| D. Dwyer, S. Ha, J.-R. Li, and V. Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. In Proc. Int. Conf. Multimedia Computing and Systems, Austin, TX, 1998. 24 |
....of specifying which frames of the video are key frames. The video producers can specify the scene change frames as key frames. ffl Adaptive Transport Protocol for Multimedia: A new transport protocol HPF, that supports multiple interleaved reliable and unreliable streams is presented in [50]. Currently, the Internet does not support heterogeneous flows. Multimedia applications have to get the different media as different streams and then synchronize them. The HPF protocol supports interleaved flows which is required by multimedia applications. The congestion control and reliability ....
D. Dwyer, S. Ha, J. Li and V. Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. In IEEE Conference on Multimedia Computing Systems, 1998.
....while the MH roams inside a switched ATM infrastructure. It provides adaptation methods within the real time stream bundle but without the notion of priorities, and it seems to lack an arbitration method during handoffs. Finally, the TIMELY project at UIUC [10] uses the HPF transport protocol [11, 12]. It is the most recent effort and the only other known architecture that supports priorities between streams for intelligent management over a wireless link. HPF transmits all the real time streams of a single application over a single connection, thus having the opportunity to prioritize packets ....
D. Dwyer, H. Sungwon, L. Jia-Ru, and V. Bharghavan, "An Adaptive Transport Protocol for Multimedia Communication," Proceedings of the IEEE International Conference on Multimedia Computing and Systems, 1998, p. 23-32.
....performing their own congestion avoidance and control: this may cause severe degradation of the overall network performance, due to potentially misbehaving sources. 1.2.2. A Networking Only View of the Problem An alternative approach to this problem consists of designing new transport protocols [3, 6], and using standard video coding algorithms. In this case, smart packetization schemes are used in order to minimize error propagation in the event of a packet loss (e.g. by gathering complete motion paths within a packet) Also, it is possible to retransmit packets selectively depending on, for ....
D. Dwyer, S. Ha, J.-R. Li, and V. Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. In Proc. Int. Conf. Multimedia Computing and Systems, Austin, TX, 1998.
....This mechanism cannot hope to provide congestion control for unreliable packets that do not require any acknowledgment. 12 5. The application speci ed priorities can act as hints for network routers to preferentially drop packets during congestion. More details about HPF are available in [2] [3] It is worth investigating the applicability of this protocol to streaming of multimedia data, especially video like data. Video frames can be sent as unreliable delay bounded packets. HPF fragments these packets and sends all the fragments with the same priority. The HPF protocol is still ....
Dane Dwyer, Sungwon Ha, Jia-Ru Li, Vaduvur Bharghavan. \An Adaptive Transport Protocol for Multimedia Communication" In Proceedings of IEEE Conference on MultiMedia Computing and Systems, June 1998, pp 23-32.
.... a given motion trajectory into a single packet, so that if this packet is lost the entire motion path is lost and therefore error propagation is limited [3] Also, it is possible to retransmit packets selectively depending on, for example, whether a lost packet contains intra coded blocks or not [9]. Fig. 3 illustrates these concepts. w error concealment) Video Decoder Transport (MPEG x, H.26x) Video coder Protocol Figure 3: An approach centered around the design of network protocols. In this case, all the intelligence goes into the design of good communication protocols, but it is ....
D. Dwyer, S. Ha, J.-R. Li, and V. Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. In Proc. Int. Conf. Multimedia Computing and Systems, Austin, TX, 1998.
....of the transport layer in the kernel rather than in the application (or a user level protocol) allows for efficient mechanisms and simpler applications. In this paper, we describe a transport protocol called HPF for effectively supporting heterogeneous packet flows in an Internet environment [3]. HPF has four key features: a) support for reliable and unreliable packets with different priority and timing (delay) requirements in the same transport connection, b) support for application level framing, and for applications to specify the priority, reliability and timing requirements of ....
....serve as feedback for both purposes. However, since HPF supports both unreliable and reliable packets in a single flow, congestion control is decoupled from reliability in HPF. While the details of the congestion control algorithm are beyond the scope of this paper, we refer the reader to [3]. III. HPF ARCHITECTURE AND DESIGN HPF is a connection oriented transport protocol. It allows applications to specify blocks of data called frames , and to provide frame specific policies for reliability, priority and timing (we call these the policy parameters) A frame is then treated as a ....
D. Dwyer, J.-R Li, S. Ha, and V. Bharghavan. An adaptive transport protocol for multimedia communication. In IEEE International Conference on Multimedia Computing Systems, June 1998.
....Our architecture consists of four horizontal network layers and a virtual vertical layer. The four horizontal 5 layers are the scheduling MAC layer [17, 22] the resource reservation and predictive advance reservation layer [6, 24, 26] the resource adaptation layer [22] and the transport layer [15]. The virtual adaptation interaction layer provides for adaptation related information to be passed across the protocol layers, and enables the different layers to adapt cooperatively. Coordinated adaptation across multiple layers is a key aspect of our resource management architecture. In this ....
