Energy and Latency-Aware Optimal Task Allocation in Edge Computing Assisted Multi-UAV System

Unmanned aerial vehicles (UAVs) have seen break-throughs for executing computationally intensive tasks generated by Internet of Things (IoT) devices due to the ease of deployment, where traditional base stations are damaged and can not execute tasks due to natural disasters. However, Aerial Edge Computing (AEC) faces significant challenges due to the limited battery capacity of the UAVs and efficient collaboration among UAVs for executing computationally intensive tasks. Existing works overlooked effective collaboration among UAVs for executing tasks while ensuring the need for efficient load distribution among UAVs. In this paper, we have developed an optimization framework for efficiently allocating computationally intensive IoT tasks in a three-stage DT-enabled multi-UAV-based network system, TUMETA, which jointly minimizes service latency and energy consumption while ensuring proper load distribution among UAVs. The experimental results demonstrate that the developed TUMETA system reduces energy consumption and latency for computationally intensive tasks compared to state-of-the-art approaches.