AEPS20201118006.
HUA Huichun,DENG Bin,LIU Zhe,et al.Intelligent Early-warning of Collusion Between Power Generation Enterprises Based on Variational Autoencoding Gaussian Mixture Model[J].Automation of Electric Power Systems,2022,46(4):188-196. DOI: 10.7500/AEPS20201118006.
随着市场交易规模越来越大,交易数据量增加,结合数据进行串谋分析成为可能。为此,结合发电企业的串谋预警指标体系和无监督的变分自编码高斯混合模型(VAEGMM),实现了对发电企业串谋的智能预警。首先,提出了完善的串谋预警指标体系和详细的指标计算方法。其次,针对指标集具有高维且正负样本不均衡的数据特点,结合异常检测思想提出了VAEGMM。然后,详细阐述了VAEGMM的网络结构,并且重新构建了联合损失函数,使得该网络能够更好地学习得到原始数据的低维表达,从而有助于进行更准确的密度估计。最后,实例测算表明,与其他传统的无监督学习模型相比较,VAEGMM可以更加高效和准确地预警串谋风险。
As the scale of market transactions becomes larger and the amount of transaction data increases
it becomes possible to conduct collusion analysis with data. Therefore
combining with the collusion early-warning indicator system of the power generation enterprises and the unsupervised variational autoencoding Gaussian mixture model (VAEGMM)
the intelligent early-warning of the collusion between power generation enterprises is realized. Firstly
a complete indicator system for the collusion early-warning and a detailed indicator calculation method are proposed. Secondly
in view of the high-dimensional data characteristics of the index set and the imbalance of positive and negative samples
the VAEGMM is proposed based on the idea of anomaly detection. Then
the network structure of VAEGMM is described in detail
and the joint loss function is reconstructed
making the network better learn the low dimensional expression of the original data. Thus it is helpful for more accurate density estimation. Finally
the actual case study shows that compared with other traditional unsupervised learning models
VAEGMM can warn the risk of collusion more efficiently and accurately.
董礼 , 王胜华 , 华回春 , 等 . 中国现货电力市场中发电企业滥用市场力违规识别 [J/OL]. 中国电机工程学报 : 1 - 11 [ 2021-11-11 ]. https://doi.org/10.13334/j.0258-8013.pcsee.201625 https://doi.org/10.13334/j.0258-8013.pcsee.201625 .
DONG Li , WANG Shenghua , HUA Huichun , et al . Identification of market power abuse in spot market of Chinese electric market [J]. Proceedings of the CSEE: 1 - 11 [ 2021-11-11 ]. https://doi.org/10.13334/j.0258-8013.pcsee.201625 https://doi.org/10.13334/j.0258-8013.pcsee.201625 .
王文举 , 范合君 . 企业价格串谋识别的博弈分析及模拟 [J]. 商业研究 , 2010 ( 5 ): 49 - 52 .
WANG Wenju , FAN Hejun . Analysis and simulation of identification of price collusion [J]. Commercial Research , 2010 ( 5 ): 49 - 52 .
EU Commission , DG Competition . Report on energy sector inquiry , SEC ( 2006 ) 1724 , 10 . 1 .2007: Brussels[R/OL]. [ 2021-11-11 ]. http://ec.europa.eu/public_opinion/archives/eb_special_en.htm http://ec.europa.eu/public_opinion/archives/eb_special_en.htm .
KANAGALA A , SAHNI M , SHARMA S , et al . A probabilistic approach of Hirschman-Herfindahl Index (HHI) to determine possibility of market power acquisition [C]// Power Systems Conference and Exposition , October 10-13 , 2004 , New York, USA : 1277 - 1282 .
BATAILLE M , BODNAR O , STEINMETZ A , et al . Screening instruments for monitoring market power—the return on withholding capacity index (RWC) [J]. Energy Economics , 2019 , 81 : 227 - 237 .
NEUHOFF K , BARQUIN J , BOOTS M G , et al . Network-constrained Cournot models of liberalized electricity markets: the devil is in the details [J]. Energy Economics , 2005 , 27 ( 3 ): 495 - 525 .
HOBBS B F , HELMAN U . Complementarity-based equilibrium modeling for electric power markets [M]. New York, USA : Wiley , 2004 .
IÑÓN J , HOBBS B F . Generation adequacy , market regulation and demand elasticity in the electricity industry: a stochastic long run equilibrium analysis of capacity markets[EB/OL]. [ 2021-11-11 ]. http://iaee.org/documents/washington/Ben_Hobbs2.pdf http://iaee.org/documents/washington/Ben_Hobbs2.pdf .
XIE W , DING Q , TU M F , et al . Market power monitoring framework and measures in electricity market [C]// 2019 IEEE Sustainable Power and Energy Conference (iSPEC) , November 21-23 , 2019 , Beijing, China : 129 - 133 .
孙波 , 邓瑞林 , 谢敬东 , 等 . 基于排序多元Logit模型的卡特尔类机组串谋竞价识别 [J]. 电力系统自动化 , 2021 , 45 ( 6 ): 109 - 115 .
SUN Bo , DENG Ruilin , XIE Jingdong , et al . Collusion bidding identification of Cartel-type generators based on ordered logit model [J]. Automation of Electric Power Systems , 2021 , 45 ( 6 ): 109 - 115 .
蒋玮 , 吴杰 , 冯伟 , 等 . 日前电力市场不完全信息条件下的电力供需双边博弈模型 [J]. 电力系统自动化 , 2019 , 43 ( 2 ): 18 - 24 .
JIANG Wei , WU Jie , FENG Wei , et al . Bilateral game model of power supply and demand sides with incomplete information in day-ahead electricity market [J]. Automation of Electric Power Systems , 2019 , 43 ( 2 ): 18 - 24 .
ESMAEILI ALIABADI D , KAYA M , ŞAHIN G . Determining collusion opportunities in deregulated electricity markets [J]. Electric Power Systems Research , 2016 , 141 : 432 - 441 .
史述红 , 刘敦楠 , 胡会文 , 等 . 市场开放下电力交易全过程违规行为识别探究 [J]. 价格理论与实践 , 2018 ( 8 ): 51 - 54 .
SHI Shuhong , LIU Dunnan , HU Huiwen , et al . Identification of violations in the whole process of electricity market transactions [J]. Price: Theory & Practice , 2018 ( 8 ): 51 - 54 .
刘敦楠 , 李瑞庆 , 陈雪青 , 等 . 电力市场监管指标及市场评价体系 [J]. 电力系统自动化 , 2004 , 28 ( 9 ): 16 - 21 .
LIU Dunnan , LI Ruiqing , CHEN Xueqing , et al . Surveillance indices and evaluating system of electricity market [J]. Automation of Electric Power Systems , 2004 , 28 ( 9 ): 16 - 21 .
TELLIDOU A C , BAKIRTZIS A G . Agent-based analysis of capacity withholding and tacit collusion in electricity markets [J]. IEEE Transactions on Power Systems , 2007 , 22 ( 4 ): 1735 - 1742 .
LIANG Y C , GUO C L , DING Z H , et al . Agent-based modeling in electricity market using deep deterministic policy gradient algorithm [J]. IEEE Transactions on Power Systems , 2020 , 35 ( 6 ): 4180 - 4192 .
刘敦楠 , 张潜 , 李霄彤 , 等 . 基于云模型与模糊Petri网的电力市场潜在危害行为识别 [J]. 电力系统自动化 , 2019 , 43 ( 2 ): 25 - 33 .
LIU Dunnan , ZHANG Qian , LI Xiaotong , et al . Identification of potential harmful behaviors in electricity market based on cloud model and fuzzy Petri net [J]. Automation of Electric Power Systems , 2019 , 43 ( 2 ): 25 - 33 .
张海生 , 曹喆 , 杨昌海 , 等 . 基于AdaBoost-DT算法的电力市场串谋行为识别研究 [J]. 电力工程技术 , 2020 , 39 ( 2 ): 152 - 158 .
ZHANG Haisheng , CAO Zhe , YANG Changhai , et al . Collusive behavior recognition in electricity market based on AdaBoost-DT algorithm [J]. Electric Power Engineering Technology , 2020 , 39 ( 2 ): 152 - 158 .
KIM K I , FRANZ M O , SCHOLKOPF B . Iterative kernel principal component analysis for image modeling [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2005 , 27 ( 9 ): 1351 - 1366 .
HUBER P J . International encyclopedia of statistical science [M]. Berlin, Heidelberg,Germany : Springer , 2011 : 1248 - 1251 .
CANDÈS E J , LI X D , MA Y , et al . Robust principal component analysis? [J]. Journal of the ACM , 2011 , 58 ( 3 ): 1 - 37 .
ZHOU C , PAFFENROTH R C . Anomaly detection with robust deep autoencoders [C]// 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , August 13-17 , 2017 , Halifax, Canada : 665 - 674 .
ZIMEK A , SCHUBERT E , KRIEGEL H P . A survey on unsupervised outlier detection in high-dimensional numerical data [J]. Statistical Analysis and Data Mining: the ASA Data Science Journal , 2012 , 5 ( 5 ): 363 - 387 .
KIM J , SCOTT C . Robust kernel density estimation [J]. The Journal of Machine Learning Research , 2012 , 13 ( 1 ): 2529 - 2565 .
CHANDOLA V , BANERJEE A , KUMAR V . Anomaly detection [J]. ACM Computing Surveys , 2009 , 41 ( 3 ): 1 - 58 .
CHEN Y Q , ZHOU X S , HUANG T S . One-class SVM for learning in image retrieval [C]// 2001 International Conference on Image Processing , October 7-10 , 2001 , Thessaloniki, Greece : 34 - 37 .
SONG Q , HU W J , XIE W F . Robust support vector machine with bullet hole image classification [J]. IEEE Transactions on Systems, Man, and Cybernetics , Part C (Applications and Reviews), 2002 , 32 ( 4 ): 440 - 448 .
ZONG B , SONG Q , MIN M R , et al . Deep autoencoding Gaussian mixture model for unsupervised anomaly detection [EB/OL]. [ 2021-11-11 ]. https://sites.cs.ucsb.edu/~bzong/doc/iclr18-dagmm.pdf https://sites.cs.ucsb.edu/~bzong/doc/iclr18-dagmm.pdf .
FAN H Y , ZHANG F B , WANG R D , et al . Correlation-aware deep generative model for unsupervised anomaly detection [C]// 24th Pacific-Asia Conference , PAKDD 2020 , May 11-14, 2020, Singapore , Singapore : 688 - 700 .
DOERSCH C . Tutorial on variational autoencoders [EB/OL].[ 2021-11-11 ]. https://arxiv.org/pdf/1606.05908.pdf https://arxiv.org/pdf/1606.05908.pdf .
AN J , CHO S . Variational autoencoder based anomaly detection using reconstruction probability [EB/OL]. [ 2021-10-10 ]. http://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf http://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf .
梁杰 , 陈嘉豪 , 张雪芹 , 等 . 基于独热编码和卷积神经网络的异常检测 [J]. 清华大学学报(自然科学版) , 2019 , 59 ( 7 ): 523 - 529 .
LIANG Jie , CHEN Jiahao , ZHANG Xueqin , et al . One-hot encoding and convolutional neural network based anomaly detection [J]. Journal of Tsinghua University (Science and Technology) , 2019 , 59 ( 7 ): 523 - 529 .
SRIVASTAVA N , HINTON G , KRIZHEVSKY A , et al . Dropout: a simple way to prevent neural networks from overfitting [J]. The Journal of Machine Learning Research , 2014 , 15 ( 1 ): 1929 - 1958 .
0
浏览量
0
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621