The main contents of this paper are to verify the environmental factors affecting the power generation of floating photovoltaic systems and to present the power generation prediction model considering environmental factors by using regression analysis and neural networks studied during the last decade. This study focused on a comparative analysis of which model is best suited for the power generation prediction of the floating photovoltaic (PV) system. To compare the power generation characteristics of a floating and a land-based PV system, two identical 2.5 kW PV systems were installed—one on the water surface in the Boryeong Dam, Korea, and the other nearby on dry land—and their performances were compared. The solar irradiance of the floating PV system was 1.1% lower than that of the land-based PV. Nevertheless, the floating PV module temperature was 4.9% lower than that of the land-based PV, generating approximately 3% more power. Using the correlation analysis of data mining techniques, environmental factors affecting the efficiency of the floating PV system were investigated. The correlation coefficient between the module temperature and water temperature was $r=0.6317$ which proves that the high efficiency and low module temperature characteristics of the floating PV system, when compared with that of the land-based PV, are due to the water evaporation effect. Considering environmental factors, power-generation prediction models based on regression analysis and neural networks are presented, and their accuracies are compared. This comparison confirms that the accuracy of the power generation prediction model using neural networks was approximately 2.59% higher than that of the regression analysis method. As a result of adjusting the hidden nodes in the neural network algorithm, it was confirmed that a neural network algorithm with ten hidden nodes was most suitable for calculating the amount of power generation.

Underwater grounding methods could be applied in deep water for grounding a floating PV (photovoltaic) system. However, the depth at which the electrodes should be located is a controversial subject. In this study, grounding resistance was measured for the first time by analyzing the water temperature at different water depths in an area where a floating PV system is installed. The theoretical calculation of the grounding resistance has a maximum error range of 8% compared to the experimentally measured data. In order to meet the electrical safety standards of a floating PV system, a number of electrodes were connected in parallel. In addition, the distance between electrodes and number of electrodes were considered in the test to obtain a formula for the grounding resistance. In addition, the coefficient of corrosion was obtained from an electrode installed underwater a year ago, and it was added to the formula. Through this analysis, it is possible to predict the grounding resistance prior to installing the floating PV system. Furthermore, the electrical safety of the floating PV system could be achieved by considering the seasonal changes in water temperature.

Underwater grounding methods could be applied in deep water for grounding a floating photovoltaic (PV) system. However, the depth at which electrodes should be located is a controversial subject. This paper measures grounding resistance for the first time by analyzing water temperature at different water depths in the area where a floating PV system is installed. The theoretically calculated value of the grounding resistance has a maximum error range of 8 [%] compared with the practically measured value of the grounding resistance. Through this analysis, it is possible to predict the grounding resistance prior to installing the floating PV system. Furthermore, the electrical safety of the floating PV system could be achieved by considering the seasonal changes in water temperature.