Distributed storage allocation problems

Leong, Derek; Dimakis, Alexandros G.; Ho, Tracey

doi:10.1109/netcod.2009.5191399

Cited by 21 publications

(33 citation statements)

References 12 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method considers the probability of failure for all storage nodes to be the same. The essence of this method is consistent with the methods in the literature [4]. The author proves that the method is optimal only if the premise of the same node-failure probability is met.…”

Section: Related Worksupporting

confidence: 72%

“…However, research into the distribution of code blocks is less common. The traditional method [4] [7] is to assign one code block per storage node.…”

Section: Related Workmentioning

confidence: 99%

“…For data distribution methods based on availability, Leong and Dimakis [4] [7] give a definition of uniform distribution and propose a storage strategy for distributed storage systems with uniform distribution. The strategy is based on an ideal model, which does not consider the storage space, storage-node failure probability, or the number of storage nodes.…”

Section: Related Workmentioning

confidence: 99%

“…To solve the allocation problem for coded data blocks, Leong and Dimakis [4] proposed a uniform code-block allocation model, for which the encoding of the data block amounts assigned to each storage node and the model were proved to be optimal. This ensured the availability of data with a minimal data-allocation overhead.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Probability-Symmetric Storage Allocation for Distributed Storage Systems Based on Network Coding

Wu¹,

Zhang²,

Zheng³

et al. 2013

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Abstract-The goal of optimal allocation is to increase stored data availability subject to minimizing the storage budget. Symmetric allocation based on the network coding has been proved to be optimal for distributed storage systems if node availability is not considered. However, because of network conditions and the inherent properties of nodes, each node will have a different availability. This paper focuses on the problem of optimizing distributed data storage when considering node availability. Using a probability model for storage systems, we redefine symmetric allocation in terms of probability-symmetric allocation and propose a probability-symmetric allocation model and strategy based on network coding. These are shown to be optimal in general. Compared with the symmetric allocation scheme proposed by Leong et al., the proposed probabilitysymmetric allocation scheme not only improves data availability in distributed storage systems but also is more practical.

show abstract

Section: Related Worksupporting

confidence: 72%

“…However, research into the distribution of code blocks is less common. The traditional method [4] [7] is to assign one code block per storage node.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Probability-Symmetric Storage Allocation for Distributed Storage Systems Based on Network Coding

Wu¹,

Zhang²,

Zheng³

et al. 2013

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

“…A survey of network coding and distributed storage systems can be found in [13]. Some problems of distributed storage systems, like storage allocations, are addressed in [11,12]. However, our problem differs from that of the distributed storage systems in the sense that our proposal does not aim to provide data reliability in case of node failure, but to allow all involved nodes to acquire local access to the complete dataset at any given time.…”

Section: Introductionmentioning

confidence: 99%

Efficient Synchronization of Multiple Databases over Broadcast Networks

Muhammad

Erl

Berioli

2013

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. This work deals with the problem of synchronizing multiple distributed databases over a broadcast network, such as satellite networks. The proposed method is based on introducing network coding techniques besides extending the well-known database reconciliation algorithm, the characteristic polynomial interpolation-based synchronization (CPISync). One key element is to elect a master node that manages the operations in a central manner. Performance is shown in terms of completion time for full synchronization, and average number of packets exchange. Compared to point-to-point and traditional broadcasting synchronization methods, the algorithm implementing network coding allows reaching the lower-bound for the number of packets exchange.

show abstract

An efficient communication relay placement algorithm for content‐centric wireless mesh networks

Wang

Zhang

et al. 2013

Int J Communication

View full text Add to dashboard Cite

In this paper, we investigate a communication relay placement problem to optimize the network throughput in a content-centric wireless mesh networks (WMN), in which the WMN is enhanced by including a small set of communication relays and a subset of wireless mesh routers serving as storage nodes. Specifically, we first define the communication relay placement problem in content-centric WMNs. We then model the problem as a mathematical programming and propose a linear programming approach for calculating the achievable network throughput when the positions of communication relays are fixed. Next, to optimally placing the communication relays, we formulate an integer linear programming problem and we develop an efficient near-optimal approximation algorithm based on linear programming relaxation. Finally, extensive simulation experiments have been conducted, and the results demonstrate the effectiveness of the proposed algorithms. AN EFFICIENT RELAY PLACEMENT ALGORITHM FOR CONTENT-CENTRIC WMNS 263For the peer-to-peer traffic, it has been shown that the maximal throughput in large-scale two- 11,12], where W is the wireless channel capacity and n is the number of nodes in the network. Intuitively, such a capacity is because of the fact that the dominating traffic (in the scale of ‚.n/) has to be routed, via multihop paths, through a certain subset of mesh routers (in the scale of ‚. p n//. In other words, the subset of mesh routers is the bottleneck of the whole WMN.For the Internet access scenario, which is the most common one today, all traffic has to pass through a limited number of Internet gateways. Consequently, the network capacity is limited by the wireless channels of the gateways. For instance, if there is only one gateway, then the capacity of a large-scale two-dimensional WMN is ‚ W n [13]. To improve the performance of WMN, in this paper we consider a content-centric WMN design, in which the WMN is enhanced by including a small set of communication relays and a subset of wireless mesh routers serving as storage nodes.In the past, relays or local gateways have been discussed in many hybrid WMN architectures [14][15][16][17][18][19][20], as shown in Figure 1(a). The advantages of using relays are as the follows. Firstly, additional communication relays can improve the connectivity of the WMN, because they can interconnect clients in different areas and can also cover areas disconnected with each other. For example, in the traditional WMN, client m 1 cannot communicate with client m 3 because they are in different communication areas and the two areas are not connected. On the other hand, in the hybrid WMN shown in Figure 1 (b), client m 1 can communicate with client m 3 because their communication areas are connected by communication relays.Secondly, additional communication relays can decrease communication delay and increase network throughput. Communication relays are usually more powerful than regular node in that they can be equipped with multiple interfaces, directional antenna, improved transceivers...

show abstract

Distributed storage allocation problems

Cited by 21 publications

References 12 publications

Probability-Symmetric Storage Allocation for Distributed Storage Systems Based on Network Coding

Probability-Symmetric Storage Allocation for Distributed Storage Systems Based on Network Coding

Efficient Synchronization of Multiple Databases over Broadcast Networks

An efficient communication relay placement algorithm for content‐centric wireless mesh networks

Contact Info

Product

Resources

About