This paper introduces a novel hybrid approach that integrates Latin hypercube sampling (LHS) and Bayesian optimization for optimizing artificial neural networks (ANNs) in fault detection, classification, and location for transmission lines. The proposed method advances the accuracy and efficiency of fault diagnosis in power systems, representing a significant step forward compared to conventional approaches. The test system is a 400 kV, 50 Hz, 300 km transmission system, and the simulations were carried out in MATLAB/Simulink environment. Using the strategic insight of LHS, optimal initial points were determined, which subsequently formed the basis for the Bayesian optimization to further refine the learning rate and training epochs. Within the fault detection domain, the model showcased remarkable precision when deployed on an evaluation dataset of 168 cases, accurately detecting every instance of normal and faulty scenarios. This culminated in an astounding 100% accuracy in fault detection. In terms of fault classification, the ANN model, trained on a dataset of 495 instances, revealed perfect regression coefficients across the training, testing, and validation subsets. When tested against unseen data, it demonstrated its proficiency by correctly classifying 154 out of 154 cases, showcasing a 100% F1 score. Also, the accuracy figures in terms of fault location fluctuated between 99.826% and 99.999%, with a mean absolute percentage error (MAPE) of 0.053%. The model's mean square error (MSE) stood at 0.0083, while the mean absolute error (MAE) was calculated at 0.0717. A deep dive into diverse fault types reaffirmed the model's precision, underscoring its consistent performance across various fault scenarios. The trained models were deployed on three different transmission lines and the models exhibited remarkable precision in all the cases tested. In summary, the innovative hybrid optimized ANN model, weaving together the strengths of LHS and Bayesian optimization, signifies an advancement in the field of power system fault analysis, ushering in heightened efficiency and reliability.
Citation: Abdul Yussif Seidu, Elvis Twumasi, Emmanuel Assuming Frimpong. Hybrid optimized artificial neural network using Latin hypercube sampling and Bayesian optimization for detection, classification and location of faults in transmission lines[J]. AIMS Electronics and Electrical Engineering, 2024, 8(4): 498-531. doi: 10.3934/electreng.2024024
This paper introduces a novel hybrid approach that integrates Latin hypercube sampling (LHS) and Bayesian optimization for optimizing artificial neural networks (ANNs) in fault detection, classification, and location for transmission lines. The proposed method advances the accuracy and efficiency of fault diagnosis in power systems, representing a significant step forward compared to conventional approaches. The test system is a 400 kV, 50 Hz, 300 km transmission system, and the simulations were carried out in MATLAB/Simulink environment. Using the strategic insight of LHS, optimal initial points were determined, which subsequently formed the basis for the Bayesian optimization to further refine the learning rate and training epochs. Within the fault detection domain, the model showcased remarkable precision when deployed on an evaluation dataset of 168 cases, accurately detecting every instance of normal and faulty scenarios. This culminated in an astounding 100% accuracy in fault detection. In terms of fault classification, the ANN model, trained on a dataset of 495 instances, revealed perfect regression coefficients across the training, testing, and validation subsets. When tested against unseen data, it demonstrated its proficiency by correctly classifying 154 out of 154 cases, showcasing a 100% F1 score. Also, the accuracy figures in terms of fault location fluctuated between 99.826% and 99.999%, with a mean absolute percentage error (MAPE) of 0.053%. The model's mean square error (MSE) stood at 0.0083, while the mean absolute error (MAE) was calculated at 0.0717. A deep dive into diverse fault types reaffirmed the model's precision, underscoring its consistent performance across various fault scenarios. The trained models were deployed on three different transmission lines and the models exhibited remarkable precision in all the cases tested. In summary, the innovative hybrid optimized ANN model, weaving together the strengths of LHS and Bayesian optimization, signifies an advancement in the field of power system fault analysis, ushering in heightened efficiency and reliability.
