An initial provisioning by a management plane of the SD-WAN is received from a centralized SD-WAN gateway with static path overlay between the network edge device on a local LAN and the centralized SD-WAN gateway. At runtime, intelligent decision are made about which overlay path to select and when for the new flow over a control plane of the SD-WAN, based on the topology of the remote network edge and the local SDWAN policy, and to build the selected overlay path.

Hybrid edge computing that includes a nimble framework that identifies services for available in a marketplace. The nimble framework defines a location for computing the services selected from the group consisting of a center server, an edge provision server and an edge node. The hybrid edge computing further includes a third party provider making are request for a service to the nimble framework. The hybrid edge computing further includes a virtualized service being provided by the nimble framework to the third party provider including a matched service to the third party provider request for the service, and an optimal location for computing.

A large-scale network node simulation method based on Linux container is provided, which solves problems of low packet transmission efficiency and multi-thread creation in real-time simulation in a large-scale network scenario. The method includes: scheduling all container nodes in a scenario; managing, by a container node, a dynamic thread through an idle thread management queue, and setting a finite state machine and a function pointer for the dynamic thread; registering, by a source container node, an output queue with a next-hop container node, and informing the next-hop container node to allocate a dynamic thread for receiving and processing the output queue. Packet transmission is realized between the container nodes through data units created in a shared memory. The sending thread and the receiving thread dynamically adjust the number of dynamic threads by checking the state of the output queue.

There is provided a method and system for communication network management. There is provided an active TE architecture and procedure that rely on the epistemic uncertainty obtained from traffic forecasting models. According to embodiments, the traffic forecasting models can predict the mean of the network traffic demand and can extract one or more of the features relating epistemic uncertainty and the aleatoric uncertainty. According to embodiments, the epistemic uncertainty is used to vary the sampling frequency of network statistics in TE applications, for specific times or specific flows. A time-window can be used to predict network traffic can be varied (e.g. increased or decreased) to adjust the epistemic uncertainty.

A system for an automated ML-based design of a wireless network. The system includes a processor of a design server node connected to at least one local, edge, or cloud server node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire aerial 3-D mapping data of a target area from an unmanned aircraft system (UAS) flying over the target area; acquire surface 3-D mapping data from a ground robotic crawler; parse the 3-D mapping data to derive an at least one feature vector; provide the at least one feature vector to a machine learning (ML) module residing on the at least one local, edge, or cloud server node for generating a predictive model of a wireless network for some or all of the target area; receive outputs of the predictive model; and generate a wireless network design for the some or all of the target area based on the predictive outputs.

Aspects of the present disclosure include systems, methods, computing devices, computer-implemented methods, and the like for modeling and/or simulating performance of a telecommunications network during one or more failure scenarios that reduces computational time and/or power over previous simulation techniques. Modeling and simulating the network may include generating an initial network model from network data information and applying one or more transformations to the initial network model to reduce the size of the model. Following transformation, simulation methods may be applied to the generated network model based on routing characteristics of the components of the network. To reduce the computations utilized to simulate such components and/or routing decisions in the network, one or more simulation algorithms may be applied to the transformed network model to reduce the number of routing decisions simulated.

Training and enhancement of neural network models, such as from private data, are described. A slave device receives a version of a neural network model from a master. The slave accesses a local and/or private data source and uses the data to perform optimization of the neural network model. This can be done such as by computing gradients or performing knowledge distillation to locally train an enhanced second version of the model. The slave sends the gradients or enhanced neural network model to a master. The master may use the gradient or second version of the model to improve a master model.

A network analytics controller is established in a network. The network includes a plurality of nodes. A plurality of network analytics agents is established; each agent at a node of the network. Network analytics configuration parameters, including a network analytics scope, are received at the networks analytics controller. A task is assigned to each agent at a node determined to be within the network analytics scope, the task comprising that portion of the network analytics specified in the network analytics configuration parameters relevant to the corresponding node. The assigned task is performed at each agent assigned a task. The networks analytics controller receives the results of each performed task, and aggregates the received results.

A computer system for evaluating the communication performance of an autonomous vehicle is provided. The vehicle may have a vehicle controller including at least one processor in communication with at least one memory device. The processor may be programmed to receive, from a standard data transmission location network device, an evaluation data packet. The processor may be programmed to decode the evaluation data packet and initiate a diagnostic test of the vehicle based upon the decoded evaluation data packet. The processor may also be programmed to record measurements of the vehicle during the diagnostic test, and transmit the measurements to the standard data transmission location network device.

Technologies for allocating resources of managed nodes to workloads to balance multiple resource allocation objectives include an orchestrator server to receive resource allocation objective data indicative of multiple resource allocation objectives to be satisfied. The orchestrator server is additionally to determine an initial assignment of a set of workloads among the managed nodes and receive telemetry data from the managed nodes. The orchestrator server is further to determine, as a function of the telemetry data and the resource allocation objective data, an adjustment to the assignment of the workloads to increase an achievement of at least one of the resource allocation objectives without decreasing an achievement of another of the resource allocation objectives, and apply the adjustments to the assignments of the workloads among the managed nodes as the workloads are performed. Other embodiments are also described and claimed.