Energy consumption and efficiency degradation predictive analysis in unmanned aerial vehicle batteries using deep neural networks

The unmanned aerial vehicles (UAVs) needs efficient energy management to ensure optimal performance and flight time.In this paper, the energy consumption and efficiency degradation in DJI Mini 2 drone batteries by the use of a deep neural network (DNN) for predictive analysis, was concern.The research conducted repeated flights and monitoring battery discharge from 100% to 27% over 20 trials.Experimental conditions, including flight duration and environmental factors, were controlled to ensure repeatability and to minimize any external influences on the recorded data.Data were stored onto AIRDATA (drone logbook) and then recollected for new labeling.The initial flights demonstrated similar, near constant performance, while following flights showed a gradual reduction in flight time (performance degradation).To ensure comparable power usage and minimize external influences, hover mode was selected for all flights.Next, on this data the DNN was trained using the metrics of mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), coefficient of variation of the root mean squared error (CVRMSE), and determination coefficient (R).The trained model achieved the MSE of 0.352%, RMSE of 0.593%, MAE of 0.324%, MAPE of 0.857%, CVRMSE of 0.743%, and R of 0.981.The obtained results show the DNN's ability to predict future power consumption for the UAV that in turn provides insights for energy management and extension of battery life.The paper contributes to the development of sustainable UAV operations by better knowledge about battery performance for in-flight conditions.