A system for allocating a different class of service to each network connection in a plurality of network connections, where each network connection corresponds to one or more virtual channels. The system can include a plurality of virtual channels that connect a first computer and a second computer. Each virtual channel can service at least a portion of the network traffic generated using a remote-display protocol. The system can also include a plurality of network connections, where each network connection corresponds to at least one of the virtual channels. Each network connection of the system can have an assigned port number and an assigned class of service that corresponds to a transmission priority level. The class of service assigned to each network connection can be unique from the classes of service assigned to other network connections.

Embodiments of the present application relate to a method, device, and system for flow control in connection with one or more access requests. The method includes detecting one or more access requests communicated from one or more access terminals, the one or more access requests associated with accessing a service application system, obtaining flow-limiting condition data, determining a new flow control threshold value based at least in part on the flow-limiting condition data, and updating a current flow control threshold value based at least in part on the new flow control threshold value.

A system, method, and computer program product are provided for augmenting a physical network system utilizing a network function virtualization orchestrator (NFV-O). In use, data traffic is monitored utilizing a Network Function Virtualization Orchestrator (NFV-O) module associated with at least a portion of a physical network system, the NFV-O module being operable to manage data flow associated with one or more Virtual Network Functions (VNFs) and one or more physical elements of the physical network system. Additionally, it is determined whether flow of the data traffic should be modified based on at least one of a traffic load or a traffic type utilizing the NFV-O module integrated in the physical network system. Further, at least a portion of the data traffic is directed from at least one of the physical elements to at least one of the VNFs when it is determined that the flow of the data traffic should be modified.

The described technology is generally directed towards a transport protocol for latency sensitive applications. The disclosed transport protocol is “semi-reliable” in that it allows for specification of an importance of data being transmitted, thereby allowing important data to be sent reliably, while other data can be dropped if necessary, e.g., under bad network conditions. A deadline can be specified for such other data, and if the other data cannot be sent prior to the deadline, it can be dropped. Furthermore, the disclosed transport protocol can allow for early discovery of network jitter. A client device can send regular acknowledgments which identify most recently received data packets as well as a number of “heartbeat transmissions” received at the client device. A server device can use the acknowledgments to discover and respond to jitter.

The described technology is generally directed towards a transport protocol for latency sensitive applications. The disclosed transport protocol is “semi-reliable” in that it allows for specification of an importance of data being transmitted, thereby allowing important data to be sent reliably, while other data can be dropped if necessary, e.g., under bad network conditions. A deadline can be specified for such other data, and if the other data cannot be sent prior to the deadline, it can be dropped. Furthermore, the disclosed transport protocol can allow for early discovery of network jitter. A client device can send regular acknowledgments which identify most recently received data packets as well as a number of “heartbeat transmissions” received at the client device. A server device can use the acknowledgments to discover and respond to jitter.

A computer-implemented method for controlling data traffic in a network system is disclosed. The method includes establishing a list of prioritized applications on a user device. The applications are monitored for network activity. One or more management packets are assembled in response to detecting network activity corresponding to one of the prioritized applications. The one or more management packets include network attribute information. The management packet is then transferred to a network switch for use in configuring the prioritization of data traffic on the network system.

Systems, methods and computer-readable media are presented for moderating the network connectivity of an application according to network connectivity quality. A monitoring component and/or process receives information regarding network requests from the computing device, filters the requests according to an application, and for each of the filtered network requests generates a network request tuple from the network request and stores the information in a communication queue. A moderating component and/or process receives a network request of the application, evaluates the network connectivity quality for the application according to the information in the communication queue, and moderates the network request activity of the application commensurate with the network connectivity quality.

Methods and apparatus for memory allocation and reallocation in networking stack infrastructures. Unlike prior art monolithic networking stacks, the exemplary networking stack architecture described hereinafter includes various components that span multiple domains (both in-kernel, and non-kernel). For example, unlike traditional “socket” based communication, disclosed embodiments can transfer data directly between the kernel and user space domains. A user space networking stack is disclosed that enables extensible, cross-platform-capable, user space control of the networking protocol stack functionality. The user space networking stack facilitates tighter integration between the protocol layers (including TLS) and the application or daemon. Exemplary systems can support multiple networking protocol stack instances (including an in-kernel traditional network stack). Due to this disclosed architecture, physical memory allocations (and deallocations) may be more flexibly implemented.

Disclosed are a process and apparatus for classifying video streams of an online streaming media service in real-time. The process includes processing data packets representing one or more video streams between a service provider and a user access network, generating flow activity data from the packets representing quantitative metrics of network transport activity, and applying a trained classifier to the flow activity data to classify each of the video streams as either a live video stream or a video-on-demand (VoD) stream.

A layer 2 (L2) modem provides traffic handling for low latency (LL) traffic. A filter is selected from an application traffic filter list. The filter determines LL traffic that is received and uses a DSC messaging process is used add a classifier for directing the LL traffic to the LL SF. If LL traffic associated with an LL traffic filter of the classifier begins to buildup in a queue, the LL traffic filter is removed from the classifier. This information is provided to a LL controller server that refines the application traffic filter list used to create the classifier. When LL traffic has not been received for a predetermined time, the classifier is removed. Once LL traffic is again detected by the L2 modem filters, a classifier is again added.