Evaluating the Performance of LSTM in Photovoltaic Energy Optimization using Sunshine Duration Prediction

Abstrak

Sunshine duration is a critical meteorological parameter with significant applications in climate studies, agriculture, and renewable energy, particularly solar energy systems. Accurate prediction of sunshine duration is crucial for optimizing solar energy utilization and addressing gaps in regions with limited radiation data. This study evaluates the performance of Long Short-Term Memory (LSTM), a deep learning model known for its ability to handle time series data, in predicting sunshine duration. The research utilizes a dataset comprising sunshine duration and related meteorological parameters, including temperature, humidity, wind speed, and precipitation. Initial correlation analysis using Spearman’s method identifies temperature and humidity as the most influential factors associated with sunshine duration. Three prediction models are developed by varying the input parameters, and their performances are evaluated using metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Pearson correlation coefficient. The best model, incorporating all meteorological parameters, achieves an RMSE of 1.02, MAE of 0.77, and Pearson correlation of 0.84, demonstrating the robustness of LSTM in capturing nonlinear relationships in complex datasets. These results underline the potential of LSTM as a reliable tool for sunshine duration prediction and provide insights into its applicability in solar energy planning and other meteorological studies.

Kata kunci

• Deep Learning
• Prediction
• renewable energy