Please wait a minute...
发电技术  2018, Vol. 39 Issue (3): 204-212    DOI: 10.12096/j.2096-4528.pgt.2018.031
能源互联网 本期目录 | 过刊浏览 |
人工智能在电力系统中应用的近期研究热点介绍
朱永利1(),石鑫2,*(),王刘旺3
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 上海交通大学大数据工程技术研究中心, 上海市 闵行区 200240
3 国网浙江省电力有限公司电力科学研究院, 浙江省 杭州市 310014
Recent Research Hotspot Introduction on the Application of Artificial Intelligence in Power System
Yongli ZHU1(),Xin SHI2,*(),Liuwang WANG3
1 State Key Laboratory of Alternate Electrical Power Systems with Renewable Energy Sources(North China Electric Power University), Baoding 071003, Hebei Provicne, China
2 Research Center for Big Data Engineering Technology, Shanghai Jiao Tong University, Minhang District, Shanghai 200240, China
3 State Grid Zhejiang Electric Power Company Electric Power Research Institute, Hangzhou 310014, Zhejiang Province, China
全文: HTML    PDF(284 KB)  
输出: BibTeX | EndNote (RIS)      
摘要: 

大数据驱动下的新一代人工智能由传统知识表示转向深度、自主知识学习,不再需要人的过多干预,展现出了更加智能的一面。近年来,深度学习成为人工智能研究热点。该文重点介绍了深度学习的特点、原理及其在电力系统中的应用研究现状,分析了新一代智能方法研究趋势及在应用过程中存在的问题,并提供了基于分布式机器学习和增量学习的解决方法,旨在为相关研究工作者提供参考。

关键词 电力系统人工智能深度学习大数据    
Abstract

The new generation of artificial intelligence driven by big data has shifted from traditional knowledge representation to deep and autonomous learning. It no longer requires too much human intervention and shows a smarter side. In recent years, deep learning (DL) has become the hotspot of artificial intelligence. This paper focuses on the characteristics, principles and the current application status of DL in the power system. It also analyzes the research trends and problems in the application process of the new generation artificial intelligence, and provides solutions based on distributed machine learning and incremental learning methods. This paper is written for providing references for researchers involved in the field.

Key wordspower system    artificial intelligence    deep learning    big data
收稿日期: 2018-03-12      出版日期: 2018-07-27
基金资助:国家自然科学基金项目(51677072)
通讯作者: 石鑫     E-mail: yonglipw@163.com;dugushixin@sjtu.edu.cn
Corresponding author: Xin SHI     E-mail: yonglipw@163.com;dugushixin@sjtu.edu.cn
作者简介: 朱永利(1963),男,教授,博士生导师,研究方向为网络化监控与智能信息处理、电力设备监测大数据处理, yonglipw@163.com|王刘旺(1988),男,博士,从事云计算、大数据及人工智能技术在电力系统的应用
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
朱永利
石鑫
王刘旺
引用本文:

朱永利,石鑫,王刘旺. 人工智能在电力系统中应用的近期研究热点介绍[J]. 发电技术, 2018, 39(3): 204-212.
Yongli ZHU,Xin SHI,Liuwang WANG. Recent Research Hotspot Introduction on the Application of Artificial Intelligence in Power System. Power Generation Technology, 2018, 39(3): 204-212.

链接本文:

http://www.pgtjournal.com/CN/10.12096/j.2096-4528.pgt.2018.031      或      http://www.pgtjournal.com/CN/Y2018/V39/I3/204

