Optimizing Multi-UAV Deployment in 3D Space to Minimize Task Completion Time in UAV-Enabled Mobile Edge Computing Systems

Mobile Edge Computing (MEC) systems that incorporate multiple Unmanned Aerial Vehicles (UAVs) have the potential to provide efficient and cost-effective solutions for a variety of applications such as surveillance, disaster management, and emergency response. In such systems, UAVs are deployed to perform tasks such as data collection, processing, and communication, which are computationally intensive and require low-latency data transmission.

One of the key challenges in multi-UAV deployment is to optimize the deployment strategy to minimize the task completion time while considering the constraints of the system. These constraints include UAVs' limited flight time, communication range, and the need to prioritize tasks based on their importance.

To address this challenge, we propose a novel optimization algorithm that leverages machine learning techniques to predict the task completion time for different deployment strategies. The algorithm uses a Genetic Algorithm (GA) to optimize the deployment strategy by considering the predicted task completion time, UAVs' flight time, and communication range.

The proposed algorithm is evaluated through simulations in a 3D space using a realistic MEC system model. The results demonstrate that our algorithm can significantly reduce the task completion time compared to other existing deployment strategies. Moreover, our algorithm can effectively handle different constraints and priorities, making it suitable for various MEC applications.

In conclusion, our proposed algorithm provides an efficient and effective solution for optimizing multi-UAV deployment in MEC systems. It can help improve the performance and scalability of MEC systems while reducing the overall cost and time required for task completion.