Nigeria possesses significant solar energy potential, yet uncertainty in generation forecasts limits large-scale adoption. This study applies ML models to forecast solar PV output using satellite- derived meteorological data. The increasing trend of using solar photovoltaic (PV) energy as an alternative to fossil fuels has increased the demand for precise forecasting tools, particularly in developing nations such as Nigeria, where grid instability and load mismatch are prevalent. This paper examines the capability of Artificial Neural Network (ANN) models for forecasting solar PV energy in grid-connected systems in the Nigerian energy sector. Based on the historical meteorological and load demand data from 2020 to 2025, an ANN model was designed, trained, and simulated using MATLAB R2022a software. The model included essential parameters such as solar irradiance, temperature, and time variables to forecast solar power generation. The simulated values were validated against the actual output to determine the accuracy of the model using parameters such as Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The ANN model yielded a MAPE of 6.83%, an RMSE of 12.47 kW, and an R² of 0.95, indicating excellent forecasting accuracy and adaptability to the non-linear solar output variations. In addition, the study presents graphical results, such as predicted vs. actual output graphs, error distribution histograms, and regression plots, which verify the robustness of the model. These findings affirm the viability of using ANN for the forecasting of solar PV and underscore its promise to improve the energy planning, stability, and dispatch of energy in Nigeria. Moreover, the findings of this study encourage the adoption of AI-based forecasting tools to improve the energy management of Nigeria to maximize the benefits of renewable energy. This paper contributes to the existing knowledge on intelligent forecasting for smart grid applications and presents a model that can be replicated in other developing countries