Next Day Power Forecast Model Using Smart Hybrid Energy Monitoring System and Meteorological Data

The increase in contribution of renewable energy sources into the grid is part of smart grid initiatives. The integration of renewables such as solar energy into the electrical network is a challenge for grid operators because of its intermittency due to weather variations. Despite this, the installed capacity of solar PV globally continues to increase. Thus, forecasting is becoming an important tool for system grid operators to manage solar photovoltaic (PV) energy production and satisfy the demand of energy consumers. This work aims to develop a forecasting model for solar irradiance that can be used in calculating next-day energy generation of solar PV systems. Site-specific solar irradiance and meteorological parameters were used as inputs to a machine learning algorithm. It is shown that the prediction model fits the measured data with a value of R2 equal to 85.89%. This model was validated through the measured data of power generation from a hybrid connected solar PV system, installed in Quezon City, Philippines.