<![CDATA[The increasing demand for electrical energy in Indonesia encourages the availability of a reliable, efficient and stable power distribution system, especially in maintaining voltage quality during the transmission to distribution process. One of the main challenges in the distribution system is the occurrence of voltage drops which if not controlled can reduce energy efficiency and damage electrical equipment. In overcoming these problems, this research applies the Artificial Neural Network (ANN) method based on the backpropagation algorithm as an alternative approach in analyzing and predicting voltage drops in power distribution networks. Simulations were conducted using MATLAB R2024b software with input variables in the form of voltage, power factor, conductor length and diameter, cable type resistance, reactance, and load current. Meanwhile, the output variable analyzed is voltage drop. The simulation results show that the ANN model has a high predictive ability indicated by the Mean Square Error (MSE) value of 0.012743, Root Mean Square Error (RMSE) of 0.11289, Mean Absolute Error (MAE) of 0.033586, and Mean Absolute Percentage Error (MAPE) of 6.4292 %. This low error value indicates that the ANN is able to recognize complex patterns between input variables and provide adaptive responses to various variations in distribution system conditions so that the application of ANN using the backpropagation algorithm proves effective and efficient as a tool in supporting the technical decision-making process.]]>
Copyrights © 2025
