Scholarlink

<p>Unmanned aerial vehicles (UAVs) serve as critical components in disaster response and emergency management systems, where real-time high-definition (HD) video transmission capabilities are essential for decision-making processes that directly impact human life preservation. However, contemporary UAV communication architectures face fundamental limitations, including constrained bandwidth allocation, elevated transmission latency, and suboptimal energy utilization efficiency. These limitations restrict operational effectiveness in time-critical emergency scenarios where immediate response is paramount. This research presents a genetic algorithm-based resource allocation framework designed to address multi-objective optimization challenges in UAV communication systems. The methodology employs evolutionary computational principles to simulate natural selection mechanisms, enabling the identification of optimal or near-optimal resource distribution solutions that balance competing performance objectives. The framework integrates two complementary algorithmic components: the Dynamic Power Optimization Task Flow Framework (DPOTFF) and the Collaborative Task Resource Scheduling (CTRS) algorithm. The DPOTFF algorithm addresses the dual optimization objective of minimizing energy consumption while simultaneously reducing task completion latency through strategic deployment optimization. Meanwhile, the CTRS algorithm tackles stochastic optimization problems by decomposing them into deterministic subproblems, thereby enhancing computational stability and solution convergence efficiency. Experimental validation was conducted using standardized UAV HD video datasets to evaluate system performance across multiple metrics. Results demonstrate that the proposed framework achieves a classification accuracy of 92%, a recall rate of 91%, and an F1-score of 0.91. Comparative analysis with baseline methodologies reveals significant performance improvements, including latency reduction of up to 60% and energy efficiency enhancement of 30%.These findings indicate that genetic algorithm-based resource allocation can substantially improve UAV communication performance in emergency response scenarios, potentially enhancing the effectiveness of disaster management operations where real-time video transmission is critical for coordinating rescue efforts and assessing situational dynamics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimized 5G-enabled UAV video transmission for emergency management: a multi-objective resource allocation framework using genetic algorithms and dynamic power optimization

  • 期刊论文

  • 发表日期：

    2026年1月7日

查看全文
  • Jiang Hu,
  • Bo Su,
  • Amuthakkannan Rajakannu

摘要

Unmanned aerial vehicles (UAVs) serve as critical components in disaster response and emergency management systems, where real-time high-definition (HD) video transmission capabilities are essential for decision-making processes that directly impact human life preservation. However, contemporary UAV communication architectures face fundamental limitations, including constrained bandwidth allocation, elevated transmission latency, and suboptimal energy utilization efficiency. These limitations restrict operational effectiveness in time-critical emergency scenarios where immediate response is paramount. This research presents a genetic algorithm-based resource allocation framework designed to address multi-objective optimization challenges in UAV communication systems. The methodology employs evolutionary computational principles to simulate natural selection mechanisms, enabling the identification of optimal or near-optimal resource distribution solutions that balance competing performance objectives. The framework integrates two complementary algorithmic components: the Dynamic Power Optimization Task Flow Framework (DPOTFF) and the Collaborative Task Resource Scheduling (CTRS) algorithm. The DPOTFF algorithm addresses the dual optimization objective of minimizing energy consumption while simultaneously reducing task completion latency through strategic deployment optimization. Meanwhile, the CTRS algorithm tackles stochastic optimization problems by decomposing them into deterministic subproblems, thereby enhancing computational stability and solution convergence efficiency. Experimental validation was conducted using standardized UAV HD video datasets to evaluate system performance across multiple metrics. Results demonstrate that the proposed framework achieves a classification accuracy of 92%, a recall rate of 91%, and an F1-score of 0.91. Comparative analysis with baseline methodologies reveals significant performance improvements, including latency reduction of up to 60% and energy efficiency enhancement of 30%.These findings indicate that genetic algorithm-based resource allocation can substantially improve UAV communication performance in emergency response scenarios, potentially enhancing the effectiveness of disaster management operations where real-time video transmission is critical for coordinating rescue efforts and assessing situational dynamics.