“AI+” Based Smart Grid Prediction Analysis

doi:10.16183/j.cnki.jsjtu.2018.10.008

Abstract

Abstract: Smart grid prediction analysis (SGPA) is the basis to ensure the economic and safe operation of power system. With the breakthrough of AI and the big data environment for smart grid, AI based SGPA is significant for the development of power system, thus this paper proposes “AI+” prediction. Firstly, the background of AI and SGPA and some related issues are introduced. Then based on different emphasis, the AI applications in renewable energy prediction, load prediction, steady state voltage stability prediction and related preventive measures are reviewed and future direction of the research content is prospected. In addition, other related technologies involved in prediction (sample generation, imbalanced data and features extraction) are summarized. Finally, limitations and future developments about AI are discussed and suggestions and ideas are proposed.

Key words: smart grid, “AI+” prediction, sample generation, imbalanced data, features extraction

CLC Number:

TM 721

WU Qianhong,HAN Bei,FENG Lin,LI Guojie,JIANG Xiuchen. “AI+” Based Smart Grid Prediction Analysis[J]. Journal of Shanghai Jiaotong University, 2018, 52(10): 1206-1219.

References

［1］鞠平, 周孝信, 陈维江, 等. “智能电网+”研究综述［J］. 电力自动化设备, 2018, 38(5): 2-11. JU Ping, ZHOU Xiaoxin, CHEN Weijiang, et al. “Smart Grid Plus” research overview［J］. Electric Power Automation Equipment, 2018, 38(5): 2-11. ［2］MAHMUD M, KAISER M S, HUSSAIN A, et al. Applications of deep learning and reinforcement learning to biological data［J］. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(6): 2063-2079. ［3］MCBEE M P, AWAN O A, COLUCCI A T, et al. Deep learning in radiology［J］. Academic Radiology, 2018: 1-9. ［4］LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis［J］. Medical Image Analysis, 2017, 42(9): 60-88. ［5］张东霞, 苗新, 刘丽平, 等. 智能电网大数据技术发展研究［J］. 中国电机工程学报, 2015, 35(1): 2-11. ZHANG Dongxia, MIAO Xin, LIU Liping, et al. Research on development strategy for smart grid big data［J］. Proceedings of the CSEE, 2015, 35(1): 2-11. ［6］AGWU O E, AKPABIO J U, ALABI S B, et al. Artificial intelligence techniques and their applications in drilling fluid engineering: A review［J］. Journal of Petroleum Science & Engineering, 2018, 167: 300-315. ［7］钟义信. 人工智能: 概念·方法·机遇［J］. 科学通报, 2017, 62(22): 2473-2479. ZHONG Yixin. Artificial intelligence: Concept, approach and opportunity［J］. Chinese Science Bulletin, 2017, 62(22): 2473-2479. ［8］孙秋野, 杨凌霄, 张化光. 智慧能源——人工智能技术在电力系统中的应用与展望［J］. 控制与决策, 2018, 33(5): 938-949. SUN Qiuye, YANG Lingxiao, ZHANG Huaguang. Smart energy—Applications and prospects of artificial intelligence technology in power system［J］. Control and Decision, 2018, 33(5): 938-949. ［9］陈学松, 杨宜民. 强化学习研究综述［J］. 计算机应用研究, 2010, 27(8): 2834-2838. CHEN Xuesong, YANG Yimin. Reinforcement learning: Survey of recent work［J］. Application Research of Computers, 2010, 27(8): 2834-2838. ［10］刘全, 翟建伟, 章宗长, 等. 深度强化学习综述［J］. 