A slice manager associated with a network access point of a telecommunication network can manage combinations of network slices and bandwidth parts for user equipment (UE). The bandwidth parts can have independently set numerologies, such as subcarrier spacing values. The UE can be configured to use one or more active bandwidth parts at a time, such that the slice manager can instruct the UE to use multiple active bandwidth parts simultaneously with respect to the same network slice or multiple network slices.

A computing system includes a distributed computing cluster including a plurality of computing nodes interconnected by an interconnect network over which the computing nodes of the plurality of computing nodes communicate with each other by passing messages. The computing nodes are configured with a first parameter governing transmissions of messages by the computing nodes over the interconnect network. The computing nodes are configured to accumulate messages for transmission as a group of messages according to the first parameter, and the computing system is configured to limit injections of computing requests into the distributed computing cluster according to a second parameter. A controller is configured to receive at least one predetermined service level requirement and to control a value of the second parameter and a value of the first parameter to control a computational throughput of the distributed computing cluster while complying with the at least one service level requirement.

A dynamic multihoming management system for reliable data transmission in a robotic system. The system maintains links for data transmission between nodes. Data is categorized into different classes each associated with a set of requirements for data transmission. A first data class is functional safety data associated with a first set of requirements including a latency level below a first threshold. A second data class is associated with a second set of requirements. The system determines a set of links that satisfy the first set and the second set of requirements and selects a link as an active link to transmit data. The system monitors link status by calculating fitness metrics using different combination of factors for each class of data. Responsive to detecting a degradation in quality of the active link, the system determines to select a new active link for transmitting the safety data based on fitness metrics.

Novel tools and techniques for network data plane management are provided. A system includes a host machine that includes a database, processor, and non-transitory computer readable media comprising instructions executable by the processor to obtain, via the database, a network configuration, spawn a container according to the network configuration, wherein the container is configured, based on the network configuration, to be coupled to a network overlay via a network interface, receive, via the network interface, incoming data associated with the container, the incoming data having attached one or more attached network data attributes, and identify, via the database, the attached one or more network data attributes attached to the incoming data as one or more network data attributes of the network data model.

Described herein are systems and methods for QoS chaining based on control-plane virtual functions for ensuring end-to-end Quality of Service (QoS) of Internet services. The QoS chaining coordinates broadband service delivery via an orchestrated “chain” or Network Service (NS) consisting of control-plane Virtual Network Functions (VNFs) running in the cloud or virtual infrastructure. Separate service elements, network elements, network domains or other service plane or data plane elements or systems have a separate corresponding VNF in the control plane provide monitor and control functions. QoS is ensured End-to-End (E2E) across the chain of VNFs by coordination through the QoS chain or by a coordinating or integrating E2E orchestrator or E2E VNF. The VNFs may be chained, may communicate directly with each other, and may communicate directly with the E2E orchestrator, may communicate with each other through the E2E orchestrator, or may communicate through a shared database.

Systems and methods for load balancing in a network are disclosed. An illustrative method includes receiving network telemetry data corresponding to network paths of a plurality of coexisting multipaths, performing an adaptive load balancing process by determining whether a network path from the plurality of coexisting multipaths is an adequate network path based on the network telemetry data, and in response to determining the network path is an adequate network path, selecting the network path for a network flow.

There are provided measures for network objectives management. Such measures for enabling network objectives management in radio access networks exemplarily comprise receiving a key performance indicator optimization input indicative of a key performance indicator and an optimization direction of said key performance indicator, deriving at least one key performance indicator entry based on said key performance indicator optimization input, said at least one key performance indicator entry comprising at least said optimization direction of said key performance indicator and prioritized target values for said key performance indicator, storing said at least one key performance indicator entry, deciding, for a cognitive function, a target value for said key performance indicator of said prioritized target values for said key performance indicator expected to be achieved by said cognitive function, and providing said decided target value for said key performance indicator and said optimization direction of said key performance indicator to said cognitive function.

A network configuration method includes determining an end-to-end latency upper bound of data traffic between two end nodes, determining an end-to-end latency constraint of the data traffic between the two end nodes, determining, based on the end-to-end latency upper bound and the end-to-end latency constraint, for a first network shaper, at least one configuration parameter that satisfies the end-to-end latency constraint, and configuring the first network shaper for the data traffic based on the at least one configuration parameter such that the traffic after being shaped by the shaper satisfies the network latency constraint.

Various embodiments comprise systems, methods, architectures, mechanisms and apparatus providing a low-latency trading platform and/or communications system wherein one or more remote client devices communicate with a proxy server via a first communications channel, the proxy server being tightly coupled to (co-located and directly communicating with) a programmable hardware platform configured to communicate with an equities exchange system via a second communications channel, the location of the proxy server and hardware platform being proximate that of at least one equities exchange system, wherein the proxy server is updated by client device communications defining trade execution profiles associated with each of a plurality of equities and corresponding trading strategies, and wherein the hardware platform executes equity trades in response to substantially real time data received from the equities exchange. Various embodiments provide a mechanism for automatically provisioning the communications system in accordance with an Infrastructure as a Service (IAAS) offering from a provider of network services.

The present invention relates to a methods and network nodes for controlling resources of a service session in a communication network as well as to a corresponding system and computer program to improve the handling of resources in the network, and particularly to optimize signaling in the network. The method for controlling resources for a service session by a policy and charging system in a communication network comprises the steps of obtaining, at a first network node, a request including service session data indicating the type of service; determining, based on the service session data obtained at said first network node, a resource type to be assigned to said service; and sending to a second network node an indication of said resource type assigned to said service, according to which resource type it is determined when a service session associated with said service is terminated.