Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-hop Differential Topology based Algorithms for Resilient Network of UAV Swarm

Huan Lin, Lianghui Ding

TL;DR

This work tackles connectivity restoration in UAV swarms after massive damage (CNS) by introducing multi-hop differential sub-graphs (MDSG) to encode local damage information. It presents two complementary recovery paradigms: a lightweight MDSG-APF method for low-computation swarms and a high-capacity MDSG-GC framework with a novel bipartite graph convolution and batch processing for advanced swarms. The authors prove convergence and derive recovery-time bounds for APF, and develop a batch-enabled GCN approach with a joint loss and GradNorm, showing substantial reductions in recovery time, improved spatial coverage, and more uniform degree distributions in simulations. The proposed MDSG-based strategies offer scalable, topology-aware resilience for USNETs in hostile environments, with practical implications for rapid, robust UAV swarm reconfiguration.

Abstract

Unmanned aerial vehicle (UAV) swarm networks face severe challenges of communication network split (CNS) issues caused by massive damage in hostile environments. In this paper, we propose a new paradigm to restore network connectivity by repositioning remaining UAVs based on damage information within local topologies. Particularly, the locations of destroyed UAVs distributed in gaps between disconnected sub-nets are considered for recovery trajectory planning. Specifically, we construct the multi-hop differential sub-graph (MDSG) to represent local damage-varying topologies. Based on this, we develop two distinct algorithms to address CNS issues. The first approach leverages an artificial potential field algorithm to calculate the recovery velocities via MDSG, enabling simple deployment on low-intelligence UAVs. In the second approach, we design an MDSG-based graph convolution framework to find the recovery topology for high-intelligence swarms. As per the unique topology of MDSG, we propose a novel bipartite graph convolution operation, enhanced with a batch-processing mechanism to improve graph convolution efficiency. Simulation results show that the proposed algorithms expedite the recovery with significant margin while improving the spatial coverage and topology degree uniformity after recovery.

Multi-hop Differential Topology based Algorithms for Resilient Network of UAV Swarm

TL;DR

This work tackles connectivity restoration in UAV swarms after massive damage (CNS) by introducing multi-hop differential sub-graphs (MDSG) to encode local damage information. It presents two complementary recovery paradigms: a lightweight MDSG-APF method for low-computation swarms and a high-capacity MDSG-GC framework with a novel bipartite graph convolution and batch processing for advanced swarms. The authors prove convergence and derive recovery-time bounds for APF, and develop a batch-enabled GCN approach with a joint loss and GradNorm, showing substantial reductions in recovery time, improved spatial coverage, and more uniform degree distributions in simulations. The proposed MDSG-based strategies offer scalable, topology-aware resilience for USNETs in hostile environments, with practical implications for rapid, robust UAV swarm reconfiguration.

Abstract

Unmanned aerial vehicle (UAV) swarm networks face severe challenges of communication network split (CNS) issues caused by massive damage in hostile environments. In this paper, we propose a new paradigm to restore network connectivity by repositioning remaining UAVs based on damage information within local topologies. Particularly, the locations of destroyed UAVs distributed in gaps between disconnected sub-nets are considered for recovery trajectory planning. Specifically, we construct the multi-hop differential sub-graph (MDSG) to represent local damage-varying topologies. Based on this, we develop two distinct algorithms to address CNS issues. The first approach leverages an artificial potential field algorithm to calculate the recovery velocities via MDSG, enabling simple deployment on low-intelligence UAVs. In the second approach, we design an MDSG-based graph convolution framework to find the recovery topology for high-intelligence swarms. As per the unique topology of MDSG, we propose a novel bipartite graph convolution operation, enhanced with a batch-processing mechanism to improve graph convolution efficiency. Simulation results show that the proposed algorithms expedite the recovery with significant margin while improving the spatial coverage and topology degree uniformity after recovery.

Paper Structure

This paper contains 37 sections, 3 theorems, 69 equations, 12 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. System model
  4. Graph Topology of USNET
  5. Damage Model and MDSG
  6. Problem Formulation
  7. MDSG-based Artificial Potential Field Algorithm
  8. MDSG-based Force Field
  9. APF Algorithm Solution
  10. Theoretical Analysis of MDSG-APF
  11. Convergence of MDSG-APF
  12. Upper Bound of Recovery Time
  13. MDSG-based Graph Convolution
  14. Design of Bipartite Graph Convolution
  15. United MDSG
  16. ...and 22 more sections

Key Result

Proposition 1

The Remained Graph is connected if the remaining nodes are located within the circle area with a diameter equal to $d_{tr}$.

Figures (12)

  • Figure 1: An example of CNS issue caused by massive damage in USNET and recovery solutions of different algorithms.
  • Figure 2: An example of USNET graph topology and massive damage that causes split the network.
  • Figure 3: Examples of MDSG-based force fields for remaining UAV nodes with different locations.
  • Figure 4: Velocity components of node $u_{r_i}$.
  • Figure 5: Connection of remaining nodes $u_{r_i}$ and $u_{r_j}$ within the circle.
  • ...and 7 more figures

Theorems & Definitions (8)

  • Definition 1: 1-hop Neighboring Set
  • Definition 2: $k$-hop Neighboring Set
  • Definition 3: Disconnected Sub-nets
  • Definition 4: Number of Sub-nets
  • Definition 5: MDSG
  • Proposition 1
  • Proposition 2
  • Proposition 3