Accurate load forecasting is essential for the efficient operation of the power sector, especially in a deregulated market. It aids in critical functions such as energy procurement, generation scheduling, load management, contract analysis and infrastructure planning. Various mathematical and Artificial Intelligence (AI) techniques have been developed to improve forecasting performance. This work focuses on Short-Term Load Forecasting for the Gujarat State Load Dispatch Centre, utilizing historical load demand and calendar-based input features. An Artificial Neural Network (ANN) model is employed for forecasting, trained on year 2022 of data to predict the electrical load for 1st week of January 2023. The performance of model is evaluated using standard error metrics, including Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Different validation splits of the dataset-20, 25, and 30% are tested. Among these, the model with a 25% validation ratio yields the best performance, achieving MAE of 301.770 MW and MAPE of 1.944%.