Şaban Fındık
Şaban Fındık has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Salih Ermiş
Kirsehir Ahi Evran Universitesi
1 shared publication
Latest Publications
- 23 July 2025
- Published by Turk Tarim ve Doga Bilimleri Dergisi in Türk Tarım ve Doğa Bilimleri Dergisi
- Vol. 12 (3) , 653-665
Forecasting the Power Output of Photovoltaic Systems Using Ant Colony Optimization and Determining the Optimal Time Interval for Agricultural Use
The rapid increase in global energy demand, driven by industrialization, population growth, and technological advances, has emphasized the importance of the transition to renewable energy sources. In addition, renewable energy, especially photovoltaic (PV) systems, has become a widespread energy source in agricultural applications to meet the energy needs in agricultural irrigation. However, the efficiency of PV systems varies depending on meteorological and environmental factors such as solar radiation and temperature. Therefore, predictability of energy production is a critical requirement for the effective operation of irrigation systems. In this study, the Ant Colony Optimization (ACO) algorithm is implemented to estimate the power output of PV systems using historical solar radiation, temperature, and actual power production data. Inspired by the foraging behavior of ants, the ACO algorithm optimizes the estimation process by iteratively refining the solutions based on pheromone trails and adaptive learning. The proposed method is evaluated using a case study on a solar power plant located in the Central Anatolian region of Türkiye. The accuracy of the model is evaluated by comparing the predicted values with the actual measurements at various time periods including hourly, daily, weekly, monthly and seasonal forecasts. The results show that the ACO based forecast model provides high accuracy in predicting the PV power output, with the Mean Absolute Percentage Error (MAPE) values improving as the forecast period increases. The findings of this study suggest that ACO is a robust and efficient optimization technique to improve PV power forecasting. The proposed model provides strategic information that can be used in energy planning of agricultural irrigation systems with high accuracy.
- 23 July 2025
- Published by Turk Tarim ve Doga Bilimleri Dergisi in Türk Tarım ve Doğa Bilimleri Dergisi
- Vol. 12 (3) , 653-665
Forecasting the Power Output of Photovoltaic Systems Using Ant Colony Optimization and Determining the Optimal Time Interval for Agricultural Use
The rapid increase in global energy demand, driven by industrialization, population growth, and technological advances, has emphasized the importance of the transition to renewable energy sources. In addition, renewable energy, especially photovoltaic (PV) systems, has become a widespread energy source in agricultural applications to meet the energy needs in agricultural irrigation. However, the efficiency of PV systems varies depending on meteorological and environmental factors such as solar radiation and temperature. Therefore, predictability of energy production is a critical requirement for the effective operation of irrigation systems. In this study, the Ant Colony Optimization (ACO) algorithm is implemented to estimate the power output of PV systems using historical solar radiation, temperature, and actual power production data. Inspired by the foraging behavior of ants, the ACO algorithm optimizes the estimation process by iteratively refining the solutions based on pheromone trails and adaptive learning. The proposed method is evaluated using a case study on a solar power plant located in the Central Anatolian region of Türkiye. The accuracy of the model is evaluated by comparing the predicted values with the actual measurements at various time periods including hourly, daily, weekly, monthly and seasonal forecasts. The results show that the ACO based forecast model provides high accuracy in predicting the PV power output, with the Mean Absolute Percentage Error (MAPE) values improving as the forecast period increases. The findings of this study suggest that ACO is a robust and efficient optimization technique to improve PV power forecasting. The proposed model provides strategic information that can be used in energy planning of agricultural irrigation systems with high accuracy.