Hybridization of Mayfly-Pelican Optimization Algorithm for Selection of CNN Optimal Hyper-Parameters
Abstract
This work develops Pelican Mayfly Algorithm (PMA) to minimize CNN high computational requirement to the minimum by the selection of its optimum parameters. PMA was designed by applying pelican exploration model to improve the attraction process of MA as deterministic process and to establish a balance between exploration and exploitation in MA. PMA was applied to optimize CNN hyper-parameters to develop hybridized CNN-PMA, and CNN-PMA was applied to South Western Nigeria electrical network for detection and classification of electrical faults. MAPE, MNE, RMSE, SNR and PSNR and confusion matrix were used as performance metrics. PMA achieved the optimum CNN architecture as follows: 1-convolutional-layer, filter size of 6 x 6, number of filters per layer is 128 and 256-batch-size with recognition-rate of 99.53%. PMA selected optimal parameters of CNN timely and accurately. CNN-PMA performed better in detection and classification of faults in SWN electrical network compared to CNN, CNN-MA and some other selected models.
Keywords
Convolutional Neural Network (CNN)
Pelican Mayfly Algorithm
Hyper-parameters.
References
Abedinia, O., Amjady, N. and Ghasemi, A. (2016). A New Metaheuristic Algorithm Based on Shark Smell Optimization. Complexity, 21(5):97-116. Afrasiabi, M., Mohammadi, M., Rastegar, M. and Kargarian, A. (2019). Probabilistic Deep Neural Network Price Forecasting Based on Residential Load and Wind Speed Predictions, IET Renewable Power Generation, 13(11):1840-1848. Allan, J. D., and Flecker, A. S. (1989). The Mating Biology of a Mass-Swarming Mayfly. Animal Behavior, 37, 361-374. Amiruddin, A. A. A. M., Zabiri, H., Taqvi, S. A. A. and Tufa, L.D. (2020). Neural Network Applications in Fault Diagnosis and Detection: An Overview of Implementations in Engineering Related Systems. Neural Computer Applications 32 (2):447-472. Anderson, J. G. (1991). Foraging Behavior of the American White Pelican (Pelecanusery- throrhyncos) in Western Nevada. Colonial Water Birds, 14, 166-172. Askarzadeh, A. (2016). A Novel Metaheuristic Method for Solving Constrained Engineering Optimization Problems: Crow Search Algorithm. Computers and Structures, 169, 1- Baykasoglu, A. and Akpinar, S. (2017). Weighted Superposition Attraction (WSA): A Swarm Intelligence Algorithm for Optimization Problems-Part1: Unconstrained Optimization. Applied Soft Computing, 56, 520-540. Bracale, A., Caramia, P., Carpinelli, G. and Fazio, A.R.D. (2017) Modeling the Three-phase Short Circuit Contribution of Photovoltaic Systems in Balanced Power Systems. Electrical Power Energy Systems. 93, 204-215. Bukhari, S. B. A., Kim, C., Mehmood, K. K., Haider, R. and Zaman, M. S. U. (2020). Convolutional Neural Network-Based Intelligent Protection Strategy for Micro Grids, IET Generation Transmission. Distribution, 14(7):1177-1185. Chen, K., Hu, J., and He, J. (2018). Detection and Classification of Transmission Line Faults Based on Unsupervised Feature Learning and Convolutional Sparse Auto Encoder. IEEE Transaction. Smart Grid, 9(3):1748-1758. Dhiman, G. and Kumar, V. (2017). Spotted Hyena Optimizer: A Novel Bio-Inspired Based Metaheuristic Technique for Engineering Applications. Advances in Engineering Software, 114, 48-70. Fahim, S. R., Sarker, Y., Islam, O. K., Sarker, S. K., Ishraque, M. F. and Das, S. K. (2019). An Intelligent Approach of Fault Classification and Localization of a Power Transmission Line. 2019 IEEE International Conference Power, Electrical Electronic Industrial Applications PEEIACON, 53-56 Fausto, F., Cuevas, E., Valdivia, A. and González, A. (2017). A Global Optimization Algorithm Inspired in the Behavior of Selfish Herds. Biosystems, 160, 39-55. Geem, Z. W. and Kim, J. H. (2001). A New Heuristic Optimization Algorithm: Harmony Search. Research Gate, 3, 34-47. Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Addison Wesley. 