Battery discharge rate prediction model for mobile phone using data mining

This paper proposes an framework to create the prediction model for energy consumption of mobile phone battery using data mining, based on three usage patterns of the phone: the standby state, video playing, and web browsing. In this model, the battery discharge rate are analyzed and used for constructing the model. To predict the power used, the perception neural network and support vector machine are employed. The measurement of prediction efficiency is done by the mean absolute error (MAE) and Root mean squared error (RMSE) of the model. According to the developed model, it is found that the Support Vector Machine with the kernel function Linear based on the polynomial equation for predicting the energy consumption of mobile phone battery effective in prediction accuracy.