计算机学报, 2018, 41(1): 1-27. LIU Quan, ZHAI Jianwei, ZHANG Zongzhang, et al. A survey on deep reinforcement learning［J］. Chinese Journal of Computers, 2018, 4(1): 1-27. ［11］EC JRC, U.S DOE. Assessing smart grid benefits and impacts: EU and U.S initiatives［R/OL］. (2012)［2018-07-09］. http:∥ses.jrc.ec.europa.eu/assessing-smart-grid-benefits-and-impacts-eu-and-us-initiatives. ［12］TONKOSKI R, TURCOTTE D, EL-FOULY T H M. Impact of high PV penetration on voltage profiles in residential neighborhoods［J］. IEEE Transactions on Sustainable Energy, 2012, 3(3): 518-527. ［13］ARISTIDOU P, VALVERDE G, CUTSEM T V. Contribution of distribution network control to voltage stability: A case study［J］. IEEE Transactions on Smart Grid, 2017, 8(1): 106-116. ［14］MORTAZAVI H, MEHRJERDI H, SAAD M, et al. A monitoring technique for reversed power flow detection with high PV penetration level［J］. IEEE Transactions on Smart Grid, 2015, 6(5): 2221-2232. ［15］YAN R, SAHA T K. Investigation of voltage stability for residential customers due to high photovoltaic penetrations［J］. IEEE Transactions on Power Systems, 2012, 27(2): 651-662. ［16］AKBARI M A, AGHAEI J, BARANI M, et al. New metrics for evaluating technical benefits and risks of DGs increasing penetration［J］. IEEE Transactions on Smart Grid, 2017, 8(6): 2890-2902. ［17］CHEN P C, MALBASE V, KEZUNOVIC M. Analysis of voltage stability issues with distributed generation penetration in distribution networks［C］∥2013 North American Power Symposium (NAPS). Manhattan, KS: IEEE, 2013: 1-6. ［18］NGUYEN H D, TURITSYN K. Voltage multistability and pulse emergency control for distribution system with power flow reversal［J］. IEEE Transactions on Smart Grid, 2015, 6(6): 2985-2996. ［19］NGUYEN H D, TURITSYN K. Voltage multi-stability in distribution grids with power flow reversal［C］∥2016 IEEE International Conference on Sustainable Energy Technologies (ICSET). Hanoi: IEEE, 2016: 19-24. ［20］TONKOSKI R, LOPES L A C, EL-FOULY T H M. Coordinated active power curtailment of grid connected PV inverters for overvoltage prevention［J］. IEEE Transactions on Sustainable Energy, 2011, 2(2): 139-147. ［21］WANG Y, CHEN Q, HONG T, et al. Review of smart meter data analytics: Applications, methodologies, and challenges［J］. IEEE Transactions on Smart Grid, 2018, DOI: 10.1109/TSG.2018.2818167. ［22］KHAN S, YAIRI T. A review on the application of deep learning in system health management［J］. Mechanical Systems & Signal Processing, 2018, 107(1): 241-265. ［23］ALZAHRANI A, SHAMSI P, DAGLI C, et al. Solar irradiance forecasting using deep neural networks［J］. Procedia Computer Science, 2017, 114: 304-313. ［24］GENSLER A, HENZE J, SICK B, et al. Deep learning for solar power forecasting — An approach using Autoencoder and LSTM neural networks［C］∥2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Budapest: IEEE, 2016: 002858-002865. ［25］WANG H, YI H, PENG J, et al. Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network［J］. Energy Conversion & Management, 2017, 153: 409-422. ［26］史佳琪, 张建华. 基于深度学习的超短期光伏精细化预测模型研究［J］. 电力建设, 2017, 38(6): 28-35. SHI Jiaqi, ZHANG Jianhua. Ultra short-term photovoltaic refined forecasting model based on deep learning［J］. Electric Power Construction, 2017, 38(6): 28-35. ［27］黎静华, 黄乾, 韦善阳, 等. 基于S-BGD和梯度累积策略的改进深度学习方法及其在光伏出力预测中的应用［J］. 