Ship power load forecasting based on PSO-SVM

Xiaoqiang Dai; Kuicheng Sheng; Fangzhou Shu; Xiaoqiang Dai; Kuicheng Sheng; Fangzhou Shu

doi:10.3934/mbe.2022210

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 5: 4547-4567. doi: 10.3934/mbe.2022210

Previous Article Next Article

Research article Special Issues

Ship power load forecasting based on PSO-SVM

1.
School of Electronics and Information, Jiangsu University of Science and Technology, Zhenjiang 212003, China
2.
Jiangsu Institute of Automation, Lianyungang 222000, China
3.
Zhoushan Jiangke ship and marine engineering equipment R & D Center, Zhoushan 316021, China

Academic Editor: Runzhang Xu

Received: 15 December 2021 Revised: 30 January 2022 Accepted: 17 February 2022 Published: 04 March 2022

Compared with the land power grid, power capacity of ship power system is small, its power load has randomness. Ship power load forecasting is of great significance for the stability and safety of ship power system. Support vector machine (SVM) load forecasting algorithm is a common method of ship power load forecasting. In this paper, water flow velocity, wind speed and ship speed are used as the features of SVM to train the load forecasting algorithm, which strengthens the correlation between features and predicted values. At the same time, regularization parameter C and standardization parameter σ of SVM has a great influence on the prediction accuracy. Therefore, the improved particle swarm optimization algorithm is used to optimize these two parameters in real time to form a new improved particle swarm optimization support vector machine algorithm (IPSO-SVM), which reduces the load forecasting error, improves the prediction accuracy of ship power load, and improves the performance of ship energy management system.
- ship power system,
- load forecasting,
- support vector machine,
- improved particle swarm optimization support vector machine
Citation: Xiaoqiang Dai, Kuicheng Sheng, Fangzhou Shu. Ship power load forecasting based on PSO-SVM[J]. Mathematical Biosciences and Engineering, 2022, 19(5): 4547-4567. doi: 10.3934/mbe.2022210

Related Papers:

Abstract

Compared with the land power grid, power capacity of ship power system is small, its power load has randomness. Ship power load forecasting is of great significance for the stability and safety of ship power system. Support vector machine (SVM) load forecasting algorithm is a common method of ship power load forecasting. In this paper, water flow velocity, wind speed and ship speed are used as the features of SVM to train the load forecasting algorithm, which strengthens the correlation between features and predicted values. At the same time, regularization parameter C and standardization parameter σ of SVM has a great influence on the prediction accuracy. Therefore, the improved particle swarm optimization algorithm is used to optimize these two parameters in real time to form a new improved particle swarm optimization support vector machine algorithm (IPSO-SVM), which reduces the load forecasting error, improves the prediction accuracy of ship power load, and improves the performance of ship energy management system.

