Multistage symbolic optimization for predictive thermal modeling of bifacial photovoltaic systems with solar tracking in tropical climates Fabián Alonso Lara-Vargas, Carlos Vargas-Salgado, Jesús Águila-León, Carlos Sanchis-Gómez Applied Thermal Engineering, 2026 Accurate prediction of module temperature in bifacial photovoltaic (PV) systems equipped with single-axis solar tracking is critical for optimizing energy yield and mitigating thermal stress, particularly in tropical climates. However, existing empirical and data-driven approaches often lack physical interpretability or fail to adequately represent the nonlinear thermal behavior of operating PV modules. This study presents a novel multistage symbolic optimization (MSO) framework for predictive thermal modeling that addresses these limitations. The proposed two-level hierarchical approach first derives a physically interpretable symbolic equation using genetic algorithms (GA), followed by a second corrective symbolic regression stage in which GA and Alpha Evolution (AE) are evaluated as competing optimizers. This work presents a novel application of the AE algorithm to symbolic regression in PV thermal modeling. The methodology is validated using one year of high-resolution (5-min) operational data from a utility-scale bifacial PV plant with solar tracking in Colombia. The MSO–AE model achieved an R 2 of 0.9439, an RMSE of 3.18 °C, and an MAE of 2.01 °C, outperforming the MSO–GA benchmark by 7.3% in MAE and 6.5% in RMSE, and surpassing recent single-stage symbolic regression models by 3.7–20%, while preserving closed-form, interpretable expressions suitable for real-time control applications. A field-derived heating coefficient of 0.034 °C/(W/m 2 ) was identified. Observations show module temperatures exceeding 70 °C between 14:00 and 16:00, reducing electrical efficiency to 17.31%, corresponding to a 12.1% loss relative to standard test conditions. This thermal degradation resulted in average economic losses of USD 110.7 per hour during peak periods and an annual energy loss of 6738.6 MWh, equivalent to USD 336,929 at a benchmark electricity price of USD 50/MWh. These results define economic thresholds for thermal management investments in bifacial PV systems operating in tropical environments. • Solar heating coefficient of 0.034 °C/(W/m 2 ) quantified for tropical PV. • Multistage symbolic optimization achieves 0.9439 determination and 3.18 °C error. • Alpha Evolution reduces MAE by 7.3% and RMSE by 6.5% over genetic algorithms. • Interpretable equations enable real-time thermal control in embedded systems. • Thermal losses reach 6739 MWh/year with annual economic impact of $202 k–$472 k.
Optimizing Bifacial Solar Modules with Trackers: Advanced Temperature Prediction Through Symbolic Regression † Fabian Alonso Lara-Vargas, Carlos Vargas-Salgado, Jesus Águila-León, Dácil Díaz-Bello Energies, 2025 Accurate temperature prediction in bifacial photovoltaic (PV) modules is critical for optimizing solar energy systems. Conventional models face challenges to balance accuracy, interpretability, and computational efficiency. This study addresses these limitations by introducing a symbolic regression (SR) framework based on genetic algorithms to model nonlinear relationships between environmental variables and module temperature without predefined structures. High-resolution data, including solar radiation, ambient temperature, wind speed, and PV module temperature, were collected at 5 min intervals over a year from a 19.9 MW bifacial PV plant with trackers in San Marcos, Colombia. The SR model performance was compared with multiple linear regression, normal operating cell temperature (NOCT), and empirical regression models. The SR model outperformed others by achieving a root mean squared error (RMSE) of 4.05 °C, coefficient of determination (R2) of 0.91, Spearman’s rank correlation coefficient of 0.95, and mean absolute error (MAE) of 2.25 °C. Its hybrid structure combines linear ambient temperature dependencies with nonlinear trigonometric terms capturing solar radiation dynamics. The SR model effectively balances accuracy and interpretability, providing information for modeling bifacial PV systems.
