摘要:
The invention comprises a method and apparatus for providing differentiated Quality-of-Service (QoS) guarantees in scalable packet switches. The invention advantageously uses a decentralized scheduling hierarchy to regulate the distribution of bandwidth and buffering resources at multiple contention points in the switch, in accordance with the specified QoS requirements of the configured traffic flows.
摘要:
A scheduling apparatus flexibly integrates guaranteed-bandwidth (GB) and best-effort (BE) flows and comprises a combination of a primary weighted-round-robin (WRR) scheduler (PWS) and a secondary WRR scheduler (SWS). The PWS distributes service to the individual GB flows and determines the amount of service that the BE flow aggregate should receive during each frame. The SWS takes care of fairly distributing the service share of the BE aggregate over the individual BE flows. The scheduling apparatus divides the service frame in two subframes. In the first subframe, the PWS fulfills the bandwidth requirements of the GB flows. In the second subframe, the SWS distributes fair service to the BE flows. For each frame, the duration depends on the amount of bandwidth allocated to the GB flows and on the number of GB flows that are backlogged at the beginning of the frame. The amount of bandwidth globally available to BE flows (i.e., the duration of the second subframe) is dynamically adapted to the backlog state of the GB flows, increasing when the GB-flow activity is low, and decreasing when the GB-flow activity intensifies.
摘要:
Single-bit-timestamp discrete-rate scheduling distributes service to competing connections (e.g., packet connections such as virtual-circuit connections) using a single bit for each connection, rather than using one or more multi-bit timestamps per connection. Single-bit timestamps are computed and sorted for scheduling packets in, for example, Asynchronous Transfer Mode (ATM) networks, for guaranteeing data transfer rates to data sources and data transfer delays from data sources to destinations. Connections are listed in one of N first-in, first-out (FIFO) rate queues j, each rate queue j, 1≦j≦N, associated with one of N service rates. A scheduler identifies the next connection for service as the connection VCj,i being at the head of the rate queue with the minimum corresponding timestamp among those rate queues having timestamps satisfying an eligibility condition. Single-bit-timestamp discrete-rate scheduling uses a multi-bit timestamp value Fj (referred to as the queue timestamp), one bit bQj (referred to as the queue bit) per rate queue j, and a single bit bVCj,i (referred to as the connection bit) for the ith connection VCj,i in rate queue j. The scheduler generates and maintains queue timestamps Fj, queue bits bQj, and connection bits bVCj,i based on whether the rate queues and the connections are backlogged. At timeslot m, the scheduler searches for the queue timestamp FS(m) having the minimum value among the rate queue timestamps associated with currently backlogged rate queues (a FIFO rate queue j is backlogged when the list has at least one connection in the rate queue) and satisfies the eligibility condition according to a selection policy. Single-bit-timestamp discrete-rate scheduling uses only a single bit for each queued connection, and achieves delay bounds and fairness indices that are identical to those of a prior art discrete-rate scheduler using per-connection multi-bit timestamps.
摘要:
An apparatus and method implement a No-Per-Connection-Timestamp Discrete-Rate Scheduler with Pivot Session which does not strictly require the computation and storage of any scheduling-related information per connection, not even a single bit, but only maintains one variable service rate and one timestamp per rate FIFO queue. In a first embodiment, the pivot-session-based scheduler does not make use of per-connection scheduling information, and further embodiments maintain a single scheduling-related bit per connection. The scheduler achieves near-optimal delay bounds, and fairness indices (both SFI and WFI) that are almost identical to those of the discrete-rate scheduler with per-connection timestamps.
摘要:
A scheduler apparatus provides bandwidth guarantees to individual data packet flows as well as to aggregations of those flows (referred to as “bundles”) in a completely transparent manner, i.e., without using any additional scheduling structure. For each bundle, the scheduler determines the ratio between the bandwidth nominally allocated to the bundle and the sum of the individual bandwidth allocations of the flows that are currently backlogged in the bundle. The scheduler uses that ratio to modulate the timestamp increments that regulate the distribution of bandwidth to the individual flows. In this manner, the greater the ratio for that bundle, the more the bandwidth that each backlogged flow in the bundle receives.
摘要:
A monolithic shaper-scheduler is used for the efficient integration of scheduling and dual-leaky-bucket shaping in a single structure. By making the evolution of the timestamps of the backlogged flows independent of their shaping parameters, the performance drawbacks of prior-art shaping architectures are overcome. The monolithic shaper-scheduler tests each packet flow as being either “virtually compliant” or “virtually incompliant” when a new packet arrives to the head of its queue. The test for “virtual compliance” is based on traffic profiles associated with the flows. The result of the test is used in conjunction with the timestamp and eligibility flag of each packet flow to efficiently schedule the transmission of packets.
摘要:
Among other things, a system for use in wireless communication includes a first device communicating via a first protocol in a first network, a cellular device communicating via a second protocol in a cellular network, the second protocol being incompatible with the first protocol, and an access point in the cellular network, the access point being accessible by the cellular device and being configured to enable communication between the first device and the cellular device.
摘要:
A network entity controls delivery of information to user devices over bearer paths including unicast channels and multicast channels. The network entity may interoperate in any of a number of network architectures, including 3GPP Internet Protocol Multimedia Subsystem (IMS) and 3GPP2 Multimedia Domain (MMD). The network entity may provide functionality of a modified 3GPP2 Broadcast and Multicast Service (BCMCS) controller component configured to enable BCMCS signaling protocol transactions to occur over 3GPP IMS interfaces and/or 3GPP2 MMD interfaces. A network entity configured to interoperate in a 3GPP IMS and/or 3GPP2 MMD network architecture may provide network-mobile multimedia services to user devices. Content associated with the multimedia services may be stored in storage devices in the network. A common interface through which a network operator defines service-specific parameters of a number of unicast and multicast multimedia services deployed in a distribution network may be provided.
摘要:
An access point detects a presence of a first device having a device identifier in a femtozone associated with the access point. The access point matches the device identifier with an identifier associated with corresponding applications and activates a set of applications associated with the device identifier.
摘要:
An access point detects a presence of a first device having a device identifier in a femtozone associated with the access point. The access point matches the device identifier with a first personal policy server identifier associated with a corresponding first personal policy profile comprising a first set of rules and retrieves the first personal policy profile corresponding to the first personal policy server identifier. The access point applies the first set of rules in the first personal policy profile.