Two Layer Stackelberg Game-Based Resource Allocation in Cloud-Network Convergence Service Computing

With the rapid development of mobile devices, limited edge computing resources, and separate cloud computing systems is difficult to meet the different needs of different applications, so the cloud-network convergence service approach came into being. This paper investigates a tiered resource alloca...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on cognitive communications and networking Jg. 10; H. 6; S. 2412 - 2426
Hauptverfasser: Lyu, Ting, Xu, Haitao, Liu, Feifei, Li, Meng, Li, Lixin, Han, Zhu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.12.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Cloud computing
cloud-network convergence
Convergence
Convexity
Edge computing
End users
Game theory
Games
Nash equilibrium
Pricing
Resource allocation
Resource management
Response functions
Servers
Task analysis
User requirements
ISSN:2332-7731, 2332-7731
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the rapid development of mobile devices, limited edge computing resources, and separate cloud computing systems is difficult to meet the different needs of different applications, so the cloud-network convergence service approach came into being. This paper investigates a tiered resource allocation scheme that can provide high-quality computing services to end-users and balance the benefit requirements of all participants to benefit the stakeholders in the cloud-network convergence service system. Firstly, considering the self-interests of each participant in the cloud-network converged service system, the hierarchical resource allocation problem is formulated as a two-layer game resource allocation problem. Subsequently, the backward induction method is used for game analysis, and Stackelberg equilibrium is proved. The optimal resource price response function for the edge layer and the offloading optimal response function for the end-users are derived by a convex optimization approach, and a gradient-based dynamic pricing algorithm is designed to obtain the optimal pricing in the cloud and the optimal resource requests in the edge layer. Finally, experimental simulation results are given, and the performance of the optimal pricing and resource allocation policy is analyzed.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2332-7731
2332-7731
DOI:10.1109/TCCN.2024.3392809