Photovoltaic power generation prediction and optimization configuration model based on GPR and improved PSO algorithm
DOI:
https://doi.org/10.4108/ew.3809Keywords:
photovoltaics, power prediction, Multi Objective Optimization, PSO Algorithm, Gaussian Process, Optimize ConfigurationAbstract
As the growing demand for energy as well as the strengthening of environmental awareness, photovoltaic power generation, as a clean and renewable energy source, has gradually attracted people's attention and attention. To facilitate the dispatching and planning of power system, this study uses historical data and meteorological data to build a photovoltaic power generation prediction and configuration optimization model on the ground of Gaussian process regression and improved particle swarm optimization algorithm. The simulation results show that the regression prediction curve of the Gaussian process regression prediction model is the closest to the real curve, and the prediction curve is stable and not easily disturbed by noise data. The Root-mean-square deviation and the average absolute proportional error of the model are small, and the disparity in the predicted value and the true value of the model is small; The integration of multi factor data has improved the accuracy of prediction data, and the regression prediction effect is good. The improved Particle swarm optimization algorithm could continuously enhance in the search for the optimal solution, and the Rate of convergence is fast. The Pareto solution can provide different solutions suitable for photovoltaic power generation optimization. Reasonable optimization configuration can effectively reduce active power line loss and voltage deviation, with the maximum reduction values reaching 132kW and 0.028, respectively. The research and design of predictive models and optimized configuration models can promote the formation of smart grids.
Downloads
References
Abdul R, Naila N, Muhammad I, Madad A. The currentdevelopments and future prospects of solar photovoltaicindustry in an emerging economy of India. Environmentalscience and pollution research international,2023,30(16):46270-46281. DOI: https://doi.org/10.1007/s11356-023-25471-1
Guo N. The impact of energy industry structureadjustment on digital media application technology. EnergyReports, 2022, 8(S4): 1463-1471. DOI: https://doi.org/10.1016/j.egyr.2022.02.042
Hui S, Al N K, Ammar K, Samaneh Sadat S, Ali MoradiA, Mahdi J, Xinghuo Y, Peter M. Multitasking recurrentneural network for photovoltaic power generation prediction.Energy Reports, 2023, 9(S3): 369-376.
Bashir U T, Fuwen Y, M. S A M, Junwei L. Solarphotovoltaic power forecasting for microgrid energymanagement system using an ensemble forecasting strategy.Energy Sources, Part A: Recovery, Utilization, andEnvironmental Effects, 2022, 44(4): 10045-10070. DOI: https://doi.org/10.1080/15567036.2022.2143945
Xinyu Z, Yanshuang A, Xinlu W, Xifeng G, Wei D.Learning with privileged information for short-termphotovoltaic power forecasting using stochasticconfiguration network. Information Sciences,2023,619(1):838-848. DOI: https://doi.org/10.1016/j.ins.2022.11.046
Chen B, Lin P, Lai Y, Wu L. Very-short-term powerprediction for PV power plants using a simple and effectiveRCC-LSTM model based on short term multivariatehistorical datasets. Electronics, 2020, 9(2): 289-308. DOI: https://doi.org/10.3390/electronics9020289
Malik P, Chandel R, Chandel S S. A power predictionmodel and its validation for a roof top photovoltaic powerplant considering module degradation. Solar Energy, 2021,224(1): 184-194. DOI: https://doi.org/10.1016/j.solener.2021.06.015
Kim D, Kwon D, Park L, Kim J, Cho S. MultiscaleLSTM-based deep learning for very-short-term photovoltaicpower generation forecasting in smart city energymanagement. IEEE Systems Journal, 2020, 15(1): 346-354. DOI: https://doi.org/10.1109/JSYST.2020.3007184
Lee D, Kim K. PV power prediction in a peak zoneusing recurrent neural networks in the absence of futuremeteorological information. Renewable Energy, 2021,173(1): 1098-1110. DOI: https://doi.org/10.1016/j.renene.2020.12.021
Aprillia H, Yang H T, Huang C M. Short-termphotovoltaic power forecasting using a convolutional neuralnetwork–salp swarm algorithm. Energies, 2020, 13(8):1879-1899. DOI: https://doi.org/10.3390/en13081879
