Abstract: A network entity for a mobile telecommunications system, including circuitry configured to perform transmission rate control of data transmissions according to a transmission control protocol, wherein the transmission rate control is performed based on an output of a machine learning algorithm including a prediction of a congestion of the data transmissions.

Abstract: Features are disclosed for dynamically managing connection parameters for multiple computing devices configured to transmit and receive data based on corresponding connection parameters. A computing device can receive multiple connection parameters corresponding to multiple distinct connections. The computing device can determine a minimum transmission parameter based on the multiple connection parameters. The computing device can set a local transmission parameter and a local reception parameter based on the minimum transmission parameter. The computing device may use the local transmission parameter and the local reception parameter for each connection. The computing device may provide the local reception parameter to each of the multiple computing devices. In some embodiments, the multiple computing devices may set a corresponding reception parameter and a corresponding transmission parameter based on the local reception parameter.

Abstract: A node in a wireless mesh network determines that a threshold level of duplicate network protocol data units (PDUs) are received. Further, the node receives one or more network PDUs comprising respective segments of transport data in a transport PDU. The node relays a subset of the received one or more network PDUs comprising respective segments to one or more neighboring nodes. The subset is relayed based on determination that the node has received a threshold level of duplicate network PDUs.

Abstract: Systems and methods for pacing data transmission are described. An illustrative method includes transmitting, by a network device, a data stream at a pacing rate to a user equipment (UE) device. The method further includes accessing a metric of a radio access network (RAN) to which the UE device is connected, the metric associated with the UE device. The method further includes adjusting, based on the metric, the pacing rate at which the data stream is transmitted to the UE device.

Abstract: A resource of a dialog-driven management service is allocated for a first set of requests based on determining that a population of capacity indicators in a throttling data structure exceeds a threshold. One or more capacity indicator deduction iterations associated with the resource are conducted during a time interval for which the resource remains allocated for the first set of requests. In a given iteration, a number of capacity indicators is deducted from the throttling data structure based on a resource throttling setting. A second set of requests is rejected based on the population of the throttling data structure.

Abstract: A storage device includes a memory controller to receive a first signal from an external device through a first channel, obtain data from a memory based on the first signal, and output the data to the external device through a second channel. The data is output through the second channel in a case where a time interval between a time when the first signal is received and a time when the data are obtained is greater than a first reference interval.

Abstract: A method of detecting patterns in network traffic is provided. The method includes receiving a plurality of packets of network traffic, each packet having a payload populated with payload data and selecting payload lengths that occurred most frequently. For each of the selected payload lengths, a pattern template is generated using characters per position of the payload that satisfy a frequency criterion. A bit encoding scheme is assigned for each of the selected payload lengths and its associated pattern template. Each packet of the plurality of packets that has a payload length equal to any of the selected payload lengths and payload content that matches a pattern template generated for the payload is encoded into a single value. The single value uses the bit encoding scheme for the payload length and the pattern template matched.

Abstract: A first node of a packet switched network transmits at least one flow of protocol data units of a network to at least one output context of one of a plurality of second nodes of the network. The first node includes X virtual output queues (VOQs). The first node receives, from at least one of the second nodes, at least one fair rate record. Each fair rate record corresponds to a particular second node output context and describes a recommended rate of flow to the particular output context. The first node allocates up to X of the VOQs among flows corresponding to i) currently allocated VOQs, and ii) the flows corresponding to the received fair rate records. The first node operates each allocated VOQ according to the corresponding recommended rate of flow until a deallocation condition obtains for the each allocated VOQ.

Abstract: Methods and systems for a networked storage system are provided. One method includes assigning a quality of service (QOS) parameter for a storage volume of a networked storage environment having a first storage node and a second storage node, where the QOS parameter is defined by a throughput value that defines a maximum data transfer rate and a number of input/output (I/O) operations executed within a time period (IOPS); distributing the QOS parameter between the first storage node and the second storage node; determining that throughput credit is available for processing an I/O request for using the storage volume; determining that IOPS credit is available for processing the request by the first storage node; and processing the I/O request when both the throughput credit and the IOPS credit is available.

