Designing Localized MPPT for PV Systems Using Fuzzy-Weighted Extreme Learning Machine
Abstract
:1. Introduction
- Fuzzy-weighted classification labeling. The concept of ‘fuzzy weight’ is introduced to improve the classification accuracy. The fuzzy weights are treated as confidence levels for the internal classifier to adjust the classification result. The overall classification accuracy reaches over 90% for both SVM and ELM methods. The high classification accuracy is an important prerequisite for the MPPT simulation.
- A novel solar irradiance classification system. Based on the concept of fuzzy weighted classification labeling, a novel solar irradiance classification system is designed. The supervised classifier (ELM or SVM) is utilized twice in the pre-processing phase and classification phase. The improved classification accuracy provides evidence to the step size of customized MPPT design.
- A customized MPPT design. The classification labels together with confidence levels provide important evidence for the customized MPPT design. Optimal step sizes are assigned to different weather types to maximize the power generation of the PV system. Simulation results justified that the overall power generation were increased by selecting the optimal perturbation size based on the classification results.
Related Works
2. Materials and Methods
2.1. Support Vector Machine (SVM)
2.2. Extreme Learning Machine (ELM)
2.3. A Novel Solar Irradiance Classification System Using Fuzzy-Weighted ELM
2.4. A Simulation Model for Customized Maximum Power Point Tracker (MPPT) Design
3. Results and Discussion
3.1. Classification Results
3.2. MPPT Simulation Results
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Liu, Y.H.; Huang, S.C.; Huang, J.W.; Liang, W.C. A Particle Swarm Optimization-Based Maximum Power Point Tracking Algorithm for PV Systems Operating Under Partially Shaded Conditions. IEEE Trans. Energy Convers. 2012, 27, 1027–1035. [Google Scholar] [CrossRef]
- Zsiborács, H.; Bai, A.; Popp, J.; Gabnai, Z.; Pályi, B.; Farkas, I.; Baranyai, N.H.; Veszelka, M.; Zentkó, L.; Pintér, G. Change of Real and Simulated Energy Production of Certain Photovoltaic Technologies in Relation to Orientation, Tilt Angle and Dual-Axis Sun-Tracking: A Case Study in Hungary. Sustainability 2018, 10, 1394. [Google Scholar] [CrossRef]
- Zsiborács, H.; Baranyai, N.H.; Vincze, A.; Háber, I.; Pintér, G. Economic and Technical Aspects of Flexible Storage Photovoltaic Systems in Europe. Energies 2018, 11, 1445. [Google Scholar] [CrossRef]
- Salas, V.; Olias, E.; Barrado, A.; Lazaro, A. Review of the maximum power point tracking algorithms for stand-alone photovoltaic systems. Sol. Energy Mater. Sol. Cells 2006, 90, 1555–1578. [Google Scholar] [CrossRef]
- Li, X.; Wen, H.; Jiang, L.; Lim, E.G.; Du, Y.; Zhao, C. Photovoltaic modified β-parameter-based mppt method with fast tracking. J. Power Electron. 2016, 16, 9–17. [Google Scholar] [CrossRef]
- Esram, T.; Chapman, P.L. Comparison of Photovoltaic Array Maximum Power Point Tracking Techniques. IEEE Trans. Energy Convers. 2007, 22, 439–449. [Google Scholar] [CrossRef] [Green Version]
- Mills, A.; Ahlstrom, M.; Brower, M.; Ellis, A.; George, R.; Hoff, T.; Kroposki, B.; Lenox, C.; Miller, N.; Stein, J.; et al. Understanding Variability and Uncertainty of Photovoltaics for Integration with the Electric Power System. Electr. J. 2010. Available online: https://pubarchive.lbl.gov/islandora/object/ir:153901/ (accessed on 30 September 2018).
