Akademik Veri Yönetim Sistemi
IJANSER, cilt.9, sa.12, ss.599-605, 2025 (Hakemli Dergi)
Natural gas consumption is a continuous process that requires an exact supply to prevent interruptions in domestic use, particularly under harsh climatic conditions. This study is presentedto forecast natural gas consumption in Hakkari Province using the Multiple Linear Regression (MLR) and Artificial Neural Network (ANN)modelsfor the first 9 months of 2023. Training data consisted of relative humidity, sunshine duration, temperature, solar intensity, radiation, and subscriber numbers for the 2020-2022 period. The consumption was selected as the dependentoutputparameter, whiletheother parameters were independentinputvariables. Data analysis and training were performed using Python in the Visual Studio Code (VSCode) environment.Data processing was conductedusing the Min-Max normalization method to ensure data consistency, and the 10-fold cross-validation technique was applied.A fully connected feed-forward neural network was usedin the ANN model, whichconsisted of three hidden layers containing 32, 16, and 8 neurons.LeakyReLU was preferred as the activation function in the hidden layers to providenon-linearity, while a linear activation function was implementedin the output layer for regression.The Adaptive Moment Estimation (Adam) algorithm was selected as the optimizer to update the network weights and minimize the loss function more efficiently. The R square,RMSE and MAE values were found as 0.755,0.128, 0.104for the MLR model, and 0.943,0.06, 0.034for the ANN model, respectively.The results indicatethat the ANN model showed betterperformancein terms of forecasting compared to the MLR model.