Downloads & Free Reading Options - Results

In this paper, we study distributed storage problems over unidirectional ring networks. A lower bound on the reconstructing bandwidth to recover total original data for each user is proposed, and it is achievable for arbitrary parameters. If a distributed storage scheme can achieve this lower bound with equality for each user, we say it an optimal reconstructing distributed storage scheme (ORDSS). Furthermore, the repair problem for a failed storage node in ORDSSes is under consideration and a tight lower bound on the repair bandwidth for each storage node is obtained. Particularly, we indicate the fact that for any ORDSS, every storage node can be repaired with repair bandwidth achieving the lower bound with equality. In addition, we present an efficient approach to construct ORDSSes for arbitrary parameters by using the concept of Euclidean division. Finally, we take an example to characterize the above approach.

The problem of exact repair of a failed node in multi-hop networked distributed storage systems is considered. Contrary to the most of the current studies which model the repair process by the direct links from surviving nodes to the new node, the repair is modeled by considering the multi-hop network structure, and taking into account that there might not exist direct links from all the surviving nodes to the new node. In the repair problem of these systems, surviving nodes may cooperate to transmit the repair traffic to the new node. In this setting, we define the total number of packets transmitted between nodes as repair-cost. A lower bound of the repaircost can thus be found by cut-set bound analysis. In this paper, we show that the lower bound of the repair-cost is achievable for the exact repair of MDS codes in tandem and grid networks, thus resulting in the minimum-cost exact MDS codes. Further, two suboptimal (achievable) bounds for the large scale grid networks are proposed.

A distributed data collection algorithm to accurately store and forward information obtained by wireless sensor networks is proposed. The proposed algorithm does not depend on the sensor network topology, routing tables, or geographic locations of sensor nodes, but rather makes use of uniformly distributed storage nodes. Analytical and simulation results for this algorithm show that, with high probability, the data disseminated by the sensor nodes can be precisely collected by querying any small set of storage nodes.

Large-scale storage is a promising emerging technology to realize a reliable smart-grid since it can enhance sustainability, reliability and asset utilization. At fast time-scales, storage can be used to mitigate fluctuations and time-variations on renewable generation and demand. On slower time scales, it can be used for load shifting and reducing the generation costs. This paper deals with the latter case and studies the following important decision problem: Given a network and an available storage budget, how should we optimally place, size and control the energy storage units across the network. When the generation cost is a nondecreasing convex function, our main result states that it is it is always optimal to allocate zero storage capacity at generator buses that connect to the rest of the power grid via single links, regardless of demand profiles and other network parameters. This provides a sound investment strategy for network planners, especially for distribution systems and isolated transmission networks. For specific network topologies, we also characterize the dependence of the optimal production cost on the available storage resources, generation capacities and flow constraints.

This paper proposes a novel algorithm to optimally size and place storage in low voltage (LV) networks based on a linearized multiperiod optimal power flow method which we call forward backward sweep optimal power flow (FBS-OPF). We show that this method has good convergence properties, its solution deviates slightly from the optimum and makes the storage sizing and placement problem tractable for longer investment horizons. We demonstrate the usefulness of our method by assessing the economic viability of distributed and centralized storage in LV grids with a high photovoltaic penetration (PV). As a main result, we quantify that for the CIGRE LV test grid distributed storage configurations are preferable, since they allow for less PV curtailment due to grid constraints.

We present a data storage scheme for sensor networks that achieves the targets of encryption and distributed storage simultaneously. We partition the data to be stored into numerous pieces such that at least a specific number of them have to be brought together to recreate the data. The procedure for creation of partitions does not use any encryption key and the pieces are implicitly secure. These pieces are then distributed over random sensors for storage. Capture or malfunction of one or more (less than a threshold number of sensors) does not compromise the data. The scheme provides protection against compromise of data in specific sensors due to physical capture or malfunction.

We consider the problem of synchronizing data in distributed storage networks under an edit model that includes deletions and insertions. We present two modifications of MDS, regenerating and locally repairable codes that allow updates in the parity-check values to be performed with one round of communication at low bit rates and using small storage overhead. Our main contributions are novel protocols for synchronizing both hot and semi-static data and protocols for data deduplication applications, based on intermediary permutation, Vandermonde and Cauchy matrix coding.

