Development of a Battery Life Cycle Predictor Using Edge Impulse


  • Mohammad Azizi Mizan UTHM
  • Khairul Anuar Mohamad
  • Afishah Alias


Lithium-ion battery, life cycle, aging, prediction, discharge voltage, Edge Impulse, regression


Lithium ion batteries are the ideal choice for energy storage systems due to aspects such as high energy density, long cycle life, and environmental friendliness. But, the battery is subject to aging which it can lose capacity and frequently fail after a number of years. The accurate prediction of battery life has an important effect on the safe and reliable operation of the equipment. This paper proposed a prediction system of a life cycle of lithium-ion battery (li-ion) using an Edge Impulse machine learning. A set of discharge voltage data was obtained when the li-ion battery was connected to a load to predict the life cycle of the battery. The dataset was analyzed using regression block in the Edge Impulse to predict the battery life cycle. The training and testing result from the Edge Impulse showed the prediction after 1000 cycles of discharge and charging process. The accuracy for the datasets after training and testing is 95.83%. The deployment to the Arduino Nano 33 BLE sense also produce prediction result, comparison with the result using Edge Impulse shows that the result is similar.




How to Cite

Mizan, M. A., Mohamad, K. A. ., & Alias, A. (2022). Development of a Battery Life Cycle Predictor Using Edge Impulse. Evolution in Electrical and Electronic Engineering, 3(2), 418–424. Retrieved from



Electrical and Power Electronics

Most read articles by the same author(s)