Jonathan C. L. Liu

Performance of a Mass-Storage System for Video-on-Demand

Advancements in storage technology along with the fast deployment of high-speed networks has allowed the storage, transmission, and manipulation of multimedia information such as text, graphics, still images, video, and audio to be feasible. Our study focused on the performance of the mass storage system for a large-scale video-on-demand server. Different video file striping schemes, such as application level striping and device driver level striping, were examined in order to study scalability and performance issues. To study the impact of different concurrent access patterns on the performance of a server, experimental results were obtained on group access on a single video file and multiple group accesses on multiple video files. All of our experiments were conducted on a fully configured Silicon Graphics Inc. Onyx computer system. The Onyx machine was connected to 31 SCSI-2 channels which have 496 GBytes disk storage, 20 MIPS R4400 processors, and 768 MBytes main memory. From the experimental results, the storage system of Onyx machine can potentially provide about 360 concurrent video accesses with guaranteed quality of service.

A survey of distance education challenges and technologies

Distance education, e-learning, and virtual university are similar terms for a trend of modern education. It is an integration of information technologies, computer hardware systems, and communication tools to support educational professionals in remote teaching. This chapter presents an overview of distance education from the perspective of policy, people, and technology. A number of questions frequently asked in distance learning panel discussions are presented, with the suggested answers from the authors. The survey presented in this chapter includes communication, intelligent, and educational technologies of distance education. Readers of this 2 Shih, Hung, Ma, and Jin Copyright

Efficient video file allocation schemes for video-on-demand services

Abstract. A video-on-demand (VOD) server needs to store hundreds of movie titles and to support thousands of concurrent accesses. This, technically and economically, imposes a great challenge on the design of the disk storage subsystem of a VOD server. Due to different demands for different movie titles, the numbers of concurrent accesses to each movie can differ a lot. We define access profile as the number of concurrent accesses to each movie title that should be supported by a VOD server. The access profile is derived based on the popularity of each movie title and thus serves as a major design goal for the disk storage subsystem. Since some popular (hot) movie titles may be concurrently accessed by hundreds of users and a current high-end magnetic disk array (disk) can only support tens of concurrent accesses, it is necessary to replicate and/or stripe the hot movie files over multiple disk arrays. The consequence of replication and striping of hot movie titles is the potential increase on the required number of disk arrays. Therefore, how to replicate, stripe, and place the movie files over a minimum number of magnetic disk arrays such that a given access profile can be supported is an important problem. In this paper, we formulate the problem of the video file allocation over disk arrays, demonstrate that it is a NP-hard problem, and present some heuristic algorithms to find the near-optimal solutions. The result of this study can be applied to the design of the storage subsystem of a VOD server to economically minimize the cost or to maximize the utilization of disk arrays.

Supporting random access on real-time retrieval of digital continuous media

In addition to the large data size requirement and real-time constraint in continuous media, future video applications such as video editing demand a random access capability at the video-frame level. This paper introduces our study on effective buffering control for the real-time retrieval of jitter-free digital video medium. We adopt a video-frame level approach to maintaining the flexibility on placement and analysing the efficiency of the buffering schemes. An integrated solution which offers efficient buffering schemes and flexible storage placement to support random access is our goal. We present two buffering schemes: the two-buffer scheme and the k-buffer compensation scheme. The two-buffer scheme requires that all the frames in a block are stored consecutively, while providing random access between blocks. However, this intuitive buffering scheme potentially requires a large block size and buffer space. The k-buffer compensation scheme is proposed to resolve this large buffer space requirement, by using more than two buffers and requiring a minimal number of blocks randomly placed in each cylinder. This scheme differs from the contiguous placement scheme because individual blocks can be stored anywhere in each cylinder. Compared to the two-buffer scheme, the k-buffer compensation scheme requires less buffer space, has higher disk utilization and finer granularity on disk data transfer. The placement requirements are more flexible and implementable than the contiguous and storage pattern placement schemes. Experimental measurement results reveal the significant improvements on the buffer-size reduction and placement flexibility by using the k-buffer compensation scheme. Extensions of the k-buffer compensation scheme to support multiple streams are also addressed.

