Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Risk-Aware UAV-Edge Service Framework for Wildfire Monitoring and Emergency Response

Yulun Huang, Zhiyu Wang, Rajkumar Buyya

TL;DR

The paper tackles the problem of timely wildfire monitoring via UAV-enabled edge computing under tight energy, revisit-time, and edge-capacity constraints. It introduces a joint optimization framework that co-designs fire-risk-aware clustering, QoS-aware edge provisioning, and 2-opt route planning with an adaptive fleet-sizing loop, plus a dynamic emergency rerouting mechanism. The approach yields substantial improvements over GA, PSO, and Greedy baselines in average response time, energy efficiency, and required fleet size, while ensuring emergency responses meet the 300-second deadline. The work advances practical wildfire surveillance by providing end-to-end QoS guarantees and a scalable planning strategy ready for integration with real-world fire-management systems.

Abstract

Wildfire monitoring demands timely data collection and processing for early detection and rapid response. UAV-assisted edge computing is a promising approach, but jointly minimizing end-to-end service response time while satisfying energy, revisit time, and capacity constraints remains challenging. We propose an integrated framework that co-optimizes UAV route planning, fleet sizing, and edge service provisioning for wildfire monitoring. The framework combines fire-history-weighted clustering to prioritize high-risk areas, Quality of Service (QoS)-aware edge assignment balancing proximity and computational load, 2-opt route optimization with adaptive fleet sizing, and a dynamic emergency rerouting mechanism. The key insight is that these subproblems are interdependent: clustering decisions simultaneously shape patrol efficiency and edge workloads, while capacity constraints feed back into feasible configurations. Experiments show that the proposed framework reduces average response time by 70.6--84.2%, energy consumption by 73.8--88.4%, and fleet size by 26.7--42.1% compared to GA, PSO, and greedy baselines. The emergency mechanism responds within 233 seconds, well under the 300-second deadline, with negligible impact on normal operations.

A Risk-Aware UAV-Edge Service Framework for Wildfire Monitoring and Emergency Response

TL;DR

The paper tackles the problem of timely wildfire monitoring via UAV-enabled edge computing under tight energy, revisit-time, and edge-capacity constraints. It introduces a joint optimization framework that co-designs fire-risk-aware clustering, QoS-aware edge provisioning, and 2-opt route planning with an adaptive fleet-sizing loop, plus a dynamic emergency rerouting mechanism. The approach yields substantial improvements over GA, PSO, and Greedy baselines in average response time, energy efficiency, and required fleet size, while ensuring emergency responses meet the 300-second deadline. The work advances practical wildfire surveillance by providing end-to-end QoS guarantees and a scalable planning strategy ready for integration with real-world fire-management systems.

Abstract

Wildfire monitoring demands timely data collection and processing for early detection and rapid response. UAV-assisted edge computing is a promising approach, but jointly minimizing end-to-end service response time while satisfying energy, revisit time, and capacity constraints remains challenging. We propose an integrated framework that co-optimizes UAV route planning, fleet sizing, and edge service provisioning for wildfire monitoring. The framework combines fire-history-weighted clustering to prioritize high-risk areas, Quality of Service (QoS)-aware edge assignment balancing proximity and computational load, 2-opt route optimization with adaptive fleet sizing, and a dynamic emergency rerouting mechanism. The key insight is that these subproblems are interdependent: clustering decisions simultaneously shape patrol efficiency and edge workloads, while capacity constraints feed back into feasible configurations. Experiments show that the proposed framework reduces average response time by 70.6--84.2%, energy consumption by 73.8--88.4%, and fleet size by 26.7--42.1% compared to GA, PSO, and greedy baselines. The emergency mechanism responds within 233 seconds, well under the 300-second deadline, with negligible impact on normal operations.
Paper Structure (30 sections, 2 theorems, 23 equations, 9 figures, 2 tables, 1 algorithm)

This paper contains 30 sections, 2 theorems, 23 equations, 9 figures, 2 tables, 1 algorithm.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. UAV Route Planning
  4. Edge Computing and Task Offloading
  5. UAV-Assisted Wildfire Monitoring
  6. Positioning of This Work
  7. MODELING AND PROBLEM FORMULATION
  8. Service Architecture
  9. Service Model
  10. Service Response Time Model
  11. Optimization Formulation
  12. PROPOSED SERVICE FRAMEWORK
  13. Fire-History-Weighted Clustering
  14. Edge Service Assignment
  15. Route Optimization
  16. ...and 15 more sections

Key Result

Theorem 1

Let $\mathbb{S}_H = \{s_i \in \mathbb{S}_{UAV} : h_{s_i} > 0\}$ denote sensors with fire history. Under the weighted distance metric (Eq. eq:weighted_distance), let $\bar{R}_H^{w}$ and $\bar{R}_H^{u}$ denote the average cluster radius experienced by sensors in $\mathbb{S}_H$ under weighted and stand where $\bar{w}_H = |\mathbb{S}_H|^{-1}\sum_{s_i \in \mathbb{S}_H} w_{s_i}$ is the average weight of

Figures (9)

  • Figure 1: Three-layer service architecture: sensors generate requests, UAVs relay data, and edge nodes process fire detection tasks.
  • Figure 2: Average service response time comparison with 95% confidence intervals.
  • Figure 3: Cumulative distribution function of service response times.
  • Figure 4: Total energy consumption comparison.
  • Figure 5: UAV fleet size comparison.
  • ...and 4 more figures

Theorems & Definitions (5)

  • Definition 1: Cluster Radius
  • Theorem 1: Risk-Aware Coverage Improvement
  • proof
  • Theorem 2: Emergency Response Bound
  • proof