S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based Data Delivery Using Broadcast Disks," IEEE Personal Communications, pp. 50-- 60, Dec. 1995.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....for higher rates of packet loss. This general approach also does not enable receivers to join the session dynamically. To eliminate the need for retransmission and to allow receivers to access data asynchronously, the use of a data carousel or broadcast disk approach can ensure full reliability [1]. In a data carousel approach, the source repeatedly loops through transmission of all data packets. Receivers may join the stream at any time, then listen until they receive all distinct packets comprising the transmission. Clearly, the reception overhead at a receiver, measured in terms of ....

S. Acharya, M. Franklin, and S. Zdonik, \Dissemination Based Data Delivery Using Broadcast Disks," IEEE Personal Communications, December 1995, pp. 50-60.

....systems application In push systems, servers broadcast pages over broadcast channels to clients. Clients who wish to access one of the broadcasted pages listen to the channels until they receive this page. In traditional push systems (e.g. the Teletext problem [2] and the Broadcast Disks problem [1]) the server broadcasts more popular pages more frequently to minimize the average access time for clients. In some situations, the server does not have this freedom since it broadcasts information of some providers who paid for some quality of service. These situations were considered by [7, ....

S. Acharya, M. J. Franklin, and S. Zdonik. Dissemination-based Data Delivery Using Broadcast Disks. IEEE Personal Communications, Vol. 2(6), 50-60, 1995.

....mechanism to disseminate data since multiple clients can have their requests satis ed simultaneously. A large amount of work in the database and algorithms literature has focused on scheduling problems based on a broadcasting model (including several PhD theses from Maryland and Brown) [7, 9, 4, 1, 5, 2, 8, 23, 6]. Broadcasting is used in commercial systems, including the Intel Intercast System [15] and the Hughes DirecPC [13] There are two primary kinds of models that have been studied the rst kind is a push based scheme, where some assumptions are made on the access probability for a certain data ....

S. Acharya, M. Franklin, and S. Zdonik. Dissemination-based data delivery using broadcast disks. In IEEE Personal Communications, 2(6), 1995.

....outperforms existing prefetching algorithms under various scenarios. Index Terms Cache management, prefetch, invalidation report, power conservation, stretch. I. INTRODUCTION B ROADCASTING has been shown to be an effective data dissemination technique in wireless networks by many studies [2], 3] 13] 14] With this technique, clients access data by simply monitoring the broadcast channel until the requested data appear in the channel. The broadcasting model exploits the asymmetric nature of the wireless channel, where more bandwidth is available for the downlink (serverto ....

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based Data Delivery Using Broadcast Disks," IEEE Personal Communications, pp. 50--60, Dec. 1995.

....instead of upon client requests, a broadcast schedule needs to be designed such that data appear on the schedule in a sequence that most requests can be satisfied with short waiting time. Flat disk [1] multi disks [1] fair queuing scheduling [5, 8] and many other data scheduling algorithms [2, 3, 4, 6, 7, 9] are proposed to address this issue. Although better overall average response time can be achieved by using proper scheduling algorithms, it is not efficient enough for all client applications to completely depend on server broadcasting. When the database is relatively large, the delay of data ....

Acharya, S., Franklin, M., and Zdonik, S., "Dissemination-based Data Delivery Using Broadcast Disks," IEEE Personal Communications, Vol. 2, No. 6, 1995, pp. 50-60.

....b) Clock based Figure 9: Web server workload. This figure shows the performance of LRU and Clock based algorithms when run on a file system trace of a web server providing art images. Graph A shows the results of the LRU based algorithms. Clock based algorithms are in Graph B. Broadcast disks [1, 2] continuously deliver data to clients through an asymmetric link following a broadcast schedule that is best able to meet the client s needs. When a client s needs are not met by the broadcast schedule, the client cache strives to manage the cache contents to mask the non ideal broadcast schedule. ....

S. Acharya, M. J. Franklin, and S. B. Zdonik. Disseminationbased Data Delivery Using Broadcast Disks. IEEE Personal Communications, 2(6), December 1995.