- Veerapen, S.; Wen, H.; Du, Y. Design of a novel MPPT algorithm based on the two stage searching method for PV systems under partial shading. In Proceedings of the Future Energy Electronics Conference and ECCE Asia (IFEEC 2017-ECCE Asia), Kaohsiung, Taiwan, 3–7 June 2017; pp. 1494–1498. [Google Scholar]
- Zsiborács, H.; Pályi, B.; Pintér, G.; Popp, J.; Balogh, P.; Gabnai, Z.; Pető, K.; Farkas, I.; Baranyai, N.H.; Bai, A. Technical-economic study of cooled crystalline solar modules. Sol. Energy 2016, 140, 227–235. [Google Scholar] [CrossRef]
- Yan, K.; Du, Y.; Ren, Z. MPPT Perturbation Optimization of Photovoltaic Power Systems Based on Solar Irradiance Data Classification. IEEE Trans. Sustain. 2018. [Google Scholar] [CrossRef]
- Du, Y.; Li, X.; Wen, H.; Xiao, W. Perturbation optimization of maximum power point tracking of photovoltaic power systems based on practical solar irradiance data. In Proceedings of the 2015 IEEE 16th Workshop on Control and Modeling for Power Electronics (COMPEL), Vancouver, BC, Canada, 12–15 July 2015. [Google Scholar]
- Yan, K.; Ji, Z.; Lu, H.; Huang, J.; Shen, W.; Xue, Y. Fast and Accurate Classification of Time Series Data Using Extended ELM: Application in Fault Diagnosis of Air Handling Units. IEEE Trans. Syst. Man Cybern. Syst. 2017, 99, 1–8. [Google Scholar] [CrossRef]
- Pashiardis, S.; Kalogirou, S.A.; Pelengaris, A. Statistical analysis for the characterization of solar energy utilization and inter-comparison of solar radiation at two sites in Cyprus. Appl. Energy 2017, 190, 1138–1158. [Google Scholar] [CrossRef]
- Yan, K.; Ji, Z.; Shen, W. Online Fault Detection Methods for Chillers Combining Extended Kalman Filter and Recursive One-class SVM. Neurocomputing 2017, 228, 205–212. [Google Scholar] [CrossRef]
- Femia, N.; Petrone, G.; Spagnuolo, G.; Vitelli, M. A Technique for Improving P&O MPPT Performances of Double-Stage Grid-Connected Photovoltaic Systems. IEEE Trans. Ind. Electron. 2009, 56, 4473–4482. [Google Scholar]
- Xiao, W.; Dunford, W.G.; Palmer, P.R.; Capel, A. Application of Centered Differentiation and Steepest Descent to Maximum Power Point Tracking. IEEE Trans. Ind. Electron. 2007, 54, 2539–2549. [Google Scholar] [CrossRef]
- Shankar, G.; Mukherjee, V. MPP detection of a partially shaded PV array by continuous GA and hybrid PSO. Ain Shams Eng. J. 2015, 6, 471–479. [Google Scholar] [CrossRef]
- Messalti, S.; Harrag, A.; Loukriz, A. A new variable step size neural networks MPPT controller: Review, simulation and hardware implementation. Renew. Sustain. Energy Rev. 2017, 68, 221–233. [Google Scholar] [CrossRef]
- Telbany, M.E.E.; Youssef, A.; Zekry, A.A. Intelligent Techniques for MPPT Control in Photovoltaic Systems: A Comprehensive Review. In Proceedings of the 2014 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology, Kota Kinabalu, Malaysia, 3–5 December 2014. [Google Scholar]
- Ke, Y.; Wen, S.; Mulumba, T.; Afshari, A. ARX model based fault detection and diagnosis for chillers using support vector machines. Energy Build. 2014, 81, 287–295. [Google Scholar]
- Lv, Y.; Liu, J.; Yang, T.; Zeng, D. A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler. Energy 2013, 55, 319–329. [Google Scholar] [CrossRef]
- Kaytez, F.; Taplamacioglu, M.C.; Cam, E.; Hardalac, F. Forecasting electricity consumption: A comparison of regression analysis, neural networks and least squares support vector machines. Int. J. Electr. Power Energy Syst. 2015, 67, 431–438. [Google Scholar] [CrossRef]
- Suykens, J.A.K.; De Brabanter, J.; Lukas, L.; Vandewalle, J. Weighted least squares support vector machines: Robustness and sparse approximation. Neurocomputing 2002, 48, 85–105. [Google Scholar] [CrossRef]
- Huang, G.B.; Zhu, Q.Y.; Siew, D.C.K. Extreme learning machine: Theory and applications. Neurocomputing 2006, 70, 489–501. [Google Scholar] [CrossRef] [Green Version]
- Hecht-Nielsen, R. Theory of the backpropagation neural network. In Proceedings of the International 1989 Joint Conference on Neural Networks, Washington, DC, USA, 18–22 June 1989. [Google Scholar] [CrossRef]
- Gardner, M.W.; Dorling, S.R. Artificial neural networks (the multilayer perceptron)—A review of applications in the atmospheric sciences. Atmos. Environ. 1998, 32, 2627–2636. [Google Scholar] [CrossRef]
- Suykens, J.A.K.; Vandewalle, J. Least Squares Support Vector Machine Classifiers. Neural Process. Lett. 1999, 9, 293–300. [Google Scholar] [CrossRef]
- Zong, W.; Huang, G.B.; Chen, Y. Weighted extreme learning machine for imbalance learning. Neurocomputing 2013, 101, 229–242. [Google Scholar] [CrossRef]
- Localized MPPT for PV Systems Using Fuzzy-Weighted ELM. Available online: http://www.keddiyan.com/files/FuzzyWELM.html (accessed on 30 September 2018).
