Deep Reinforcement Learning for Task Offloading in UAV-Aided Smart Farm Networks

TL;DR

This paper proposes a deep reinforcement learning approach to optimize task offloading for UAVs in smart farms, improving decision speed and energy efficiency in agricultural monitoring networks.

Contribution

It introduces a Deep Q-Learning method for UAV task offloading, outperforming traditional Q-Learning and heuristics in convergence speed and resource management.

Findings

DQL reaches convergence 13 times faster than Q-Learning.

The method maintains UAV battery levels effectively.

It reduces deadline violations in task processing.

Abstract

The fifth and sixth generations of wireless communication networks are enabling tools such as internet of things devices, unmanned aerial vehicles (UAVs), and artificial intelligence, to improve the agricultural landscape using a network of devices to automatically monitor farmlands. Surveying a large area requires performing a lot of image classification tasks within a specific period of time in order to prevent damage to the farm in case of an incident, such as fire or flood. UAVs have limited energy and computing power, and may not be able to perform all of the intense image classification tasks locally and within an appropriate amount of time. Hence, it is assumed that the UAVs are able to partially offload their workload to nearby multi-access edge computing devices. The UAVs need a decision-making algorithm that will decide where the tasks will be performed, while also considering the time constraints and energy level of the other UAVs in the network. In this paper, we introduce a Deep Q-Learning (DQL) approach to solve this multi-objective problem. The proposed method is compared with Q-Learning and three heuristic baselines, and the simulation results show that our proposed DQL-based method achieves comparable results when it comes to the UAVs' remaining battery levels and percentage of deadline violations. In addition, our method is able to reach convergence 13 times faster than Q-Learning.