THERMAL SCIENCE

International Scientific Journal

COST PREDICTION ON FABRICATED SUBSTATION CONSIDERING SUPPORT VECTOR MACHINE VIA OPTIMIZED QUANTUM PARTICLE SWARM OPTIMIZATION

ABSTRACT
At present, the prediction of the life cycle cost of fabricated substation is of great significance for the construction of fabricated substation. An enhanced prediction model based on quantum particle swarm optimization (QPSO) via least squares support vector machine is established. The relevant characteristic index of the life cycle of the fabricated substation is used as the input of the model, and the output is the life cycle cost. The simulation results are compared with the prediction results of QPSO optimized least squares support vector machine (LS-SVM), PSO optimized LS-SVM, traditional LS-SVM, and backpropagation neural network, which shows that the QPSO optimized LS-SVM model has better prediction accuracy, can predict and evaluate the life cycle cost more quickly, and can improve the benefits of fabricated substation construction.
KEYWORDS
PAPER SUBMITTED: 2019-08-29
PAPER REVISED: 2019-11-20
PAPER ACCEPTED: 2019-12-06
PUBLISHED ONLINE: 2020-01-19
DOI REFERENCE: https://doi.org/10.2298/TSCI190829010X
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2020, VOLUME 24, ISSUE Issue 5, PAGES [2773 - 2780]
REFERENCES
  1. Hu, X., Research on Cost Management of Fabricated Substation Project Based on Life Cycle Theory, (in Chinese), Ph. D., thesis, Beijing: North China Electric Power University, Beijing, 2015
  2. Morozumi, A., et al., Reliability of Power Cycling for IGBT Power Semiconductor Modules, IEEE Transactions on Industry Applications, 39 (2003), 3, pp. 665-671
  3. Tan, E., et al., Cloud Model Improves Firefly Algorithm Optimization for Analog Circuit Fault Diagnosis, Electrical measurement and instrumentation, (2016), 9, pp. 45-49
  4. Jiang, H., et al., Ant Colony Optimization Least Squares Support Vector Machine Application in Measurement Data Fitting, Nuclear power engineering, 39 (2018), 6, pp. 24-31
  5. Cheng, M.-Y., et al., Hybrid Intelligence Approach Based on LS-SVM and Differential Evolution for Construction Cost Index Estimation: A Taiwan case study, Automation in Construction, (2013), 35, pp. 306-313
  6. Yi, G., Yang, Y., Crack Image Detection Based on LS-SVM Optimized by PSO, IEEE: Proceedings of the 32nd Chinese Control Conference, (2013), 10, pp. 45-50
  7. Morozumi, A, et al., Reliability of Power Cycling for IGBT Power Semiconductor Modules, IEEE Transactions on Industry Applications, 39 (2003), 3, pp. 665-671
  8. Zhou, C., et al., Multi Objective Coordination Optimization of Microgrid Based on Model Predictive Control (in Chinese), Electrical Measurement & Instrumentation, 56 (2019), 22, pp. 44-50
  9. Chen, J., et al., A New Short-Term Load Forecasting Based on XGBoost Algorithm (in Chinese), Electrical Measurement & Instrumentation, 56 (2019), 21, pp. 23-29
  10. Cheng, Y., Short-Term Prediction of Wind Power Based on Improved TLBO Optimization LSSVM (in Chinese), Electrical Measurement & Instrumentation, 56 (2019), 13
  11. Gong, Y., Teng, H., Short-Term Load Forecasting Based on GOA-SVM (in Chinese), Electrical Measurement & Instrumentation, 56 (2019), 14, pp. 12-16
  12. Bayerer, R., et al., Model for Power Cycling lifetime of IGBT Modules - Various Factors Influencing Lifetime, Proceedings, 5th International Conference on Integrated Power Systems, London, 2008
  13. Dong, G., Xiong, Y., The Research on the Electric Vehicle Charging Load Forecasting Based on the Response Behavior of Uncertainty, Electrical Measurement & Instrumentation, 55 (2018), 20
  14. Kovačević, I. F., et al., New Physical Model for Lifetime Estimation of Power Modules, Proceedings, IEEE International Power Electronics Conference, Singapour, 2010

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence