Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms

Elarbi Badidi; Omar El Harrouss

doi:10.1109/ICUFN65838.2025.11170026

Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms

Elarbi Badidi
, Omar El Harrouss

Department of Computer Science and Software Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The efficient scheduling of tasks within loosely coordinated Unmanned Aerial Vehicle (UAV) swarms poses challenges due to UAV heterogeneity, task dependencies, resource limitations, and constrained communication. We introduce a reinforcement learning (RL)-based framework using Q-learning to optimize task allocation dynamically. Our RL method outperforms traditional heuristics (MinMin, MaxMin) and metaheuristics (PSO, GA), reducing task completion time by up to 18%, improving load balance, and achieving higher energy consumption compared to GA/PSO. The framework adapts to dynamic task arrivals and heterogeneous UAV capabilities, demonstrating its scalability and robustness in decentralized swarm operations.

Original language	English
Title of host publication	ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks
Publisher	IEEE Computer Society
Pages	486-491
Number of pages	6
ISBN (Electronic)	9798331524876
DOIs	https://doi.org/10.1109/ICUFN65838.2025.11170026
Publication status	Published - 2025
Event	16th International Conference on Ubiquitous and Future Networks, ICUFN 2025 - Hybrid, Lisbon, Portugal Duration: Jul 8 2025 → Jul 11 2025

Publication series

Name	International Conference on Ubiquitous and Future Networks, ICUFN
ISSN (Print)	2165-8528
ISSN (Electronic)	2165-8536

Conference

Conference	16th International Conference on Ubiquitous and Future Networks, ICUFN 2025
Country/Territory	Portugal
City	Hybrid, Lisbon
Period	7/8/25 → 7/11/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Genetic Algorithms
Particle Swarm Optimization
Reinforcement Learning
Task Scheduling
UAV Swarms

ASJC Scopus subject areas

Hardware and Architecture
Computer Science Applications
Computer Networks and Communications

Access to Document

10.1109/ICUFN65838.2025.11170026

Cite this

Badidi, E., & El Harrouss, O. (2025). Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms. In ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks (pp. 486-491). (International Conference on Ubiquitous and Future Networks, ICUFN). IEEE Computer Society. https://doi.org/10.1109/ICUFN65838.2025.11170026

Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms. / Badidi, Elarbi; El Harrouss, Omar.
ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks. IEEE Computer Society, 2025. p. 486-491 (International Conference on Ubiquitous and Future Networks, ICUFN).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Badidi, E & El Harrouss, O 2025, Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms. in ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks. International Conference on Ubiquitous and Future Networks, ICUFN, IEEE Computer Society, pp. 486-491, 16th International Conference on Ubiquitous and Future Networks, ICUFN 2025, Hybrid, Lisbon, Portugal, 7/8/25. https://doi.org/10.1109/ICUFN65838.2025.11170026

@inproceedings{dea4109e45af45dfb43c5b85be9fd9c8,

title = "Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms",

abstract = "The efficient scheduling of tasks within loosely coordinated Unmanned Aerial Vehicle (UAV) swarms poses challenges due to UAV heterogeneity, task dependencies, resource limitations, and constrained communication. We introduce a reinforcement learning (RL)-based framework using Q-learning to optimize task allocation dynamically. Our RL method outperforms traditional heuristics (MinMin, MaxMin) and metaheuristics (PSO, GA), reducing task completion time by up to 18\%, improving load balance, and achieving higher energy consumption compared to GA/PSO. The framework adapts to dynamic task arrivals and heterogeneous UAV capabilities, demonstrating its scalability and robustness in decentralized swarm operations.",

keywords = "Genetic Algorithms, Particle Swarm Optimization, Reinforcement Learning, Task Scheduling, UAV Swarms",

author = "Elarbi Badidi and \{El Harrouss\}, Omar",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 16th International Conference on Ubiquitous and Future Networks, ICUFN 2025 ; Conference date: 08-07-2025 Through 11-07-2025",

year = "2025",

doi = "10.1109/ICUFN65838.2025.11170026",

language = "English",

series = "International Conference on Ubiquitous and Future Networks, ICUFN",

publisher = "IEEE Computer Society",

pages = "486--491",

booktitle = "ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks",

}

TY - GEN

T1 - Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms

AU - Badidi, Elarbi

AU - El Harrouss, Omar

PY - 2025

Y1 - 2025

N2 - The efficient scheduling of tasks within loosely coordinated Unmanned Aerial Vehicle (UAV) swarms poses challenges due to UAV heterogeneity, task dependencies, resource limitations, and constrained communication. We introduce a reinforcement learning (RL)-based framework using Q-learning to optimize task allocation dynamically. Our RL method outperforms traditional heuristics (MinMin, MaxMin) and metaheuristics (PSO, GA), reducing task completion time by up to 18%, improving load balance, and achieving higher energy consumption compared to GA/PSO. The framework adapts to dynamic task arrivals and heterogeneous UAV capabilities, demonstrating its scalability and robustness in decentralized swarm operations.

AB - The efficient scheduling of tasks within loosely coordinated Unmanned Aerial Vehicle (UAV) swarms poses challenges due to UAV heterogeneity, task dependencies, resource limitations, and constrained communication. We introduce a reinforcement learning (RL)-based framework using Q-learning to optimize task allocation dynamically. Our RL method outperforms traditional heuristics (MinMin, MaxMin) and metaheuristics (PSO, GA), reducing task completion time by up to 18%, improving load balance, and achieving higher energy consumption compared to GA/PSO. The framework adapts to dynamic task arrivals and heterogeneous UAV capabilities, demonstrating its scalability and robustness in decentralized swarm operations.

KW - Genetic Algorithms

KW - Particle Swarm Optimization

KW - Reinforcement Learning

KW - Task Scheduling

KW - UAV Swarms

UR - https://www.scopus.com/pages/publications/105018736750

UR - https://www.scopus.com/pages/publications/105018736750#tab=citedBy

U2 - 10.1109/ICUFN65838.2025.11170026

DO - 10.1109/ICUFN65838.2025.11170026

M3 - Conference contribution

AN - SCOPUS:105018736750

T3 - International Conference on Ubiquitous and Future Networks, ICUFN

SP - 486

EP - 491

BT - ICUFN 2025 - 16th International Conference on Ubiquitous and Future Networks

PB - IEEE Computer Society

T2 - 16th International Conference on Ubiquitous and Future Networks, ICUFN 2025

Y2 - 8 July 2025 through 11 July 2025

ER -

Reinforcement Learning for Scalable and Efficient Task Scheduling in Loosely Coordinated UAV Swarms

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this