Hybrid solar-wind street lamps have gained popularity as a more efficient alternative to stand-alone street lamps, benefiting from the availability of two renewable energy sources: solar and wind. However, the system's energy generation is directly influenced by unpredictable weather parameters, posing a challenge for consistent performance. To overcome the declared challenge and concern, this study aimed to develop a forecasting model using Artificial Neural Network (ANN) to forecast the energy generation of a hybrid solar-wind powered lamppost. The forecasting model will aid in the assessment of the future performance of the street lamp. The accuracy of the forecasting model was validated through statistical analyses, including Mean Squared Error (MSE), Rall value, and Root Mean Squared Error (RMSE). The optimal number of hidden neurons was determined by modeling networks with different quantities, and 12 hidden neurons yielded the most satisfactory results. The researchers also assessed the parameter weights and biases using the Garson’s Algorithm to provide insights into the causal relationships between inputs and outputs. Moreover, One-Sample T-test revealed a significant difference between forecasted and actual energy Generation, indicating the need for prototype upgrade and calibration. The study recommends further research in different locations and highlights the need for prototype upgrades to enhance performance