Multifaceted Simultaneous Load Balancing in DHT-Based P2P Systems: A New Game with Old Balls and Bins

Aberer, Karl; Datta, Anwitaman; Hauswirth, Manfred

doi:10.1007/11428589_24

Cited by 22 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The limitation of this approach is that as more nodes join in the system, these virtual servers consume more resources. Aberer et al in [5] tried to balance the load in a DHT by checking its load with its neighbor nodes. In the system, each node repeatedly checks the load information of its neighbor nodes to achieve load balancing.…”

Section: Load Balancing Strategiesmentioning

confidence: 99%

Moving Target With Load Balancing in a Hierarchical Cloud

2014

STCC

View full text Add to dashboard Cite

In this paper we propose a 'moving target' security mechanism for a P2P cloud where files are partitioned and sensitive sections are moved at different times without modifying the routing or finger tables, to reduce the risk of the file being compromised. Two drawbacks with this approach are the problem of determining the locality of the data and load unbalancing. We present a hierarchical P2P cloud system that leads to scalability and efficiency. A 3-step load balancing scheme for hierarchical P2P cloud system to globally balance the network is proposed. Our simulation results show that our algorithm is effective in achieving load balancing in hierarchical peer-to-peer cloud systems.

show abstract

Section: Load Balancing Strategiesmentioning

confidence: 99%

Moving Target With Load Balancing in a Hierarchical Cloud

2014

STCC

View full text Add to dashboard Cite

show abstract

“…2) Floating ID: The approach which we follow in this paper is to have the THON's nodes dynamically changing their associated tessellation of the ID space ("bucketing" [16], [17]) decoupled from their (unique and stable) identifier. The routing between peers is based on the associated tessellation, rather than on the peer identifiers.…”

Section: A Identifier Spacementioning

confidence: 99%

THON: A Tessellation-based Hierarchical Overlay Network for DGET Grid Middleware

Hudzia

Kechadi

2007

2007 16th International Conference on Computer Communications and Networks

View full text Add to dashboard Cite

P2P and Grid computing are two paradigms that are increasingly used in today's computing environments; their potential to provide better quality of service to users is very promising compared to the cost involved. This paper presents a hierarchical virtual network topology built on top of a physical one, which is used to manage distributed resources in a Grid environment. The virtual topology defines an efficient and robust virtual machine, which will serve as a distributed computing platform. This topology is called THON (Tessellation-based Hierarchical Overlay Network) and is the successor of the Treep topology. THON is exploited in DGET, a data-grid middleware environment, and provides P2P resource discovery and load balancing. Here, we present the virtual topology theoretically and we show that this topology is very scalable, robust, loadbalanced, and easy to construct and maintain. The topology efficiently exploits the heterogeneity of the network while limiting the overhead introduced by the overlay maintenance.

show abstract

“…Several examples of such mechanisms have been recently discussed in the literature [2,15,11]. Thus each peer acquires its identifier according to a non-uniform probability density function f .…”

Section: Model For Skewed Key Distributionmentioning

confidence: 99%

“…Search efficiency in terms of the number of overlay hops can't be guaranteed in CAN for arbitrary partitioning of the key-space (zones). In contrast, P-Grid's randomization helps retaining routing efficiency [2], however peers require more than logarithmic routing states. Pursuing the idea of building the small-world overlay topology we propose a further extension that can handle skewed key distributions without loosing efficient routing properties.…”

Section: Introductionmentioning

confidence: 99%