Credibility‐Driven Adaptive PSO for Load Balancing in SDN ‐Based Data Center Networks
Concurrency and Computation: Practice and Experience · 2026-07 · 38 (13)
DOI: 10.1002/cpe.70810 ↗Kurz gefasst
Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 02.07.2026. Verfasst von Wang Shun‐zhong und 4 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This paper addresses the limitations of traditional load‐balancing algorithms in software‐defined networking data centers, namely their reliance on single metrics and limited adaptability. We propose APSO‐C, a credibility‐driven adaptive particle swarm optimization method. A multidimensional credibility model is constructed from key indicators (bandwidth utilization, latency, jitter, packet loss, and throughput), and a three‐tier credibility function over nodes, links, and paths serves as the fitness criterion. APSO‐C integrates simulated annealing with dynamic inertia weights, incorporating random perturbations and adaptive adjustment to balance exploration and exploitation. Within the SDN centralized architecture, it enables dynamic rerouting of elephant flows and collaborative resource scheduling. Experiments on a Fat‐tree topology with k = 4 demonstrate that APSO‐C outperforms Hedera and ECMP, achieving improvements in link utilization by 17.1%, throughput by 18.9%, and load balance by 38.1%. In structured traffic scenarios, throughput approaches that of an ideal nonblocking network, confirming the method's reliability and real‐time performance.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Shun‐zhong, W., Xiao‐jie, Y., Zi‐wei, A., Jia, Z., & Deng‐yin, Z. (2026). Credibility‐Driven Adaptive PSO for Load Balancing in SDN ‐Based Data Center Networks. Concurrency and Computation: Practice and Experience, 38(13). https://doi.org/10.1002/cpe.70810
Vancouver
Shun‐zhong W, Xiao‐jie Y, Zi‐wei A, Jia Z, Deng‐yin Z. Credibility‐Driven Adaptive PSO for Load Balancing in SDN ‐Based Data Center Networks. Concurrency and Computation: Practice and Experience. 2026;38(13). doi:10.1002/cpe.70810
BibTeX
@article{Shunzhong2026,
author = {Shun‐zhong, Wang and Xiao‐jie, Yan and Zi‐wei, AO. and Jia, Zhong and Deng‐yin, Zhang},
title = {Credibility‐Driven Adaptive PSO for Load Balancing in SDN ‐Based Data Center Networks},
journal = {Concurrency and Computation: Practice and Experience},
year = {2026},
volume = {38},
number = {13},
doi = {10.1002/cpe.70810}
}
EUVIMED