Temperature Prediction for Photovoltaic Inverters Using Particle Swarm Optimization-Based Symbolic Regression: A Comparative Study Fabian Alonso Lara-Vargas, Jesus Aguila-Leon, Carlos Vargas-Salgado, Oscar J. Suarez International Journal of Advanced Computer Science and Applications, 2025 Accurate temperature modeling is crucial for maintaining the efficiency and reliability of solar inverters. This paper presents an innovative application of symbolic regression based on particle swarm optimization (PSO) for predicting the temperature of photovoltaic inverters, offering a novel approach that balances accuracy and computational efficiency. The study evaluates the performance of a PSO-based symbolic regression model compared to multiple linear regression (MLR) and a symbolic regression model based on genetic algorithms (GA). The models were developed using a dataset that included inverter temperature, active power, and DC bus voltage, collected over a year in hourly intervals from a rooftop photovoltaic system in a tropical region. The dataset was divided, with 70% used for training and the remaining 30% for testing. The symbolic regression model based on PSO demonstrated superior performance, achieving lower values of the root mean square error (RMSE) and mean absolute error (MAE) of 3.97 and 3.31, respectively. Furthermore, the PSO-based model effectively captured the nonlinear relationships between variables, outperforming the MLR model. It also exhibited greater computational efficiency, requiring fewer iterations than traditional symbolic regression approaches. These findings open new possibilities for real-time monitoring of photovoltaic inverters and suggest future research directions, such as generalizing the PSO model to different environmental conditions and inverter types.
Model of Significant Experiences for the Development of Competencies Fabian Alonso Lara Vargas, Dayan Ariadna Guzmán Bejarano, Rosa Liliana Tarazona Caceres, Carlos Vargas Salgado 16th Congreso De Tecnologia Aprendizaje Y Ensenanza De La Electronica Taee 2024, 2024 This mixed-methods approach examines the effect of a pedagogical model based on significant experience on the perceptions of capacity, motivation, and complexity among students of a Power Electronics course at a private university in the Caribbean region of Colombia. The 15 student-participants study's results revealed a 59.40% increase in capacity perception, 33.33% increase in motivation perception, and 25.56% decrease in complexity perception over a 16-week work period. These results demonstrate that the proposed model contributes to developing students' learning capabilities and, at the same time, makes course content more accessible. Therefore, this pedagogical approach promises to be effective in improving the quality of technical higher education.
Training Model for STEM-Oriented High School Students Fabian Alonso Lara Vargas, Miguel Angel Ortiz Padilla, Natali Rocio Galeano Gaviria, Carlos Vargas Salgado 16th Congreso De Tecnologia Aprendizaje Y Ensenanza De La Electronica Taee 2024, 2024 This study addresses the growing need to foster interest in technological careers among young people by implementing an innovative teaching model based on robotics. Through theoretical and practical sessions led by engineering students under the supervision of a teacher, peer tutoring, collaboration, and project-based learning were promoted for a case study in a high school institution. The knowledge assessment conducted six months after the completion of the program indicated 70% conceptual assimilation, and one year after the completion, 66% of the participants showed that the proposed model influenced their career decisions. The results suggest that the proposed robotics-based educational model is a valuable tool for inspiring young people towards STEM disciplines.
Real-Time Monitoring of Solar Photovoltaic Power Plants: A Concentrated Validation Study Fabian Alonso Lara Vargas, Jimena de la Ossa Rivera, Santiago Jaramillo Mira, Carlos Vargas Salgado, Jesus Aguila Leon, Evelyn Villabon Lopez 2024 IEEE Colombian Conference on Applications of Computational Intelligence Colcaci 2024 Proceedings, 2024 This paper presents a low-cost Internet of Things (IoT) monitoring system for rooftop solar photovoltaic (PV) power plants in response to the need for sustainable solutions. Real-time monitoring was achieved by utilizing Raspberry Pi Pico W and affordable sensors. The validation, conducted in Monteria, Colombia, demonstrated high accuracy: correlations (Panel Temperature: 0.94, Solar Radiation: 0.98, Inverter Temperature: 0.84, Ambient Temperature: 0.98, and Humidity: 0.8) and low REMC (Panel Temperature: 1.09°C, Solar Radiation: 6.12 W/m<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, Inverter Temperature: 2.71°C, Ambient Temperature: 0.83°C, and Humidity: 6.81%) compared to commercial measurement equipment. These results underscore the system’s ability to optimize the performance of solar installations, thereby promoting a more sustainable energy transition.
