Dynamic Buffer Allocation in Video-on-Demand Systems

2013

Proceedings International Phoenix Conference on Computers and Communications, 1995

A s the number of video streams to be supported b y a Dig-ita1 Video Delivery System (DVDS) increases, we more and more start to understand that the ability to reliably and cost-eficiently support a considerable number of video streams (in the magnitude of tens of thousands) largely depends on software capabilities. Even in the presence of the best hardware configuration (not ignoring software vs hardware costs), the software exploitation of the hardware capabilities is of paramount importance. It is imperative that current software developments account for the eventual scalability of the number of video streams without commensurate increase in hardware. In this paper, we present strategies for the management of video streams in order to maintain and satisfy their space and time requirements. We present a detailed analysis of the issues related to queuing I / O requests and data buffering. The designs for the arrangement and scheduling of 1/0 requests and data buffers are presented with the objective of guaranteeing the required data availability rates for continuous media display. cation, data striping, stream management, video delivery. to remember that one of the perturbing characteristics of video data is its enormous size. A result of that is the amount of data that is consumed per unit time during video display. Its continuous nature requires that there should not be a data lapse with respect to data availability during display. In addition to the fact that video data are inherently large, even after compression, the quaility of video affects its size. The better the quality, the larger the size. Several architectural configurations for efficient and reliable storage and delivery of video data have been proposed and utilized [1]-[8]. Some of these works address only the configurability of the system components while others address only the support of small number of video streams, in the magnitude of less than 10,000. Although it is arguable that the DVDSs are relatively in their infancy, it is necessary that current software developments account for the scalability of the number of video streams without commensurate increase in hardware. As the number of video streams increases, the ability to support them increasely depends on the software capabilities. In this paper, we describe a protocol for the managetheir space and time requirements. we use a DVDS architectural model based on partitioned nodes where one node partition is responsible for data retrieval while the other accepts user requests, determines object locations, Keywords: buffer queues, buffer scheduling, data all@ ment of video streams in order to maintain and satisfy 2 DVDS Architectural Model

Lecture Notes in Computer Science, 2001

In spite of the attractiveness of Video-on-demand (VoD) services, their implantation to the present has not been as widespread as could have been desired due to centralized VoD systems have a limited streaming capacity and its grown is costly. One level proxy-based systems have been proposed to increase the system capacity but their scalability are still limited by the main network bandwidth. Our investigation are focussed on designing a flexible LVoD (large-scale Video-on-Demand) system capable of easy scaling with limited costs, which can adapt its size to the needs of the system. To achieve a scalable LVoD system, it is essential that the communications system bandwidth is able to grow in keeping with system growth (with a reasonable cost and limited loss of efficiency). To get these requirements we have proposed a hierarchical tree topology based on the use of independent local networks with proxies. To allow the system's grow, the functionality of the proxy has been modified in such a way that it works at the same time as cache for the most watched movies, and as a mirror for the remaining movies. The evaluation of these systems has been done using an analytical model. The results shows that this architecture guarantees unlimited and low-cost growth for LVoD systems, the VoD system capacity can easily be adapted to any number of users and the system is fault-tolerant. 1 Introduction. Video-on-demand (VoD) systems have been one of the most active areas of research in recent years due to the coming together of two factors: the growing interest from diverse sectors of industry (entertainment, education, information, cable companies, telecommunications, etc.) in developing such systems, and the great complexity that these systems have (integrating various types of information together with real-time requisites, very strict quality of service levels, a great number of users and a high volume of information). In spite of the attractiveness of these services for the public in general, their implantation to the present has not been as widespread as could have been desired. The construction of large-scale video-on-demand (LVoD) is currently limited both by the capacity of the server as well as by the capacity for simultaneous transmissions that can be supported by a communication network (network bandwidth), limitations on the subsequent growth of these systems, the significant initial investment required and high maintenance costs, among others.

