Given the significant importance of renewable or alternative energies today, extensive research is being conducted to enhance the efficiency and reduce the costs of utilizing these energy sources. Among these studies, solar energy forecasting plays a crucial role in achieving these objectives. Accurate forecasting can optimize energy yield, improve grid management, and facilitate the integration of solar power into existing energy systems, ultimately contributing to more reliable and cost-effective renewable energy solutions. This contribution investigates how data volume influences forecasting accuracy. In particular, the impacts on forecasting accuracy of varying forecast horizons and optimal data splitting for training and testing phases are examined. Additionally, the effects on forecasting Global Horizontal Irradiance (GHI) of clustering the data into 3, 5, or 7 groups using the K-means algorithm are investigated. Five different predictive models are employed— multi layer perceptron (MLP), support vector regression (SVR), random forest (RF), convolutional neural network (CNN), and long short-term memory (LSTM)— alongside the newly proposed kResCLSTM hybrid method. Using GHI observations at an arid site in southern Algeria, it is found that a 10-year time series is optimal, along with a 60%-40% split in it for the training vs. testing periods.