Abstract: Systems and methods for estimating available bandwidth with multiple overloading streams are described. In one aspect, a set of packets are communicated by a probing sender to a receiver. The packets are sent at multiple sending rates. At least two of the sending rates result in multiple overloading streams of packets being sent to the receiver. The probing sender receives a set of queuing delay information from the receiver. The queuing delay information is based one-way delay measurements corresponding to receipt by the receiver of at least two pairs of successive packets of the packets. The probing sender estimates available bandwidth of the network based on the received queuing delay information and multiple sending rates associated with the multiple overloading streams of packets.

Abstract: An application-level multicasting architecture that enables multiple nodes to interact in real time with data packets that are routed based on information about the connection states between the nodes is provided. Each node shares their connection states with other nodes in the same interactive session. The data packets may be routed in the application level using multiple packet transport protocols that are available on the sending node. A particular transport protocol may be selected based on a Quality of Service (QoS) requirement of the data packet. Nodes in the interactive session may relay data packet to other nodes according to a routing map that is created based on the connection states. The application-level multicasting architecture may be implemented for any multiparty interactive application, such as an application for videoconferencing, multiplayer games, distance learning, virtual meeting, and voice communication.

Abstract: Systems and methods are described for implementing an application-level routing protocol for multiparty audio-video conferencing. In one implementation, application-level per-stream routing techniques separately control audio data and video data between conference members hosted on a network. Different audio application-level multicast (ALM) trees are generated by each member, are dynamically updated according to shortest-path-first selection of data delivery paths, and are used to send audio data to the other members of the videoconference. Likewise, different video ALM trees are generated by each member, are dynamically updated according to broadest-path-first selection of data delivery paths, and are used to send video data to the other members of the videoconference. Separate audio and video ALM trees for each member can utilize IP multicast in segments of the network in which IP multicast is enabled.

Abstract: Described is a communication mechanism that provides push-to-talk functionality for mobile and desktop computing environments. Mobile and desktop computers are configured as client computers in a client/server architecture. Some of the client computers are configured to handle multiple push-to-talk sessions simultaneously. If multiple streams from different sessions are active at the same time, the client computer may determine which of these overlapped streams to record and then record them for later playback. A server handles the registration of the client computers, manages the multiple sessions for each of the client computers, and performs a floor control process so that each push-to-talk session operates in a half-duplex mode.

Abstract: Transmission optimization for application-level multicast is described. For each member of a video conference, a multicast tree is generated that represents a data communication configuration of a data source and the other members of a video conference which are data recipients that receive video and audio data from the data source. An end-to-end transmission delay from each data source to each of the respective data recipients is determined, and the available bandwidth between each data source and the respective data recipients is determined. One or more of the multicast trees, each corresponding to a data source, are refined according to the end-to-end transmission delay and available bandwidth for a particular data source to optimize the data communication configuration of the data source in the video conference.

Abstract: The techniques and mechanisms described herein are directed to controlling communication paths between conference members in a decentralized multi-party conference that supports a full mesh architecture. Several check points are tested in order to handle concurrency issues and to ensure quality of service. First, a check is made to determine whether any pending communication paths exist between the two systems. Second, a check is made to determine whether one of the systems is in the process of leaving the multi-party conference. Third, a check is made to determine whether a maximum number of conference members already exist in the conference. Upon failing any of these checks, the communication path between the two systems fails. Upon success, the new system initiates the joining process with each of the other members in the conference in order to maintain the full mesh architecture.