摘要
以多能源互补协调、"信息—物理—社会"系统深度融合为特征的大能源系统正在出现。因此,急需对面向能源系统的数据科学及大数据挖掘理论与技术开展深入研究。在此背景下,初步探讨了数据科学及其在大能源系统中的应用。首先介绍了数据科学的基本理论,并着重讨论了统计学习理论及数据质量理论的重要性。接着,介绍了深度学习、转移学习和多源数据融合等大数据挖掘技术的新进展。最后,对数据挖掘技术在能源系统中的应用现状做了简单回顾,并展望了未来能源系统数据挖掘研究中值得关注的若干问题。
The comprehensive energy system,which can coordinate multiple types of energy and be characterized by a deep integration of"cyber-physical-social"systems,is emerging. There is therefore an urgent need to conduct in-depth study on data science and big data mining for energy systems. This paper presents an initial discussion on data science and its applications in comprehensive energy systems. The fundamentals of data science,in particular the importance of the statistical learning theory and data quality,are discussed first. The new progresses in big data mining,such as deep learning,transfer learning and cross domain data fusion,are introduced then. Finally,a brief review is given on the applications of data mining techniques in energy systems; some research problems in energy system data mining,which require further attentions in future,are also discussed.
引文
[1]Big data[J].Nature,2008,455(1):1-136.
[2]Dealing with data[J].Science,2008,331:639-806.
[3]国务院关于印发促进大数据发展行动纲要的通知[EB/OL].[2015-08-31].http://www.gov.cn/zhengce/content/2015-09/05/content_10137.htm.
[4]PROVOST F,FAWCETT T.Data science and its relationship to big data and data-driven decision making[J].Big Data,2013,1(1):51-59.
[5]李国杰,程学旗.大数据研究:未来科技及经济社会发展的重大战略领域——大数据的研究现状与科学思考[J].中国科学院院刊,2012,27(6):647-657.LI Guojie,CHENG Xueqi.Research status and scientific thinking of big data[J].Bulletin of Chinese Academy of Sciences,2012,27(6):647-657.
[6]XUE Yusheng.Energy Internet or comprehensive energy network[J].Journal of Modern Power Systems and Clean Energy,2015,3(3):297-301.
[7]董朝阳,赵俊华,文福拴,等.从智能电网到能源互联网:基本概念与研究框架[J].电力系统自动化,2014,38(15):1-11.DOI:10.7500/AEPS20140613007.DONG Zhaoyang,ZHAO Junhua,WEN Fushuan,et al.From smart grid to Energy Internet:basic concept and research framework[J].Automation of Electric Power Systems,2014,38(15):1-11.DOI:10.7500/AEPS20140613007.
[8]贾宏杰,王丹,徐宪东,等.区域综合能源系统若干问题研究[J].电力系统自动化,2015,39(7):198-207.DOI:10.7500/AEPS20141009011.JIA Hongjie,WANG Dan,XU Xiandong,et al.Research on some key problems related to integrated energy systems[J].Automation of Electric Power Systems,2015,39(7):198-207.DOI:10.7500/AEPS20141009011.
[9]赵俊华,文福拴,薛禹胜,等.电力CPS的架构及其实现技术与挑战[J].电力系统自动化,2010,34(16):1-7.ZHAO Junhua,WEN Fushuan,XUE Yusheng,et al.Cyber physical power systems:architecture,implementation techniques and challenges[J].Automation of Electric Power Systems,2010,34(16):1-7.
[10]赵俊华,文福拴,薛禹胜,等.电力信息物理融合系统的建模分析与控制研究框架[J].电力系统自动化,2011,35(16):1-8.ZHAO Junhua,WEN Fushuan,XUE Yusheng,et al.Modeling analysis and control research framework of cyber physical power systems[J].Automation of Electric Power Systems,2011,35(16):1-8.
[11]VASANT D.Data science and prediction[J].Communications of the ACM,2013,56(1):64-73.
[12]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(一)大数据与电力大数据[J].电力系统自动化,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part one big data and power big data[J].Automation of Electric Power Systems,2016,40(1):1-8.DOI:10.7500/AEPS20151208005.
[13]薛禹胜,赖业宁.大能源思维与大数据思维的融合:(二)应用及探索[J].电力系统自动化,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.XUE Yusheng,LAI Yening.Integration of macro energy thinking and big data thinking:Part two applications and exploration[J].Automation of Electric Power Systems,2016,40(8):1-13.DOI:10.7500/AEPS20160311004.
[14]PEARL J.An introduction to causal inference[J].International Journal of Biostatistics,2010,6(2):1-67.