We have developed and deployed a distributed-parallel storage system (DPSS) in several high speed asynchronous transfer mode (ATM) wide area networks (WAN) testbeds to support several different types of data-intensive applications. Architecturally, the DPSS is a network striped disk array, but is fairly unique in that its implementation allows applications complete freedom to determine optimal data layout, replication and/or coding redundancy strategy, security policy, and dynamic reconfiguration. In conjunction with the DPSS, we have developed a 'top-to-bottom, end-to-end' performance monitoring and analysis methodology that has allowed us to characterize all aspects of the DPSS operating in high speed ATM networks. In particular, we have run a variety of performance monitoring experiments involving the DPSS in the MAGIC testbed, which is a large scale, high speed, ATM network and we describe our experience using the monitoring methodology to identify and correct problems that limit the performance of high speed distributed applications. Finally, the DPSS is part of an overall architecture for using high speed, WAN's for enabling the routine, location independent use of large data-objects. Since this is part of the motivation for a distributed storage system, we describe this architecture.

We consider a distributed storage problem in a large-scale wireless sensor network with $n$ nodes among which $k$ acquire (sense) independent data. The goal is to disseminate the acquired information throughout the network so that each of the $n$ sensors stores one possibly coded packet and the original $k$ data packets can be recovered later in a computationally simple way from any $(1+\epsilon)k$ of nodes for some small $\epsilon>0$. We propose two Raptor codes based distributed storage algorithms for solving this problem. In the first algorithm, all the sensors have the knowledge of $n$ and $k$. In the second one, we assume that no sensor has such global information.

In this paper, we study distributed storage problems over unidirectional ring networks, whose storage nodes form a directed ring and data is transmitted along the same direction. The original data is distributed to store on these nodes. Each user can connect one and only one storage node to download the total data. A lower bound on the reconstructing bandwidth to recover the original data for each user is proposed, and it is achievable for arbitrary parameters. If a distributed storage scheme can achieve this lower bound with equality for every user, we say it an optimal reconstructing distributed storage scheme (ORDSS). Furthermore, the repair problem for a failed storage node in ORDSSes is under consideration and a tight lower bound on the repair bandwidth is obtained. In particular, we indicate the fact that for any ORDSS, every storage node can be repaired with repair bandwidth achieving the lower bound with equality. In addition, we present two constructions for ORDSSes of arbitrary parameters, called MDS construction and ED construction, respectively. Particularly, ED construction, by using the concept of Euclidean division, is more efficient by our analysis in detail.

Reliability is essential for storing files in many applications of distributed storage systems. To maintain reliability, when a storage node fails, a new node should be regenerated by a repair process. Most of the previous results on the repair problem assume perfect (error-free) links in the networks. However, in practice, especially in a wireless network, the transmitted packets (for repair) may be lost due to, e.g., link failure or buffer overflow. We study the repair problem of distributed storage systems in packet erasure networks, where a packet loss is modeled as an erasure. The minimum repair-bandwidth, namely the amount of information sent from the surviving nodes to the new node, is established under the ideal assumption of infinite number of packet transmissions. We also study the bandwidth-storage tradeoffs in erasure networks. Then, the use of repairing storage nodes (nodes with smaller storage space) is proposed to reduce the repair-bandwidth. We study the minimal storage of repairing storage nodes. For the case of a finite number of packet transmissions, the probability of successful repairing is investigated. We show that the repair with a finite number of packet transmissions may use much larger bandwidth than the minimum repair-bandwidth. Finally, we propose a combinatorial optimization problem, which results in the optimal repair-bandwidth for the given packet erasure probability and finite packet transmissions.

In this paper we propose distributed flooding-based storage algorithms for large-scale wireless sensor networks. Assume a wireless sensor network with $n$ nodes that have limited power, memory, and bandwidth. Each node is capable of both sensing and storing data. Such sensor nodes might disappear from the network due to failures or battery depletion. Hence it is desired to design efficient schemes to collect data from these $n$ nodes. We propose two distributed storage algorithms (DSA's) that utilize network flooding to solve this problem. In the first algorithm, DSA-I, we assume that every node utilizes network flooding to disseminate its data throughout the network using a mixing time of approximately O(n). We show that this algorithm is efficient in terms of the encoding and decoding operations. In the second algorithm, DSA-II, we assume that the total number of nodes is not known to every sensor; hence dissemination of the data does not depend on $n$. The encoding operations in this case take $O(C\mu^2)$, where $\mu$ is the mean degree of the network graph and $C$ is a system parameter. We evaluate the performance of the proposed algorithms through analysis and simulation, and show that their performance matches the derived theoretical results.

