View in EDS

QoS-driven reinforcement learning-based resource allocation in space–air–ground–sea integrated networks.

Saved in:
Bibliographic Details
Title: QoS-driven reinforcement learning-based resource allocation in space–air–ground–sea integrated networks.
Authors: Tang, Bing, Li, Jiayao, Cao, Yujun, Yang, Qing
Source: Cluster Computing; 2025, Vol. 28 Issue 8, p1-17, 17p
Abstract: With the rapid advancements in Space-Air-Ground-Sea Integrated Networks (SAGSIN), optimizing intelligent network resource allocation has become a pivotal research problem. Effective resource allocation can significantly enhance network performance, ensure quality of service (QoS) for users, and optimize resource utilization. To tackle this challenge, this paper proposes a network resource allocation optimization algorithm based on reinforcement learning, specifically designed to guarantee user QoS. Simulation results demonstrate that as the number of users increases, the proposed allocation algorithm, Q-DER, outperforms baseline algorithms, including random algorithms, greedy algorithms, the Q-DR algorithm and the Q-DE algorithm, in terms of average delay, access success rate, access energy consumption, and resource utilization rate. Furthermore, the proposed Q-DER algorithm significantly mitigates congestion in wireless resource-constrained scenarios. A comparative analysis of user satisfaction degree reveals that the proposed Q-DER algorithm performs better in guaranteeing user QoS in complex network environments. [ABSTRACT FROM AUTHOR]
Copyright of Cluster Computing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:With the rapid advancements in Space-Air-Ground-Sea Integrated Networks (SAGSIN), optimizing intelligent network resource allocation has become a pivotal research problem. Effective resource allocation can significantly enhance network performance, ensure quality of service (QoS) for users, and optimize resource utilization. To tackle this challenge, this paper proposes a network resource allocation optimization algorithm based on reinforcement learning, specifically designed to guarantee user QoS. Simulation results demonstrate that as the number of users increases, the proposed allocation algorithm, Q-DER, outperforms baseline algorithms, including random algorithms, greedy algorithms, the Q-DR algorithm and the Q-DE algorithm, in terms of average delay, access success rate, access energy consumption, and resource utilization rate. Furthermore, the proposed Q-DER algorithm significantly mitigates congestion in wireless resource-constrained scenarios. A comparative analysis of user satisfaction degree reveals that the proposed Q-DER algorithm performs better in guaranteeing user QoS in complex network environments. [ABSTRACT FROM AUTHOR]
ISSN:13867857
DOI:10.1007/s10586-025-05209-z