Related Experiment Video
Updated: Feb 3, 2026

Automated Deployment of an Internet Protocol Telephony Service on Unmanned Aerial Vehicles Using Network Functions Virtualization
Published on: November 26, 2019
A Design and Simulation of the Opportunistic Computation Offloading with Learning-Based Prediction for Unmanned
Rico Valentino1, Woo-Sung Jung2, Young-Bae Ko3
1Department of Computer Engineering, Ajou University, Suwon 16499, Korea. ricovalentino94@ajou.ac.kr.
This study introduces an opportunistic computational offloading system for drone clusters. By intelligently borrowing resources, drone swarms can significantly reduce task completion times and improve efficiency.
Area of Science:
- Computer Science
- Robotics
- Artificial Intelligence
Background:
- Drones are increasingly used in military and civilian sectors for complex tasks.
- Drone clusters offer advantages in coverage, flexibility, and reliability.
- Limited onboard computing power and energy resources pose challenges for drone task completion.
Purpose of the Study:
- To propose an opportunistic computational offloading system for drone clusters.
- To address the challenge of limited resources in drone swarms.
- To enable drone clusters to complete tasks more efficiently.
Main Methods:
- Developed an opportunistic computational offloading scheme for drone clusters.
- Integrated an artificial neural network (ANN) for response time prediction.
- Offloading decisions are made based on predicted offloading response time versus local computing time.
Main Results:
- The proposed scheme allows drone clusters to borrow computing resources opportunistically.
- The ANN-based prediction module accurately estimates offloading response times.
- Simulation results demonstrate a decrease in drone cluster response times.
Conclusions:
- Opportunistic computational offloading is an effective strategy for enhancing drone swarm performance.
- ANN-based prediction enhances the decision-making process for offloading.
- The system improves the efficiency and timeliness of complex drone operations.
Related Concept Videos
Design Example: Traverse Angle Computations
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Factorial Design
Predicting Molecular Geometry
Network Covalent Solids
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
Group Design

