Machine learning-based drone route planning and energy consumption optimization

With the wide application of drones in logistics, monitoring and other fields, the collaborative optimization of energy efficiency and route planning has become a key challenge. In this study, we propose a hybrid machine learning framework that integrates random forest (RF) and support vector regression (SVR) to achieve simultaneous optimization of route and energy consumption by integrating environmental factors (wind speed, terrain) and flight status data. Experimental results show that compared with the independent model, the Stacked Model reduces the Mean Square Error (MSE) of path prediction by 99.8%, the energy consumption prediction error by 73.8%, and the flight efficiency by 18%. This study provides theoretical and technical support for the sustainable application of UAVs.