Diffusion-Model-enhanced Multiobjective Optimization for Improving Forest Monitoring Efficiency in UAV-enabled Internet-of-Things

TL;DR

The paper tackles forest monitoring with UAV-enabled IoT by formulating a three-objective optimization to minimize computing delay, UAV motion energy, and computing resource. It introduces a diffusion-model-enhanced IMOGWO to solve the hybrid continuous-discrete MINLP, leveraging archive diffusion, quasi-oppositional learning, and discrete updates to improve Pareto-front quality and robustness. Across small and large network scales, IMOGWO achieves substantial reductions in motion energy and computing resource while maintaining delay, outperforming several MO heuristics and demonstrating scalability and practicality for real-world forest-monitoring deployments. The work provides a practical framework for jointly optimizing sensing, communication, and edge-computing resources in UAV-enabled IoT systems.

Abstract

The Internet-of-Things (IoT) is widely applied for forest monitoring, since the sensor nodes (SNs) in IoT network are low-cost and have computing ability to process the monitoring data. To further improve the performance of forest monitoring, uncrewed aerial vehicles (UAVs) are employed as the data processors to enhance computing capability. However, efficient forest monitoring with limited energy budget and computing resource presents a significant challenge. For this purpose, this paper formulates a multi-objective optimization framework to simultaneously consider three optimization objectives, which are minimizing the maximum computing delay, minimizing the total motion energy consumption, and minimizing the maximum computing resource, corresponding to efficient forest monitoring, energy consumption reduction, and computing resource control, respectively. Due to the hybrid solution space that consists of continuous and discrete solutions, we propose a diffusion model-enhanced improved multi-objective grey wolf optimizer (IMOGWO) to solve the formulated framework. The simulation results show that the proposed IMOGWO outperforms other benchmarks for solving the formulated framework. Specifically, for a small-scale network with $6$ UAVs and $50$ SNs, compared to the suboptimal benchmark, IMOGWO reduces the motion energy consumption and the computing resource by $53.32\%$ and $9.83\%$, respectively, while maintaining computing delay at the same level. Similarly, for a large-scale network with $8$ UAVs and $100$ SNs, IMOGWO achieves reductions of $41.81\%$ in motion energy consumption and $7.93\%$ in computing resource, with the computing delay also remaining comparable.

Figures (11)

• Figure 1: Illustration of a UAV-enabled IoT system for monitoring forests.
• Figure 2: Modified model for forest environment.
• Figure 3: Example diagram of a bi-objective optimization.
• Figure 4: An example of conversion from matrix to vector when $M=4$ and $K=5$.
• Figure 5: An example to calculate Euclidean distance from each solution to target solution in a normalized bi-objective optimization problem.