Archives
:: International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies
http://TuEngr.com
ISSN 2228-9860
eISSN 1906-9642
CODEN: ITJEA8
FEATURE PEER-REVIEWED ARTICLE
Vol.12(10) (2021) |
Optimized Deep Learning Procedure by Adaptive Parameters Based Genetic Algorithms for Determining Reservoir Inflow
Krotsuwan Phosuwan and Panuwat Pinthong(Faculty of Technical Education, King Mongkut's University of Technology North Bangkok, THAILAND).
Disciplinary: Civil Engineering & Technology (Hydrology), Computer Application.
doi: 10.14456/ITJEMAST.2021.205
Keywords: Rainfall-Runoff model; Reservoir Operation; Multilayer Perceptron; ANNs; AGA; APOGA; APGA; Kaeng Krachan reservoir; Phetchaburi river basin; Optimum deep learning parameters; Remaining Life Time (RLT); Water resource manangement; Reduced flood; Reservoir management.
AbstractThe determination of the reservoir inflow would be directly affected the efficiency of reservoir operation. Artificial intelligence techniques such as Artificial Neural Networks, Deep Learning (DL), and Genetic Algorithms (GAs) have been applied to many case studies of water resource management, for example, the determined relationship between rainfall and runoff, and rainfall forecast. DL has been successful for the rainfall-runoff model, but the performance of the model depends on its parameters that take more time-consuming for model development and is difficult to determine the optimum values. This paper presents the development of the Adaptive Parameters Based Genetic Algorithms (APGA) model to explore the optimum procedure of deep learning for reservoir inflow simulation for the Kaeng Krachan Reservoir and compare performance with the Adaptive Genetic Algorithm (AGA). The current study found that the mean absolute percentage error (MAPE) of the reservoir inflow from APGA was lower than AGA in all periods, so the optimum DL procedure from APGA outperforms AGA, while the DL layer architecture from APGA was more complex than AGA. In summary, APGA may be suitable for determining optimum DL procedure than AGA, but the probability of crossover (pc) and probability of mutation (pm) parameters should be studied in the future.Paper ID: 12A10P
Cite this article:
Phosuwan, K., Pinthong, P. (2021). Optimized Deep Learning Procedure by Adaptive Parameters Based Genetic Algorithms for Determining Reservoir Inflow. International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies, 12(10), 12A10P, 1-14. http://doi.org/10.14456/ITJEMAST.2021.205
References
- S. Yang and T. Yang, "Uncertainty Assessment: Reservoir Inflow Forecasting with Ensemble Precipitation Forecasts and HEC-HMS," Advance in Meteorology, pp. 1-11, 2014. DOI: 10.1155/2014/581756
- A. W. Minns and M. J. Hall, "Artificial Neural Networks as Rainfall-Runoff Models," Hydrological Sciences journal, pp. 399-417, 1996. DOI: 10.1080/02626669609491511
- J. Heaton, "Deep Learning and Neural Networks," Heaton Research Publisher Vol.3, 2015.
- S. Afaq and S. Rao, "Significance Of Epochs On Training A Neural Network," International Journal Of Scientific & Technology, Vol. 9, pp. 485-488, 2020.
- D., Rivero, Dorado J., Fern?ndez-Blanco E., Pazos A., "A Genetic Algorithm for ANN Design, Training and Simplification,". In: Cabestany J., Sandoval F., Prieto A., Corchado J.M. (eds) Bio-Inspired Systems: Computational and Ambient Intelligence. IWANN 2009. Lecture Notes in Computer Science, vol.5517. Springer, Berlin, Heidelberg, 2009. DOI: 10.1007/978-3-642-02478-8_49
- G. A. Beatriz and V. A. Roberto, "Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms," Computational Intelligence and Neuroscience, 2015. DOI: 10.1155/2015/369298
- S. N. Sivanandam and S. N. Deepa, " Introduction to Genetic Algorithms", New York: Springer, 2008.
- T. A. Pham, V. Q. Tran and H.-L. T. Vu, "Design Deep Neural Network Architecture Using a Genetic Algorithm for Estimation of Pile Bearing Capacity," LoS ONE, pp. 1-25, 2020. DOI: 10.1371/journal.pone.0243030
- B.R.Rajakumara and A. George, "APOGA: An Adaptive Population Pool Size Based Genetic Algorithm," 2013.
- A. Laoufi, S. Hadjeri and A. Hazzab, "Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms for power economic dispatch," International Journal of Applied Engineering Research, vol. 1(3), pp. 393-408, 2006.
- M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner and P. Tucker, "TensorFlow: A System for Large-Scale Machine Learning," in 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI'16), Savannah, GA, USA, 2016.
- P. M. Swamidass "MAPE (mean absolute percentage error) Mean Absolute Percentage Error (MAPE)." Encyclopedia of Production and Manufacturing Management, 462-462, 2000. DOI: 10.1007/1-4020-0612-8_580
Other issues:
Vol.12(10)(2021)
Vol.12(9)(2021)
Vol.12(8)(2021)
Archives
Call-for-Papers
Call-for-Scientific PapersCall-for-Research Papers: ITJEMAST invites you to submit high quality papers for full peer-review and possible publication in areas pertaining engineering, science, management and technology, especially interdisciplinary/cross-disciplinary/multidisciplinary subjects.
To publish your work in the next available issue, your manuscripts together with copyright transfer document signed by all authors can be submitted via email to Editor @ TuEngr.com (no space between). (please see all detail from Instructions for Authors)
Publication and peer-reviewed process:
After the peer-review process (4-10 weeks), articles will be on-line published in the available next issue. However, the International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies cannot guarantee the exact publication time as the process may take longer time, subject to peer-review approval and adjustment of the submitted articles.