an-Tse Yu

An adaptive control scheme for real-time media streaming over wireless networks

Real time video streaming over wireless networks is not trivial because of the two characteristics of the wireless networks - (1) smaller bandwidth and (2) unreliable transmission media. An adaptive real-time video streaming scheme that uses the layered video technique is proposed. Two attributes that are used to determine the network situation and then adjust the sending rate accordingly are loss rate and round trip time (RTT). Since the unreliable media cause of packet loss in the wireless environment is rate-independent, a method that can separate the rate-independent loss from the congestion loss is needed. We use inter-arrival time between two received packets to identify if an out of order packet was received in time to do the packet loss separating. When a congestion situation is determined, the sending rate of the sender is dropped down one layer; when an unloaded situation is determined, the sending rate of the sender is raised up one layer. In this way, the adaptive real-time video streaming can be achieved for wireless networks.

Location-aware multimedia proxy handoff over the IPv6 mobile network environment

In a server-proxy-client 3-tier networking architecture that is executed in the mobile network, proxies should be dynamically assigned to serve mobile hosts according to geographical dependency and the network situation. The goal of proxy handoff is to allow a mobile host still can receive packets from the corresponding server while its serving proxy is switched from the current one to another one. Once proxy handoff occurs, a proper proxy should be selected based on the load balance concern and the network situation concern. In this paper, a 3-tier Multimedia Mobile Transmission Platform, called MMTP, is proposed to solve the proxy handoff problem in the IPv6-based mobile network. A proxy handoff scheme based on the application-layer anycasting technique is proposed in MMTP. A proper proxy is selected from a number of candidate proxies by using the application-layer anycast. An experimental environment based on MMTP is also built to analyze the performance metrics of MMTP, including load balance among proxies and handoff latency.

Efficient resource reservation based on communication paradigms for multicast multimedia applications

In modern multimedia applications, heterogeneous hosts may get involved in a complicated multicast communication paradigm. For facilitating the analysis on resource reservation in such an environment, a useful model for describing the multicast communication paradigm, termed the CP graph, is presented in this paper. Based on this model, we develop a set of reservation modeling frameworks, respectively employing the RSVP reservation scheme and a proposed scheme. We prove the proposed scheme is able to achieve more efficient reservation than the RSVP scheme, while incurs very limited information and processing overheads. We simulate two applications: one with a distant learning scenario and the other B2B bargain scenario. The simulation results confirm the effectiveness of our scheme.

A video caching policy for providing differentiated service grades and maximizing system revenue in hierarchical video servers

A video server normally targets at providing abundant bandwidth access and massive storage in supporting large-scale video archival applications. Its performance is sensitive to the deployment of the stored contents. In this paper, we propose a video caching policy for a video server, based on the knowledge of video profiles, namely: access rate, video size and bandwidth, tolerable rejection probability, and rental price. We consider the video server as having a hierarchical architecture which consists of a set of high-speed disk drives located in the front end for caching a subset of videos, and another set of high-capacity tertiary devices located in the back end for archiving the entire video collection. The front-end disks particularly, are organized together by employing a proposed data striping scheme, termed the adaptive striping (AS), which is flexible on heterogeneous disk integration. The proposed policy determines what video set should be cached, and how to arrange them in the front-end disks with two objectives in mind: (1) offering differentiated service grades conforming to the video profiles as well as (2) maximizing the overall system revenue. We simulate the system with various configurations, and the results affirm our effective approach.

A location-aware layer 7 proxy handoff mechanism over the mobile network environment

In a server-proxy-client 3-tier architecture of the wireless mobile network, proxies should be dynamically assigned to serve mobile hosts according to geographical dependency and the network situation. The goal of proxy handoff is to allow a mobile host still can receive packets from the corresponding server even though its served proxy is switched from the current one to the other one. A 3-tier multimedia mobile transmission platform, called MMTP, is proposed to solve the proxy handoff problem in the IPv6-based wireless mobile network. In MMTP, a proxy handoff scheme, which is based on the application layer anycast technique, is proposed to select from a number of candidate proxies according to the load balance concern and wireless network situation concern.