Abstract: Techniques for implementing resilient hashing with compression are provided. In some embodiments, a network device can maintain a compressed partition and an uncompressed partition for a logical hash table, where the logical hash table comprises a first set of mappings between bucket identifiers and active next-hop destinations, the compressed partition comprises a second set of mappings between compressed indices and the active next-hop destinations, and the uncompressed partition comprises a third set of mappings between uncompressed indices and the active next-hop destinations. The network device can compute a hash value using a portion of a packet. When the hash value is addressed by a compressed index, the packet is sent to a next-hop destination in the compressed partition. When the hash value is addressed by an uncompressed index, the packet is sent to a next-hop destination in the uncompressed partition.

Abstract: Telemetry for cloud switches queuing excursion may be provided. A first hysteresis threshold and a second hysteresis threshold for a queue of the network switch may be specified. Next, a queue position relative to the first hysteresis threshold and the second hysteresis threshold may be determined for each incoming packets for the queue. A number of crossings including the queue position passing the first hysteresis threshold and subsequently passing the second hysteresis threshold in a first predetermined time period may be determined. A number of data packets being sent to the queue of the network switch may then be altered based on one or more of the number of crossings, the first hysteresis threshold, and the second hysteresis threshold.

Abstract: This disclosure relates to wireless communication techniques. According to some embodiments, a wireless device may select a random number and sequentially advertise the bits of the random number. If the wireless device advertises the highest random number, it may proceed to transmit a packet using a channel. If another device advertises a higher number, the wireless device may not transmit its packet and may restart the process.

Abstract: Examples herein involve managing credit returns in a multi-source credit managed communication system. In examples herein, a first amount of slots of a credit managed destination are allocated for a credit managed source and a second amount of slots of the credit managed destination are allocated for a secondary source. Credit returns are controlled to the credit managed source based on the second amount of slots and in response to a value of a counter that tracks an amount of data sent from the secondary source to the credit managed destination, an amount of data sent from the credit managed destination, the credit returns providing an ability for the first source to send data to the credit managed destination.

Abstract: A method of communication includes generating a control message at a particular device. The control message indicates availability of data to be sent by the particular device. The data includes first data corresponding to a first access category. The method also includes, subsequent to determining that transmission of the control message is to be delayed, determining a first delay based on the first access category. The method further includes sending the control message from the particular device upon expiration of a delay period. The delay period is based on the first delay.

Abstract: A system and method that facilitates mobile device selection among available qualities of service is described herein. A mobile device presents a user interface to enable selection of change to a current quality of service on the mobile device. The user interface further enables selection of one or more parameters associated with the selected change to the current quality of service. In response to the selection, the mobile device transmits to the telecommunications network the selected change in quality of service. The mobile device then receives the selected change in quality of service if the telecommunications network is able to accommodate the selected change.

Abstract: A traffic control method, where a network device adds a traffic control tag to traffic that is over guaranteed bandwidth or to traffic of the guaranteed bandwidth, and sends, to a backbone network switching device, a data flow that carries the traffic control tag. The backbone network switching device discards, according to the traffic control tag, the traffic that is over the guaranteed bandwidth. Hence, traffic of guaranteed bandwidth of a user is ensured.

Abstract: A method and apparatus for reporting a feature of an OpenFlow switch are provided. The method includes: when the OpenFlow switch learns that an OpenFlow controller needs to query for port information, reporting port group identifiers of port groups, to which each port of the OpenFlow switch or each port to be queried by the OpenFlow controller belongs, to the OpenFlow controller, herein the port groups are obtained by grouping ports with different features in the OpenFlow switch based on one or more feature types, and each of the port groups has a port group identifier.

Abstract: A system and method for managing an application delivery controller (ADC) cluster including a plurality of ADCs are provided. The method includes creating a hash table including a plurality of buckets, wherein a number of the plurality of buckets is a multiple of a maximum number of active ADCs that can be supported by the ADC cluster; allocating, to each active ADC of the ADC cluster, one of the plurality of buckets; and instructing at least one network element to distribute traffic to and from the active ADCs based on the hash table.

