A method in a telecommunications network comprises acquiring values of one or more parameters relating to traffic flow between a first group of nodes in the network. The method further comprises using a first reinforcement learning agent to dynamically adjust a first routing metric used to route traffic through the first group of nodes, based on the values of the one or more parameters, so as to alter the traffic flow through the first group of nodes.

A method for controlling congestion in a datacenter network or server is described. The server includes a processor configured to host a plurality of virtual machines and an ingress engine configured to maintain a plurality of per-virtual machine queues configured to store received packets. The processor is also configured to execute a CPU-fair fair queuing process to control the processing of the packets by the processor. The processor is also configured to selectively trigger temporary packet per second packet transmission limits on top of a substantially continuously enforced bit per second transmission limit upon detection of a per virtual machine queue overload.

A conferencing computing device, including memory storing one or more dispatch data structures. The conferencing computing device may further include a processor configured to receive a plurality of input packets at a shared port from a plurality of sender computing devices. Based on input packet data and the one or more dispatch data structures, the processor may add each input packet to an input queue bound to the shared port. The processor may transmit the input packets to a plurality of application program instances associated with the input queues. The processor may generate a plurality of output packets at the application program instances. The processor may add each output packet to an output queue associated with the application program instance at which that output packet was generated. The processor may, through the shared port, transmit the output packets to a plurality of recipient computing devices.

A conferencing computing device, including memory storing one or more dispatch data structures. The conferencing computing device may further include a processor configured to, at a port, receive, from a sender computing device, a first input packet including first input packet data and a second input packet that includes a copy of the first input packet data, via a first communication channel and a second communication channel, respectively. Based on the input packet data and the one or more dispatch data structures, the processor may add the input packets to a queue of a transport provider bound to the port. The processor may transmit the input packets to an application program instance associated with the queue. The processor may determine that the first communication channel or the second communication channel is disconnected and may maintain communication with the sender computing device through the port via a remaining communication channel.

Some embodiments are associated with multi-tenant software defined data center network traffic management. A data center computing system may calculate a first value for a first traffic flow, associated with a first user, using a dynamic, distributed, and substantially real-time model. The system may calculate a second value for to a second traffic flow, associated with a second user, using the dynamic, distributed, and substantially real-time model. The system may then dynamically allocate network resources to the first and second traffic flows based on the first and second priorities. Some embodiments may establish a plurality of network device queues and perform queue selection for optimization. According to some embodiments, the first user may be categorized as a premium user while the second user is categorized as an enterprise user.

Embodiments of network processing resource management in computing devices are disclosed therein. An example method includes receiving a request from a network interface controller to perform network processing operations at a first core of a main processor for packets assigned by the network interface controller to a queue of a virtual port of the network interface controller. The method also includes determining whether the first core has a utilization level higher than a threshold when performing the network processing operations to effect processing and transmission of the packets. If the first core has a utilization level higher than the threshold, the method includes issuing a command to the network interface to modify affinitization of the queue from the first core to a second core having a utilization level lower than the threshold.

The present solution relates to an improved system and method for reducing traffic flow between the subscriber's device, network, and a charging system. The methods and systems described herein can provide a mediator (or buffer) between the network and the charging system. The mediator can be controlled independently of the charging system and for each client device on the network can run an instance of a quota cache. The charging system can provide the quota cache with a service quota that is allocated out as resource grans to the client device over a given period of time. The mediator can be configured to include a plurality of charging and reporting parameters, which determine how the mediator reports subscriber consumption back to the charging system. The mediator can receive the consumption updates from the client device and aggregate the consumption and report back to the charging system at predefined intervals.

Various methods and systems for implementing request scheduling and processing in a multi-tenant distributed computing environment are provided. Requests to utilize system resources in the distributed computing environment are stored in account queues corresponding to tenant accounts. If storing a request in an account queue would exceed a throttling threshold such as a limit on the number of requests stored per account, the request is dropped to a throttling queue. A scheduler prioritizes processing requests stored in the processing queue before processing requests stored in the account queues. The account queues can be drained using dominant resource scheduling. In some embodiments, a request is not picked up from an account queue if processing the request would exceed a predefined hard limit on system resource utilization for the corresponding tenant account. In some embodiments, the hard limit is defined as a percentage of threads the system has to process requests.

Methods, systems, and computer readable media for lock-free communications processing at a network node are disclosed. One method occurs at a first network node configured to add messages to a plurality of queues, wherein each of the plurality of queues is accessed by one of a plurality of threads. The method comprises receiving a first message associated with a first mobile subscriber; determining that the first message is associated with a first partition key; assigning, based on the first partition key, the first message to a first queue of the plurality of queues, wherein the first queue includes messages associated with the first mobile subscriber and wherein the first queue is accessible by a first thread of the plurality of threads; and processing, by the first thread, messages of the first queue in a first in, first out order.

A conferencing computing device, including memory storing one or more dispatch data structures. The conferencing computing device may further include a processor configured to receive a plurality of input packets at a port from a plurality of sender computing devices. Based on input packet data and the one or more dispatch data structures, for each input packet, the processor may to add that input packet to a queue of a transport provider bound to the port. The processor may transmit the plurality of input packets to a plurality of application program instances and instantiate a respective plurality of concurrent multipoint conferencing sessions. The processor may transmit a plurality of output packets from the plurality of application program instances to a plurality of recipient computing devices. The plurality of output packets may be multiplexed through the port and each have a multiplexed local socket address of the port.