Controlling the process with distributed multimedia

The process control industry has many uses for multimedia, from incorporating diverse imaging sensors to visualizing, monitoring and controlling time-critical processes. A distributed client-server architecture, together with specialized image-processing hardware and a number of commercial products, demonstrates the effectiveness of using multimedia data in a simulated film-coating process. >

Handoff algorithms in dynamic spreading WCDMA system supporting multimedia traffic

The undergoing third-generation wireless network needs to support the integration of voice and multimedia data services with varying quality-of-service (QoS) requirements. It is critical that the least bit-error rate (BER) for voice traffic, World Wide Web (WWW) traffic, and streaming video traffic be guaranteed at all time. In this paper, we discussed the integration of soft handoff and dynamic spreading factor in wideband code-division multiple-access system in supporting multimedia traffic. The contribution of our work is twofold. First, the processing time of the handoff request is analyzed. We found that intensive mobile handoff might consume significant amount of access channel time and increase the delay of handoff. We, therefore, proposed a batch mechanism such that multiple handoff requests could be processed simultaneously. The average delay is reduced from 1.12 s to 800 ms at heavy handoff rate. Our second contribution is a new resource allocation algorithm, where the spreading factor and transmission power for the handoff mobiles are jointly considered to maximize the throughput. The BER requirements for the handoff mobiles and the target cell are maintained during the handoff process. The original problem is formulated into a nonlinear programming format. We proposed a procedure to simplify it into a linear constraint problem, which is solved by a revised simplex method. Numerical results show a 25% increase in throughput for WWW traffic and a 26% improvement for the video traffic.

Supporting Video Data in Wireless Sensor Networks

In this paper, we investigate issues associated with the transporting of multimedia streams across wireless sensor networks. We developed a prototype wireless sensor device that is capable of streaming video data through its wireless interface. Our experiments results showed that wireless sensor networks perform poorly with existing networking stack for such applications due to long delivery path and small transmission buffer sizes on the relaying nodes. The effect of a poor link often propagates backwards upstream and causes unnecessary data retransmission. To overcome these problems, we proposed a pipelined transmission scheme with a novel flow control method that monitors local buffer levels. A secondary buffer scheme is also used to reduce the retransmission overhead caused by node failure. Simulation results show that the proposed scheme significantly increase the network efficiency. We also propose a novel stochastic route discovery algorithm for multiple video stream in wireless sensor networks. Our method uses a probing stage where possible routes are explored and their delivery performance recorded. The data collected during the probing stage are used to select the final routes.

An integrated network/storage architecture for sharing high-quality broadcast TV contents

With the advent of personal video recorders (PVRs), the way people watch TV is rapidly changing. By recording or time-shifting live TV programs into the embedded-disk storage of a PVR, people can watch what they want independent of the broadcasting schedule. Furthermore, peer-to-peer networking technology provides an additional TV content distribution channel to unidirectional broadcasting. However, due to the current limited broadband bandwidth, it is difficult to support high-quality TV content streaming between PVRs on the Internet. In this article we propose novel integrated network/storage architecture to provide the streaming of high-quality broadcast TV contents over fast network connections. To take full advantage of our system resources, we also develop efficient sharing schemes such as matching of a communication pair and channel assignment for extensive time-shifting.

Multimedia support for wireless W-CDMA with dynamic spreading

The emerging multimedia communication needs more support in operating systems in order to be successful over a wireless environment. The system needs to support a seamless integration (i.e., transparent application switching) of voice, audio and conventional data (e.g., e-mails, and ftp). It should also support multiple users with a guaranteed quality. In this paper, we investigate effective protocol design with dynamic spreading factors such that various QoS based on different traffic types can be provided. Increasing spreading factors can benefit the system because it will increase the desired signal strength linearly. The measured bit error rate can be reduced 75 times with a long spreading factor. By taking advantage of this benefit, we propose some middle-ware solutions to monitor the network load and switch the spreading factors dynamically based on the current load with multimedia traffic. These middle-ware solutions are implemented in mobile and base stations and experiments are performed to measure the actual system performance. The preliminary results indicate that our proposed system can always maintain a desired quality for all the voice connections. We further extend our protocol to guarantee a balanced support among different traffic types. While the voice communication is still guaranteed to be non-interrupted, the data traffic is proved to be served with reasonable response time by our proposed system.

Traffic dispersion strategies for multimedia streaming

Traditional multimedia streaming techniques usually assume single-path (unicast) data delivery. But when the aggregate traffic between 2 nodes exceeds the bandwidth capacity of single link/path, a feasible solution is to appropriately disperse the aggregate traffic over multiple paths between these 2 nodes. In this paper we propose a set of multi-path streaming models for MPEG video traffic transmission. In addition to the attributes (such as load balancing and security) inherited from conventional data dispersion models, the proposed multimedia dispersion models are designed to achieve high error-free frame rate based on the characteristics of MPEG video structure. Our simulation results show that significant quality improvement can be observed if the proposed streaming models are employed appropriately.