图1  受限玻尔兹曼机网络结构
图2  自动编码器网络结构
图3  卷积神经网络结构
图4  RNN网络结构示意图
图5  增强学习原理图
图6  深度混合网络结构示意图
图7  模型并行与数据并行
图8  电力设备在线并行故障诊断拓扑
1 LeCun Y , Bengio Y , Hinton G . Deep learning[J]. Nature, 2015, 521 (7553): 436.
doi: 10.1038/nature14539
2 Serre T , Kreiman G , Kouh M , et al. A quantitative theory of immediate visual recognition[J]. Progress in Brain Research, 2007, 165, 33- 56.
doi: 10.1016/S0079-6123(06)65004-8
3 Hinton G E , Osindero S , Teh Y W . A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18 (7): 1527- 1554.
doi: 10.1162/neco.2006.18.7.1527
4 Hinton G E , Salakhutdinov R R . Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313 (5786): 504- 507.
doi: 10.1126/science.1127647
5 LeCun Y , Boser B , Denker J S , et al. Backpropagation applied to handwritten zip code recognition[J]. Neural computation, 1989, 1 (4): 541- 551.
doi: 10.1162/neco.1989.1.4.541
6 Graves A, Mohamed A R, Hinton G. Speech recognition with deep recurrent neural networks[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, Canada, 2013: 6645-6649.
7 Sutskever I , Vinyals O , Le Q V . Sequence to sequence learning with neural networks[J]. 2014, (4): 3104- 3112.
8 Graves A. Generating sequences with recurrent neural networks[J]. arXiv preprint arXiv: 1308. 0850, 2013.
9 石鑫, 朱永利, 萨初日拉, 等. 基于深度信念网络的电力变压器故障分类建模[J]. 电力系统保护与控制, 2016, 44 (1): 71- 76.
doi: 10.7667/j.issn.1674-3415.2016.01.010
10 代杰杰, 宋辉, 杨祎, 等. 基于深度信念网络的变压器油中溶解气体浓度预测方法[J]. 电网技术, 2017, 41 (8): 2737- 2742.
11 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.
doi: 10.1016/j.apenergy.2016.08.108
12 Goodfellow I , Bengio Y , Courville A , et al. Deep learning[M]. Cambridge: MIT Press, 2016: 300- 320.
13 石鑫, 朱永利, 宁晓光, 等. 基于深度自编码网络的电力变压器故障诊断[J]. 电力自动化设备, 2016, 36 (5): 122- 126.
14 代杰杰, 宋辉, 杨祎, 等. 基于栈式降噪自编码器的输变电设备状态数据清洗方法[J]. 电力系统自动化, 2017, 41 (12): 224- 230.
doi: 10.7500/AEPS20161201003
15 刘辉海, 赵星宇, 赵洪山, 等. 基于深度自编码网络模型的风电机组齿轮箱故障检测[J]. 电工技术学报, 2017, 32 (17): 156- 163.
16 Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. Nevada, USA, 2012: 1097-1105.
17 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[C]//International conference on learning representations. San Diego, USA, 2014.
18 Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recogintion, Boston, USA, 2015.
19 Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 580-587.
20 Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems, Montreal, Canada, 2015: 91-99.
21 李军锋, 王钦若, 李敏. 结合深度学习和随机森林的电力设备图像识别[J]. 高电压技术, 2017, (11): 3705- 3711.
22 王万国, 田兵, 刘越, 等. 基于RCNN的无人机巡检图像电力小部件识别研究[J]. 地球信息科学学报, 2017, 19 (2): 256- 263.
23 魏东, 龚庆武, 来文青, 等. 基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J]. 中国电机工程学报, 2016, 36 (S1): 21- 28.
24 Hochreiter S , Schmidhuber J . Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780.
doi: 10.1162/neco.1997.9.8.1735
25 Graves A, Jaitly N, Mohamed A R. Hybrid speech recognition with deep bidirectional LSTM[C]//Automatic Speech Recognition and Understanding. IEEE, Olomouc, Czech Republic, 2014: 273-278.
26 Gensler A, Henze J, Sick B, et al. Deep learning for solar power forecasting-an approach using AutoEncoder and LSTM neural networks[C]//Systems, Man, and Cybernetics (SMC), 2016 IEEE International Conference. on IEEE, Budapest, Magyarország, 2016: 002858-002865.
27 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, (12): 3797- 3802.
28 Mnih V, Kavukcuoglu K, Silver D, et al. Playing atari with deep reinforcement learning[J]. arXiv preprint arXiv: 1312(5602), 2013.
29 Silver D , Huang A , Maddison C J , et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529 (7587): 484- 489.
doi: 10.1038/nature16961
30 王继业.人工智能在能源电力领域的探索[R].北京:中国电科院, 2017.
31 肖亮,戴灿煌,肖星宇,等.基于深度强化学习的微电网电能交易方法: CN107067190A[P]. 2017-08-18.
32 Vincent P, Larochelle H, Bengio Y, et al. Extracting and composing robust features with denoising autoencoders[C]//International Conference on Machine Learning. ACM, Maryland, USA, 2008: 1096-1103.
33 Cho K H, Raiko T, Ilin A. Gaussian-Bernoulli deep Boltzmann machine[C]//International Joint Conference on Neural Networks. IEEE, Beijing, China, 2014: 1-7.
34 何子襄.深度混合网络研究及其在变压器故障诊断中的应用[D].保定:华北电力大学, 2018.
35 石祥滨, 房雪键, 张德园, 郭忠强. 基于深度学习混合模型迁移学习的图像分类[J]. 系统仿真学报, 2016, 28 (1): 167- 173, 182.
36 罗文慧, 董宝田, 王泽胜. 基于CNN-SVR混合深度学习模型的短时交通流预测[J]. 交通运输系统工程与信息, 2017, 17 (5): 68- 74.
37 赵俊华, 董朝阳, 文福拴, 等. 面向能源系统的数据科学:理论、技术与展望[J]. 电力系统自动化, 2017, 41 (4): 1- 11.
38 Hutchinson B , Deng L , Yu D . Tensor Deep Stacking Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35 (8): 1944- 1957.
39 Raina R, Madhavan A, Ng A Y. Large-scale deep unsupervised learning using graphics processors[C]//International Conference on Machine Learning. ACM, California, USA, 2009: 873-880.
40 Dean J, Corrado G S, Monga R, et al. Large scale distributed deep networks[C]//International Conference on Neural Information Processing Systems. Curran Associates Inc. 2012: 1223-1231.
41 Li M, Andersen D G, Park J W, et al. Scaling distributed machine learning with the parameter server[C]//In Proceedings of the 11th USENIX conference on Operating Systems Design and Implementation (OSDI'14). USENIX Association, Berkeley, CA, USA, 583-598.
42 Meng X , Bradley J , Yavuz B , et al. MLlib:machine learning in apache spark[J]. Journal of Machine Learning Research, 2015, 17 (1): 1235- 1241.
43 Abadi M, Barham P, Chen J, et al. TensorFlow: a system for large-scale machine learning[C]//In Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation (OSDI'16). USENIX Association, Berkeley, CA, USA, 265-283.
44 王保义, 赵硕, 张少敏. 基于云计算和极限学习机的分布式电力负荷预测算法[J]. 电网技术, 2014, 38 (2): 526- 531.
45 王德文, 孙志伟. 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015, 35 (3): 527- 537.
46 王保义, 王冬阳, 张少敏. 基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J]. 电力自动化设备, 2016, 36 (1): 117- 122.
47 张少敏, 毛冬, 王保义. 大数据处理技术在风电机组齿轮箱故障诊断与预警中的应用[J]. 电力系统自动化, 2016, 40 (14): 129- 134.
doi: 10.7500/AEPS20160316013
48 王德文, 刘晓建. 基于MapReduce的电力设备并行故障诊断方法[J]. 电力自动化设备, 2014, 34 (10): 116- 120.
doi: 10.3969/j.issn.1006-6047.2014.10.019
49 王刘旺, 朱永利, 贾亚飞, 等. 局部放电大数据的并行PRPD分析与模式识别[J]. 中国电机工程学报, 2016, 36 (5): 1236- 1244.
50 朱永利,王刘旺.并行EEMD算法及其在局部放电信号特征提取中的应用[J/OL].电工技术学报, http://kns.cnki.net/kcms/detail/11.2188.TM.20171220.1103.003.html.
51 王德文, 杨力平. 智能电网大数据流式处理方法与状态监测异常检测[J]. 电力系统自动化, 2016, 40 (14): 122- 128.
doi: 10.7500/AEPS20150828001
52 屈志坚, 王冬. 面向智能调度监测的流计算并行滑动窗口技术[J]. 电网技术, 2016, 40 (7): 2219- 2226.
53 王桂兰, 周国亮, 赵洪山, 等. 大规模用电数据流的快速聚类和异常检测技术[J]. 电力系统自动化, 2016, 40 (24): 27- 33.
doi: 10.7500/AEPS20160123002
54 王刘旺.基于云计算的电力设备监测数据的集中并行处理与诊断[D].北京:华北电力大学, 2017.
[1] 周博文,陈麒宇,杨东升. 巴西大停电的思考[J]. 发电技术, 2018, 39(2): 97-105.
[2] 朱永利,尹金良. 人工智能在电力系统中的应用研究与实践综述[J]. 发电技术, 2018, 39(2): 106-111.
[3] 李本新,韩学山,蒋哲,李文博. 计及网损的快速经济调度方法[J]. 发电技术, 2018, 39(1): 90-95.