Abstract: Computer-implemented methods and a system are provided for distributing tasks between a plurality of processes in a computer network. A method includes distributing, by a load balancer in the computer network, tasks between the plurality of processes. The method further includes maintaining, by the load balancer, a registry for each of the tasks. For a given task, the registry indicates which of the plurality of processes to which the given task is distributed based on a hash function. The method also includes forming, by the load balancer, a respective set of registries for each of the plurality of processes, based on a set of thresholds. The method additionally includes redefining, by the load balancer, the set of thresholds when one of the plurality of processes ceases or a new process, added to the plurality of processes, commences.

Abstract: Systems, apparatuses and methods may provide for detecting an issued request in a queue that is shared by a plurality of domains in a memory architecture, wherein the plurality of domains are associated with non-uniform access latencies. Additionally, a destination domain associated with the issued request may be determined. Moreover, a first set of additional requests may be prevented from being issued to the queue if the issued request satisfies an overrepresentation condition with respect to the destination domain and the first set of additional requests are associated with the destination domain. In one example, a second set of additional requests are permitted to be issued to the queue while the first set of additional requests are prevented from being issued to the queue, wherein the second set of additional requests are associated with one or more remaining domains in the plurality of domains.

Abstract: A control apparatus sets, in a node located at the start point of an aggregatable segment of two or more packet forwarding paths including the aggregatable segment, a packet handling operation for each flow, the packet handling operation being for writing a flow identifier for identifying the flow and a path identifier used for packet forwarding through the aggregatable segment in a region of each of packets to be matched against the matching rule and then causing the packet to be output. The packets respectively belong to the individual flows, and each of the packets is to be forwarded through a corresponding one of the two or more packet forwarding paths. Further, the control apparatus sets, in a node located intermediate on the aggregatable segment, a common packet handling operation for causing the packet that matches the path identifier to be forwarded according to the packet forwarding path.

Abstract: A system and method for optimizing voice communications in a wireless network including an AP having a message waiting time that provides proper QoS while losing minimal communication bandwidth. The QoS may be responsive to the amount of user traffic in both the AP and neighboring APs. The method may include setting parameters for each level of QoS in response to a measure of the degree of contention for that level of QoS, and in response to a measure of the degree of contention for those levels of QoS with higher priority, and setting waiting time parameters in response to a stochastic model of contention at each level of QoS. Operational parameters might include contention window time, AIFS time, and back-off value(s), and might be modified in response to message QoS.

Abstract: A method and apparatus are disclosed for prioritizing logical channels when a new transmission is performed. Logical channel resources are allocated for available data to a plurality of logical channels. A maximum bit rate (MBR) credit (i.e., token) is decremented in a buffer (i.e., bucket) associated with a particular one of the logical channels by the size of a medium access control (MAC) service data unit (SDU). The MBR credit may have a negative value. If any of the allocated channel resources remain, the logical channels are served n a decreasing priority order until the data is exhausted. A radio link control (RLC) SDU is not segmented if the whole RLC SDU fits into the remaining resources. The MAC SDU excludes a MAC PDU header and MAC padding.

Abstract: A system and method for optimizing voice communications in a wireless network including an AP having a message waiting time that provides proper QoS while losing minimal communication bandwidth. The QoS may be responsive to the amount of user traffic in both the AP and neighboring APs. The method may include setting parameters for each level of QoS in response to a measure of the degree of contention for that level of QoS, and in response to a measure of the degree of contention for those levels of QoS with higher priority, and setting waiting time parameters in response to a stochastic model of contention at each level of QoS. Operational parameters might include contention window time, AIFS time, and back-off value(s), and might be modified in response to message QoS.

Abstract: A method of monitoring data flow in a network is provided. The method includes: configuring a data flow including a plurality of data packets by a switch controller, the switch controller configured to control routing through the switch and switch configuration, wherein configuring includes storing an indication of a flow control policy in one or more of the data packets; monitoring a network switch receiving the data flow, wherein monitoring includes determining flow statistics in the switch; determining whether a congestion condition exists for the data flow based on the flow statistics and the flow control policy; and based on determining that the congestion condition exists for the data flow, performing a remedial action specific to the data flow to address the congestion condition.

Abstract: Embodiments provide techniques for synchronizing forwarding tables across forwarding pipelines. One embodiment includes receiving, in a network switch comprising a plurality of forwarding pipelines, a plurality of data packets. Each of the plurality of data packets corresponds to a respective one of the plurality of forwarding pipelines. Each of the plurality of forwarding pipelines maintains a respective forwarding table corresponding to a respective plurality of ports managed by the forwarding pipeline. A plurality of update operations to be performed on the forwarding tables are determined, based on the received plurality of data packets. Embodiments further include performing the plurality of update operations on the forwarding tables, such that the forwarding tables across all forwarding pipelines of the plurality of forwarding pipelines are synchronized.

Abstract: An inter-operator radio resource sharing method for sharing radio resources between two or more radio communication systems each controlled by a respective operator and configured to control respective proprietary radio resources and to provide respective served user equipments with radio communication services.

Abstract: Hosts for virtual computing nodes may communicate health and status information through a low-bandwidth interface. Event descriptions evolving over time may be communicated through a fixed-length bit field whose format also evolves over time. Information describing the evolving data format may be communicated through an out-of-band communications channel. Event descriptions transmitted using the evolving data format may be processed once the format is accessible to the recipient of the event descriptions.

Abstract: In some implementations, a system and corresponding method for load balancing data traffic addressed to an anycast address include maintaining, by each of a plurality of load balancing (LB) devices a data structure including entries associated with application instances in a group of application instances served by the LB device. The frequency with which each served application instance is included in the data structure is indicative of a weight value associated with a capacity of the corresponding served application instance. Upon receiving a data packet, originally addressed to an anycast address, the LB device uses one or more header fields of the received data packet to identify a virtual Internet protocol (IP) address of one of the served application instances in the data structure maintained by the LB device. The LB device then forwards the data packet to the identified application instance.

Abstract: In a network communication apparatus, transfer and discard processing is realized for each transfer frame having a priority, and a band limitation is carried out to prevent the congestion of a transfer destination apparatus. Specifically, a bucket is provided for every priority, and tokens of an amount determined based on the priority are supplemented. Moreover, before a bucket evaluation, one shared bucket is provided. All of the tokens existing in the bucket provided for every priority are transferred to the shared bucket for every constant period. The tokens overflowing beyond a capacity of the shared bucket are discarded. All of the frames are equally evaluated and transferred regardless of the priority of each of the frames, as far as the token exists in the shared bucket. When there is no token in the shared bucket, switching to the preferential band limitation is carried out and each priority bucket is evaluated.

Abstract: A transmitting apparatus transmits a data stream via multiple wireless links and includes a storage unit that stores a guaranteed rate to be guaranteed for the data stream; a dividing unit that divides traffic of the data stream into first traffic corresponding to the guaranteed rate stored in the storage unit and second traffic corresponding to a portion of the traffic exceeding the guaranteed rate; and a distributing unit that distributes the first traffic to at least any one of the wireless links preferentially over the second traffic, and distributes the second traffic to available bandwidths of the plural wireless links.

Abstract: Techniques for media access in wireless networks are disclosed. For instance, embodiments may provide a time interval for accessing a wireless communications channel. In addition, embodiments may prevent channel access during the time interval by stations incapable of employing a first channel access technique. This access technique employs an access probability P.

Abstract: Embodiments perform adaptive throttling of tasks into a virtual datacenter having dynamically changing resources. Tasks are processed concurrently in batches. The rate of change in throughput at different batch sizes is calculated. With each iteration, the batch size is increased or decreased based on the rate of change to achieve a maximum throughput for given resources and load on the virtual datacenter.

Abstract: Methods and apparatus for compound token buckets usable for burst-mode admission control are disclosed. A peak burst rate and a sustained burst rate of work requests that are to be supported at a work target are determined. The maximum token populations of a peak-burst token bucket and a sustained-burst token bucket are configured, based on the peak burst rate and the sustained burst rate respectively. In response to receiving a work request directed at the work target, a determination to accept the work request for execution is made based at least in part on the token population of the peak-burst token bucket and/or the sustained-burst token bucket.