Yan J, Hu L, Zhen Z, Wang F, Qiu G, Li Y, zhong YaoL, Shafie-khah M, Catalão J. Frequency-domaindecomposition and deep learning based solar PV powerultra-short-term forecasting model. IEEE Transactions onIndustry Applications, 2021, 57(4): 3282-3295. DOI: https://doi.org/10.1109/TIA.2021.3073652
AlShafeey M, Csáki C. Evaluating neural network andlinear regression photovoltaic power forecasting modelsbased on different input methods. Energy Reports, 2021, 7:7601-7614. DOI: https://doi.org/10.1016/j.egyr.2021.10.125
Hao Y, Dong L, Liang J, et al. Power forecasting-basedcoordination dispatch of PV power generation and electricvehicles charging in microgrid. Renewable Energy, 2020,155: 1191-1210. DOI: https://doi.org/10.1016/j.renene.2020.03.169
Yan M, Guo W, Hu Y, Xu F, Chen J, Du Q, Qin T.Improved hybrid sparrow search algorithm for an extremelearning machine neural network for short‐termphotovoltaic power prediction in 5G energy‐routing basestations. IET Renewable Power Generation, 2023, 17(2):336-348. DOI: https://doi.org/10.1049/rpg2.12600
Song H, Al Khafaf N, Kamoona A, Sajjadi S S, AmaniA M, Jalili M, McTaggart P. Multitasking recurrent neuralnetwork for photovoltaic power generation prediction.Energy Reports, 2023, 9(5): 369-376. DOI: https://doi.org/10.1016/j.egyr.2023.01.008
Wang S, Zhu H, Zhang S. Two-stage grid-connectedfrequency regulation control strategy based on photovoltaicpower prediction. Sustainability, 2023, 15(11): 8929-8949. DOI: https://doi.org/10.3390/su15118929
Yang X, Zhao Z, Peng Y, Ma J. Research on distributedphotovoltaic power prediction based on spatiotemporalinformation ensemble method. Journal of Renewable andSustainable Energy, 2023, 15(3): 36102-36118. DOI: https://doi.org/10.1063/5.0150186
Chen G, Zhang T, Qu W, Wang W. Photovoltaic PowerPrediction Based on VMD-BRNN-TSP. Mathematics, 2023,11(4): 1033-1046. DOI: https://doi.org/10.3390/math11041033
Wang Z , Zhang J , Jiang D, Liu F, Hao L. Predictivemodelling for contact angle of liquid metals and oxideceramics by comparing Gaussian process regression withother machine learning methods. CERAMICSINTERNATIONAL, 2022,48(1): 665-673. DOI: https://doi.org/10.1016/j.ceramint.2021.09.146
Zhao X, Zhang D, Zhang R, Xu B. A comparativestudy of Gaussian process regression with other threemachine learning approaches in the performance predictionof centrifugal pump. Proceedings of the Institution ofMechanical Engineers, Part C: Journal of MechanicalEngineering Science, 2022, 236(8): 3938-3949. DOI: https://doi.org/10.1177/09544062211050542
Barma M, Modibbo U M. Multiobjective mathematicaloptimization model for municipal solid waste managementwith economic analysis of reuse/recycling recovered wastematerials. Journal of Computational and CognitiveEngineering, 2022, 1(3): 122-137. DOI: https://doi.org/10.47852/bonviewJCCE149145
Libotte G B, Lobato F S, Moura Neto F D, Platt G M.A Novel Reliability-Based Robust Design MultiobjectiveOptimization Formulation Applied in Chemical Engineering.Industrial & Engineering Chemistry Research, 2022, 61(9):3483-3501. DOI: https://doi.org/10.1021/acs.iecr.1c04635
Liu Y, Yang Y. An extended VIKOR method based onparticle swarm optimization and novel operations ofprobabilistic linguistic term sets for multicriteria groupdecision‐making problem. International journal of intelligentsystems, 2022, 37(8): 5381-5424. DOI: https://doi.org/10.1002/int.22796
Mao L , Zhao J , Zhu Y ,Chen J .A noise‐immunemodel identification method for lithium‐ion battery usingtwo‐swarm cooperative particle swarm optimizationalgorithm based on adaptive dynamic sliding window.International Journal of Energy Research, 2022, 46(3):3512-3528. DOI: https://doi.org/10.1002/er.7401
Xia G, Chen J, Tang X, Zhao L, Sun B. Shift qualityoptimization control of power shift transmission based onparticle swarm optimization–genetic algorithm. Proceedingsof the Institution of Mechanical Engineers, Part D: Journalof Automobile Engineering, 2022, 236(5): 872-892. DOI: https://doi.org/10.1177/09544070211031132
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 EAI Endorsed Transactions on Energy Web
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 3.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