....mobile flows. 5. The network performs resource adaptation among the adaptable static flows in order to resolve resource conflicts and also distribute additional resources. 6. Since the resources allocated to a flow can vary dynamically, applications use an adaptive transport protocol called HPF [15] to transmit packets. HPF enables applications to interleave multiple packet substreams with different priorities in a single stream, such that only the important substream is transmitted during sudden resource reductions. Also, the congestion control mechanisms in HPF use 6 the resource ....
[Article contains additional citation context not shown here]
D. Dwyer, S. Ha, J. Li and V. Bharghavan, "An adaptive transport protocol for multimedia communications, " To appear in the International Conference on Multimedia Computing Systems, August 1998.
....equal probability, and priority drop, described below. For shared queues with constant or division sharing policies, we use only tail drop. For shared queues with aggregate sharing policies or for per flow queues, we can use any of the four dropping policies. Some transport protocols, such as HPF [2], allow an application to specify the relative priority of packets within a flow. The priority drop policy uses these priorities to drop lower priority packets instead of higher priority packets (in the same queue) when there is congestion. In priority drop, when the packet admission policy fails ....
D. Dwyer, S. Ha, J.-R. Li, and V. Bharghavan. An adaptive transport protocol for multimedia communication. Proceedings of IEEE ICMCS, June 1998.
....on behalf of the mobile hosts in its cell. Each base station thus has a resource reservation manager. Resource allocation within the cell is done through the WPS algorithm, described in [20] The resource reservation protocol works as shown in Figure 3. Applications set up TCP, UDP, or HPF [23] connections using standard socket connect accept mechanisms. An ongoing connection is identified by the 5 tuple src addr, src port, dst addr, dst port, protocol . Once a connection is setup, applications may transmit packets using best effort service till either end point seeks to make a ....
D. Dwyer, S. Ha, J. Li and V. Bharghavan, "An adaptive transport protocol for multimedia communications," Internal Technical Report, TIMELY research group, Univ. of Illinois, http://timely.crhc.uiuc.edu, June 1997.
....environments. Our architecture consists of four horizontal layers and a virtual vertical layer. The four horizontal layers are the scheduling MAC layer [12, 16] the resource reservation and predictive advance reservation layer [4, 18] the resource adaptation layer [17] and the transport layer [10]. The virtual adaptation interaction layer provides for adaptation related information to be passed across the protocol layers, and enables the different layers to adapt cooperatively. Coordinated adaptation across multiple layers is a key aspect of our resource management architecture. In this ....
....mobile flows. 5. The network performs resource adaptation among the adaptable static flows in order to resolve resource conflicts and also distribute additional resources. 6. Since the resources allocated to a flow can vary dynamically, applications use an adaptive transport protocol called HPF [10] to transmit packets. HPF enables applications to interleave multiple packet substreams with different priorities in a single stream, such that only the important substream is transmitted during sudden resource reductions. Also, the congestion control mechanisms in HPF use the resource adaptation ....
[Article contains additional citation context not shown here]
D. Dwyer, S. Ha, J. Li and V. Bharghavan, "An adaptive transport protocol for multimedia communications, " To appear in the International Conference on Multimedia Computing Systems, Durham, North Carolina, August 1998.
....kernel rather than in the application (or a user level protocol) allows for efficient mechanisms and simpler applications. In this paper, we describe a novel transport protocol called HPF (Heterogeneous Packet Flows) for effectively supporting heterogeneous packet flows in an Internet environment [4]. Our approach is based on the following key principles: a) support for reliable and unreliable packets with different priority and timing (delay) requirements in the same transport connection, b) decoupling of the congestion control and reliability mechanisms (that are integrated in TCP) in ....
....there is no congestion control for unreliable packet flows. In order to support heterogeneous packet flows effectively, congestion and flow control must be performed for both unreliable and reliable packet flows. Thus, the mechanisms for congestion control and reliability must be decoupled [4, 15]. In particular, the two questions how many packets can be transmitted next and which packet needs to be transmitted next are independent. It is an artifact of TCP that cumulative acknowledgements are used to answer both these questions. Recent work in TCP including SACK and FACK [11, 12] have ....
Dane Dwyer, Jia-Ru Li, Sungwon Ha, and Vaduvur Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. IEEE International Conference on Multimedia Computing Systems, June 1998.
No context found.
D. Dwyer, S. Ha, J.-R. Li, and V. Bharghavan. An Adaptive Transport Protocol for Multimedia Communication. In Proc. Int. Conf. Multimedia Computing and Systems, Austin, TX, 1998. 24
No context found.
D. Dwyer, S. Ha, J-R. Li and V. Bhargavan, \An Adaptive Transport Protocol for Multimedia Communication," in IEEE International Conference on Multimedia Computing Systems, Austin, TX, June 1998, pp. 23-32.
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