Photovoltaic (PV) system installations have increased in recent years partly due to growing energy needs from a rising population. Such PV systems producing electricity contribute in promoting green energy. However, solar energy is highly intermittent and uncontrollable due to its high spatial and temporal variations of atmospheric conditions. With such variability, PV power forecasting is therefore crucial for full integration of solar energy into the grid. In this study, Support Vector Regression (SVR) and Random Forest Regression (RFR) models were built and used to forecast real-time PV power output of a 1.5kW solar PV system installed at the Department of Physics, University of Nairobi in Kenya. SVR model outperforms RFR model with root mean square (RMSE) of 43.16 adjusted R2 of 0.97 and mean absolute error (MAE) of 32.57 on the validation. Dataset compared to RMSE of 86, adjusted R2 of 0.90, MAE of 69 were obtained for RFR model. A real time power forecast application based on the SVR model was successfully built using the Shiny application in R software. This shows that SVR model is more robust than RFR and has capabilities of reducing errors during computations.

Photovoltaic Solar systems have become attractive for powering autonomous systems and various devices. So far, the installation and usage of solar photovoltaic systems has been limited to either land or space. Lately, underwater solar photovoltaic power generation has attracted interest due to some of its unique application in powering underwater devices. The thermal control and cooling that result makes it more dependable for underwater devices. Around the equator, and some other parts of the world, some regions can be quite hot compromising a panel performance. A systematic study on the performance of stationary under water panel using normal tap water would provide information on the applicability of underwater panels in such places. In this work, a detailed study was carried out to determine the performance of 20W monocrystalline photovoltaic solar panels locally acquired and placed at various water depths. A locally purchased plastic translucent water tank was filled with normal tap water and the panels placed in the water at various depths. Solar irradiance, ambient and panel temperature were obtained using a solar 02 device and an irradiance power meter which were connected to a solar current-voltage (I-V) analyzer. Data was collected at 30-minute intervals between 11:00 a.m. and 3:00 p.m. East African Time (EAT) for panels at different depths up to 0.6m. The results revealed that as the water depth increased form 0 m to 0.6m, the panel temperature reduced by 15.48% (at a rate of 0.062 °C/cm), ambient temperature decreased by 5.13%, solar irradiance decreased by 63.79% while power output decreased by 75.00 %. It was noted that the submerged photovoltaic panels reduced the cleaning problem and power loss caused by high temperature. However, positioning the panels deep reduces the power production due to decreased irradiance which has a strong effect on the photocurrent and hence the power production of the panel. It is therefore advisable to keep the panels just below the water surface to maximize power production. The set up can be applied in very hot places for better power production.