ELM | SVM | |
---|---|---|
Amount of testing data | 365 | 365 |
Amount of error | 20 | 28 |
Accuracy | 94.52% | 92.33% |
Extreme Learning Machine (ELM) | Support Vector Machine (SVM) | |||||
---|---|---|---|---|---|---|
Type of the weather | 1 | 0 | −1 | 1 | 0 | −1 |
Amount of testing data | 178 | 134 | 53 | 174 | 135 | 56 |
Amount error | 8 | 11 | 1 | 6 | 21 | 1 |
Accuracy | 95.51% | 91.79% | 98.11% | 95.56% | 84.44% | 98.21% |
Date | Confidence Level |
---|---|
07.29 (HSU) | 1.26 |
06.10 (UNLV) | 0.91 |
02.03 (UNLV) | 0.59 |
04.16 (HSU) | 0.35 |
11.09 (UNLV) | 0.02 |
Date | Confidence Level |
---|---|
05.20 (HSU) | 1.03 |
04.29 (HSU) | 0.76 |
09.18 (UNLV) | 0.48 |
04.10 (UNLV) | 0.24 |
09.06 (UNLV) | 0.02 |
Date (place) | MPPT 0.03 | MPPT 0.02 | MPPT 0.015 | MPPT 0.01 | MPPT 0.002 | MPPT 0.0002 | Type |
---|---|---|---|---|---|---|---|
01.21 (UNLV) | 44.62 | 45.34 | 45.28 | 45.15 | 38.88 | 37.21 | 1 |
10.04 (UNLV) | 87.69 | 90.00 | 90.34 | 90.96 | 87.59 | 85.41 | 0 |
06.08 (UNLV) | 125.21 | 129.55 | 130.39 | 132.11 | 133.06 | 130.87 | −1 |
Date | 5.2 | 4.29 | 4.10 | 9.6 | 3.18 | 11.09 | 4.16 | 8.14 | 3.2 | 5.6 | 8.22 | 7.29 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Location | HSU | HSU | UNLV | UNLV | HSU | UNLV | HSU | HSU | UNLV | HSU | HSU | HSU |
Confidence level | −1.03 | −0.76 | −0.24 | −0.02 | −0.01 | 0.02 | 0.35 | 0.81 | 0.82 | 0.94 | 1 | 1.26 |
MPPT 0.02 (kWh) | 129.6 | 128.8 | 117.9 | 107.2 | 99.7 | 65.98 | 117.1 | 99.31 | 97.29 | 120.1 | 80.81 | 115.6 |
MPPT 0.01 (kWh) | 132.1 | 131.2 | 119.5 | 108.8 | 101.2 | 67.03 | 117.9 | 99.72 | 73.98 | 118.9 | 76.84 | 110.7 |
MPPT 0.002 (kWh) | 133.1 | 131.4 | 119.6 | 109.3 | 99.9 | 65.61 | 113.5 | 98.67 | 69.96 | 110.5 | 70.86 | 100.8 |
Conclusion | −1 | −1 | −1 | −1 | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 |
Date | 9.18 | 7.31 | 7.18 |
---|---|---|---|
Confidence level | −0.48 | 0.62 | 0.83 |
MPPT 0.02 (kWh) | 103.2 | 128.6 | 91.2 |
MPPT 0.01 (kWh) | 104.9 | 129.8 | 90.2 |
MPPT 0.002 (kWh) | 105.4 | 123.4 | 86.7 |
Conclusion | −1 | 0 | 1 |
© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Du, Y.; Yan, K.; Ren, Z.; Xiao, W. Designing Localized MPPT for PV Systems Using Fuzzy-Weighted Extreme Learning Machine. Energies 2018, 11, 2615. https://doi.org/10.3390/en11102615
Du Y, Yan K, Ren Z, Xiao W. Designing Localized MPPT for PV Systems Using Fuzzy-Weighted Extreme Learning Machine. Energies. 2018; 11(10):2615. https://doi.org/10.3390/en11102615
Chicago/Turabian StyleDu, Yang, Ke Yan, Zixiao Ren, and Weidong Xiao. 2018. "Designing Localized MPPT for PV Systems Using Fuzzy-Weighted Extreme Learning Machine" Energies 11, no. 10: 2615. https://doi.org/10.3390/en11102615