Abstract
Phasor Measurement Units (PMU) are capable to generate multi-dimensional time series data, which is one of the most important parts for monitoring power system operation. However, various internal and external factors frequently cause the system to generate anomalous data randomly, so we expect to clean and re-fill the raw PMU data with anomalies to provide support for further advanced applications such as situational awareness, early warning, and dispatch control of the system. Existing methods mostly use classical mathematics and traditional machine learning to analyze PMU data, which makes it difficult to identify the pattern changes of the data under multiple operating conditions in power systems. In this paper, we propose a hybrid model named IRFLMDNN, which consists of an improved CART random forest model and a dynamic neural network optimized by the Levenberg Marquardt algorithm for PMU data anomaly detection and adaptive data re-filling, respectively. Experimental results based on the IEEE 39-node 10-machine New England Power System show that the proposed method has accurate and robust anomaly detection and data refilling performance.
Similar content being viewed by others
Data availability
Data sharing not applicable to this article as no datasets were generated or analyzed during the current study.
References
Phadke AG, Thorp JS (2008) Synchronized phasor measurements and their applications. Springer, New York, p 81
Phadke AG, Bi T (2018) Phasor measurement units, WAMS, and their applications in protection and control of power systems. J Mod Power Syst Clean Energy 6(4):619–629
Duan G, Yan Y, Xie X, Tao H, Yang D, Li J (2015) Development status quo and tendency of wide area phasor measuring technology. Autom Electr Power Syst 39(1):73–80 (in Chinese)
Xu F, Xue A, Chang N, Kong H, Xu J (2021) Research status and prospects of detection, correction and recovery for abnormal synchrophasor data in power system. Proc CSEE 41(20):6869–6886 (in Chinese)
Zhang Q, Vittal V, Heydt GT, Logic N, Sturgill S (2011) The integrated calibration of synchronized phasor measurement data in power transmission systems. IEEE Trans Power Delivery 26(4):2573–2581
Huang C, Li F, Zhou D, Guo J, Pan Z, Liu Y, Liu Y (2016) Data quality issues for synchrophasor applications part I: a review. J Modern Power Syst Clean Energy 4(3):342–352
Zhang Q, Vittal V, Heydt G, Chakhchoukh Y, Logic N, Sturgill S (2012) The time skew problem in PMU measurements. In: 2012 IEEE Power and energy society general meeting (pp. 1–6). IEEE
Shepard DP, Humphreys TE, Fansler AA (2012) Evaluation of the vulnerability of phasor measurement units to GPS spoofing attacks. Int J Crit Infrastruct Prot 5(3–4):146–153
Zhou M, Wang Y, Srivastava AK, Wu Y, Banerjee P (2018) Ensemble-based algorithm for synchrophasor data anomaly detection. IEEE Trans Smart Grid 10(3):2979–2988
Cai J Fan J (2022) Perturbation learning based anomaly detection. In: The 36th conference on neural information processing systems (pp: 1–18). NeurIPS
Fan J, Chow TW, Qin SJ (2022) Kernel-based statistical process monitoring and fault detection in the presence of missing data. IEEE Trans Ind Inf 18(7):4477–4487
Marquardt DW (1963) An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math 11(2):431–441
Wang X, Shi D, Wang Z, Xu C, Zhang Q, Zhang X, Yu Z (2017) Online calibration of phasor measurement unit using density-based spatial clustering. IEEE Trans Power Deliv 33(3):1081–1090
Lu X, Shi D, Zhu B, Wang Z, Luo J, Su D, Xu C (2017) PMU assisted power system parameter calibration at Jiangsu electric power company. In: 2017 IEEE Power & Energy Society General Meeting (pp. 1–5). IEEE
Kong H, Xue A, Xu F, Leng S (2019) A novel detection method for abnormal PMU amplitude data obtained in both ends of transmission line. In: 2019 IEEE sustainable power and energy conference (iSPEC) (pp. 2916–2921). IEEE
Wan C, Chen H, Guo M, Liang Z (2016) Wrong data identification and correction for WAMS. In: 2016 IEEE PES Asia-pacific power and energy engineering conference (APPEEC) (pp. 1903–1907). IEEE
Wu M, Xie L (2016) Online detection of low-quality synchrophasor measurements: a data-driven approach. IEEE Trans Power Syst 32(4):2817–2827
Chen Y, Chen W, Yao W, Liao S, Miao S (2016) Rapid identification and recovery of wrong WAMS data. Electr Power Autom Equip 36(12):95–101 (in Chinese)
Vanfretti L, Chow JH, Sarawgi S, Fardanesh B (2010) A phasor-data-based state estimator incorporating phase bias correction. IEEE Trans Power Syst 26(1):111–119
Yao W, Liu Y, Zhou D, Pan Z, Till MJ, Zhao J, Liu Y (2016) Impact of GPS signal loss and its mitigation in power system synchronized measurement devices. IEEE Trans Smart Grid 9(2):1141–1149
Liu Y, Jia Y, Lin Z, Zhang Y, Wang L, Tomsovic K, Liu Y (2011) Impact of GPS signal quality on the performance of phasor measurements. In: 2011 16th international conference on intelligent system applications to power systems (pp.1–6). IEEE
Liu FT, Ting KM, Zhou ZH (2008) Isolation forest. In: 2008 8th IEEE International conference on data mining (pp.413–422). IEEE
Guha S, Mishra N, Roy G, Schrijvers O (2016) Robust random cut forest based anomaly detection on streams. In: International conference on machine learning (pp.2712–2721). PMLR
Xu H, Pang G, Wang Y, Wang Y (2022) Deep isolation forest for anomaly detection. arXiv preprint arXiv:2206.06602
Lin G, Feng X, Guo W, Cui X, Liu S, Jin W, Ding Y (2021) Electricity theft detection based on stacked autoencoder and the undersampling and resampling based random forest algorithm. IEEE Access 9:124044–124058
Bhattacharyya S, Majumder S, Debnath P, Chanda M (2021) Arrhythmic heartbeat classification using ensemble of random forest and support vector machine algorithm. IEEE Trans Artif Intell 2(3):260–268
Wang J, Qiu J, Fang Y, Zhou S (2020) Short term load forecasting based on deep LSTM neural network. Guangdong Electr Power 33(8):62–68 (in Chinese)
Guo Y, Ding Y (2020) Design and implementation of grid information search engine based on knowledge map. University of Chinese Academy of Sciences, Shenyang (in Chinese)
Alhussein M, Aurangzeb K, Haider SI (2020) Hybrid CNN-LSTM model for short-term individual household load forecasting. IEEE Access 8:180544–180557
You Q, Qian Z, Nie Z (2020) Research on filling method of abnormal and missing data of wind turbines. Electr Meas Instrum 57(23):1–8 (in Chinese)
Wang J, Lu Y, Gao Q, Yu Y (2021) Nonlinear predictive control and application in microgrid. J Henan Univ Sci Technol 42(2):46–52 (in Chinese)
Wan C, Song Y (2021) Theories, methodologies and applications of probabilistic forecasting for probabilistic forecasting for power systems with renewable energy sources. Power Syst Autom 45(1):2–16 (in Chinese)
Bhardwaj R, Vatta S (2013) Implementation of ID3 algorithm. Int J Adv Res Comput Sci Softw Eng 3(6):845–851
Korting TS (2006) C4.5 algorithm and multivariate decision trees. In: Image processing division, national institute for space research–INPE Sao Jose dos Campos–SP, Brazil, 1–5
Denison DGT, Mallick BK, Smith AFM (1998) A bayesian cart algorithm. Biometrika 85(2):363–377
Han Y, Huang G, Song S, Yang L, Wang H, Wang Y (2021) Dynamic neural networks: a survey. IEEE Trans Pattern Anal Mach Intell 44(11):7436–7456
Denil M, Shakibi B, Dinh L, Ranzato MA, de Freitas N (2013) Predicting parameters in deep learning. In: Advances in neural information processing Systems, 1–9
Wilamowski BM, Yu H (2010) Improved computation for Levenberg–Marquardt training. IEEE Trans Neural Netw 21(6):930–937
Athay T, Podmore R, Virmani S (1979) A practical method for the direct analysis of transient stability. IEEE Trans Power Appar Syst PAS 98(2):573–584
Son S, Gil MS, Moon YS, Won HS (2016) Anomaly detection of hadoop log data using moving average and 3-sigma. KIPS Trans Softw Data Eng 5(6):283–288
Tian J, Azarian MH, Pecht M (2014) Anomaly detection using self-organizing maps-based k-nearest neighbor algorithm. In: 2014 2nd European Conference of the Prognostics and Health Management Society (ECPHM) (pp.1–9). PHM Society
Huang T, Zhu Y, Zhang Q, Zhu Y, Wang D, Qiu M, Liu L (2013). An lof-based adaptive anomaly detection scheme for cloud computing. In: 2013 IEEE 37th Annual computer software and applications conference workshops (pp. 206–211). IEEE
Erfani SM, Rajasegarar S, Karunasekera S, Leckie C (2016) High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recogn 58:121–134
Acknowledgements
This work was supported by the State Key Laboratory of Pyramid Talent Training Project of Beijing University of Civil Engineering and Architecture (JDYC20200324), BUCEA Post Graduate Innovation Project (PG2022132), Security Control and Simulation for Power System and Large Power Generation Equipment (SKLD20M17), Project of Beijing Association of Higher Education (YB2021131), National Natural Science Foundation of China (51407201).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest regarding the publication of this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yu, M., Yang, C., Li, W. et al. IRFLMDNN: hybrid model for PMU data anomaly detection and re-filling with improved random forest and Levenberg Marquardt algorithm optimized dynamic neural network. Neural Comput & Applic 35, 15563–15572 (2023). https://doi.org/10.1007/s00521-023-08571-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-08571-4