Skip to main content

Advertisement

SpringerLink
Log in

A novel microgrid islanding classification algorithm based on combining hybrid feature extraction approach with deep ResNet model

  • Original Paper
  • Published:
Electrical Engineering Aims and scope Submit manuscript

Abstract

Microgrids are essential for developing the future energy systems. Microgrids can be utilized in grid-connected or island mode, enabling increased integration of renewable energy sources into a power system. However, due to the increased penetration of converter-based renewable energy sources, the quality of power in microgrids may be adversely affected. Therefore, finding an appropriate technique to classify and detect islanding and non-islanding events in microgrids is one of the major challenges associated with the design of renewable energy sources. This paper presents a new hybrid approach by using wavelet transform, Stockwell transform and residual neural networks for classification and detection of islanding and non-islanding events. The proposed hybrid approach consists of two main stages: in the first stage, optimum feature images of islanding and non-islanding events are obtained by performing wavelet transform and Stockwell transform. In the second stage, a residual neural network model which is fine-tuned with optimal hyperparameters is determined in order to detect and classify islanding and non-islanding events. Thus, feature image data obtained from microgrid test model are structured as input to residual neural network for classifying of islanding and non-islanding events. By employing the hybrid signal processing approaches with deep learning-based residual neural networks, the validation accuracy of 99.40% is obtained for islanding and non-islanding events with average detection time of 0.1260 s. The effectiveness of the hybrid approach was evaluated through comparative analysis with the results obtained for normal and noisy environments in approaches used by similar studies presented in the literature. Unlike traditional passive island detection techniques, the proposed deep learning-based hybrid approach is considered to have superior performance due to its more dynamic behavior.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Pereira BR, da Costa GRM, Contreras J, Mantovani JRS (2016) Optimal distributed generation and reactive power allocation in electrical distribution systems. IEEE Trans Sustain Energy 7(3):975–984

    ADS  Google Scholar 

  2. Priyadarshini L, Dash PK (2021) Detection of islanding and non-islanding fault disturbances in microgrid using LMD and deep stacked RVFLN based auto-encoder. Electr Eng 103:2747–2767

    Google Scholar 

  3. Serrano-Fontova A, Martinez JA, Casals-Torrens P, Bosch R (2021) A robust islanding detection method with zero-non-detection zone for distribution systems with DG. Int J Electr Power Energy Syst 133:107247

    Google Scholar 

  4. Shukla A, Dutta S, Sadhu PK (2021) An island detection approach by μ-PMU with reduced chances of cyber attack. Int J Electr Power Energy Syst 126(A):106599

    Google Scholar 

  5. Dash PK, Padhee M, Barik SK (2012) Estimation of power quality indices in distributed generation systems during power islanding conditions. Int J Electr Power Energy Syst 36(1):18–30

    Google Scholar 

  6. IEEE Standard for Interconnecting Distributed Resources with Electric Power Systems, IEEE Standard 1547-2003, Jul. 2003

  7. Dutta S, Reddy MJB, Mohanta DK, Kushwah MS, Sadhu PK (2020) μPMU-based intelligent island detection—the first crucial step toward enhancing grid resilience with MG. IET Smart Grid 3(2):162–173

    Google Scholar 

  8. Liu S, Zhuang S, Xu Q, Xiao J (2016) Improved voltage shift islanding detection method for multi-inverter grid-connected photovoltaic systems. IET Gener Transm Distrib 10(13):3163–3169

    Google Scholar 

  9. Karan S, Bhalja BR, Maheshwari RP (2016) Islanding detection technique based on inverse hyperbolic secant function. IET Renew Power Gener 10(7):1002–1009

    Google Scholar 

  10. Nale R, Venkatanagaraju K, Biswal S, Biswal M, Kishor N (2019) Islanding detection in distributed generation system using intrinsic time decomposition’. IET Gener Transm Distrib 13(5):626–633

    Google Scholar 

  11. Mishra S, Mallick RK, Gadanayak DA, Nayak P (2021) A novel hybrid downsampling and optimized random forest approach for islanding detection and non-islanding power quality events classification in distributed generation integrated system. IET Renew Power Gener 15(8):1662–1677

    Google Scholar 

  12. Kumar SA, Subathra MSP, Kumar NM, Malvoni M, Sairamya NJ, George ST, Suviseshamuthu ES, Chopra SS (2020) A novel islanding detection technique for a resilient photovoltaic-based distributed power generation system using a tunable-q wavelet transform and an artificial neural network. Energies 13(16):4238

