UAV-Assisted Cluster-Based Task Allocation for Mobile Crowdsensing in a Space-Air-Ground-Sea Integrated Network

Area of Science:

• Computer Science
• Network Engineering
• Data Science

Background:

• Mobile crowdsensing (MCS) is gaining traction in space-air-ground-sea integrated networks (SAGSINs).
• Dynamic environmental conditions and variable participant capabilities in SAGSINs challenge data quality and coverage in MCS.
• Existing MCS approaches struggle with the complexities of SAGSINs.

Purpose of the Study:

• To propose a novel UAV-assisted cluster-based task allocation (UCTA) algorithm for MCS in SAGSINs.
• To address the challenges of data quality and coverage in dynamic SAGSIN environments.
• To improve the efficiency of task allocation in MCS within SAGSINs.

Main Methods:

• Introduced edge nodes and a three-layer hierarchical system (Platform-Edge Cluster-Participants) with UAV assistance.
• Developed an edge-aided attribute-based clustering algorithm to organize tasks, reducing communication and computation overhead.
• Employed a greedy selection algorithm for optimal task assignment within clusters.

Main Results:

• The proposed UCTA algorithm demonstrated superior performance compared to three benchmark algorithms.
• Significant reduction in communication overhead and computational complexity was achieved.
• Enhanced efficiency in task allocation for MCS in SAGSINs was validated through extensive simulations.

Conclusions:

• The UCTA algorithm effectively improves data quality and coverage in MCS within SAGSINs.
• The hierarchical structure and clustering approach are key to the algorithm's success.
• UCTA offers a promising solution for efficient and effective mobile crowdsensing in complex integrated networks.