Optimizing IoT Workloads for Minimal Time and Energy with UAV Networks Using Deep Q Network

The rapid growth in the use of IoT devices has highlighted significant challenges due to their limited computational power and battery life, often resulting in long task execution times and potential battery depletion. The problem we address is the inefficiency in task completion and high battery usage in IoT devices. Our key objective is to minimize time delays and energy consumption in IoT workloads. To solve this problem, we propose a partial offloading algorithm for IoT devices, utilizing Unmanned Aerial Vehicles (UAVs) due to their larger battery capacity and greater computational power. UAVs provide flexibility in task management by moving to high-demand areas. Given the battery constraints of UAVs, a network of UAVs is used to share tasks among neighboring UAVs, balancing the load. Additionally, tasks can be offloaded to a ground-based cloud server to prevent overloading the UAV network. Our main contribution is the implementation of a Deep Q Network (DQN) reinforcement learning approach to manage the dynamic nature of task distribution. We achieved a significant reduction in both time delays and energy consumption. Our results displayed approximately a 15-fold reduction in total delay and a 6-fold reduction in total energy consumption, demonstrating the effectiveness of DQNs in this task offloading scenario.