Methodology to Estimate the Impact of the DC to AC Power Ratio, Azimuth, and Slope on Clipping Losses of Solar Photovoltaic Inverters: Application to a PV System Located in Valencia Spain Dácil Díaz-Bello, Carlos Vargas-Salgado, Jesus Águila-León, Fabián Lara-Vargas Sustainability Switzerland, 2023 Renewable power capacity sets records annually, driven by solar photovoltaic power, which accounts for more than half of all renewable power expansion in 2021. In this sense, photovoltaic system design must be correctly defined before system installation to generate the maximum quantity of energy at the lowest possible cost. The proposed study analyses the oversizing of the solar array vs. the capacity of the solar inverter, seeking low clipping losses in the inverter. A real 4.2 kWp residential PV installation was modelled and validated using the software SAM and input data from different sources, such as a weather station for weather conditions, ESIOS for electricity rates, and FusionSolar to obtain energy data from the PV installation. Once data were validated through SAM, the DC to AC ratio was varied between 0.9 and 2.1. The azimuth and slope sensitivity analyses were performed regarding clipping inverter losses. Results have been evaluated through the energy generated and the discounted payback period, showing that, depending on the weather conditions, slope, and azimuth, among others, it is advisable to increase the DC to AC ratio to values between 1.63 and 1.87, implying low discounted payback periods of about 8 to 9 years. In addition, it was observed that inverter clipping losses significantly vary depending on the defined azimuth and slope.
Multistage symbolic optimization for predictive thermal modeling of bifacial photovoltaic systems with solar tracking in tropical climates FA Lara-Vargas, C Vargas-Salgado, J Aguila-Leon, C Sanchis-Gómez Applied Thermal Engineering, 131138 , 2026 2026
Comparative evaluation of PVGIS, PVsyst, and SAM models for predicting solar power output in equatorial tropical climates FA Lara-Vargas, MA Ortiz Padilla, A Torres Amaya, C Vargas Salgado Indonesian Journal of Electrical Engineering and Computer Science 40 (3), 1221 , 2025 2025
Experimental research on the impact of air-conditioning on solar inverter performance in PV systems under tropical conditions FA Lara-Vargas, C Vargas-Salgado, D Díaz-Bello, J Águila-León Clean Technologies and Environmental Policy, 1-15 , 2025 2025 Citations: 2
Optimización del rendimiento de plantas solares en azotea mediante monitoreo IoT de bajo costo: Un estudio de caso en Montería, Colombia1 FA Lara, J Ossa, S Jaramillo, CA Vargas Entre Ciencia e Ingeniería 19 (37), 71-78 , 2025 2025
Optimización del rendimiento de plantas solares en azotea mediante monitoreo IoT de bajo costo: Un estudio de caso en Montería, Colombia1 FA Lara, J Ossa, S Jaramillo, CA Vargas Entre Ciencia e Ingeniería 19 (37), 71-78 , 2025 2025 Citations: 1
Modelo de estrategias didácticas para el desarrollo de experiencias de aprendizaje significativas FA Lara Vargas, RL Tarazona Cáceres, C Vargas Salgado La Universidad se renueva: Modelos, competencias y fórmulas de nueva … , 2025 2025
Optimizing Bifacial Solar Modules with Trackers: Advanced Temperature Prediction Through Symbolic Regression FA Lara-Vargas, C Vargas-Salgado, J Águila-León, D Díaz-Bello Energies 18 (8), 2019 , 2025 2025 Citations: 5
Temperature Prediction for Photovoltaic Inverters Using Particle Swarm Optimization-Based Symbolic Regression: A Comparative Study. F Alonso Lara-Vargas, J Águila-León, C Vargas-Salgado, OJ Suarez International Journal of Advanced Computer Science & Applications 16 (2) , 2025 2025
Thermal analysis of bifacial photovoltaic modules with single-axis trackers in a large power plant: Modeling by symbolic equations in tropical climates FA Lara-Vargas, C Vargas-Salgado, A Chacón Encalada, ... International Journal of Renewable Energy Development 14 (6), 1160-1170 , 2025 2025 Citations: 1
