217 results about "Queuing delay" patented technology

Embodiments of the invention enable the synchronization of clocks across packet switched networks, such as the Internet, sufficient to drive a jitter buffer and other quality-of-service related buffering. Packet time stamps referenced to a local clock create a phase offset signal. A shortest-delay offset generator uses a moving-window filter to select the samples of the phase offset signal having the shortest network propagation delay within the window. This shortest network propagation delay filter minimizes the effect of network jitter under the assumption that queuing delays account for most of the network jitter. The addition of this filtered phase offset signal to a free-running local clock creates a time reference that is synchronized to the remote clock at the source thus allowing for the transport of audio, video, and other time-sensitive real-time signals with minimal latency.

A method and apparatus for rate control adjusts or otherwise requests adjustment of a communication link data rate based on transmit queuing delays. For example, a mobile station may monitor expected transmit queuing delays relative to one or more delay targets or other Quality-of-Service constraints, and request reverse link rate increases or decreases accordingly. Similarly, the mobile station may be configured periodically to request reverse link rate changes based on determining the rate needed to meet targeted queuing delays for one or more service instances being supported by the mobile station in each of a succession of ongoing rate control intervals. Requested rates may be defined data rates or may be virtual rates that can be achieved by using combinations of defined data rates. Queuing-based rate control also can be applied to the base station's forward link, and, more broadly, to essentially any rate controlled communication link.

An automated playlist chaser (APC) improves the recovery time and robustness of playlists to component failures and/or human errors in a content sourcing and editing environment. Following detection and correction of an error in a content sourcing subsystem controlled by a playlist, the APC retrieves a last known good playlist from a playlist archive and automatically builds a new playlist for resynchronization of the subsystem. Building the new playlist involves iteratively solving for the first new program segment entry in the new playlist and the new “on-air time,”“start-of message,” and “duration” attributes for the entry as a function of a reference time (e.g., the present time of day), the original on-air time for the entry, the subsystem recovery time, the APC processing time, and the queuing delay of the audio-video source for the program segment.

The present invention is a delay based model and in fact uses queueing delay as a congestion measure, providing advantages over prior art loss based systems. One advantage is that queueing delay can be more accurately estimated than loss probability. This is because packet losses in networks with large bandwidth-delay product are rare events under TCP Reno and its variants (probability on the order 10⁻⁷ or smaller), and because loss samples provide coarser information than queueing delay samples. Indeed, measurements of delay are noisy, just as those of loss probability. Thus, another advantage of the present invention is that each measurement of queueing delay provides multi-bit information while each measurement of packet loss (whether a packet is lost) provides only one bit of information for the filtering of noise. This makes it easier for an equation-based implementation to stabilize a network into a steady state with a target fairness and high utilization. In addition, the dynamics of queueing delay provides scaling with respect to network capacity. This helps maintain stability as a network scales up in capacity.

According to the teachings presented herein, a base station implements active queue management (AQM) for uplink transmissions from user equipment (UE), such as a mobile terminal. The base station, e.g., an eNodeB in a Long Term Evolution (LTE) network, uses buffer status reports, for example, to estimate packet delays for packets in the UE's uplink transmit buffer. In one embodiment, a (base station) method of AQM for the uplink includes estimating at least one of a transmit buffer size and a transmit buffer queuing delay for a UE, and selectively dropping or congestion-marking packets received at the base station from the UE. The selective dropping or marking is based on the estimated transmit buffer size and/or the estimated transmit buffer queuing delay.

Without using additional probing packets, estimates of the narrow link bandwidth and available bandwidth of a network path are computed based on existing traffic. The network can be of different types such as a wireless battlefield network context or a wired or wireless commercial network environment. “Fast packets”, i.e. those packets which do not experience any queuing delay in the network, are identified. Fast packets are identified to resolve end-to-end packet delay into its constituent components (deterministic, transmission and queuing delays), estimate path utilization and eliminate the uncertainty (false alarms) that causes the prior art method to lose its effectiveness. An estimation algorithm computes end-to-end transmission delay and end-to-end deterministic delay of fast packets traveling along a path in a network. Examples of deterministic delay include satellite propagation delays and clock effects. Then, based on the results of the fast packet identifying algorithm, two logic branches are followed. A first branch calculates utilization and a second branch calculates narrow link bandwidth. The narrow link bandwidth is determined from the packet pair dispersion. The available bandwidth is obtained from the narrow link bandwidth and the utilization. Estimation of available bandwidth for an end-to-end network path allows traffic sources to judiciously regulate the volume of application traffic injected into the network.

The invention provides a wireless Mesh intelligent power grid routing mechanism NQA-LB with QoS perceiving and loading balancing. The mechanism comprises four steps: firstly differentiating intelligent power grid service flows with different QoS requirements through an EDCA mechanism, and calculating the frame error rate of different service flows according to the data packet collision rate of the EDCA mechanism; secondly, calculating data packet queuing delay with different priorities of the queue length of forwarding node cache and the successful transmission probability of data packets; then designing the routing metric of QoS perceiving and loading balancing by comprehensively considering the data frame error rate and queuing delay of different service flows, and selecting an optimal path with less load for the service flow with different QoS demands; finally dynamically adjusting the data packet priority on an MAC layer according to network total loading and loading conditions of all priority service flows. The mechanism can more accurately perceive the link quality of the MAC layer, guarantees the QoS demands of different service flows of a power grid, further increases the data packet delivery rate and average throughput capacity, and reduces the end-to-end delay of all service flows.