1-6. Goni, M. F., Nahiduzzaman, M., Anower, M.S., Rahman, M.M., Islam, M.R., Ahsan, M., Haider, J. and Shahjalal, M. (2023). Fast and Accurate Fault Detection and Classification in Transmission Lines using Extreme Learning Machine. Advances in Electrical Engineering, Electronics and Energy, 3(100107):1-12. Guo, M. F., Yang, N. C. and Chen, W. F. (2019). Deep Learning-based Fault Classification using Hilbert–Huang Transform and Convolutional Neural Network in Power Distribution Systems. IEEE Sensors, 19(16):6905-6913. Hatata, A. Y., Essa, M. A. and Sedhom, B. E. (2022). Adaptive Protection Scheme for FREEDM Microgrid Based on Convolutional Neural Network and Gorilla Troops Optimization Technique. IEEE Access, 10, 55583-55595. Holland, J. H. (1960). Genetic Algorithms: Compare Programs that ‘Evolve’ in Ways the Resemble Natural Selection can Solve Complex Problems even their Creators do not fully understand. http//www.econ.lastate.edu/tesfatsi/Holland.G.AIntro. htm. 07/02/2023. Husseinzadeh-Kashan, A., Tavakkoli-Moghaddam, R., and Gen, M. (2019). Find-Fix-Finish- xploit-Analyze (F3EA) Meta-heuristic Algorithm: An Effective Algorithm with New Evolutionary Operators for Global Optimization. Computers and Industrial Engineering, 128, 192-218. Illias, H. A., Chai, X. R., Abu Bakar, A. H., Mokhlis, H. (2015). Transformer Incipient Fault Prediction Using Combined Artificial Neural Network and Various Particle Swarm Optimisation Techniques. Plosone, 10(6):1-16. Jahani, E. and Chizari, M. (2018). Tackling Global Optimization Problems with a Novel Algorithm: Mouth Brooding Fish Algorithm. Applied Soft Computing, 62, 987-1002. Jing, L., Zhao, M., Li, P. and Xu, X. (2017). A Convolutional Neural Network-Based Feature Learning and Fault Diagnosis Method for the Condition Monitoring of Gearbox. Measurement, 111, 1-10. Kaveh, A., and Dadras, A. (2017). A Novel Meta-Heuristic Optimization Algorithm: Thermal Exchange Optimization. Advances in Engineering Software, 110, 69-84. Kennedy, J. and Eberhart, R. (1995). Particle Swarm Optimization. Proceedings of ICNN’95- International Conference on Neural Networks, 1942-1948. Leh, N. A. M., Zain, F. M., Muhammad, Z., Abd Hamid, S. and Rosli, A. D. (2020). Fault Detection Method using ANN for Power Transmission Line, in: 2020 10th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), 79-84. Li, M. D., Zhao, H., Weng, X. W., and Han, T. (2016). A Novel Nature-Inspired Algorithm for Optimization: Virus Colony Search. Advances in Engineering Software, 92, 65-88. Lu, J., Ye, Y., Xu, X. and Li, Q. (2019). Application Research of Convolution Neural Network in Image Classification of Icing Monitoring in Power Grid. EURASIP Journal on Image and Video Processing, 49, 1-11. Marchant, S. (1990). Handbook of Australian, New Zealand and Antarctic Birds: Australian Pelican to Ducks; Oxford University Press: Melbourne, Australia. Mehrabian, A. R. and Lucas, C. (2006). A Novel Numerical Optimization Algorithm Inspired from Weed Colonization. Ecological Informatics, 1(4):355–366. Mirjalili, S. and Lewis, A. (2016). The Whale Optimization Algorithm. Advances in Engineering Software, 95(C):51-67. Mirjalili, S., Gandomi, A. H., Mirjalili, S. Z., Saremi, S., Faris, H., and Mirjalili, S. M. (2017). Salp Swarm Algorithm: A Bio-Inspired Optimizer for Engineering Design Problems. Advances in Engineering Software, 114, 163-191. Mirjalili, S., Mirjalili, S. M., and Hatamlou, A. (2016). Multi-Verse Optimizer: A Nature Inspired Algorithm for Global Optimization. Neural Computing and Applications, 27(2):495- Moradzadeh, A., Teimourzadeh, H., Mohammadi-Ivatloo, B. and Pourhossein, K. (2022). Hybrid CNN-LSTM Approaches for Identification of Type and Locations of Transmission Line Faults, International Journal of Electrical Power Energy System, 135(107563):117-131. Mozo, A., Ordozgoiti, B. and GoÂmez-Canaval, S. (2018). Forecasting Short-Term Data Center Network Traffic Load with Convolutional Neural Networks. PLOS ONE, 13(2):1-31. Nematollahi, A.F., Rahiminejad, A. and Vahidi, B. (2017). A Novel Physical Based Meta- Heuristic Optimization Method known as Lightning Attachment Procedure Optimization. Applied Soft Computing Journal, 59, 596-621. Ogundoyin, S. O. and Kamil, I. A. (2021). Optimization Techniques and Applications in Fog Computing: An Exhaustive Survey. Elsevier: Swarm and Evolutionary Computation, 66(100937):1-55. Pakzad-Moghaddam, S. H., Mina, H., and Mostafazadeh, P. (2019). A Novel Optimization Booster Algorithm. Computers and Industrial Engineering, 136, 591-613. Pan, C., Lu, M., Biao Xu, B. and Gao, H. (2019). An Improved CNN Model for Within Project Software Defect Prediction. Applied Sciences. 9(2138):1-27. Peckarsky, B. L., McIntosh, A. R., Caudill, C. C. and Dahl, J. (2002). Swarming and Mating Behavior of a Mayfly Baetisbicaudatus suggest Stabilizing Selection for Male Body Size. Behavioral Ecology and Sociobiology, 51(6):530-537.