[15]VAPNIK V.The nature of statistical learning theory[M].New York,USA:Springer Science&Business Media,2000.
[16]WANG H,FAN W,YU P S.Mining concept-drifting data streams using ensemble classifiers[C]//Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 24-27,2003,Washington DC,USA:226-235.
[17]MADNICK S E,WANG R Y,LEE Y W.Overview and framework for data and information quality research[J].ACM Journal of Data and Information Quality,2009,1(1):1-22.
[18]WANG R Y,STRONG D M.Beyond accuracy:what data quality means to data consumers?[J].Journal of Management Information Systems,1996,12(4):5-33.
[19]PIPINO L L,LEE Y W,WANG R Y.Data quality assessment[J].Communications of the ACM,2002,45(4):211-218.
[20]TAYI G K,BALLOU D P.Examining data quality[J].Communications of the ACM,1998,41(2):54-57.
[21]HAN J,PEI J,KAMBER M.Data mining:concepts and techniques[M].USA:Morgan Kaufmann,2011.
[22]HODGE V J,AUSTIN J.A survey of outlier detection methodologies[J].Artificial Intelligence Review,2004,22(2):85-126.
[23]AREL I,ROSE D C,KARNOWSKI T P.Deep machine learning—a new frontier in artificial intelligence research[J].IEEE Computational Intelligence Magazine,2010,5(4):13-18.
[24]BENGIO Y,LAMBLIN P,POPOVICI D.Greedy layer-wise training of deep networks[C]//Annual Conference on Advances in Neural Information Processing Systems(NIPS),December 5-7,2005,Whistler,BC,Canada:8p.
[25]HUANG F,LECUN Y.Large-scale learning with SVM and convolutional nets for generic object recognition[C]//Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,June 17-22,2006,New York,USA:284-291.
[26]HINTON G E,OSINDERO S,THE Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[27]FAN Y,QIAN Y,XIE F L.TTS synthesis with bidirectional LSTM based recurrent neural networks[C]//International Speech Communication Association(Interspeech)Conference,September14-18,2014,Singapore:1964-1968.
[28]WEISS K,KHOSHGOFTAAR T M,WANG D.A survey of transfer learning[J].Journal of Big Data,2016,3(1):1-40.
[29]HUANG P,WANG G,QIN S.Boosting for transfer learning from multiple data sources[J].Pattern Recognition Letters,2012,33(5):568-579.
[30]RAINA R,BATTLE A,LEE H.Self-taught learning:transfer learning from unlabeled data[C]//Proceedings of the 24th International Conference on Machine Learning,June 1-5,2007,Corvalis,OR,USA:759-766.
[31]LAWRENCE N D,PLATT J C.Learning to learn with the informative vector machine[C]//Proceedings of the 21st International Conference on Machine Learning,July 4-8,2004,Banff,AB,Canada:8p.
[32]XIAO X,ZHENG Y,LUO Q.Finding similar users using category-based location history[C]//Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems,November 2-5,2010,San Jose,CA,USA:442-445.
[33]BLUM A,MITCHELL T.Combining labeled and unlabeled data with co-training[C]//Proceedings of the Eleventh Annual Conference on Computational Learning Theory,July 24-26,1998,Madison,WI,USA:92-100.
[34]YUAN N J,ZHENG Y,XIE X.Discovering urban functional zones using latent activity trajectories[J].IEEE Trans on Knowledge and Data Engineering,2015,27(3):712-725.
[35]ZHENG V W,ZHENG Y,XIE X.Collaborative location and activity recommendations with GPS history data[C]//Proceedings of the 19th International Conference on World Wide Web,April26-30,2010,Raleigh,NC,USA:1029-1038.
[36]HIPPERT H S,PEDREIRA C E,SOUZA R C.Neural networks for short-term load forecasting:a review and evaluation[J].IEEE Trans on Power Systems,2001,16(1):44-55.
[37]VERMAAK J,BOTHA E.Recurrent neural networks for shortterm load forecasting[J].IEEE Trans on Power Systems,1998,13(1):126-132.
[38]GONZALEZ C,WILLIAMS J M,JUAREZ I.Important variable assessment and electricity price forecasting based on regression tree models:classification and regression trees,bagging and random forests[J].IET Generation,Transmission&Distribution,2015,9(11):1120-1128.
[39]DING Q.Long-term load forecast using decision tree method[C]//Proceedings of IEEE PES Power Systems Conference and Exposition,October 29-November 1,2006,Atlanta,GA,USA:1541-1543.
[40]ALRASHIDI M,EL-NAGGAR K.Long term electric load forecasting based on particle swarm optimization[J].Applied Energy,2010,87(1):320-326.
