Conference proceeding
Hybrid Model of Ensemble RUSBoosted Tree Optimized by Linear Programming for Photovoltaic System Efficiency Improvement under Sudden Change of Environmental Conditions
2022 IEEE 6th Conference on Energy Internet and Energy System Integration (EI2), pp 1538-1544
11 Nov 2022
Abstract
Photovoltaic (PV) farms can supply vital merits to the electrical systems economically and environmentally. Nevertheless, the variation of the PV power leads to technical challenges under partially shaded conditions (PSC). For this reason, Global maximum power point (GMPP) tracking represents a critical mechanism for power optimization uncertainty to guarantee system stability. In this study, a novel hybrid algorithm for GMPP tracking for a PV system under PSC is presented. The proposed hybrid system integrates machine learning (ML) Ensemble RUSBoosted tree (ERBT) and Metaheuristic Linear Programming (LP) to solve optimization problems under PSC with a fast response time and good convergence speed. The integration of ERBT-LP combines the benefits of the two algorithms into a single model. The presented algorithms have been tested and validated using MATLAB SIMULINK environment with very promising results.
Metrics
2 Record Views
Details
- Title
- Hybrid Model of Ensemble RUSBoosted Tree Optimized by Linear Programming for Photovoltaic System Efficiency Improvement under Sudden Change of Environmental Conditions
- Creators
- Mpho Sam Nkambule - University of JohannesburgAli N. Hasan - Higher Colleges of TechnologyAhmed Ali - University of Johannesburg
- Publication Details
- 2022 IEEE 6th Conference on Energy Internet and Energy System Integration (EI2), pp 1538-1544
- Publisher
- IEEE
- Number of pages
- 7
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Engineering Leadership and Society/Engineering Technology
- Scopus ID
- 2-s2.0-85160204976
- Other Identifier
- 991022004621504721