| [1] | Ogar, VN, Hussain S, Gamage KA (2023) The use of artificial neural network for low latency of fault detection and localisation in transmission line. Heliyon 9. https://doi.org/10.1016/j.heliyon.2023.e13376. |
| [2] |
Goni MO, Nahiduzzaman M, Anower MS, Rahman MM, Islam MR, Ahsan M, et al. (2023) Fast and Accurate Fault Detection and Classification in Transmission Lines using Extreme Learning Machine. e-Prime - Advances in Electrical Engineering, Electronics and Energy 3: 100107. https://doi.org/10.1016/j.prime.2023.100107 doi: 10.1016/j.prime.2023.100107
|
| [3] | Naji HA, Fayadh RA, Mutlag AH (2023) ANN-based Fault Location in 11 kV Power Distribution Line using MATLAB. 2023 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, JEEIT, 134–139. https://doi.org/10.1109/JEEIT58638.2023.10185849. |
| [4] |
Venkata P, Pandya V, Vala K, Sant AV (2022) Support vector machine for fast fault detection and classification in modern power systems using quarter cycle data. Energy Reports 8: 92–98. https://doi.org/10.1016/j.egyr.2022.10.279 doi: 10.1016/j.egyr.2022.10.279
|
| [5] |
Ahmadipour M, Othman MM, Bo R, Salam Z, Ridha HM, Hasan K (2022) A novel microgrid fault detection and classification method using maximal overlap discrete wavelet packet transform and an augmented Lagrangian particle swarm optimization-support vector machine. Energy Reports 8: 4854–4870. https://doi.org/10.1016/j.egyr.2022.03.174 doi: 10.1016/j.egyr.2022.03.174
|
| [6] |
Aiswarya R, Nair DS, Rajeev T, Vinod V (2023) A novel SVM based adaptive scheme for accurate fault identification in microgrid. Electr Pow Syst Res 221: 109439. https://doi.org/10.1016/j.epsr.2023.109439 doi: 10.1016/j.epsr.2023.109439
|
| [7] |
De Santis E, Rizzi A, Sadeghian A (2018) A cluster-based dissimilarity learning approach for localized fault classification in Smart Grids. Swarm Evol Comput 39: 267–278. https://doi.org/10.1016/j.swevo.2017.10.007 doi: 10.1016/j.swevo.2017.10.007
|
| [8] | Bhuyan A, Panigrahi BK, Pal K, Pati S (2022) Convolutional Neural Network Based Fault Detection for Transmission Line. 2022 International Conference on Intelligent Controller and Computing for Smart Power, ICICCS, 1-4. https://doi.org/10.1109/ICICCSP53532.2022.9862446. |
| [9] |
Omar AMS, Osman MK, Ibrahim MN, Hussain Z, Abidin AF (2020) Fault classification on transmission line using LSTM network. Indonesian Journal of Electrical Engineering and Computer Science 20: 231–238. https://doi.org/10.11591/ijeecs.v20.i1.pp231-238 doi: 10.11591/ijeecs.v20.i1.pp231-238
|
| [10] |
Biswas S, Nayak PK, Panigrahi BK, Pradhan G (2023) An intelligent fault detection and classification technique based on variational mode decomposition-CNN for transmission lines installed with UPFC and wind farm. Electr Pow Syst Res 223: 109526. https://doi.org/10.1016/j.epsr.2023.109526 doi: 10.1016/j.epsr.2023.109526
|
| [11] |
Mirshekali H, Keshavarz A, Dashti R, Hafezi S, Shaker HR (2023) Deep learning-based fault location framework in power distribution grids employing convolutional neural network based on capsule network. Electr Pow Syst Res 223: 109529. https://doi.org/10.1016/j.epsr.2023.109529 doi: 10.1016/j.epsr.2023.109529
|
| [12] |
Tabari M, Sadeh J (2022) Fault location in series-compensated transmission lines using adaptive network-based fuzzy inference system. Electr Pow Syst Res 208: 107800. https://doi.org/10.1016/j.epsr.2022.107800 doi: 10.1016/j.epsr.2022.107800
|
| [13] | Naidu K, Ali MS, Abu Bakar AH, Tan CK, Arof H, Mokhlis H (2020) Optimized artificial neural network to improve the accuracy of estimated fault impedances and distances for underground distribution system. PLoS One 15: e0227494. https://doi.org/10.1371/journal.pone.0227494. |
| [14] |
Iliyaeifar MM, Hadaeghi A (2023) Extreme learning machine-based fault location approach for terminal-hybrid LCC-VSC-HVDC transmission lines. Electr Pow Syst Res 221: 109487. https://doi.org/10.1016/j.epsr.2023.109487 doi: 10.1016/j.epsr.2023.109487
|
| [15] |