SSRN Electronic Journal, 2019

ÎÖ²ÍÞÂÀÍÍß ÑÒ²ÉÊÎÑÒ² ÃÓÌÎÂÈÕ ÓÙ²ËÜÍÞÂÀײ ÄÂÈÃÓͲ ÄÎ Ä²Ñ Ó̲ØÅÂÎÃÎ ÄÈÇÅËÜÍÎÃÎ ÏÀËÈÂÀ ÄÂÍÇ Óêðà¿íñüêèé äåðaeàâíèé õ³ì³êî-òåõíîëîã³÷íèé óí³âåðñèòåò, ì. Äí³ïðî, Óêðà¿íà  ðîáîò³ îõàðàêòåðèçîâàíî ñîðáö³éíî-äèôóç³éí³ âëàñòèâîñò³ ãóì ïðè êîíòàêò³ ç ïàëèâàìè, ùî ì³ñòÿòü ìåòèëîâ³ åñòåðè aeèðíèõ êèñëîò ç íåõàð÷îâî¿ ñèðîâèíè. Âèñóíóòà ã³ïîòåçà ùîäî çàëåaeíîñò³ ìàñëîñò³éêîñò³ ãóì â³ä ¿õ ïàðàìåòðà ðîç÷èííîñò³ áóòà䳺í-í³òðèëüíîãî êàó÷óêó. Âëàñòèâîñò³ ñòàíäàðòíèõ îëèâîñò³éêèõ ãóì íà îñíîâ³ áóòà䳺í-í³òðèëüíèõ êàó÷óê³â ìàðîê ÑÊÍ-18 òà ÑÊÍ-40 ïîð³âíþâàëè ç ãóìàìè íà îñíîâ³ êàó÷óê³â ìàðêè ÑÊÍ-18 ³ õëîðîïðåíîâîãî êàó÷óêó ìàðêè Áàéïðåí 110, äî ÿêèõ áóâ äîäàíèé ïëàñòèô³êîâàíèé ïîë³â³í³ëõëîðèä â ê³ëüêîñò³ 30% â êîaeíèé. Âñòàíîâëåíî, ùî íàéñèëüí³øîãî ðóéí³âíîãî âïëèâó íà âñ³ ï³ääîñë³äí³ çðàçêè ãóìè, êð³ì ãóì íà îñíîâ³ êàó÷óêó ìàðêè ÑÊÍ-40, çàâäຠêîíòàêò ³ç ïàëèâíîþ êîìïîçèö³ºþ, ÿêà ñêëàäàºòüñÿ ³ç 70% äèçåëüíîãî ïàëèâà òà 30% ìåòèëîâèõ åñòåð³â aeèðíèõ êèñëîò, âèãîòîâëåíèõ ç òåõí³÷íî¿ ñîíÿøíèêîâî¿ î볿. Âèçíà÷åíî, ùî ãóìà íà îñíîâ³ êàó÷óêó ÑÊÍ-40, ÿêèé õàðàêòåðèçóºòüñÿ ìàêñèìàëüíèì ïàðàìåòðîì ðîç÷èííîñò³, º íàéá³ëüø ñò³éêîþ ïî â³äíîøåííþ äî ïàëèâíèõ êîìïîçèö³é, ùî ì³ñòÿòü ìåòèëîâ³ åñòåðè aeèðíèõ êèñëîò ð³çíîãî ïîõîäaeåííÿ. Íà ï³äñòàâ³ àíàë³çó åêñïåðèìåíòàëüíèõ äàíèõ íàäàí³ ðåêîìåíäàö³¿ ùîäî âèêîðèñòàííÿ ãóìè íà îñíîâ³ êàó÷óêó ÑÊÍ-40 äëÿ âèãîòîâëåííÿ óù³ëüíþâà÷³â àâòîìîá³ëüíèõ äâèãóí³â â óìîâàõ ñâ³òîâî¿ òåíäåíö³¿ ùîäî çá³ëüøåííÿ ÷àñòêè àëüòåðíàòèâíèõ êîìïîíåíò³â ó äèçåëüíèõ ïàëèâàõ.

There has been an increasing trend in designing the Video-on-Demand systems using parallel server-based architectures to meet the client demands for online streaming of videos. We use a distributed architecture for effective Buffer management which efficiently utilizes various server resources like the disk Bandwidth, memory utilization and provides clients with VCR like functionalities. In this paper we proposed a unique On-line dynamic buffer replacement policy that does not base its results solely on a single parameter such as video popularity but calculates a cumulative popularity based on several other factors and hence chooses the video with the least popularity thus calculated. It is necessary to batch requests to minimize the bandwidth requirement, to reduce I/O demand, improve throughput and increase the number of customers served by using less number of streams. We proposed a Modified Adaptive Batching Policy for batching requests arriving at a server. This is different fr...