电网技术, 2017, 41(10): 3292-3299. LI Jinghua, HUANG Qian, WEI Shanyang, et al. Improved deep learning algorithm based on S-BGD and gradient pile strategy and its application in PV power forecasting［J］. Power System Technology, 2017, 41(10): 3292-3299. ［28］KHODAYAR M, WANG J. Spatio-temporal graph deep neural network for short-term wind speed forecasting［J］. IEEE Transactions on Sustainable Energy, 2018, DOI 10.1109/TSTE.2018.2844102. ［29］CHEN J, ZENG G, ZHOU W, et al. Wind speed forecasting using nonlinear-learning ensemble of deep learning time series prediction and extremal optimization［J］. Energy Conversion and Management, 2018, 165: 681-695. ［30］WANG H Z, WANG G B, LI G Q, et al. Deep belief network based deterministic and probabilistic wind speed forecasting approach［J］. Applied Energy, 2016, 182: 80-93. ［31］雷正新, 韩蓓, 聂萌, 等. 配电网大数据环境下的多点负荷预测算法与应用研究［J］. 电力系统保护与控制, 2016, 44(23): 68-78. LEI Zhengxin, HAN Bei, NIE Meng, et al. Research and application of multi-node load forecasting algorithm under the environment of distribution network’s big data［J］. Power System Protection and Control, 2016, 44(23): 68-78. ［32］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. ［33］梁智, 孙国强, 李虎成, 等. 基于VMD与PSO优化深度信念网络的短期负荷预测［J］. 电网技术, 2018, 42(2): 598-606. LIANG Zhi, SUN Guoqiang, LI Hucheng, et al. Short-term load forecasting based on VMD and PSO optimized deep belief network［J］. Power System Technology, 2018, 42(2): 598-606. ［34］CHEN K, CHEN K, WANG Q, et al. Short-term load forecasting with deep residual networks［J］. IEEE Transactions on Smart Grid, 2018, DOI 10.1109/TSG.2018.2844307. ［35］DEDINEC A, FILIPOSKA S, DEDINEC A, et al. Deep belief network based electricity load forecasting: An analysis of Macedonian case［J］. Energy, 2016, 115: 1688-1700. ［36］QIU X, REN Y, SUGANTHAN P N, et al. Empirical mode decomposition based ensemble deep learning for load demand time series forecasting［J］. Applied Soft Computing, 2017, 54: 246-255. ［37］ZHANG B, XU X, XING H, et al. A deep learning based framework for power demand forecasting with deep belief networks［C］∥2017 18th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT). Taipei: IEEE Computer Society, 2017: 191-195. ［38］JARABEK T, LAURINEC P, LUCKA M. Energy load forecast using S2S deep neural networks with k-Shape clustering［C］∥2017 IEEE 14th International Scientific Conference on Informatics. Poprad: IEEE, 2017: 140-145. ［39］AMARASINGHE K, MARINO D L, MANIC M. Deep neural networks for energy load forecasting［C］∥2017 IEEE 26th International Symposium on Industrial Electronics (ISIE). Edinburgh: IEEE, 2017: 1483-1488. ［40］LI L, OTA K, DONG M. Everything is image: CNN-based short-term electrical load forecasting for smart grid［C］∥2017 14th International Symposium on Pervasive Systems, Algorithms and Networks & 2017 11th International Conference on Frontier of Computer Science and Technology & 2017 Third International Symposium of Creative Computing (ISPAN-FCST-ISCC). Exeter: IEEE Computer Society, 2017: 344-351. ［41］KONG W, DONG Z Y, JIA Y, et al. Short-term residential load forecasting based on LSTM recurrent neural network［J］. IEEE Transactions on Smart Grid, 2017, DOI 10.1109/TSG.2017.2753802. ［42］KONG W, DONG Z Y, HILL D J, et al. Short-term residential load forecasting based on resident behavior learning［J］. IEEE Transactions on Power Systems, 2018, 33(1): 1087-1088. ［43］SHI H, XU M, LI R. Deep learning for household load forecasting—A novel pooling deep RNN［J］. IEEE Transactions on Smart Grid, 2017, DOI 10.1109/TSG.2017.2686012. ［44］SHI H, XU M, MA Q, et al. A whole system assessment of novel deep learning approach on short-term load forecasting［J］. Energy Procedia, 2017, 142: 2791-2796. ［45］FU G. Deep belief network based ensemble approach for cooling load forecasting of air-conditioning system［J］. Energy, 2018, 148: 269-282. ［46］HONG T, FAN S. Probabilistic electric load forecasting: A tutorial review［J］. International Journal of Forecasting, 2016, 32: 914-938. ［47］WANG Y, ZHANG N, TAN Y, et al. Combining probabilistic load forecasts［J］. IEEE Transactions on Smart Grid, 2018, DOI 10.1109/TSG.2018.2833869. ［48］MA R, YU P, HUANG M. Spatial load forecasting based on unstructured information processing and multi-attribute deep learning［C］∥2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE). Galati: IEEE, 2017: 1-7.. ［49］LI H, CHIANG H D, YOSHIDA H, et al. The generation of ZIP-V curves for tracing power system steady state stationary behavior due to load and generation variations［C］∥1999 IEEE Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.99CH36364). Edmonton, Alta.: IEEE, 1999, 2: 647-651. ［50］BAONE C A, VEDA S, PAN Y, et al. Measurement based static load model identification［C］∥2015 IEEE Power & Energy Society General Meeting. Denver, CO: IEEE, 2015: 1-5. ［51］GU X, CANIZARES C A. Fast prediction of loadability margins using neural networks to approximate security boundaries of power systems［J］. IET Generation, Transmission & Distribution, 2008, 1(3): 466-475. ［52］ZHOU D Q, ANNAKKAGE U D, RAJAPAKSE A D. Online monitoring of voltage stability margin using an artificial neural network［J］. IEEE Transactions on Power Systems, 2010, 25(3): 1566-1574. ［53］ZHANG R, XU Y, DONG Z Y, et al. Voltage stability margin prediction by ensemble based extreme learning machine［C］∥2013 IEEE Power & Energy Society General Meeting. Vancouver, BC: IEEE, 2013: 1-5. ［54］DIAO R, SUN K, VITTAL V, et al. Decision tree-based online voltage security assessment using PMU measurements［J］. IEEE Transactions on Power Systems, 2009, 24(2): 832-839. ［55］ZHENG C, MALBASA V, KEZUNOVIC M. Regression tree for stability margin prediction using synchrophasor measurements［J］. IEEE Transactions on Power Systems, 2013, 28(2): 1978-1987. ［56］NEGNEVITSKY M, TOMIN N, KURBATSKY V, et al. A random forest-based approach for voltage security monitoring in a power system［C］∥2015 IEEE Eindhoven PowerTech. Eindhoven: IEEE, 2015: 1-6. ［57］ANZAI A H, SILVA L C P D, FREITAS W, et al. Real time voltage stability margin estimation using auto-regressive models and PMUs［C］∥2011 IEEE Power and Energy Society General Meeting. San Diego, CA: IEEE, 2011: 1-8. ［58］LEONARDI B, AJJARAPU V. Development of multilinear regression models for online voltage stability margin estimation［J］. IEEE Transactions on Power Systems, 2011, 26(1): 374-383. ［59］FAN Y, LIU S, QIN L, et al. A novel online estimation scheme for static voltage stability margin based on relationships exploration in a large data set［J］. IEEE Transactions on Power Systems, 2015, 30(3): 1380-1393. ［60］FAN Y, LI X, ZHANG P, et al. Real-time static voltage stability assessment in large-scale power systems based on maximum-relevance minimum-redundancy ensemble approach［J］. IEEE Access, 2017, 5: 27281-27291. ［61］MALBASA V, ZHENG C, CHEN P C, et al. Voltage stability prediction using active machine learning［J］. IEEE Transactions on Smart Grid, 2017, 8(6): 3117-3124. ［62］LI S, AJJARAPU V, DJUKANOVIC M. Adaptive online monitoring of voltage stability margin via local regression［J］. IEEE Transactions on Power Systems, 2018, 33(1): 701-713. ［63］LI S, AJJARAPU V. Real-time monitoring of long-term voltage stability via convolutional neural network［C］∥2017 IEEE Power & Energy Society General Meeting. Chicago, IL: IEEE, 2017: 1-5. ［64］ETTEHADI M, GHASEMI H, VAEZ-ZADEH S. Voltage stability-based DG placement in distribution networks［J］. IEEE Transactions on Power Delivery, 2013, 28(1): 171-178. ［65］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. XUE Yusheng, LAI Yening. Integration of macro energy thinking and big data thinking part two applications and explorations［J］. Automation of Electric Power Systems, 2016, 40(8): 1-13. ［66］LAGARDE C M D, LANTZ F. How renewable production depresses electricity prices: Evidence from the German market［J］. Energy Policy, 2018, 117: 263-277. ［67］王万良, 李卓蓉. 生成式对抗网络研究进展［J］. 通信学报, 2018, 39(2): 135-148. WANG Wanliang, LI Zhuorong. Advances in generative adversarial network［J］. Journal on Communications, 2018, 39(2): 135-148. ［68］李鹏. 基于高斯混合模型的变分自动编码器［D］. 哈尔滨: 哈尔滨工业大学, 2017. LI Peng. Variational auto-encoders based on Gaussian mixture model［D］. Harbin: Harbin Institute of Technology, 2017. ［69］张营营. 生成对抗网络模型综述［J］. 电子设计工程, 2018, 26(5): 34-37. ZHANG Yingying. A survey on generative adversarial networks［J］. Electronic Design Engineering, 2018, 26(5): 34-37. ［70］徐一峰. 生成对抗网络理论模型和应用综述［J］. 金华职业技术学院学报, 2017, 17(3): 81-88. XU Yifeng. The review of generative adversarial network’s theory models and applications［J］. Journal of Jinhua Polytechnic, 2017, 17(3): 81-88. ［71］CHEN Y, WANG Y, KIRSCHE D S, et al. Model-free renewable scenario generation using generative adversarial networks［J］. IEEE Transactions on Power Systems, 2018, 33(3): 3265-3275. ［72］CHEN Y, LI P, ZHANG B. Bayesian renewables scenario generation via deep generative networks［C］∥2018 52nd Annual Conference on Information Sciences and Systems (CISS). Princeton, NJ: IEEE, 2018: 1-6. ［73］王守相, 陈海文, 李小平, 等. 风电和光伏随机场景生成的条件变分自动编码器方法［J］. 电网技术, 2018, 42(6): 1860-1867. WANG Shouxiang, CHEN Haiwen, LI Xiaoping, et al. Conditional variational automatic encoder method for stochastic scenario generation of wind power and photovoltaic system［J］. Power System Technology, 2018, 42(6): 1860-1867. ［74］WAN Z, ZHANG Y, HE H. Variational autoenco-der based synthetic data generation for imbalanced learning［C］∥2017 IEEE Symposium Series on Computational Intelligence (SSCI). Honolulu, HI: IEEE, 2017: 1-7. ［75］ALZANTOT M, CHAKRABORTY S, SRIVASTAVA M. SenseGen: A deep learning architecture for synthetic sensor data generation［C］∥2017 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). Kona, HI: IEEE, 2017: 188-193. ［76］XU Y, SHI L, NI Y. Deep-learning-based scenario generation strategy considering correlation between multiple wind farms［J］. The Journal of Engineering, 2017, 2017(13): 2207-2210. ［77］SONG Q, GUO Y, SHEPPERD M. A comprehensive investigation of the role of imbalanced learning for software defect prediction［J］. IEEE Transactions on Software Engineering, 2018, DOI 10.1109/TSE.2018.2836442. ［78］HE H, GARCIA E A. Learning from imbalanced data［J］. IEEE Transactions on Knowledge & Data Engineering, 2009, 21(9): 1263-1284. ［79］HU Z, JIANG P. An imbalance modified deep neural network with dynamical incremental learning for chemical fault diagnosis［J］. IEEE Transactions on Industrial Electronics, 2018, DOI 10.1109/TIE.2018.2798633. ［80］YU L, ZHOU R, TANG L, et al. A DBN-based resampling SVM ensemble learning paradigm for credit classification with imbalanced data［J］. Applied Soft Computing, 2018, 69: 192-202. ［81］XENOPOULOS P. Introducing DeepBalance: Random deep belief network ensembles to address class imbalance［C］∥2017 IEEE International Conference on Big Data (Big Data). Boston, MA: IEEE, 2017: 3684-3689. ［82］KHAN S H, HAYAT M, BENNAMOUN M, et al. Cost-sensitive learning of deep feature representations from imbalanced data［J］. IEEE Transactions on Neural Networks & Learning Systems, 2018, 29(8): 3573-3587. ［83］WANG S, LIU W, WU J, et al. Training deep neural networks on imbalanced data sets［C］∥2016 International Joint Conference on Neural Networks (IJCNN). Vancouver, BC: IEEE, 2016: 4368-4374. ［84］LANGKVIST M, KARLSSON L, LOUTFI A. A review of unsupervised feature learning and deep learning for time-series modeling［J］. Pattern Recognition Letters, 2014, 42: 11-24. ［85］ZHONG G, WANG L N, LING X, et al. An overview on data representation learning: from traditional feature learning to recent deep learning［J］. Journal of Finance & Data Science, 2016, 2: 265-278. ［86］BENGIO Y, COURVILLE A, VINCENT P. Representation learning: a review and new perspectives［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35(8): 1798-1828. ［87］HE W. Load forecasting via deep neural networks［J］. Procedia Computer Science, 2017, 122: 308-314. ［88］WANG Y, CHEN Q, GAN D, et al. Deep learning-based socio-demographic information identification from smart meter data［J］. IEEE Transactions on Smart Grid, 2018, DOI 10.1109/TSG.2018.2805723. ［89］CLAESSENS B J, VRANCX P, RUELENS F. Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control［J］. IEEE Transactions on Smart Grid, 2018, 9(4): 3259-3269. ［90］YIN Z, WAN B, YUAN F, et al. A deep normalization and convolutional neural network for image smoke detection［J］. IEEE Access, 2017, 5: 18429-18438. ［91］WANG Z, REN J, ZHANG D, et al. A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos［J］. Neurocomputing, 2018, 287: 68-83. ［92］TONG C, LI J, LANG C, et al. An efficient deep model for day-ahead electricity load forecasting with stacked denoising auto-encoders［J］. Journal of Parallel & Distributed Computing, 2018, 117: 267-273. ［93］RUELENS F, CLAESSENS B, QUAIYUM S, et al. Reinforcement learning applied to an electric water heater: From theory to practice［J］. IEEE Transactions on Smart Grid, 2018, 9(4): 3792-3800. ［94］李智, 侯兴哲, 刘永相, 等. 基于深度学习的充电站容量规划方法［J］. 电力系统保护与控制, 2017, 45(21): 67-73. LI Zhi, HOU Xingzhe, LIU Yongxiang, et al. A capacity planning method of charging station based on depth learning［J］. Power System Protection and Control, 2017, 45(21): 67-73. ［95］WANG H, RUAN J, WANG G, et al. Deep learning based interval state estimation of AC smart grids against sparse cyber attacks［J］. IEEE Transactions on Industrial Informatics, 2018. ［96］CHEN K, HU J, HE J. Detection and classification of transmission line faults based on unsupervised feature learning and convolutional sparse autoencoder［J］. IEEE Transactions on Smart Grid, 2018, 9(3): 1748-1758. ［97］JIANG G, HE H, XIE P, et al. Stacked multilevel-denoising autoencoders: A new representation learning approach for wind turbine gearbox fault diagnosis［J］. IEEE Transactions on Instrumentation & Measurement, 2017, 66(9): 2391-2402. ［98］TANG S, SHEN C, WANG D, et al. Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis［J］. Neurocomputing, 2018, 305: 1-14. ［99］ZHANG Y, LI X, GAO L, et al. A new subset based deep feature learning method for intelligent fault diagnosis of bearing［J］. Expert Systems with Applications, 2018, 110: 125-142. ［100］SHI H, LI H, ZHANG D, et al. An efficient feature generation approach based on deep learning and feature selection techniques for traffic classification［J］. Computer Networks, 2018, 132: 81-98. ［101］FARIAS G, DORMIDO-CANTO S, VEGA J, et al. Automatic feature extraction in large fusion databases by using deep learning approach［J］. Fusion Engineering & Design, 2016, 112: 979-983. ［102］FENG C, CUI M, HODGE B M, et al. A data-driven multi-model methodology with deep feature selection for short-term wind forecasting［J］. Applied Energy, 2017, 190: 1245-1257. ［103］ZHANG Q, YANG L T, CHEN Z, et al. A survey on deep learning for big data［J］. Information Fusion, 2018, 42: 146-157. ［104］张娜. 基于深层堆叠网络的脑电信号特征提取及识别［D］. 重庆: 重庆邮电大学, 2017. ZHANG Na. EEG feature extraction and recognition based on deep stacking network［D］. Chongqing: Chongqing University of Posts and Telecommunications, 2017. ［105］DEAN J, CORRADO G, MONGA R, et al. Large scale distributed deep networks［J］. Proceedings of Advances in Neural Information Processing Systems, MIT, 2012: 1223-1231. ［106］NGIAM J, KHOSLA A, KIM M, et al. Multimodal deep learning［C］∥Proceedings of the 28th International Conference on Machine Learning. Bellevue, Washington, USA: ACM, 2011: 689-696. ［107］熊宇, 张一飞, 冯时, 等. 基于多模态特征深度融合的微博流事件检测与跟踪［J］. 控制与决策, 2018. XIONG Yu, ZHANG Yifei, FENG Shi, et al. Event detection and tracking in microblog stream based on multimodal feature deep fusion［J］. Control and Decision, 2018. ［108］孙宇. 针对含有概念漂移问题的增量学习算法研究［D］. 合肥: 中国科学技术大学, 2017. SUN Yu. Incremental learning algorithms with concept drift adaptation［D］. Hefei: University of Science and Technology of China, 2017. ［109］FU L M, HUANG H, PRINCIPE J C. Incremental backpropagation learning networks［J］. IEEE Transactions on Neural Networks, 1996, 7(3): 757-761. ［110］VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and composing robust features with denoising autoencoders［C］∥Proceedings of the 25th International Conference on Machine Learning. New York, USA: ACM, 2008: 1096-1103. ［111］卜范玉, 陈志奎, 张清辰. 基于深度学习的不完整大数据填充算法［J］. 微电子学与计算机, 2014, 31(12): 173-176. BU Fanyu, CHEN Zhigui, ZHANG Qingchen. Incomplete big data imputation algorithm based on deep learning［J］. Microelectronics & Computer, 2014, 31(12): 173-176. ［112］WANG R, TAO D. Non-local auto-encoder with collaborative stabilization for image restoration［J］. IEEE Transactions on Image Processing, 2016, 25(5): 2117-2129. ［113］PEARL J. Theoretical impediments to machine learning with seven sparks from the causal revolution［R］. Cornell University, 2018. ［114］BATTAGLIA P W, HAMRICK J B, BAPST V, et al. Relational inductive biases, deep learning, and graph networks［R］. Cornell University, 2018.