Kanwal S, Jiriwibhakorn S (2023) Artificial Intelligence Based Faults Identification, Classification, and Localization Techniques in Transmission Lines-A Review. IEEE Latin America Transactions 21: 1291-1305. https://doi.org/10.1109/TLA.2023.10305233 doi: 10.1109/TLA.2023.10305233
|
| [16] |
Yadav A, Dash Y (2014) An Overview of Transmission Line Protection by Artificial Neural Network: Fault Detection, Fault Classification, Fault Location, and Fault Direction Discrimination. Advances in Artificial Neural Systems 2014: 230382. https://doi.org/10.1155/2014/230382 doi: 10.1155/2014/230382
|
| [17] |
Kanwal S, Jiriwibhakorn S (2024) Advanced Fault Detection, Classification, and Localization in Transmission Lines: A Comparative Study of ANFIS, Neural Networks, and Hybrid Methods. IEEE Access 12: 49017–49033. https://doi.org/10.1109/ACCESS.2024.3384761 doi: 10.1109/ACCESS.2024.3384761
|
| [18] |
Ravesh NR, Ramezani N, Ahmadi I, Nouri H (2022) A hybrid artificial neural network and wavelet packet transform approach for fault location in hybrid transmission lines. Electr Pow Syst Res 204: 107721. https://doi.org/10.1016/j.epsr.2021.107721 doi: 10.1016/j.epsr.2021.107721
|
| [19] |
Hannan MA, How DN, Lipu MH, Ker PJ, Dong ZY, Mansur M, et al. (2020) SOC Estimation of Li-ion Batteries with Learning Rate-Optimized Deep Fully Convolutional Network. IEEE T Power Electr 36: 7349–7353. https://doi.org/10.1109/TPEL.2020.3041876 doi: 10.1109/TPEL.2020.3041876
|
| [20] | Liu S, Ghosh R, Min JT, Motani M (2022) Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks. arXiv preprint arXiv: 2212.06144. |
| [21] | Xu C, Liu S, Huang Y, Huang C, Zhang Z (2021) Over-the-air Learning Rate Optimization for Federated Learning. 2021 IEEE International Conference on Communications Workshops, ICC Workshops, 1-7. https://doi.org/10.1109/ICCWorkshops50388.2021.9473663. |
| [22] | Yasusi K (2016) Optimizing Neural-network Learning Rate by Using a Genetic Algorithm with Per-epoch Mutations. 2016 International Joint Conference on Neural Networks (IJCNN), 1472-1479. IEEE. |
| [23] | Hsieh HL, Shanechi MM (2018) Optimizing the learning rate for adaptive estimation of neural encoding models. PLoS Comput Biol 14: e1006168. https://doi.org/10.1371/journal.pcbi.1006168. |
| [24] | Dai Z, Yu H, Low BK, Jaillet P (2019) Bayesian Optimization Meets Bayesian Optimal Stopping. International conference on machine learning, 1496-1506. |
| [25] | Serizawa T, Fujita H (2020) Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization. https://doi.org/10.11517/pjsai.JSAI2022.0_2S4IS2b03. |
| [26] |
Sheikholeslami R, Razavi S (2017) Progressive Latin Hypercube Sampling: An efficient approach for robust sampling-based analysis of environmental models. Environmental Modelling and Software 93: 109–126. https://doi.org/10.1016/j.envsoft.2017.03.010 doi: 10.1016/j.envsoft.2017.03.010
|
| [27] |
Shields MD, Zhang J (2016) The generalization of Latin hypercube sampling. Reliab Eng Syst Saf 148: 96–108. https://doi.org/10.1016/j.ress.2015.12.002 doi: 10.1016/j.ress.2015.12.002
|
| [28] |
Wu J, Chen XY, Zhang H, Xiong LD, Lei H, Deng SH (2019) Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology 17: 26–40. https://doi.org/10.11989/JEST.1674-862X.80904120 doi: 10.11989/JEST.1674-862X.80904120
|
| [29] |
Thelen A, Zohair M, Ramamurthy J, Harkaway A, Jiao W, Ojha M, et al. (2023) Sequential Bayesian optimization for accelerating the design of sodium metal battery nucleation layers. J Power Sources 581: 233508. https://doi.org/10.1016/j.jpowsour.2023.233508 doi: 10.1016/j.jpowsour.2023.233508
|
| [30] |
Shin S, Lee Y, Kim M, Park J, Lee S, Min K (2020) Deep neural network model with Bayesian hyperparameter optimization for prediction of NOx at transient conditions in a diesel engine. Eng Appl Artif Intell 94: 103761. https://doi.org/10.1016/j.engappai.2020.103761 doi: 10.1016/j.engappai.2020.103761
|
| [31] | Burrage K, Burrage P, Donovan D, Thompson B (2015) Populations of models, experimental designs and coverage of parameter space by Latin Hypercube and Orthogonal sampling. Procedia Computer Science, 1762–1771. https://doi.org/10.1016/j.procs.2015.05.383. |
