在現今的電力系統中，電壓源轉換器(VSC)已被廣泛的應用於電力的轉換，因此如何讓VSC可靠的運轉便成為非常重要的議題。而在VSC的故障診斷以及預防性的維護中，參數預測(PE)就是一個相當有用的工具。一般來說，根據量測資料的獲得方式，參數預測可以分為侵入式以及非侵入式兩種方法，而非侵入式的參數預測不需要任何從外部注入的激發訊號，因此被認為較適用於PE。
本論文提出一種非侵入式的參數預測方法，本方法使用精確的VSC模型(白盒子模型)來產出大量訓練資料，並利用這些資料訓練獲得一深度神經網路模型(黑盒子模型)來進行VSC的參數預測，本論文提出的模型具有能力預測VSC一定範圍內的工作點，並且能在在多VSC的系統中使用總電流取代個別電流加上直流電壓諧波來預測個別VSC的參數。另外，本文利用領域自適應技巧，僅使用小量的量測資料(目標域資料)進行參數預測以減少收集大量測量資料的成本

Voltage source converters (VSCs) have been widely used in modern power systems. Consequently, reliable operations of VSCs are essential for the power system to operate properly. A parameter estimator (PE) for a VSC system acts as a useful tool for problem diagnosis and preventive maintenance. Generally speaking, depending on how the measurement data are attained, a parameter estimation method can be classified into invasive and non-invasive. Non-invasive methods, which do not require any external excitation, are generally preferred for parameter estimation. This thesis proposes a non-invasive parameter estimation method.

The proposed method uses a detailed VSC model (white box model) to generate training data to obtain a deep neural network (black box model) for estimating parameters of VSC. The proposed model is able to estimate parameters for various operating points, and estimate parameters for individual VSC in a multi-VSCs system where only aggregated current measurement and dc harmonics voltage are available. Otherwise, by employing domain adaptation, we perform parameters estimation with small amount of measurement data (target domain) to reduce the cost of collecting large amounts of measurement data.

[1] S. Yang, D. Xiang, A. Bryant, P. Mawby, L. Ran, and P. Tavner, Condition
monitoring for device reliability in power electronic converters: A review, IEEE
Transactions on Power Electronics, vol. 25, no. 11, pp. 27342752, 2010.
[2] J. Huang, K. A. Corzine, and M. Belkhayat, Small-signal impedance measurement of power-electronics-based ac power systems using line-to-line current
injection, IEEE Transactions on Power Electronics, vol. 24, no. 2, pp. 445455,
2009.
[3] W. Zhou, Y. Wang, and Z. Chen, A gray-box parameters identification method
of voltage source converter using vector fitting algorithm, in 2019 10th International Conference on Power Electronics and ECCE Asia (ICPE 2019 - ECCE
Asia), 2019, pp. 29482955.
[4] A. Vidal, A. G. Yepes, F. D. Freijedo, O. Lopez, J. Malvar, F. Baneira, and
J. Doval-Gandoy, A method for identication of the equivalent inductance and
resistance in the plant model of current-controlled grid-tied converters, IEEE
Transactions on Power Electronics, vol. 30, no. 12, pp. 72457261, 2015.
[5] A. Vidal, A. G. Yepes, F. D. Freijedo, J. Malvar, O. Lopez, and J. DovalGandoy, A technique to estimate the equivalent loss resistance of grid-tied converters for current control analysis and design, IEEE Transactions on Power
Electronics, vol. 30, no. 3, pp. 17471761, 2015.
[6] L. Chang, X. Jiang, M. Mao, and H. Zhang, Parameter identification of controller for photovoltaic inverter based on l-m method, in 2018 IEEE International Power Electronics and Application Conference and Exposition (PEAC),
2018, pp. 16.
[7] Y. Li, T. Wang, S. Zhou, and G. Zhao, Coupled harmonic admittance identification based on measurement, in 2018 8th International Conference on Power
and Energy Systems (ICPES), 2018, pp. 109113.
[8] V. Valdivia, A. Barrado, A. LAzaro, P. Zumel, C. Raga, and C. FernAndez,
Simple modeling and identication procedures for "black-box" behavioral modeling of power converters based on transient response analysis, IEEE Transactions on Power Electronics, vol. 24, no. 12, pp. 27762790, 2009.
[9] T. Noda, Identification of a multiphase network equivalent for electromagnetic
transient calculations using partitioned frequency response, IEEE Transactions on Power Delivery, vol. 20, no. 2, pp. 11341142, 2005.