Guaranteeing quality-of-service for delivery of compressed videos based on GOP-aware effective envelopes

Exploitation of the statistical multiplexing gain in the delivery of compressed videos is essential for achieving efficient network resource utilization. This paper proposes an analytical framework based on a GOP-aware effective envelope for guaranteeing statistical quality-of-service (QoS) to an aggregate flow from a class of connections. The GOP-aware effective envelope intends to model more realistic traffic burst by taking the information of individual flows launch time and group-of-picture (GOP) into account With this information, the QoS guarantee is applicable not only to the aggregate flow but also to individual flows. Through numerical experiments, we show that the significant improvement on multiplexing gain can be achieved, particularly, under those cases with short delay bounds and small-to-moderate aggregation scales.

ATPOO: An adaptive transmitting platform for supporting on-time and at-one-time data delivering over opportunistic networks

The link performance is highly unpredictable and the connections are broken frequently in opportunistic networks (Oppnets). The transmission control protocol will perform badly in Oppnets because the end-to-end connection always needs to be reconstructed and data need to be retransmitted from the original sender again through the reconstructed connection. To solve this problem, the study investigates the principles of on-time and at-one-time delivery, in which `on-time` means to transmit data to the receiver during a pre-scheduled time period and `at-one-time` means to transmit each piece of data from the sender just once. Based on the principles, the designed adaptive transmitting platform (ATPOO) supports the on-time and at-one-time delivering capacities in Oppnets. In ATPOO, the authors separate the transmitting process into macro- and micro-stages. The macro-stage deals with the end-to-end transmission quality of service; the micro-stage focuses on the transmission between adjacent nodes along with the pre-constructed delivering path. The proposed ATPOO based on the delay-tolerant network (DTN) has been implemented in this study. The experimental results show that the designed ATPOO performs the highest successful delivery ratio of 97% over complex and unpredictable network environments while the ratios of best effort, S-FTP and DTN methods are 81, 76 and 89%, respectively.

An adaptive differentiated service multicast gateway

This paper proposes a DiffServ-based multicast media gateway, called Adaptive Differentiated Service Multicast Gateway (ADMG), to guarantee QoS and scalability for multimedia presentation. The two goals of the ADMG system are (1) to increase bandwidth utilization by reserving statistical multiplexing bandwidth based on layered-media aggregation and (2) to improve the quality of presentation of the received layered media streams by dynamically modifying the sending rates of various service queues when the network passes heavy traffic. To reach these two goals, the proposed statistical layered aggregation model exploits the traffic-burst regularity of each layered aggregating flow, including I-frame, P-frame and B-frame flows, to determine the approximate reserved bandwidth. Additionally, the ADMG system dynamically changes the sending rates of various service queues to ensure that layered media packets with higher priority are always sent before those with lower priority. The proposed aggregation model, which is inconsistent with unaware GOP-based layered-media aggregation methods, has been experimentally tested on several layered-video streams. The results reveal that the proposed scheme outperforms others with a substantial reduction of bandwidth reservation even given tight delay bounds. The experimental results of the ADMG system on DiffServ networks also reveal the capability for dynamic bandwidth adjustment in various networking situations.

Efficient Region Layouts for Region-based Video Servers Employing Multi-zone Disks

This paper investigates the implementation of video servers employing multi-zone disks. A multizone disk consists of a set of concentric disk zones with non-uniform storage capacities and data transfer rates. Superimposing a customized region layout on the top of such a disk is essential for facilitating the video server design and improving the disk resource utilization. This paper develops theories concerning the optimal region layouts for implementing the region-based data placement. Based on them, two efficient region layout algorithms are proposed, namely, the free-π scheme and fixed-π scheme. The former can achieve better resource utilization than the latter, but the latter requires a simpler timing control than the former. Extension of the fixed-π scheme to perform the disk striping in a disk array platform is also investigated. A spiral synchronization scheme is proposed to improve the system scalability by alleviating the disk bus congestion problem, caused by variable data transfer rates from individual disks. The analytical results reveal that the proposed schemes can effectively customize region layouts to achieve 85‐99% resource utilization. By considering the region layout together with other design factors, an efficient configuration strategy is proposed for building a cost-effective server subject to the performance requirements of a target application.

A statistical flow control mechanism for layered multimedia over the differentiated service network

In this paper, we proposed a DiffServ based multicast media gateway, which is called adaptive differentiated service multicast gateway (ADMG), to achieve the QoS guarantee and scalability considerations for multimedia presentation systems. The purpose of the ADMG system is twofold: (1) improve the bandwidth utilization by doing bandwidth reservation based on the layered-media aggregation and (2) improve the receiving quality of the layered media streams while the network is under heavy traffic by dynamically adjusting the sending rate according to the networking situation.