....ratio (i.e. percentage of requests served) as well as low mean waiting time for the requests. Performance evaluation results based on simulations are provided. 1 Introduction In a wireless environment, providing a large population of clients with access to data is a significant challenge [3]. In recent years, data broadcasting has been studied extensively (e.g. 5, 6, 9, 10, 17, 11, 12, 7] as a mechanism for information delivery. In this approach, a server broadcasts the data over a broadcast channel which is listened to by all the users. All pending requests for a given data item ....

....waiting time for the users, the broadcast schedule must be chosen by taking into account the demands for various data items. Prior work on broadcast scheduling has considered different ways of reducing the waiting time and energy consumption, for instance, by scheduling the broadcast properly [5, 4, 16, 15, 3, 14], by utilizing client side caching and prefetching [17, 2, 3, 1] or by energy efficient indexing [11] Prior research assumes that once a data request is generated by a user, the request will be held until it is satisfied. This assumption is not always true in practice. For various reasons, users ....

[Article contains additional citation context not shown here]

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based data delivery using broadcast disks," IEEE Personal Communication, pp. 50--60, Dec. 1995.

....: 6 3.3 On line Scheduling Algorithm : 8 3.4 On line Algorithm with Bucketing : 9 3.4. 1 Comparison of Buckets and Multi disk [3] : 11 4 Effect of Transmission Errors on Scheduling Strategy 11 5 Multiple Broadcast Channels 13 6 Performance Evaluation 14 6.1 Demand Probability Distribution : 15 6.2 Length ....

....evaluate these algorithms: ffl Access time: This is the amount of time a client has to wait for some information that it needs. It is important to minimize the access time so as to decrease the idle time at the client. Several researchers have considered the problem of minimizing the access time [4, 6, 10, 11, 12, 7, 3, 2, 18, 19] ffl Tuning time: This is the amount of time a client must listen to the broadcast until it receives the information it needs. It is important to minimize the tuning time, because the power consumption of a wireless client is higher when it is listening to the transmissions, as compared to when ....

[Article contains additional citation context not shown here]

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based data delivery using broadcast disks," IEEE Personal Communication, pp. 50--60, Dec. 1995.

....the desirability of this technology in some application domains. First, if clients request the full file and can tolerate relatively high start up delays (say, approaching the file playback duration) it is unknown how the scalable streaming protocols compare to scalable download protocols (e.g. [1,3,6,20]) with respect to required server bandwidth . By download, we mean protocols in which clients receive all of the media data prior to beginning playback, in contrast to streaming in which clients can begin playback while concurrently receiving subsequent media data. Since, scalable download ....

S. Acharya, M. J. Franklin, and S. Zdonik, "Dissemination-based Data Delivery Using Broadcast Disks", IEEE Personal Communications 2, 6 (Dec. 1995), pp. 50-60.

....data item is likely to be distributed to many clients. Data broadcasting is considered to be an efficient way, in terms of bandwidth and energy, for the distribution of such information for both wireless and wired communication environments and has been extensively studied (see [11] 12] [14] and [15] Furthermore, broadcast transmission compared to traditional unicast can be much more efficient for disseminating information, because unicast by having to transmit every data item, often identical, at least once for every client who requests it, creates scalability problems as the ....

....data broadcast. Intel has also been broadcasting data along with normal TV signals, 9] 1. 1 Related Work The problem of determining an efficient broadcast schedule for information distribution systems has been extensively studied in the past ( 1] 2] 3] 4] 5] 10] 11] 12] and [14]) In [1] the authors propose the RxW scheduling algorithm which calculates the product of the number of outstanding Requests (R) times the Wait time (W) of the oldest outstanding request for all data items corresponding to the requests pending in the broadcast server queue. The data item with ....

S. Acharya, M. Franklin, S. Zdonik, "Dissemination-based Data Delivery Using Broadcast Disks", IEEE Personal Communications, 2(6), 1995.

....work, the effect of transmission errors is not considered. We assume that when a data item is broadcast, all the users requesting that item receive it completely. It is assumed that access probabilities follow the Zipf [21] distribution over the database items as in many other related work (e.g. [3, 5, 20]) Data items are supposed to be ordered in the database according to their access probabilities in decreasing order, i.e. the most favorite data item is in the first place in the database. Zipf s law states that the relative probability of a request for the i th most popular data item is ....

S. Acharya, M. J. Franklin, and S. Zdonik. Dissemination-based data delivery using broadcast disks. IEEE Personal Communications, 2(6):50--60, December 1995.