[41]LIU H,LIU D,LIANG Y M.Research on natural gas load forecasting based on least squares support vector machine[C]//Proceedings of 2004 International Conference on Machine Learning and Cybernetics,August 26-29,2004,Shanghai,China:3124-3128.
[42]IDOWU S,SAGUNA S,AHLUND C.Forecasting heat load for smart district heating systems:a machine learning approach[C]//Proceedings of IEEE International Conference on Smart Grid Communications,November 3-6,2014,Venice,Italy:554-559.
[43]LI Q,MENG Q,CAI J.Applying support vector machine to predict hourly cooling load in the building[J].Applied Energy,2009,86(10):2249-2256.
[44]FIGUEIREDO M,ALMEIDA A D,RIBEIRO B.Home electri-cal signal disaggregation for non-intrusive load monitoring(NILM)systems[J].Neurocomputing,2012,96(1):66-73.
[45]MITTELSDORF M,HUWEL A,KLINGENBEG T.Submeter based training of multi-class support vector machines for appliance recognition in home electricity consumption data[C]//International Conference on Smart Cities and Green ICT Systems(SMARTGREENS),May 9-10,2013,Aachen,Germany:151-158.
[46]PARADISO F,PAGANELLI F,LUCHETTA A.ANN-based appliance recognition from low-frequency energy monitoring data[C]//Proceedings of IEEE 14th International Symposium and Workshops on World of Wireless,Mobile and Multimedia Networks,June 4-7,2013,Madrid,Spain:1-6.
[47]KONG S,KIM Y,KO R.Home appliance load disaggregation using cepstrum-smoothing-based method[J].IEEE Trans on Instrumentation and Measurement,2015,61(1):24-30.
[48]EGARTER D,BHUVANA V P,ELMENREICH W.PALDi:online load disaggregation via particle filtering[J].IEEE Trans on Instrumentation and Measurement,2014,64(2):467-477.
[49]HU X,LI S,YANG Y.Advanced machine learning approach for lithium-ion battery state estimation in electric vehicles[J].IEEE Trans on Transportation Electrification,2016,2(2):140-149.
[50]LIU A,PENTLAND A.Towards real-time recognition of driver intentions[C]//Proceedings of IEEE Conference on Intelligent Transportation System,November 9-12,1997,Boston,MA,USA:236-241.
[51]MURPHEY Y L,PARK J,CHEN Z.Intelligent hybrid vehicle power control:Part 1 machine learning of optimal vehicle power[J].IEEE Trans on Vehicular Technology,2012,61(8):3519-3530.
[52]张洪财,胡泽春,宋永华,等.考虑时空分布的电动汽车充电负荷预测方法[J].电力系统自动化,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.ZHANG Hongcai,HU Zechun,SONG Yonghua,et al.A prediction method for electric vehicle charging load considering spatial and temporal distribution[J].Automation of Electric Power Systems,2014,38(1):13-20.DOI:10.7500/AEPS20130613009.
[53]罗卓伟,胡泽春,宋永华,等.电动汽车充电负荷计算方法[J].电力系统自动化,2011,35(14):36-42.LUO Zhuowei,HU Zechun,SONG Yonghua,et al.Study on plug in electric vehicles charging load calculating[J].Automation of Electric Power Systems,2011,35(14):36-42.
[54]MAJIDPOUR M,QIU C,CHU P.Fast prediction for sparse time series:demand forecast of EV charging stations for cell phone applications[J].IEEE Trans on Industrial Informatics,2015,11(1):242-250.
[55]SOLTANI N Y,KIM S J,GIANNAKIS G B.Real-time load elasticity tracking and pricing for electric vehicle charging[J].IEEE Trans on Smart Grid,2015,6(3):1303-1313.
[56]GOPALAKRISHNAN R,BISWAS A,LIGHTWALA A.Demand prediction and placement optimization for electric vehicle charging stations[EB/OL].[2016-07-13].2016.ar Xiv preprint ar Xiv:1604.05472.
[57]WEIDLICH A,VEIT D.A critical survey of agent-based wholesale electricity market models[J].Energy Economics,2008,30(4):1728-1759.
[58]YOUNG D,PLOETTI S,BROWNE O.Can agent-based models forecast spot prices in electricity markets?Evidence from the New Zealand electricity market[J].Energy Economics,2014,45(1):419-434.
[59]JONES R H.Reductionism:analysis and the fullness of reality[M].USA:Bucknell University Press,2000.
[60]ZHENG Y,CAPRA L,WOLFSON O.Urban computing:concepts,methodologies,and applications[J].ACM Trans on Intelligent Systems and Technology(TIST),2014,5(3):1-55.