| [32] |
Shu Z, Jirutitijaroen P (2011) Latin hypercube sampling techniques for power systems reliability analysis with renewable energy sources. IEEE T Power Syst 26: 2066–2073. https://doi.org/10.1109/TPWRS.2011.2113380 doi: 10.1109/TPWRS.2011.2113380
|
| [33] |
Deutsch JL, Deutsch CV (2012) Latin hypercube sampling with multidimensional uniformity. J Stat Plan Inference 142: 763–772. https://doi.org/10.1016/j.jspi.2011.09.016 doi: 10.1016/j.jspi.2011.09.016
|
| [34] | Nguyen V (2019) Bayesian optimization for accelerating hyper-parameter tuning. Proceedings - IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE, 302–305. https://doi.org/10.1109/AIKE.2019.00060. |
| [35] | D. Singh D, Singh B (2022) Feature wise normalization: An effective way of normalizing data. Pattern Recogn 122: 108307. https://doi.org/10.1016/j.patcog.2021.108307. |
| [36] |
Islam MJ, Ahmad S, Haque F, Reaz MB, Bhuiyan MA, Islam MR (2022) Application of Min-Max Normalization on Subject-Invariant EMG Pattern Recognition. IEEE T Instrum Meas 71: 1-12. https://doi.org/10.1109/TIM.2022.3220286 doi: 10.1109/TIM.2022.3220286
|
| [37] |
Szabó S, Holb IJ, Abriha-Molnár VE, Szatmári G, Singh SK, Abriha D (2024) Classification Assessment Tool: A program to measure the uncertainty of classification models in terms of class-level metrics. Appl Soft Comput 155: 111468. https://doi.org/10.1016/j.asoc.2024.111468 doi: 10.1016/j.asoc.2024.111468
|
| [38] |
Chicco D, Jurman G (2020) The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 21: 1-13. https://doi.org/10.1186/s12864-019-6413-7 doi: 10.1186/s12864-019-6413-7
|
| [39] | Borkhade AD (2014) Transmission line fault detection using wavelet transform. International Journal on Recent and Innovation Trends in Computing and Communication 2: 3138-3142. |
| [40] | Teja ON, Ramakrishna MS, Bhavana GB, Sireesha K (2020) Fault Detection and Classification in Power Transmission Lines using Back Propagation Neural Networks. Proceedings of the International Conference on Smart Electronics and Communication (ICOSEC 2020), 1150–1156. |
| [41] |
Fan R, Liu Y, Huang R, Diao R, Wang S (2018) Precise Fault Location on Transmission Lines Using Ensemble Kalman Filter. IEEE T Power Deliver 33: 3252–3255. https://doi.org/10.1109/TPWRD.2018.2849879 doi: 10.1109/TPWRD.2018.2849879
|
| [42] |
Arranz R, Paredes Á, Rodríguez A, Muñoz F (2021) Fault location in Transmission System based on Transient Recovery Voltage using Stockwell transform and Artificial Neural Networks. Electr Pow Syst Res 201: 107569. https://doi.org/10.1016/j.epsr.2021.107569 doi: 10.1016/j.epsr.2021.107569
|
| [43] |
Moradzadeh A, Teimourzadeh H, Mohammadi-Ivatloo B, Pourhossein K (2022) Hybrid CNN-LSTM approaches for identification of type and locations of transmission line faults. Int J Electr Power 135: 107563. https://doi.org/10.1016/j.ijepes.2021.107563 doi: 10.1016/j.ijepes.2021.107563
|
| [44] |
Shang B, Luo G, Li M, Liu Y, Hei J (2023) Transfer learning-based fault location with small datasets in VSC-HVDC. Int J Electr Power 151: 109131. https://doi.org/10.1016/j.ijepes.2023.109131 doi: 10.1016/j.ijepes.2023.109131
|
| [45] | Pouabe Eboule PS, Pretorius JHC, Mbuli N (2018) Artificial Neural Network Techniques apply for Fault detecting and Locating in Overhead Power Transmission Line. 2018 Australasian Universities Power Engineering Conference (AUPEC), 1-6 |
| [46] |
Said A, Saad MH, Eladl SM, Elbarbary ZS, Omar AI, Saad MA (2023) Support Vector Machine Parameters Optimization for 500 kV Long OHTL Fault Diagnosis. IEEE Access 11: 3955–3969. https://doi.org/10.1109/ACCESS.2023.3235592 doi: 10.1109/ACCESS.2023.3235592
|
Figures(24) / Tables(3)
Abdul Yussif Seidu, Elvis Twumasi, Emmanuel Assuming Frimpong. Hybrid optimized artificial neural network using Latin hypercube sampling and Bayesian optimization for detection, classification and location of faults in transmission lines[J]. AIMS Electronics and Electrical Engineering, 2024, 8(4): 498-531. doi: 10.3934/electreng.2024024
DownLoad: