EUVIMEDEUVIMED entdecken
Crossref

Reverse-Offloading Incentive Mechanism With Long-Term Optimization in Social-Aware Cloud-Edge Systems

Gailun Zeng, Jianxiong Guo, Xingjian Ding, Zhiqing Tang, Tian Wang, Weijia Jia

IEEE Transactions on Services Computing · 2026-07 · 19 (4) · 2998-3014

DOI: 10.1109/tsc.2026.3704824 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2026-07. Verfasst von Gailun Zeng und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Start-up Fund from Beijing Normal University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reverse-offloading services to edges in cloud-edge systems play a pivotal role since they can effectively facilitate the resource utilization of edges, such as crowdsensing, where tasks are offloaded to workers via incentives. Additionally, edges are objectively closer to mobile end users, which aligns more closely with the latency-sensitive task requirements, such as real-time inference tasks. However, the natural complexity caused by social relationships between edges is non-trivial for modeling, as these relationships provide potential extra benefits, such as data sharing between edges. The real-time interactions between the cloud and edges bring the system dynamics, which is also challenging to meet long-term constraints, such as total energy or payment costs. To end this, we revisit these challenges and propose a novel multi-service and multi-edge reverse-offloading incentive mechanism, where the cloud utilizes reward strategies to recruit social-aware edges, and the edges employ appropriate task strategies, including the choice of cooperation with social-connected edges, to maximize their benefits. The natural bilateral framework is modeled as a two-stage Stackelberg game (SG), where both sides can selfishly optimize their strategies. To tackle the dynamics of the system, we design a coupled Lyapunov optimization approach for the bilateral framework, which effectively decomposes the long-term optimizations for both sides into online optimizations. Theoretical analysis proves the existence and uniqueness of the Stackelberg equilibrium, along with error gap guarantees for the coupled Lyapunov-based approach. An algorithm is designed to get approximate optimal solutions. Extensive simulations using both synthetic and real-world datasets validate the outperformance of our method and investigate critical factors, such as the impact of social relationships.

Förderung

  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Start-up Fund from Beijing Normal University
  • Internal Fund from Beijing Normal-Hong Kong Baptist University
  • Interdisciplinary Intelligence SuperComputer Center of Beijing Normal University

Zitieren

APA

Zeng, G., Guo, J., Ding, X., Tang, Z., Wang, T., & Jia, W. (2026). Reverse-Offloading Incentive Mechanism With Long-Term Optimization in Social-Aware Cloud-Edge Systems. IEEE Transactions on Services Computing, 19(4), 2998-3014. https://doi.org/10.1109/tsc.2026.3704824

Vancouver

Zeng G, Guo J, Ding X, Tang Z, Wang T, Jia W. Reverse-Offloading Incentive Mechanism With Long-Term Optimization in Social-Aware Cloud-Edge Systems. IEEE Transactions on Services Computing. 2026;19(4):2998-3014. doi:10.1109/tsc.2026.3704824

BibTeX
@article{Zeng2026,
  author = {Zeng, Gailun and Guo, Jianxiong and Ding, Xingjian and Tang, Zhiqing and Wang, Tian and Jia, Weijia},
  title = {Reverse-Offloading Incentive Mechanism With Long-Term Optimization in Social-Aware Cloud-Edge Systems},
  journal = {IEEE Transactions on Services Computing},
  year = {2026},
  volume = {19},
  number = {4},
  pages = {2998--3014},
  doi = {10.1109/tsc.2026.3704824}
}
Kostenlos starten →