Abstract: A method in a communication node for handling a packet to a destination node in a communications network, and associated nodes. The communication node associates the packet with a remaining value, with the remaining value being a packet value reduced by a threshold value of an outgoing link from the communication node towards the destination node. The threshold value corresponds to a congestion level of the outgoing link. The communication node further handles the packet based on the remaining value, the handling including determining whether to drop or to transmit the packet along the outgoing link based on the remaining value.

Abstract: In one embodiment, a processor-readable medium storing code representing instructions that when executed by a processor cause the processor to update, at a memory location, a first flow state value associated with a data flow to a second flow state value when at least one of a packet from the data flow is received or the memory location is selected after a time period has expired. At least a portion of the packet is analyzed when the second flow state value represents a flow rate of a network data flow anomaly.

Abstract: Disclosed is a method for performing a measurement (namely, a data loss measurement and/or a time measurement) on a data flow to be transmitted in a communication network. The method includes: upon transmission of the data flow, during first block periods that alternate in time with second block periods, marking each data unit of the data flow by setting a feature thereof to a first value and updating a first parameter; upon reception of the data flow, checking the feature for each received data unit and updating a second parameter when the feature is equal to the first value; while transmission and reception are performed, processing a timer for determining whether a current block period is one of the second block periods and, in the affirmative, providing current values of the first and second parameters; and performing a measurement using the current values of the first and second parameters.

Abstract: A method for sending a packet includes determining whether a packet is a fragmented packet, if the packet is a fragmented packet, determining whether the number of tokens in a token bucket is sufficient, when the number of tokens in the token bucket is sufficient, sending the fragmented packet, and deducting the number of tokens in the token bucket, where the deducted number of tokens corresponds to the number of bytes of the sent fragmented packet, when the number of tokens in the token bucket is insufficient, sending the fragmented packet, and deducting the number of tokens in the token bucket, where the deducted number of tokens corresponds to the number of bytes of the sent fragmented packet, and the number of tokens in the token bucket is a negative number after the number of tokens corresponding to the number of bytes of the sent fragmented packet is deducted.

Abstract: Providing a dynamic bandwidth increase using at least one token bucket is disclosed. At least one token bucket is pre-loaded to capacity using PCMM commands to dynamically implement speed increases in the network. By pre-loading the at least one token bucket to capacity, the rate cap assigned to the customer is overridden. When the token bucket is exhausted the customer continues at their provisioned rate cap. Only a configuration file has to be changed to implement the temporary bandwidth increase. The token buckets may be implemented on a per service flow basis. Further, a plurality of token buckets may be provided, wherein a first token bucket is configured to control a total burst size and a second token bucket is configured to control an individual flow burst rate up until the first token bucket is depleted.

Abstract: Methods and apparatus for token-sharing mechanisms for burst-mode operations are disclosed. A first and a second token bucket are respectively configured for admission control at a first and a second work target. A number of tokens to be transferred between the first bucket and the second bucket, as well as the direction of the transfer, are determined, for example based on messages exchanged between the work targets. The token transfer is initiated, and admission control decisions at the work targets are made based on the token population resulting from the transfer.

Abstract: According to an example, in a method for MAC address distribution by an apparatus, a MAC address is received in the apparatus, in which the apparatus includes a data store on which is stored a local slice set containing a plurality of slices, and in which each of the plurality of slices is assigned a respective slice identifier. An address value for the received MAC address may be determined and a correlation between the determined address value and one of the slice IDs of the plurality of slices may be identified. In addition, the received MAC address may be stored in the slice having the slice identifier identified as being correlated to the determined address value.

Abstract: The disclosure discloses a method for traffic limitation by a leaky bucket, including that: during traffic-limitation of a group of packets sharing a same leaky bucket and having separate weighted priorities, the overall leaky bucket is divided into multiple sub-buckets according to priority parameters of the packets including a number of the weighted priorities and ratios between the weighted priorities; after packet information is received, parameters relevant to traffic-limitation by a leaky bucket is acquired; a total number of tokens to be added to the overall leaky bucket is calculated; token-addition is performed on the sub-buckets according to a state of the overall leaky bucket after addition of the total number of tokens and the weighted priorities corresponding to the sub-buckets; a packet is forwarded, or discarded, or marked according to a length of the packet and a number of tokens in a sub-bucket corresponding to a weighted priority, wherein in performing token-addition on the sub-buckets, afte

Abstract: Communicating among stations in a network includes, from each of multiple stations in the network, transmitting information indicating which other stations from which that station is able to reliably receive transmissions. A schedule for communicating among the stations is determined based on the information from the stations and transmitting the schedule over the network. The schedule includes a plurality of time slots during which respective contention groups of stations are assigned to communicate using a contention-based protocol.