2005

One of the most important characteristics of videoondemand (VOD) services is their very high bandwidth requirements. Assuming that the videos are in MPEG -2 format, each user request will require the delivery of approximately six megabits of data per second. Hen ce, a video server allocating a separate stream of data t o each request would need an aggregate bandwidth of six gi gabits per second to accommodate one thousand overlapping requests. Servers capable of handling such bandwid ths require a costly infrastructure, typically consisti ng of a large number of computing nodes linked by sophistic ated interconnection network. This situation has led to numerous proposals aimed at reducing the bandwidth requirements of VOD services . These proposals can be broadly classified into two groups. Proposals in the first group are said to be proactive because they distribute each video according to a fixed sch edule that is not affected by the presence–or the absence–of r quests for that vi...

Proceedings 23rd Euromicro Conference New Frontiers of Information Technology - Short Contributions -, 1997

Memory management is a key issue when designing cost-effective video-on-demand servers. State-of-the-art techniques, like double-buffering, allocate buffers in a per-stream basis and require huge amounts of memory. In this paper, we propose a buffering policy, namely Single Pair of Buffers, that reduces dramatically server memory requirements by reserving a pair of buffers per storage device. By considering in detail disk and network interaction we have also identified the particular conditions under which this policy can be successfully applied to engineer Video-On-Demand servers. Reduction factors of two orders of magnitude compared to the double-buffering approach can be obtained. Current disk and network parameters make this technique feasible.

IEEE Transactions on Multimedia, 2004

The focus of the research presented in this paper is the end-to-end analysis of a distributed Video-on-Demand (VoD) system. We analyze the distributed architecture of a VoD system to design global request handling and admission control strategies and evaluate them using global metrics. The performance evaluation methodology developed in this paper helps in determining efficient ways of using all resources in the VoD architecture within the constraints of providing guaranteed high quality service to each request. For instance, our simulation results show that request handling policies based on limited redirection of blocked requests to other resources perform better than load sharing policies. We also show that request handling policies based on redirection have simpler connection establishment semantics than load sharing policies and, therefore, are easily incorporated into reservation or signaling protocols.

The traditional start-to-finish playback model is not suitable for all modern interactive video streams. Users expect support for higher levels of interactivity such as fast forward and rewind or the ability to arbitrary seek within their media quickly and efficiently. By conducting user studies we have observed start-to-finish is not applicable to many genres of video, and that different playback models fit better. We discuss how existing delivery techniques are impacted by these new observations. Novel interactive controls such as bookmarks have also highly impacted user behaviour. This has lead to the segments within the media being accessed in a uneven fashion, causing hotspots of interest to form; areas with orders of magnitudes more viewers than others. These hotspots typically began at the beginning of a bookmark, however not always, which lead us to design a dynamic bookmark positioning algorithm. As well as their position, determining the hotspot's length can be beneficial. This aids in autonomic techniques such as replication and pre-fetching as well as allowing the users to find what they want quicker. Under high level of interactivity, delivery techniques are less efficient due to the unpredictability of the users. We however developed techniques which restore some of this predictability, allowing clients or servers to predict future actions based on past user actions. These technique proves exceeding useful for pre-fetching which reduces seek latencies for client and can reduce load on servers. However knowledge of past user activities need to be gathered from network, thus we develop techniques to do this in a distributed manner.

2008

Due to high buffer and bandwidth requirement and rate variability of compressed video, delivering video across the wide area networks is a challenging issue. Proxy servers have been used to reduce bandwidth requirement and improve client access time on the internet by caching the passing data. In this paper, we propose a unique VoD architecture and On-line dynamic buffer allocation algorithm for efficient buffer and bandwidth management. This scheme reduces the bandwidth requirement between the main multimedia sever and the Proxy servers. Also reduces the client waiting time by sharing the videos among the proxy servers of the Local proxy servers group, by allocating and then reallocating the buffer at Proxy sever (PS) dynamically based on the current frame size. The proposed scheme results in efficient usage of buffer and bandwidth for the videos, very low request rejection ratio. And also results in low client waiting time by balancing the load among the neighboring proxy servers ...