Temperature Prediction for Photovoltaic Inverters Using Particle Swarm Optimization-Based Symbolic Regression: A Comparative Study FA Lara-Vargas, J Aguila-León, C Vargas-Salgado, OJ Suarez International Journal of Advanced Computer Science & Applications 16 (2) , 2025 2025 Citations: 3
Validations of HOMER and SAM tools in predicting energy flows and economic analysis for renewable systems: Comparison to a real-world system result C Vargas-Salgado, D Díaz-Bello, D Alfonso-Solar, F Lara-Vargas Sustainable Energy Technologies and Assessments 69, 103896 , 2024 2024 Citations: 27
Implementing IoT Technology for Energy Optimization in Rooftop Solar PV Plants: A Concentrated Validation Study FA Lara-Vargas, J de la Ossa-Rivera, S Jaramillo-Mira, ... Communications in Computer and Information Science, 14-26 , 2024 2024
Real-time monitoring of solar photovoltaic power plants: A concentrated validation study FAL Vargas, J de la Ossa Rivera, SJ Mira, CV Salgado, JA Leon, ... 2024 IEEE Colombian Conference on Applications of Computational Intelligence … , 2024 2024 Citations: 1
Model of Significant Experiences for the Development of Competencies FAL Vargas, DAG Bejarano, RLT Caceres, CV Salgado 2024 XVI Congreso de Tecnología, Aprendizaje y Enseñanza de la Electrónica … , 2024 2024
Training Model for STEM-Oriented High School Students FAL Vargas, MAO Padilla, NRG Gaviria, CV Salgado 2024 XVI Congreso de Tecnología, Aprendizaje y Enseñanza de la Electrónica … , 2024 2024
Experiencias significativas inspiradoras de prácticas pedagógicas innovadoras A Uribe Urzola, AK Romero Severiche, AL Malluk, A Niampira Daza, ... UPB , 2024 2024 Citations: 1
Comparative experimental analysis of the annual energy production of a 72kWn photovoltaic solar power plant installed on a roof for self-consumption in the city of Monteria … FA Lara Vargas, MÁ Ortiz Padilla, CV Salgado REVISTA COLOMBIANA DE TECNOLOGIAS DE AVANZADA 1 (43), 6 , 2024 2024 Citations: 1
Modelo de estrategias didácticas para el desarrollo de experiencias de aprendizaje significativas FAL Vargas, RLT Cáceres, CV Salgado La Universidad se renueva: modelos, competencias y fórmulas de nueva … , 2024 2024
Modelo de experiencias significativas en el desarrollo de competencias FAL Vargas, DAG Bejarano, RLT Cáceres, CV Salgado XVI Congreso de Tecnología, Aprendizaje y Enseñanza de la Electrónica: TAEE … , 2024 2024
Modelo de formación para estudiantes de secundaria con vocación STEM FAL Vargas, MÁO Padilla, NRG Gaviria, CV Salgado XVI Congreso de Tecnología, Aprendizaje y Enseñanza de la Electrónica: TAEE … , 2024 2024
MOST CITED SCHOLAR PUBLICATIONS
Methodology to estimate the impact of the DC to AC power ratio, azimuth, and slope on clipping losses of solar photovoltaic inverters: Application to a PV system located in … D Díaz-Bello, C Vargas-Salgado, J Águila-León, F Lara-Vargas Sustainability 15 (3), 2797 , 2023 2023 Citations: 38
Validations of HOMER and SAM tools in predicting energy flows and economic analysis for renewable systems: Comparison to a real-world system result C Vargas-Salgado, D Díaz-Bello, D Alfonso-Solar, F Lara-Vargas Sustainable Energy Technologies and Assessments 69, 103896 , 2024 2024 Citations: 27
Optimizing Bifacial Solar Modules with Trackers: Advanced Temperature Prediction Through Symbolic Regression FA Lara-Vargas, C Vargas-Salgado, J Águila-León, D Díaz-Bello Energies 18 (8), 2019 , 2025 2025 Citations: 5
Comparative experimental analysis of the annual energy production of a 72kWn photovoltaic solar power plant installed on a roof for self-consumption in the city of Monteria … PDCV Salgado RTCA , 2024 2024 Citations: 5
Temperature Prediction for Photovoltaic Inverters Using Particle Swarm Optimization-Based Symbolic Regression: A Comparative Study FA Lara-Vargas, J Aguila-León, C Vargas-Salgado, OJ Suarez International Journal of Advanced Computer Science & Applications 16 (2) , 2025 2025 Citations: 3
Experimental research on the impact of air-conditioning on solar inverter performance in PV systems under tropical conditions FA Lara-Vargas, C Vargas-Salgado, D Díaz-Bello, J Águila-León Clean Technologies and Environmental Policy, 1-15 , 2025 2025 Citations: 2
PROYECTOS DE IMPLEMENTACIÓN DE SISTEMAS DE EJECUCIÓN DE MANUFACTURA MES MODELO DE PLANIFICACIÓN DE ALCANCE APLICADO EN LA INDUSTRIA COLOMBIANA FA Lara Vargas, LA Esteban Villamizar, RL Tarazona Cáceres Revista Colombiana de Tecnologías de Avanzada 1 (27), 1-6 , 2015 2015 Citations: 2
Optimización del rendimiento de plantas solares en azotea mediante monitoreo IoT de bajo costo: Un estudio de caso en Montería, Colombia1 FA Lara, J Ossa, S Jaramillo, CA Vargas Entre Ciencia e Ingeniería 19 (37), 71-78 , 2025 2025 Citations: 1
Thermal analysis of bifacial photovoltaic modules with single-axis trackers in a large power plant: Modeling by symbolic equations in tropical climates FA Lara-Vargas, C Vargas-Salgado, A Chacón Encalada, ... International Journal of Renewable Energy Development 14 (6), 1160-1170 , 2025 2025 Citations: 1
Real-time monitoring of solar photovoltaic power plants: A concentrated validation study FAL Vargas, J de la Ossa Rivera, SJ Mira, CV Salgado, JA Leon, ... 2024 IEEE Colombian Conference on Applications of Computational Intelligence … , 2024 2024 Citations: 1
Experiencias significativas inspiradoras de prácticas pedagógicas innovadoras A Uribe Urzola, AK Romero Severiche, AL Malluk, A Niampira Daza, ... UPB , 2024 2024 Citations: 1
Comparative experimental analysis of the annual energy production of a 72kWn photovoltaic solar power plant installed on a roof for self-consumption in the city of Monteria … FA Lara Vargas, MÁ Ortiz Padilla, CV Salgado REVISTA COLOMBIANA DE TECNOLOGIAS DE AVANZADA 1 (43), 6 , 2024 2024 Citations: 1
Análisis experimental comparativo de la producción anual de energía de una planta solar fotovoltaica de 72kWn instalada sobre techo para autoconsumo en la ciudad de Montería … FAL Vargas, MÁO Padilla, CV Salgado Revista Colombiana de Tecnologías de Avanzada 1 (43), 51-56 , 2024 2024 Citations: 1
Deployment model for software processes in collaborative and distributed environments typical of free and open-source FLOSS communities FA Lara Vargas, LAE Villamizar Revista Ingenierías Universidad de Medellín 22 (43) , 2023 2023 Citations: 1
Modelo de planificación para la gestión de alcance de proyectos de implementación de sistemas de ejecución de manufactura. aplicación en la industria del sector de bebidas y … L Vargas, F Alonso Universidad de Pamplona–Facultad de Ingenierías y Arquitectura. , 2016 2016 Citations: 1
Multistage symbolic optimization for predictive thermal modeling of bifacial photovoltaic systems with solar tracking in tropical climates FA Lara-Vargas, C Vargas-Salgado, J Aguila-Leon, C Sanchis-Gómez Applied Thermal Engineering, 131138 , 2026 2026
Comparative evaluation of PVGIS, PVsyst, and SAM models for predicting solar power output in equatorial tropical climates FA Lara-Vargas, MA Ortiz Padilla, A Torres Amaya, C Vargas Salgado Indonesian Journal of Electrical Engineering and Computer Science 40 (3), 1221 , 2025 2025
Optimización del rendimiento de plantas solares en azotea mediante monitoreo IoT de bajo costo: Un estudio de caso en Montería, Colombia1 FA Lara, J Ossa, S Jaramillo, CA Vargas Entre Ciencia e Ingeniería 19 (37), 71-78 , 2025 2025
Modelo de estrategias didácticas para el desarrollo de experiencias de aprendizaje significativas FA Lara Vargas, RL Tarazona Cáceres, C Vargas Salgado La Universidad se renueva: Modelos, competencias y fórmulas de nueva … , 2025 2025
Temperature Prediction for Photovoltaic Inverters Using Particle Swarm Optimization-Based Symbolic Regression: A Comparative Study. F Alonso Lara-Vargas, J Águila-León, C Vargas-Salgado, OJ Suarez International Journal of Advanced Computer Science & Applications 16 (2) , 2025 2025