Abstract: An example method for a distributed NetFlow exporter with a single IP endpoint in a network environment is provided and includes configuring a network protocol stack of an exporter with switched virtual interface (SVI) state information of an SVI associated with a switch in a network, retrieving flow data from a NetFlow cache, and communicating the flow data to a collector according to the configured network protocol stack. Although the communication bypasses the SVI, the collector perceives the flow records as being communicated by the SVI. The SVI state information includes a public Internet Protocol (IP) address and a Media Access Control (MAC) address of the SVI, where the exporter executes on an adaptor of a server in the network. The method also includes configuring a destination IP address and a destination MAC address on the exporter according to a NetFlow policy.

Abstract: The present invention discloses a method for maintaining quality of service QoS, which includes: identifying a CLP and a service type of a newly received ATM cell, and obtaining a corresponding QoS label; when the QoS label corresponding to the newly received ATM cell is different from a QoS label corresponding to a buffered ATM cell, encapsulating the buffered ATM cell into a pseudo wire PW packet in a concatenation manner and sending the pseudo wire PW packet, where the QoS label corresponding to the buffered ATM cell is used as a QoS label of a PSN transport header of the PW packet, or is used as QoS labels of both the PSN transport header and a PW header of the PW packet, and buffering the newly received ATM cell. The present invention further provides a corresponding provider edge PE device and a corresponding ATM PWE3 system.

Abstract: A method and apparatus for uplink (UL) starvation avoidance includes determining a current buffer status information. The current buffer status information is reported to an evolved Node B (eNB). A grant that includes a determination of a number of tokens a wireless transmit/receive unit (WTRU) may accumulate is received from the eNB.

Abstract: Embodiments of the present invention disclose a method and an apparatus for maintaining tokens, and relate to the field of communications technologies, so as to solve a problem of a burst excess of data to be transmitted and improve QoS. The method of the present invention includes: obtaining a peak information rate (PIR) of a network node; splitting the PIR into a first rate and a second rate; obtaining, according to the first rate, the first number of added tokens corresponding to a first period, and obtaining, according to the second rate, the second number of added tokens corresponding to a second period; adding tokens according to the first period and the first number of added tokens, and adding tokens according to the second period and the second number of added tokens.

Abstract: Aspects of the disclosure provide a device transmitting a sequence of packets. The device may include a first queue configured to queue the sequence of packets for transmission by an egress port to a receiving device, and a queue control module configured to transmit the sequence of packets in time slots of the egress port. The sequence of packets can be uniformly distributed across the time slots to satisfy an agreed data rate between the device and the receiving device.

Abstract: Methods and apparatus for congestion control in computer networks achieve high burst tolerance, low latency and high throughput with shallow-buffered switches. A method for controlling congestion includes transmitting a set of data packets on a network connection from a first computing device to a second computing device, identifying each data packet in the set of data packets that experienced congestion on the network connection, sending, by the second computing device to the first computing device, a sequence of bits that represents the number of data packets in the set of data packets that were identified as having experienced congestion, and adjusting a rate of transmitting data packets on the network connection based on the sequence of bits sent to the first computing device.

Abstract: Methods, systems, and computer readable media for network traffic regulation of multi-priority traffic in a telecommunications network are disclosed. According to one aspect, a method for regulation of multi-priority traffic in a telecommunications network includes, at a node for processing messages in a telecommunications network, receiving a message having an intended destination, determining a priority of the message, and obtaining, from a plurality of threshold values, each threshold value being associated with one of a plurality of message priorities, a threshold value that is associated with the determined priority. The number of messages that have been allowed during a current measurement period is determined, an action to perform on the message is selected based a relationship between the threshold value and the message count, and the selected action is performed. The method includes detecting a refresh condition, and, in response to detecting the refresh condition, starting a new measurement period.