[10] L. Asiminoaei, R. Teodorescu, F. Blaabjerg, and U. Borup, Implementation
and test of an online embedded grid impedance estimation technique for pv
inverters, IEEE Transactions on Industrial Electronics, vol. 52, no. 4, pp.
11361144, 2005.
[11] N. Hoffmann and F. W. Fuchs, Minimal invasive equivalent grid impedance
estimation in inductive-resistive power networks using extended kalmanfilter,
IEEE Transactions on Power Electronics, vol. 29, no. 2, pp. 631641, 2014.
[12] M. Esparza, J. Segundo, C. Gurrola-Corral, N. Visairo-Cruz, E. Barcenas, and
E. Barocio, Parameter estimation of a grid-connected vsc using the extended
harmonic domain, IEEE Transactions on Industrial Electronics, vol. 66, no. 8,
pp. 60446054, 2019.
[13] A. Vahidnia, G. Ledwich, E. Palmer, and A. Ghosh, Identication and estimation of equivalent area parameters using synchronised phasor measurements,
IET Generation, Transmission Distribution, vol. 8, no. 4, pp. 697704, 2014.
[14] S. Neshvad, S. Chatzinotas, and J. Sachau, Wideband identification of power
network parameters using pseudo-random binary sequences on power inverters,
IEEE Transactions on Smart Grid, vol. 6, no. 5, pp. 22932301, 2015.
[15] Z.-H. Liu, H.-L. Wei, Q.-C. Zhong, K. Liu, X.-S. Xiao, and L.-H. Wu, Parameter estimation for vsi-fed pmsm based on a dynamic pso with learning
strategies, IEEE Transactions on Power Electronics, vol. 32, pp. 31543165,
2017.
[16] M. Sumner, B. Palethorpe, and D. W. P. Thomas, Impedance measurement
for improved power quality-part 1: the measurement technique, IEEE Trans-
actions on Power Delivery, vol. 19, no. 3, pp. 14421448, 2004.
[17] M. Sumner, B. Palethorpe, and D. W. P. Thomas, Impedance measurement
for improved power quality-part 2: a new technique for stand-alone active shunt
lter control, IEEE Transactions on Power Delivery, vol. 19, no. 3, pp. 1457
1463, 2004.
[18] M. Ahmeid, M. Armstrong, S. Gadoue, and P. Missailidis, Parameter estimation of a dc-dc converter using a kalman lter approach, in 7th IET International Conference on Power Electronics, Machines and Drives (PEMD 2014) ,
2014, pp. 16.
[19] B. H. Lin, J. T. Tsai, and K. L. Lian, A non-invasive method for estimating
circuit and control parameters of voltage source converters, IEEE Transactions
on Circuits and Systems I: Regular Papers, vol. 66, no. 12, pp. 49114921, 2019.
[20] K. Liu and Z. Q. Zhu, Position-oset-based parameter estimation using the
adaline nn for condition monitoring of permanent-magnet synchronous ma-
chines, IEEE Transactions on Industrial Electronics, vol. 62, no. 4, pp. 2372
2383, 2015.
[21] K. L. Lian and P. W. Lehn, Steady-state simulation methods of closed-loop
power converter systems-a systematic solution procedure, IEEE Transactions
on Circuits and Systems I: Regular Papers, vol. 59, no. 6, pp. 12991311, 2012.
[22] A. Oppenheim, A. Willsky, and S. Nawab, Signals and Systems, ser. Prentice-
Hall signal processing series. Prentice Hall, 1997.
[23] R. Carbone, A. Lo Schiavo, P. Marino, and A. Testa, A new method based
on periodic convolution for sensitivity analysis of multi-stage conversion systems, in Ninth International Conference on Harmonics and Quality of Power.
Proceedings (Cat. No.00EX441), vol. 1, 2000, pp. 6974 vol.1.
[24] C. Saniter, A. R. Wood, R. Hanitsch, and D. Schulz, Modelling the effects of
ac system impedance unbalance on pwm converters using frequency coupling
matrices, in 2003 IEEE Bologna Power Tech Conference Proceedings,, vol. 2,
2003, pp. 6 pp. Vol.2.
[25] P. W. Lehn, Direct harmonic analysis of the voltage source converter, IEEE
Transactions on Power Delivery, vol. 18, no. 3, pp. 10341042, 2003.
[26] F. Gao, S. Bozhko, A. Costabeber, C. Patel, P. Wheeler, C. I. Hill, and
G. Asher, Comparative stability analysis of droop control approaches in
voltage-source-converter-based dc microgrids, IEEE Transactions on Power
Electronics, vol. 32, no. 3, pp. 23952415, 2017.
[27] H. Zhang, L. Harnefors, X. Wang, H. Gong, and J. Hasler, Stability analysis
of grid-connected voltage-source converters using siso modeling, IEEE Trans-
actions on Power Electronics, vol. 34, no. 8, pp. 81048117, 2019.
[28] H. R. Baghaee, M. Mirsalim, G. B. Gharehpetian, and H. A. Talebi, A generalized descriptor-system robust h-inf control of autonomous microgrids to
improve small and large signal stability considering communication delays and
load nonlinearities, International Journal of Electrical Power and Energy Systems, vol. 92, pp. 6382, 2017.
[29] A. Semlyen, J. F. Eggleston, and J. Arrillaga, Admittance matrix model of
a synchronous machine for harmonic analysis, IEEE Transactions on Power
Systems, vol. 2, no. 4, pp. 833839, 1987.
[30] Shen Dong, Wang Zhonghong, J. Y. Chen, and Y. H. Song, Harmonic resonance phenomena in statcom and relationship to parameters selection of passive
components, IEEE Transactions on Power Delivery, vol. 16, no. 1, pp. 4652,
2001.
[31] C. K. Sao, P. W. Lehn, M. R. Iravani, and J. A. Martinez, A benchmark system for digital time-domain simulation of a pulse-width-modulated d-statcom,
IEEE Transactions on Power Delivery, vol. 17, no. 4, pp. 11131120, 2002.
[32] S. Bai, J. Kolter, and V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, 03 2018.
[33] A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves,
N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, Wavenet: A generative
model for raw audio, in Arxiv, 2016.
[34] K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition
(CVPR), 2016, pp. 770778.
[35] R. Caruana, Multitask learning: A knowledge-based source of inductive bias,
in ICML, 1993.
[36] X. Glorot and Y. Bengio, Understanding the diculty of training deep feedforward neural networks, in Proceedings of the Thirteenth International Conference on Articial Intelligence and Statistics, vol. 9. PMLR, 1315 May 2010,
pp. 249256.
[37] N. S. Keskar, D. Mudigere, J. Nocedal, M. Smelyanskiy, and P. T. P. Tang, On
large-batch training for deep learning: Generalization gap and sharp minima,
2016.
[38] E. Hoer, I. Hubara, and D. Soudry, Train longer, generalize better: closing
the generalization gap in large batch training of neural networks, ArXiv, vol.
abs/1705.08741, 2017.
[39] D. Kingma and J. Ba, Adam: A method for stochastic optimization, Inter-
national Conference on Learning Representations, 12 2014.
[40] L. Liu, H. Jiang, P. He, W. Chen, X. Liu, J. Gao, and J. Han, On the variance
of the adaptive learning rate and beyond, ArXiv, vol. abs/1908.03265, 2020.

[41] J. Blitzer, R. McDonald, and F. Pereira, Domain adaptation with structural
correspondence learning, in Proceedings of the 2006 Conference on Empirical
Methods in Natural Language Processing. Sydney, Australia: Association for
Computational Linguistics, Jul. 2006, pp. 120128.
[42] E. Tzeng, J. Homan, T. Darrell, and K. Saenko, Simultaneous deep transfer
across domains and tasks, in 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 40684076.
[43] M.-Y. Liu and O. Tuzel, Coupled generative adversarial networks, in Advances
in Neural Information Processing Systems 29. Curran Associates, Inc., 2016,
pp. 469477.
[44] K. Grauman, Geodesic ow kernel for unsupervised domain adaptation, 06
2012, pp. 20662073.
[45] S. Motiian, M. Piccirilli, D. A. Adjeroh, and G. Doretto, Unified deep supervised domain adaptation and generalization, in The IEEE International
Conference on Computer Vision (ICCV), Oct 2017.
[46] R. Hadsell, S. Chopra, and Y. LeCun, Dimensionality reduction by learning an
invariant mapping, in 2006 IEEE Computer Society Conference on Computer
Vision and Pattern Recognition (CVPR'06), vol. 2, 2006, pp. 17351742.
[47] H. Shimodaira, Improving predictive inference under covariate shift by weighting the log-likelihood function, Journal of Statistical Planning and Inference,
vol. 90, pp. 227244, 10 2000.
[48] L. van der Maaten and G. Hinton, Visualizing data using t-SNE, Journal of
Machine Learning Research, vol. 9, pp. 25792605, 2008. [Online]. Available:
http://www.jmlr.org/papers/v9/vandermaaten08a.html