Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Dynamic threshold-enhanced diffusion PPO for multi-UAV collaborative optimization in wireless rechargeable sensor

Yalin Nie¹, Zeyu Sun², Yang Zhang¹

¹School of Artificial Intelligence, Luoyang Institute of Science and Technology, Luoyang, 471023, China.

Scientific Reports

|July 4, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Research on Construction of High-Quality Application-Oriented Talent Cultivation System for Internet of Things Engineering: Based on Educational Psychology.

Frontiers in psychology·2022

Same author

CS-FCDA: A Compressed Sensing-Based on Fault-Tolerant Data Aggregation in Sensor Networks.

Sensors (Basel, Switzerland)·2018

Same author

Two superoxide dismutase (SOD) with different subcellular localizations involved in innate immunity in Crassostrea hongkongensis.

Fish & shellfish immunology·2011

Same author

Density hysteresis of heavy water confined in a nanoporous silica matrix.

Proceedings of the National Academy of Sciences of the United States of America·2011

Same author

Protein-protein complex structure predictions by multimeric threading and template recombination.

Structure (London, England : 1993)·2011

Same author

Cu2+ triggers reversible aggregation of a disordered His-rich dehydrin MpDhn12 from Musa paradisiaca.

Journal of biochemistry·2011

This study introduces a novel algorithm for optimizing Unmanned Aerial Vehicle (UAV) networks to reduce communication delays and balance loads. The dynamic threshold-enhanced diffusion proximal policy optimization (DTD-PPO) algorithm improves network efficiency and stability.

Area of Science:

Computer Science
Electrical Engineering
Network Optimization

Background:

Multi-Unmanned Aerial Vehicle (UAV) systems face challenges in optimizing communication delay and load balancing.
Wireless Rechargeable Sensor Networks (WRSNs) require efficient management for sustained operation.
Existing algorithms struggle with the dynamic and complex nature of these networks.

Purpose of the Study:

To develop a robust algorithm for collaborative optimization of communication delay and UAV load balancing in multi-UAV-assisted WRSNs.
To enhance the feasibility and practicality of optimization solutions by incorporating multi-dimensional constraints.
To improve the exploration ability and training stability of reinforcement learning algorithms in this domain.

Main Methods:

Keywords:

Collaborative optimization Data collection Proximal policy optimization Wireless rechargeable sensor networks

Related Experiment Videos

Constructed a multi-objective optimization model for multi-UAV-assisted WRSNs.

Designed a Markov Decision Process (MDP) framework with dynamic weighting for objective balancing.

Integrated a diffusion model into the Proximal Policy Optimization (PPO) policy network for action diversification.

Implemented a dynamic threshold strategy based on normalized reward change rate for real-time policy updates.

Main Results:

The proposed Dynamic Threshold-enhanced Diffusion Proximal Policy Optimization (DTD-PPO) algorithm effectively balances communication delay and UAV load.
The diffusion model integration enhanced exploration and training stability.
The dynamic threshold strategy allowed for adaptive policy updates.
Validated effectiveness using metrics including data collection delay, UAV flight distance deviation, and energy efficiency.

Conclusions:

The DTD-PPO algorithm demonstrates superior performance and robustness compared to benchmark methods.
The proposed approach offers a significant advancement in optimizing complex multi-UAV-assisted WRSNs.
This work provides a practical and effective solution for enhancing the performance of UAV-assisted networks.