Skip to content
Log in

Author

Zheng Chang

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

2026

Data Collection for UAV-Assisted Emergency IoT Networks: An AoI-Energy Tradeoff Perspective Under Imperfect CSI

The unmanned aerial vehicle (UAV)-assisted Internet-of-Things (IoT) network architecture has emerged as a key technology for supporting communications in emergency scenarios. The quality and freshness of the data collected by UAVs directly impact the effectiveness of emergency decision-making and the overall responsiveness of the system in time-critical situations. However, limited by the battery capacity of UAVs, a fundamental tradeoff exists between information freshness and energy consumption in UAV-assisted IoT networks, which constrains the effective coverage range of emergency operations. Accordingly, this paper explores the inherent trade-off between Age of Information (AoI) and energy consumption in UAV-assisted emergency IoT systems. To reflect the highly dynamic and uncertain channel conditions typical of post-disaster environments, this work further incorporates an imperfect channel state information (CSI) model. Then, a probabilistic constraint AoI-energy tradeoff problem is formulated to jointly optimizing the time allocation of data collection, UAV trajectory, and duration of time slots. To address the resulting non-convex non-linear problem, we first convert the probabilistic constraint problem into a non-probability one, then employ a block coordinate descent method to iteratively solve the highly coupled multi-variable problem. Finally, comprehensive simulation results validate the effectiveness of the proposed method.

Mingan Luan, Xin Zhang, Zheng Chang et al. · 0 citations
2026

When Split Federated Learning Meets Prototype Learning: A Communication-Efficient Approach in Wireless Networks

Nowadays, split federated learning (SFL) has emerged as an effective paradigm for enabling privacy-preserving collaborative intelligence across heterogeneous devices with limited computation. However, SFL incurs significant communication overhead in wireless networks due to the uplink transmission of high-dimensional smashed data, which degrades network efficiency. To mitigate the communication bottleneck, we propose a prototype-based SFL framework ProtoSFL. Specifically, each selected client computes local prototypes for observed classes and uploads them to the server. Based on the received prototypes, the server derives global prototypes and optimizes a weighted objective that combines classification loss with prototype alignment loss. The server then updates the model accordingly and returns personalized prototype gradients to the clients. Simulation results verify the effectiveness of ProtoSFL in reducing communication overhead, achieving a substantial reduction in uplink communication, while maintaining competitive testing accuracy under various heterogeneous data settings compared with SFL baselines.

Xinran Zhang, Xianke Qiang, Weilong Chen et al. · 0 citations