References

[1]	G. G. Box, G. M. Jenkins, G. C. Reinsel, Time series analysis: forecasting and control, J. Time, 31 (1976), 238–242. https://doi.org/10.1111/j.1467-9892.2009.00643.x doi: 10.1111/j.1467-9892.2009.00643.x
[2]	J. He, G. Wei, L. L. Xiong, Fuzzy improvement of linear regression analysis for load forecasting, East China Electr. Power, 11 (2003), 21–23.
[3]	C. B. Yuan, T. Zhang, J. L. Zhu, Short-term power load forecasting based on MRA and regression analysis, Inf. Technol., 10 (2007), 88–90.
[4]	Q. Li, Z. Y. Wang, Z. R. Wang, Uncertainty evaluation for the dynamic calibration of pressure transducer, J. Bei-jing Univ. Aeronaut. Astronaut., 41 (2015), 847–856. https://doi.org/10.13700/j.bh.1001-5965.2014.0356 doi: 10.13700/j.bh.1001-5965.2014.0356
[5]	S. L. Guo, Q. L. Shui, X. Y. Gu, Summary of application of gray system theory in load forecasting, Ind. Instrum. Autom., 3 (2017), 24–27.
[6]	Y. Xue, N. Zhang, H. Wu, Z. Yu, R. Li, Short-term load forecasting method for user side microgrid based on UTCI-MIC and amplitude compression grey model, Power Syst. Technol., 44 (2020), 556–563. https://doi.org/10.13335/j.1000-3673.pst.2019.1870 doi: 10.13335/j.1000-3673.pst.2019.1870
[7]	G. J. Zhang, J. J. Qiu, J. H. Li, Multi-factor short-term load forecasting based on fuzzy inference system, Autom. Electr. Power Syst., 26 (2002), 49–53.
[8]	S. K. Ha, K. B. Song, B. S. Kim, Short-term load forecasting for the holidays using fuzzy linear regression method, IEEE Trans. Power Syst., 20 (2005), 96–101. https://doi.org/10.1109/TPWRS.2004.835632 doi: 10.1109/TPWRS.2004.835632
[9]	L. Feng, J. J. Qiu, Short-term load forecasting for anomalous days based on fuzzy multi-objective genetic optimization algorithm, Proc. CSEE, 25 (2005), 29–34. https://doi.org/10.1109/PES.2006.1708902 doi: 10.1109/PES.2006.1708902
[10]	X. AI, Z. Y. Zhou, Y. P. Wei, H. Zhang, L. Li, Bidding strategy of transferable load based on autoregressive integrated moving average model, Autom. Electr. Power Syst., 41 (2017), 26–31. https://doi.org/10.7500/AEPS20170119009 doi: 10.7500/AEPS20170119009
[11]	L. L. Liu, Short-term power load forecasting based on SARI-MA and SVR, Ph.D thesis, East China University of Technology, 2018.
[12]	X. Y. Wu, J. H. He, P. Zhang, J. Hu, Power system short-term load forecasting based on improved random forest with grey relation projection, Autom. Electr. Power Syst., 39 (2015), 50–55. https://doi.org/10.7500/AEPS20140916005 doi: 10.7500/AEPS20140916005
[13]	N. T. Huang, G. B. Lu, D. G. Xu, A permutation importance-based feature selection method for short-term electricity load forecasting using random forest, Energies, 9 (2016), 767. https://doi.org/10.3390/en9100767 doi: 10.3390/en9100767
[14]	Y. C. Li, T. J. Fang, E. K. Yu, Study of support vector machine method for short-term load forecasting, Proc. CSEE, 6 (2003), 55–59. https://doi.org/10.1109/ICNC.2007.659 doi: 10.1109/ICNC.2007.659
[15]	D. F. Zhao, W. C. Pang, J. S. Zhang, X. F. Wang, Based on Bayesian theory and online learning SVM for short term load forecasting, Proc. CSEE, 25 (2005), 8–13. https://doi.org/10.1109/ICNC.2007.659 doi: 10.1109/ICNC.2007.659
[16]	D. F. Zhao, X. F. Wang, L. Zhou, T. Zhang, D. Z. Xia, Short-term load forecasting using radial basis function networks and expert system, J. Xi'an Jiaotong Univ., 4 (2001), 331–334.
[17]	H. D. Zhao, Research on intelligent power short-term load forecasting system based on fuzzy expert system, Master thesis, South China University of Technology, 2001.
[18]	L. Li, J. Wei, C. B. Li, Y. Cao, B. Fang, Prediction of load model based on artificial neural network, Trans. China Electrotech. Soc., 30 (2015), 225–230. https://doi.org/10.19595/j.cnki.1000-6753.tces.2015.08.028 doi: 10.19595/j.cnki.1000-6753.tces.2015.08.028
[19]	J. R. Zhang, Research on power load forecasting based on the improved elman neural network, Chem. Eng. Trans., 51 (2016), 589–594. https://doi.org/10.3303/CET1651099 doi: 10.3303/CET1651099
[20]	R. Hu, S. Wen, Z. Zeng, T. Huang, A short-term power load forecasting model based on the generalized regression neural network with decreasing step fruit fly optimization algorithm, Neurocomputing, 221 (2017), 24–31. https://doi.org/10.1016/j.neucom.2016.09.027 doi: 10.1016/j.neucom.2016.09.027
[21]	X. Dai, C. Yang, S. Huang, T. Yu, Y. Zhu, Finite time blow-up for wave equation with dynamic boundary condition at critical and high energy levels in control systems, Electron. Res. Arch., 28 (2020), 91–102. https://doi.org/10.3934/era.2020006 doi: 10.3934/era.2020006