    Google Scholar 

  13. Mishra M, Rout PK (2019) Fast discrete s-transform and extreme learning machine based approach to islanding detection in grid-connected distributed generation. Energy Syst 10(3):757–789

    Google Scholar 

  14. Kim JH, Kim JG, Ji YH, Jung YC, Won CY (2011) An islanding detection method for a grid-connected system based on the Goertzel algorithm. IEEE Trans Power Electron 26(4):1049–1055

    ADS  Google Scholar 

  15. Erişti B, Erişti H (2022) Classification of power quality disturbances in solar PV integrated power system based on a hybrid deep learning approach. Int Trans Electr Energy Syst 2022; vol 2022, Article ID 8519379, 13 pages

  16. Puliyadi Kubendran AK, Loganathan AK (2017) Detection and classification of complex power quality disturbances using S-transform amplitude matrix-based decision tree for different noise levels. Int Trans Electr Energy Syst 27(4):e2286

    Google Scholar 

  17. Sahani M, Dash PK (2019) FPGA-based online power quality disturbances monitoring using reduced-sample HHT and class-specific weighted RVFLN. IEEE Trans Ind Inf 15(8):4614–4623

    Google Scholar 

  18. Abdelsalam AA, Eldesouky AA, Sallam AA (2012) Characterization of power quality disturbances using hybrid technique of linear Kalman filter and fuzzy-expert system. Electr Power Syst Res 83(1):41–50

    Google Scholar 

  19. Liu H, Hussain F, Shen Y, Arif S, Nazir A, Abubakar M (2018) Complex power quality disturbances classification via curvelet transform and deep learning. Electr Power Syst Res 163:1–9

    Google Scholar 

  20. Chakravorti T, Patnaik RK, Dash PK (2018) Detection and classification of islanding and power quality disturbances in microgrid using hybrid signal processing and data mining techniques. IET Signal Proc 12(1):82–94

    Google Scholar 

  21. Chakravorti T, Priyadarshini L, Dash PK, Sahu BN (2019) Islanding and non-islanding disturbance detection in microgrid using optimized modes decomposition based robust random vector functional link network. Eng Appl Artif Intell 85:122–136

    Google Scholar 

  22. Manikonda SK, Gaonkar DN (2020) Islanding detection method based on image classification technique using histogram of oriented gradient features. IET Gener Transm Distrib 14(14):2790–2799

    Google Scholar 

  23. Manikonda SK, Gaonkar DN (2019) IDM based on image classification with CNN. J Eng 2019(10):7256–7262

    Google Scholar 

  24. Dutta S, Olla S, Sadhu PK (2021) A secured, reliable and accurate unplanned island detection method in a renewable energy based microgrid. Eng Sci Technol Int J 24:1102–1115

    Google Scholar 

  25. Ray PK, Kishor N, Mohanty SR (2012) Islanding and power quality disturbance detection in grid-connected hybrid power system using wavelet and S-transform. IEEE Trans Smart Grid 3(3):1082–1094

    Google Scholar 

  26. Gong R, Ruan T (2020) A new convolutional network structure for power quality disturbance identification and classification in micro-grids. IEEE Access 8:88801–88814

    Google Scholar 

  27. Guo Y, Pang Z, Du J, Jiang F, Hu Q (2020) An improved AlexNet for power edge transmission line anomaly detection. IEEE Access 8:97830–97838

    Google Scholar 

  28. Cheng XR, Cui BJ, Hou SZ (2022) Fault line selection of distribution network based on modified CEEMDAN and GoogLeNet neural network. IEEE Sens J 22:13346–13364

    ADS  Google Scholar 

  29. Su D, Li K, Shi N (2021) Power quality disturbances recognition using modified S-transform based on optimally concentrated window with integration of renewable energy. Sustainability 13(17):9868

    Google Scholar 

  30. Stockwell RG (2007) A basis for efficient representation of the S-transform. Digit Signal Process 17(1):371–393

    Google Scholar 

  31. Kumar R, Singh B, Kumar R, Marwaha S (2023) Online identification of underlying causes for multiple and multi-stage power quality disturbances using S-transform. IETE J Res 69(6):3739–3749

    Google Scholar 

  32. Kumar R, Singh B, Shahani DT, Chandra A, Al-Haddad K (2014) Recognition of power-quality disturbances using S-transform-based ANN classifier and rule-based decision tree. IEEE Trans Ind Appl 51(2):1249–1258

    Google Scholar 

  33. Suganthi ST, Vinayagam A, Veerasamy V, Deepa A, Abouhawwash M, Thirumeni M (2021) Detection and classification of multiple power quality disturbances in microgrid network using probabilistic based intelligent classifier. Sustain Energy Technol Assess 47:101470

    Google Scholar 

  34. Chamchuen S, Siritaratiwat A, Fuangfoo P, Suthisopapan P, Khunkitti P (2021) High-accuracy power quality disturbance classification using the adaptive ABC-PSO as optimal feature selection algorithm. Energies 14(5):1238

    Google Scholar 

  35. Khokhar S, Zin AAM, Memon AP, Mokhtar AS (2017) A new optimal feature selection algorithm for classification of power quality disturbances using discrete wavelet transform and probabilistic neural network. Measurement 95:246–259

    ADS  Google Scholar 

  36. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  37. Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157–166

    CAS  PubMed  Google Scholar 

  38. Zhang M, Yu Z, Wang H, Qin H, Zhao W, Liu Y (2019) Automatic digital modulation classification based on curriculum learning. Appl Sci 9:2171

    Google Scholar 

  39. Mhasakar P, Triverdi P, Mandal S, Mitra SK (2012) Handwritten digit recognition using Bayesian ResNet. SN Comput Sci 2:399

    Google Scholar 

  40. Li Y, Song B, Kang X, Du X, Guizani M (2018) Vehicle-type detection based on compressed sensing and deep learning in vehicular networks. Sensors 18:4500

    PubMed  PubMed Central  ADS  Google Scholar 

  41. Standard I. IEEE recommended practice for monitoring electric power quality. IEEE Std, pp 1159–2009

  42. Wu J, Chen XY, Zhang H, Xiong LD, Lei H, Deng SH (2019) Hyperparameter optimization for machine learning models based on Bayesian optimization. J Electron Sci Technol 17(1):26–40

    ADS  Google Scholar 

  43. Eristi B, Eristi H (2022) A new deep learning method for the classification of power quality disturbances in hybrid power system. Electr Eng 104:3753–3768

    Google Scholar 

  44. Kong X, Xu X, Yan Z, Chen S, Yang H, Han D (2018) Deep learning hybrid method for islanding detection in distributed generation. Appl Energy 210:776–785

    ADS  Google Scholar 

  45. Bhatt N, Chandel AK (2021) A random under-sampling based passive approach for fast and accurate detection of islanding in electrical distribution system. IETE Tech Rev. https://doi.org/10.1080/02564602.2021.1976291

    Article  Google Scholar 

  46. Mohanty SR, Ray PK, Kishor N, Panigrahi BK (2013) Classification of disturbances in hybrid DG system using modular PNN and SVM. Electr Power Energy Syst 44:764–777

    Google Scholar 

  47. Dash PK, Barik SK, Patnaik RK (2014) Detection and classification of islanding and nonislanding events in distributed generation based on fuzzy decision tree. J Control Autom Electr Syst 25:699–719

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Electrical and Energy Department, Vocational School of Technical Sciences, Mersin University, Mersin, Turkey

    Belkis Eristi

  2. Computer Engineering Department, Engineering Faculty, Mersin University, Mersin, Turkey

    Volkan Yamacli

  3. Electrical and Electronics Engineering Department, Engineering Faculty, Mersin University, Mersin, Turkey

    Huseyin Eristi

Authors
  1. Belkis Eristi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Volkan Yamacli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huseyin Eristi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Belkis Eristi designed the project, analyzed of data, wrote and reviewed the main manuscript text. Volkan Yamacli designed the project, analyzed of data, wrote and reviewed the main manuscript text. Huseyin Eristi designed the project, analyzed of data, wrote and reviewed the main manuscript text.

Corresponding author

Correspondence to Huseyin Eristi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

See Tables

Table 11 Specifications of distributed generators
Full size table

11 and

Table 12 Specifications of lines and transformers
Full size table

12.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Eristi, B., Yamacli, V. & Eristi, H. A novel microgrid islanding classification algorithm based on combining hybrid feature extraction approach with deep ResNet model. Electr Eng 106, 145–164 (2024). https://doi.org/10.1007/s00202-023-01977-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00202-023-01977-2

Keywords

Search

Navigation