We consider the problem of distributing a file in a network of storage nodes whose storage budget is limited but at least equals to the size file. We first generate $T$ encoded symbols (from the file) which are then distributed among the nodes. We investigate the optimal allocation of $T$ encoded packets to the storage nodes such that the probability of reconstructing the file by using any $r$ out of $n$ nodes is maximized. Since the optimal allocation of encoded packets is difficult to find in general, we find another objective function which well approximates the original problem and yet is easier to optimize. We find the optimal symmetric allocation for all coding redundancy constraints using the equivalent approximate problem. We also investigate the optimal allocation in random graphs. Finally, we provide simulations to verify the theoretical results.

Rapid advances in high performance computing are making possible more complete and accurate computer-based modeling of complex physical phenomena, such as weather front interactions, dynamics of chemical reactions, numerical aerodynamic analysis of airframes, and ocean-land-atmosphere interactions. Many of these 'grand challenge' applications are as demanding of the underlying storage system, in terms of their capacity and bandwidth requirements, as they are on the computational power of the processor. A global view of the Earth's ocean chlorophyll and land vegetation requires over 2 terabytes of raw satellite image data. In this paper, we describe our planned research program in high capacity, high bandwidth storage systems. The project has four overall goals. First, we will examine new methods for high capacity storage systems, made possible by low cost, small form factor magnetic and optical tape systems. Second, access to the storage system will be low latency and high bandwidth. To achieve this, we must interleave data transfer at all levels of the storage system, including devices, controllers, servers, and communications links. Latency will be reduced by extensive caching throughout the storage hierarchy. Third, we will provide effective management of a storage hierarchy, extending the techniques already developed for the Log Structured File System. Finally, we will construct a protototype high capacity file server, suitable for use on the National Research and Education Network (NREN). Such research must be a Cornerstone of any coherent program in high performance computing and communications.

We consider large-scale wireless sensor networks with $n$ nodes, out of which k are in possession, (e.g., have sensed or collected in some other way) k information packets. In the scenarios in which network nodes are vulnerable because of, for example, limited energy or a hostile environment, it is desirable to disseminate the acquired information throughout the network so that each of the n nodes stores one (possibly coded) packet so that the original k source packets can be recovered, locally and in a computationally simple way from any k(1 + \epsilon) nodes for some small \epsilon > 0. We develop decentralized Fountain codes based algorithms to solve this problem. Unlike all previously developed schemes, our algorithms are truly distributed, that is, nodes do not know n, k or connectivity in the network, except in their own neighborhoods, and they do not maintain any routing tables.

We consider large-scale sensor networks with n nodes, out of which k are in possession, (e.g., have sensed or collected in some other way) k information packets. In the scenarios in which network nodes are vulnerable because of, for example, limited energy or a hostile environment, it is desirable to disseminate the acquired information throughout the network so that each of the n nodes stores one (possibly coded) packet and the original k source packets can be recovered later in a computationally simple way from any (1 + \epsilon)k nodes for some small \epsilon > 0. We developed two distributed algorithms for solving this problem based on simple random walks and Fountain codes. Unlike all previously developed schemes, our solution is truly distributed, that is, nodes do not know n, k or connectivity in the network, except in their own neighborhoods, and they do not maintain any routing tables. In the first algorithm, all the sensors have the knowledge of n and k. In the second algorithm, each sensor estimates these parameters through the random walk dissemination. We present analysis of the communication/transmission and encoding/decoding complexity of these two algorithms, and provide extensive simulation results as well

We consider the use of distributed storage (DS) to reduce the communication cost of content delivery in wireless networks. Content is stored (cached) in a number of mobile devices using an erasure correcting code. Users retrieve content from other devices using device-to-device communication or from the base station (BS), at the expense of higher communication cost. We address the repair problem when a device storing data leaves the cell. We introduce a repair scheduling where repair is performed periodically and derive analytical expressions for the overall communication cost of content download and data repair as a function of the repair interval. The derived expressions are then used to evaluate the communication cost entailed by DS using several erasure correcting codes. Our results show that DS can reduce the communication cost with respect to the case where content is downloaded only from the BS, provided that repairs are performed frequently enough. If devices storing content arrive to the cell, the communication cost using DS is further reduced and, for large enough arrival rate, it is always beneficial. Interestingly, we show that MDS codes, which do not perform well for classical DS, can yield a low overall communication cost in wireless DS.