....large or for higher rates of packet loss. Their approach also does not enable receivers to join the session dynamically. To eliminate the need for retransmission and to allow receivers to access data asynchronously, the use of a data carousel or broadcast disk approach can ensure full reliability [1]. In a data carousel approach, the source repeatedly loops through transmission of all data packets. Receivers may join the stream # Erasure codes are sometimes called forward error correcting codes (FEC codes) in the networking community. However, FEC often refers to codes that detect and ....

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination Based Data Delivery Using Broadcast Disks," IEEE Personal Communications, December 1995, pp. 50-60.

....is common for storage systems. Second, web caching often uses whole document caching, which differs from fixed size blocks used in storage systems. Finally, in web caching, the replacement cost of one web page is not strongly correlated with the replacement costs of other pages. Broadcast disks [1, 2] continuously deliver data to clients through an asymmetric link following a broadcast schedule that is best able to meet the client s needs. When a client s needs are not met by the broadcast schedule, the client cache strives to manage the cache contents to mask the non ideal broadcast schedule. ....

S. Acharya, M. J. Franklin, and S. B. Zdonik. Disseminationbased Data Delivery Using Broadcast Disks. IEEE Personal Communications, 2(6), December 1995.

....only supports session level adaptation. The problem of reliable distribution of bulk data to many receivers was studied extensively. Proposed solutions included those that use techniques such as local repair, polling or hierarchy [14] 10] 25] 13] 11] Additionally, the data carousel approach [51] was proposed to eliminate retransmission and to ensure full reliability at the expense of high overhead. Furthermore, forward error correction based on erasure codes was proposed to achieve reliable multicast [44] 45] 13] 46] 47] 49] 50] 27] Recently, Nonnenmacher, Biersack and Towsley ....

S. Acharya, M. Franklin and S. Zdonik, "Dissemination Based Data Delivery Using Broadcast Disks," IEEE Personal Communications, December 1995, p. 50-60.

....method for delivering popular files with a minimal footprint on a single server leverages network mechanisms such as native multicast. Researchers have built scalable solutions which use non adaptive, cyclic transmissions over multicast or broadcast channels to provide eventual reliability [2] [1], and more sophisticated solutions which employ forward error correction to achieve scalable reliability without a significant performance penalty [12] 26] These solutions scale to large audiences, as the marginal cost of adding an additional client as perceived by the server is near zero. The ....

S. Acharya, M. Franklin, and S. Zdonik. Dissemination based data delivery using broadcast disks. In IEEE Personal Communications, pages 50--60, December 1995.

No context found.

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based Data Delivery Using Broadcast Disks," IEEE Personal Communications, pp. 50-- 60, Dec. 1995.

No context found.

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based data delivery using broadcast disks," IEEE Personal Commun., vol. 2, pp. 50--60, Dec. 1995.

No context found.

S. Acharya, M. Franklin and S. Zdonik. "Dissemination-Based Data Delivery Using Broadcast Disks." Personal Communications, 2(6), December 1995.

No context found.

Swarup Acharya, Michael Franklin, and Stanley Zdonik. Dissemination-based data delivery using broadcast disks. IEEE Personal Communications, 2(6), December 1995.

No context found.

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-Based Data Delivery Using Broadcast Disks", IEEE Personal Communications, 50-60, Dec. 1995.

No context found.

Acharya, S., Franklin, M. and S. Zdonik, "Dissemination - Based Data Delivery Using Broadcast Disks", IEEE Personal Communications, pp.50-60, Dec 1995.

No context found.

S. Acharya, M. Franklin, and S. Zdonik, "Dissemination-based data delivery using broadcast disks," IEEE Person. Commun., pp. 50--60, Dec. 1995.

No context found.

S. Acharya, M. Franklin, and S. Zdonik. Dissemination-based data delivery using broadcast disks. IEEE Personal Communications, 2(6), 1995.

No context found.

Swarup Acharya, Michael Franklin, and Stanley Zdonik. "Dissemination-based Data Delivery using Broadcast Disks", IEEE Personal Communications. Dec. 1995

No context found.

S. Acharya, M. Franklin, and S. Zdonik, Dissemination-based data delivery using broadcast disks. IEEE Personal Communication, pp. 50--60, Dec. 1995

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC