Load forecasting involves estimating future electricity demand by analyzing historical data, as well as factors like weather, economic and other related variables. Various methods for estimating variables range from traditional statistical techniques to more advanced approaches, including interval analysis, regression models, and machine learning methods such as neural networks and deep learning. These methods aim to enhance prediction accuracy. This paper investigates the effectiveness of a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) hybrid model for load forecasting. The focus is on assessing how well this combined approach can predict future electricity demand compared to any other traditional forecasting methods. A day-ahead prediction is conducted using data from 1 January 2023 to 31 August 2024, to assess overall performance. The dataset is split into training and testing sets, with the training portion further subdivided, allocating 80% for training and 20% for validation. The model's performance is assessed using metrics such as mean absolute error (MAE) and mean absolute percentage error (MAPE) to evaluate its effectiveness. These metrics measure the discrepancies between the actual and predicted values.