An access point station responds to a request from a user station for contention-based access of a new traffic flow to a wireless transmission medium by applying a model of the wireless local area network to estimate delay that data packets will experience when delivered through the wireless network, in order to admit the new flow upon determining that admission will not violate quality of service requirements of neither the new flow nor of already admitted flows. For example, the access point station applies the model by determining an average packet inter-arrival rate, solving a system of nonlinear equations to determine probabilities of successful transmission, applying network stability conditions, computing an upper bound on queuing delay for the packets, computing a service delay budget for the packets, and computing an expected fraction of missed packets from the service delay budget.

Described embodiments provide systems and methods for path selection proportional to a penalty delay in processing packets. A server-side intermediary may identify a delay penalty for processing packets of a server destined for a client. The server-side intermediary may be in communication via links of different latencies with a client-side intermediary. The server-side intermediary may select a second link with a latency that deviates from the lowest latency of a first link by the delay penalty. The server-side intermediary may transmit, to the client-side intermediary, duplicates of the packets via the selected second link with information indicating to hold the duplicates at the client-side intermediary. The server-side intermediary may receive an indication to drop or send the duplicates to the client. The server-side intermediary may transmit the indication to the client-side intermediary to drop or send the duplicates according to the indication.

The invention discloses an SDN based distributed control load balancing system and method, aiming at mainly solving the problems of distributed extension, network overheads, uneven load and link congestion in existing small-scale single data center networks. The system disclosed by the invention comprises a three-layer Clos underlying network and two SDN controllers, wherein the SDN controller isadditionally provided with link information, a routing table and a routing calculation module, and the above modules act together to calculate a path for a data stream. The load balancing method includes the following steps: adopting two-step path selection, partitioning the data stream into stream slices in a buffer area of an end host, separately monitoring and collecting local link informationof two local area networks by using the two controllers, and taking a queuing delay of each port of a switch as the link information to optimize the selection of routing links. According to the schemeof the invention, the distributed multi-controller and two-step path selection are adopted in the three-layer Clos network, and a significant network balancing effect can be achieved; and the schemecan be used for load balancing control of large-scale single data center networks.

This invention relates to methods and devices for compensating for path asymmetry, particularly with reference to time and frequency synchronization. The invention has particular application where time and frequency synchronization over packet networks using, for example, the IEEE 1588 Precision Time Protocol (PTP) is being carried out. Typically communication path delays between a time server (master) and a client (slave) are estimated using the assumption that the forward delay on the path is the same as the reverse delay. As a result, differences between these delays (delay asymmetries) can cause errors in the estimation of the offset of the slave clock from that of the master. Embodiments of the invention provide techniques and devices for compensating for path delay asymmetries that arise when timing protocol messages experience dissimilar queuing delays in the forward and reverse paths.

An apparatus in a wireless network includes a video encoder for encoding uncompressed video information into packets with variable length of compressed frames, and a decision processor for selecting a partial bandwidth and queuing delay on a wireless channel for each of the packets based on an intended reception quality. Preferably, the queuing delay and partial bandwidth are one of a plurality of distinct queuing delay and partial bandwidth representative of wireless transmission quality of service classes.

The invention discloses a method for realizing multipath load balance in an MPLS network and a data transmitting device. The method comprises the following steps: input flow is separated into a plurality of flow buffers; the least message queuing delay metrics and the loss rate metrics of each label switched path are measured; and according to the least message queuing delay metrics and the loss rate metrics of the label switched path, the flow in the buffer is mapped into the label switch path. The flow separation is simple and high-efficient, and the message queuing delay metrics and the loss rate metrics can reflect the load on each LSP better, thus realizing the multipath load balance. The method has good stability and expandability and is easy to realize in an operation network.

The invention discloses a TDMA based long propagation delay wireless link time slot distribution method which is mainly used for solving the problem of low throughput rate and low channel utilization rate of an existing long propagation delay wireless ad hoc network. The implementation scheme comprises the steps of 1, initializing a node; 2, judging whether the node receives a synchronous frame, if so, carrying out network access synchronization by the node, and otherwise, building a network by regarding the local clock as a reference by the node; 3, after synchronization is finished, generating a super-frame structure automatically by the node, and dividing the local time into multiple time slots with different functions; and 4, judging whether the current time slot is a service time slot by the node, if so, sending and receiving data, and otherwise, updating network information. as the TDMA is adopted as a channel access mode, the node can access the channel without any conflict; and through an interactive sending mechanism and a data frame queue scheduling mechanism, the network throughput rate and the channel utilization rate are increased, the queuing delay of the data frames is reduced; and the TDMA based long propagation delay wireless link time slot distribution method can be used for a time division multiple access ad hoc network.