[22]	X. Q. Dai, Global existence of solution for multidimensional generalized double dispersion equation, Boundary Value Probl., 1 (2019), 1–4. https://doi.org/10.1186/s13661-019-1266-1 doi: 10.1186/s13661-019-1266-1
[23]	X. Q. Dai, W. K. Li, Non-global solution for visco-elastic dynamical system with nonlinear source term in control problem, Electron. Res. Arch., 29 (2021), 4087–4098. https://doi.org/10.3934/era.2021073 doi: 10.3934/era.2021073
[24]	N. Y. Liu, F. Mu, Short-term power load forecasting based on least squares support vector machine optimized by NRS and PSO algorithm, Mod. Electr. Tech., 42 (2019), 115–118. https://doi.org/10.16652/j.issn.1004-373x.2019.07.028 doi: 10.16652/j.issn.1004-373x.2019.07.028
[25]	W. L. Gong, Short-term load forecasting based on least squares support vector machine, Master thesis, Hunan University, 2014.
[26]	X. G. Zhang, About statistical learning theory and support vector machine, J. Autom., 26 (2000), 32–42. https://doi.org/10.16383/j.aas.2000.01.005 doi: 10.16383/j.aas.2000.01.005
[27]	T. Liu, Y. Wang, W. Liu, Research on Least Squares Support Vector Machine Combinatorial Optimization Algorithm, in 2009 International Forum on Computer Science-Technology and Applications, (2009), 452–454. https://doi.org/10.1109/IFCSTA.2009.116
[28]	W. D. Chang, An improved PSO algorithm for solving nonlinear programing problems with constrained conditions, Int. J. Model. Simul. Sci. Comput., 12 (2021), 2150001. https://doi.org/10.1142/S179396232150001X doi: 10.1142/S179396232150001X
[29]	H. Yang, SVM kernel parameter optimization research and application, Master thesis, Zhejiang University, 2014.
[30]	J. Dong, Y. Zhao, C. Liu, Z. F. Han, C. S. Leung, Orthogonal least squares based center selection for fault-tolerant RBF networks, Neurocomputing, 339 (2019), 217–231. https://doi.org/10.1016/j.neucom.2019.02.039 doi: 10.1016/j.neucom.2019.02.039
[31]	Y. Bai, Kernel function-based interior-point algorithms for conic optimization, Science Press, 2010.
[32]	W. Jiang, SVM parameter optimization and application based on improved particle swarm optimization, P. D. thesis, Jiangsu University of Science and Technology, 2020.
[33]	P. W. Li, J. Zhao, Intelligent single particle optimization and particle swarm optimization fusion algorithm, Int. J. Appl. Math. Stat., 45 (2013), 395–403.
[34]	J. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
[35]	Y. Shi, R. Eberhart, Empirical study of particle swarm optimization, in International Conference on Evolutionary Computation, 3 (1999), 1945–1950. https://doi.org/10.1109/CEC.1999.785511
[36]	J. D. Tang, X. Y. Xiong, Y. W. Wu, Reactive power optimization of power system based on improved PSO algorithm, Power Autom. Equip., 7 (2004), 81–84.
[37]	J. D. C. Little, The use of storage Water in a Hydroelectric System, Oper. Res., 3 (1995), 187–197. https://doi.org/10.1287/opre.3.2.187 doi: 10.1287/opre.3.2.187
[38]	K. De Jong, An analysis of the behavior of a class of genetic adaptive systems, P. D. thesis, University of Michigan, 1975.
[39]	J. X. Hu, J. H. Zeng, Adjustment strategy of inertia weight in particle swarm optimization, Comput. Eng., 11 (2007), 193–195.
[40]	Y. Shi, R. Eberhart, A modified particle swarm optimizer, in IEEE International Congress on Evolutionary Computation Proceedings, (1998), 69–73. https://doi.org/10.1109/ICEC.1998.699146
[41]	H. Y. Liu, Y. E. Lin, J. S. Zhang, Hybrid particle swarm optimization algorithm based on chaotic search to solve premature convergence, Comput. Eng. Appl., 42 (2006), 77–79.
[42]	Z. S. Lu, Z. R. Hou, Adaptive mutation particle swarm optimization algorithm, J. Electr., 32 (2004), 416–420.
[43]	X. L. Zhang, S. H. Wen, H. N. Li, Q. Lu, M. Wu, X. Wang, Chaos particle swarm optimization algorithm based on Tent mapping and its application, China Mech. Eng., 19 (2008), 2108–2112.
[44]	J. P. He, Application of support vector machine in short-term power load forecasting, Master thesis, Three Gorges University, 2014.
[45]	D. Wang, Short-term load forecasting of power system based on improved least squares support vector machine, Master thesis, Xi'an University of Technology, 2015.
[46]	H. B. Wang, Electric propulsion ship load forecasting research, Master thesis, Jiangsu University of Science and Technology, 2013.

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)