基于预测模型的发电厂异常数据辨识方法
作者:
基金项目:

国家自然科学基金资助项目(51577030)


Abnormal data analysis method of power plant data based on forecast model
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [22]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    发电统计数据是我国实施电力监管的重要依据,其中的发电厂用电率作为反映电厂生产效能、论证节能降耗情况的关键指标,验证其上报数据的真实性和准确性十分重要。为此,提出一种基于预测模型的发电厂异常数据辨识方法。该方法首先利用Adaboost改进非线性有源自回归模型(NARX)神经网络构建发电厂用电率预测模型,通过不断引入上报值以动态的方式对当前时刻发电厂用电率进行预测。当发电厂用电率时间序列出现突变时,残差时间序列会出现明显的增大或减小,进而利用孤立森林算法得到各残差向量组的异常分值从而辨识出异常点。最后,利用该方法对注入了虚假数据的实际发电数据进行辨识,验证了所提方法的有效性。

    Abstract:

    As an important index reflecting the production efficiency and energy saving of power plants, the authenticity and accuracy of the reported data of power plant power consumption rate are very important. Therefore, a method of abnormal data identification based on predictive model is proposed. Firstly, the NARX neural network is improved by Adaboost to build the forecasting model of the power consumption rate. Then, the present power consumption rate is forecasted in a dynamic way by continuously introducing the reported value. When the time series of the power consumption rate suddenly changes, the residual time series obviously increase or decrease. Then the outliers of each residual vector group are obtained by using the isolation forest algorithm. Finally, the method is used to identify the actual generation data injected with false data, and the effectiveness of the proposed method is verified.

    参考文献
    [1] 国家能源局综合司. 国家能源局综合司关于进一步做好电力监管统计信息报送工作的通知:国能局发[2017] 90号[A/OL].(2017-10-18)[2019-10-30].http://fjb.nea.gov.cn/news_view.aspx?id=28398. National Energy Administration. Notice of the National Energy Administration on further improving the reporting of statistical information on electricity regulation:National Energy Administration issued No.90[A/OL].(2017-10-18)[2019-10-30]. http://fjb.nea.gov.cn/news_view.aspx?id=28398.
    [2] 邢希东. 600 MW火电机组降低厂用电率措施[J]. 中国电力, 2007(9):60-64. XING Xidong. Countermeasures to reduce the auxiliary power consumption rate of 600 MW thermal power units[J]. Electric Power, 2007(9):60-64.
    [3] 陈波, 刘厚泉, 赵志凯. 时间序列多尺度异常检测方法[J]. 计算机工程与应用, 2018, 54(20):122-127. CHEN Bo, LIU Houquan, ZHAO Zhikai. Method of multi-scale anomaly detection in time series[J]. Computer Engineering and Applications, 2018, 54(20):122-127.
    [4] LAURA B, KAUSLER B X, MARTIN S, et al. Time series ano-maly detection based on shapelet learning[J]. Computational Statistics, 2018.
    [5] CHEN Y T, QIAN J, SALIGRAMA V. A new one-class SVM for anomaly detection[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. 2013:3567-3571.
    [6] 刘亚丽, 孟令愚, 丁云峰. 电网工控系统流量异常检测的应用与算法改进[J]. 计算机系统应用, 2018, 27(3):173-178. LIU Yali, MENG Lingyu, DING Yunfeng. Application and algorithm improvement of abnormal traffic detection in smart grid industrial control system[J]. Computer System & Applications, 2018, 27(3):173-178.
    [7] 李鑫, 孟亨, 杨桢, 等. 基于BP神经网络递推积分PI-重复控制在微电网APF中的研究[J]. 电力系统保护与控制, 2019, 47(6):132-140. LI Xin, MENG Heng, YANG Zhen, et al. Research on recursive integral PI-repetitive control based on BP neural network in micro-grid APF[J]. Power System Protection and Control, 2019, 47(6):132-140.
    [8] 杨光. 基于神经网络的异常用电检测算法模型研究[J]. 供用电, 2016, 33(10):56-59. YANG Guang. Research and analysis on the algorithm model of anomaly detection based on neural network[J]. Power Utilization, 2016, 33(10):56-59.
    [9] 林峻, 严英杰, 盛戈皞, 等. 考虑时间序列关联的变压器在线监测数据清洗[J]. 电网技术, 2017, 41(11):3733-3740. LIN Jun, YAN Yingjie, SHENG Gehao, et al. Online monitoring data cleaning of transformer considering time series correlation[J]. Power System Technology, 2017, 41(11):3733-3740.
    [10] FENG Huo. NARX-network based wind speed estimation for wind turbines[C]//Proceedings of 2016 International Conference on Power, Energy Engineering and Management. 2016:5.
    [11] 付青, 单英浩, 朱昌亚. 基于NARX神经网络的光伏发电功率预测研究[J]. 电气传动, 2016, 46(4):42-45. FU Qing, SHAN Yinghao, ZHU Changya. Generated power forecasting for photovoltaic system based on NARX neural network[J]. Electric Drive, 2016, 46(4):42-45.
    [12] 胡倩, 陈红坤, 孙志达. 风电场短期风速的集成学习预测模型[J]. 电力系统及其自动化学报, 2016, 28(1):1-4. HU Qian, CHEN Hongkun, SUN Zhida. An ensemble learning predictive model for short-term wind speed forecasting[J]. Proceedings of the CSU-EPSA, 2016, 28(1):1-4.
    [13] 芦婧, 曾明. 短期风速的Adaboost_GRNN组合预测模型[J]. 电力系统及其自动化学报, 2019, 31(4):70-76. LU Jing, ZENG Ming. Adaboost_GRNN combination forecasting model for short-term wind speed [J]. Proceedings of the CSU-EPSA, 2019, 31(4):70-76.
    [14] 谭津, 邓长虹, 杨威, 等. 微电网光伏发电的Adaboost天气聚类超短期预测方法[J]. 电力系统自动化, 2017, 41(21):33-39. TAN Jin, DENG Changhong, YANG Wei, et al. Ultra-short-term photovoltaic power forecasting in microgrid based on Adaboost clustering[J]. Automation of Electric Power Systems, 2017, 41(21):33-39.
    [15] 吴俊利, 张步涵, 王魁. 基于Adaboost的BP神经网络改进算法在短期风速预测中的应用[J]. 电网技术, 2012, 36(9):221-225. WU Junli, ZHANG Buhan, WANG Kui. Application of Adaboost-based BP neural network for short-term wind speed forecast[J]. Power System Technology, 2012, 36(9):221-225.
    [16] 李新鹏, 高欣, 阎博, 等. 基于孤立森林算法的电力调度流数据异常检测方法[J]. 电网技术, 2019, 43(4):1447-1456. LI Xinpeng, GAO Xin, YAN Bo, et al. An approach of data anomaly detection in power dispatching streaming data based on isolation forest algorithm[J]. Power System Technology, 2019, 43(4):1447-1456.
    [17] 刘佳翰, 陈克绪, 马建, 等. 基于卷积神经网络和随机森林的三相电压暂降分类[J]. 电力系统保护与控制, 2019, 47(20):112-118. LIU Jiahan, CHEN Kexu, MA Jian, et al. Classification of three-phase voltage dips based on CNN and random forest[J]. Power System Protection and Control, 2019, 47(20):112-118.
    [18] 王继业, 朱欣焰, 赵光, 等. 基于深度人工神经网络和GIS数据的最优停电模型研究[J]. 电力系统保护与控制, 2019, 47(16):58-63. WANG Jiye, ZHU Xinyan, ZHAO Guang, et al. Research on optimal outage model based on deep artificial neural network and GIS data[J]. Power System Protection and Control, 2019, 47(16):58-63.
    [19] LIU F T, KAI M T, ZHOU Z H. Isolation-based anomaly detection[J]. ACM Transactions on Knowledge Discovery from Data, 2012, 6(1):1-39.
    [20] 贾育康, 赵力芬. 300 MW火电机组厂用电分析及节电措施[J]. 山西电力, 2009(2):49-51. JIA Yukang, ZHAO Lifen. Analysis of service power and electricity saving measures of 300 MW thermal power unit[J]. Shanxi Electric Power, 2009(2):49-51.
    [21] 田野, 张程, 毛昕儒, 等. 运用PCA改进BP神经网络的用电异常行为检测[J]. 重庆理工大学学报(自然科学版), 2017, 31(8):125-133. TIAN Ye, ZHANG Cheng, MAO Xinru, et al. Research on abnormal behavior of power consumption based in BP neural network with PCA[J]. Journal of Chongqing University of Technology(Natural Science), 2017, 31(8):125-133.
    [22] 李磊, 严正, 冯冬涵, 等. 结合主成分分析及生产函数的电网智能技术评价探讨[J]. 电力系统自动化, 2014, 38(11):56-61. LI Lei, YAN Zheng, FENG Donghan, et al. Discussion on intelligent technology evaluation of electrical power grid based on principal component analysis and production function[J]. Automation of Electric Power Systems, 2014, 38(11):56-61.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

高骞,张浩天,汤奕.基于预测模型的发电厂异常数据辨识方法[J].电力工程技术,2020,39(4):164-170

复制
分享
文章指标
  • 点击次数:1168
  • 下载次数: 2401
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2020-02-25
  • 最后修改日期:2020-03-19
  • 录用日期:2019-11-25
  • 在线发布日期: 2020-08-03
  • 出版日期: 2020-07-28
文章二维码