Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks
Sarathchandra, Sankani; Eldeeb, Eslam; Shehab, Mohammad; Alves, Hirley; Mikhaylov, Konstantin; Alouini, Mohamed-Slim (2025-06-13)
IEEE
13.06.2025
S. Sarathchandra, E. Eldeeb, M. Shehab, H. Alves, K. Mikhaylov and M. -S. Alouini, "Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks," in IEEE Transactions on Vehicular Technology, doi: 10.1109/TVT.2025.3579626
https://creativecommons.org/licenses/by/4.0/
© 2025 IEEE. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
https://creativecommons.org/licenses/by/4.0/
© 2025 IEEE. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
https://creativecommons.org/licenses/by/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202506174650
https://urn.fi/URN:NBN:fi:oulu-202506174650
Tiivistelmä
Abstract
Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle (UAV) that collects data. Our aim is to optimize the UAV's flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.
Age-of-information (AoI) and transmission power are crucial performance metrics in low energy wireless networks, where information freshness is of paramount importance. This study examines a power-limited internet of things (IoT) network supported by a flying unmanned aerial vehicle (UAV) that collects data. Our aim is to optimize the UAV's flight trajectory and scheduling policy to minimize a varying AoI and transmission power combination. To tackle this variation, this paper proposes a meta-deep reinforcement learning (RL) approach that integrates deep Q-networks (DQNs) with model-agnostic meta-learning (MAML). DQNs determine optimal UAV decisions, while MAML enables scalability across varying objective functions. Numerical results indicate that the proposed algorithm converges faster and adapts to new objectives more effectively than traditional deep RL methods, achieving minimal AoI and transmission power overall.
Kokoelmat
- Avoin saatavuus [38841]
Ellei muuten mainita, aineiston lisenssi on https://creativecommons.org/licenses/by/4.0/