Mingwei Wu

Ms. Mingwei Wu


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2025 in Drones
Verified
Journal Article
Open access
PDF file
MWMingwei Wu
Mingwei Wu
BJBo Jiang
Bo Jiang
SCSiji Chen
Siji Chen
HXHong Xu
Hong Xu
TPTAO PANG
TAO PANG
FXFei Xia
Fei Xia
Routing in flying ad hoc networks (FANETs) is hindered by high mobility, trajectory-induced topology dynamics, and energy constraints. Conventional topology-based or position-based protocols often fail due to stale link information and limited neighbor awareness. This paper proposes a trajectory-informed routing protocol enhanced by Q-learning: Traj-Q-GPSR, tailored for mission-oriented UAV swarm networks. By leveraging mission-planned flight trajectories, the protocol builds time-aware two-hop neighbor tables, enabling routing decisions based on both current connectivity and predicted link availability. This spatiotemporal information is integrated into a reinforcement learning framework that dynamically optimizes next-hop selection based on link stability, queue length, and node mobility patterns. To further enhance adaptability, the learning parameters are adjusted in real time according to network dynamics. Additionally, a delay-aware queuing model is introduced to forecast optimal transmission timing, thereby reducing buffering overhead and mitigating redundant retransmissions. Extensive ns-3 simulations across diverse mobility, density, and CBR connections demonstrate that the proposed protocol consistently outperforms GPSR, achieving up to 23% lower packet loss, over 80% reduction in average end-to-end delay, and improvements of up to 37% and 52% in throughput and routing efficiency, respectively.

6 November 2026 in Telecom
Verified
Journal Article
Open access
PDF file
MGMingke Gao
Mingke Gao
TPTao Pang
Tao Pang
HXHong Xu
Hong Xu
SCSiji Chen
Siji Chen
MWMingwei Wu
Mingwei Wu
MZMiankuan Zhu
Miankuan Zhu
In highly mobile 3D flying ad hoc networks (FANETs) for UAV swarms, conventional GPSR suffers from significant packet loss and transmission delays. GPSR implicitly assumes that links to nearby nodes remain stable, an assumption that often fails for fast-moving UAVs. Its greedy forwarding tends to select edge-of-range neighbors, and minor changes in UAV speed or heading can readily break these fragile wireless connections. Existing GPSR enhancements have two key limitations: trajectory-prediction-based schemes introduce heavy overhead for onboard UAV hardware and incur large prediction errors during sharp turns or obstacle avoidance, whereas static RSSI-threshold solutions cannot track time-varying channel fading. To address these limitations, this paper proposes LL-SQ-GPSR, a lightweight stateless geographic routing protocol that moves beyond pure distance-based forwarding. The dual-metric link stability evaluation framework combines Expected Link Duration (ELD) with Signal Decay Rate (SDR). ELD is derived analytically from relative motion vectors between neighboring nodes, whereas SDR is estimated from sliding-window RSSI sequences using low-complexity linear regression. The proposed framework selects next-hop relays that simultaneously approach the destination and maintain long kinematic link lifetimes and stable physical-layer signals. Monte Carlo simulations in highly mobile 3D mission scenarios indicate that, compared with baseline GPSR, LL-SQ-GPSR reduces path length by 24.1–76.5% and hop count by 20.0–76.2%. Even at a high flight speed of 30 m/s, the proposed protocol achieves a higher packet delivery ratio and lower routing-level end-to-end latency than existing protocols, including GPSR+ and GPSR. It maintains asymptotic complexity comparable to that of the original GPSR, with only bounded per-node overhead. These results demonstrate its effectiveness as a communication solution for resource-limited cooperative UAV swarms operating in highly dynamic 3D airspace.