In one embodiment, a device obtains metadata for routing decisions made by a predictive routing service for a plurality of network deployments. The device identifies a network topology for a network deployment that does not use the predictive routing service. The device estimates, based on the metadata for routing decisions made by the predictive routing service, performance metrics for the predictive routing service were it to be used to make routing decisions for the network topology. The device sends, to a user interface, report data indicative of the performance metrics estimated for the predictive routing service were it to be used to make routing decisions for the network topology.

Content propagation control can include determining a classification of a message formatted for conveyance over a data communications network. The classification can be based on content of the message and determined using a classification model constructed by analyzing prior message propagation rates and corresponding propagation paths that are each associated with one of multiple message content types. Content propagation control also can include selecting propagation rate and propagation path control indicators based on the classification of the message determined using the classification model and embedding the propagation rate and propagation path control indicators in the message.

Methods, systems, and apparatus, including computer-readable storage media, optimizing interior gateway protocol (IGP) metrics using reinforcement learning (RL) for a network domain. The system can receive a topology (G) of a network domain, a set of flows (F), and an objective function. The system can optimize, using reinforcement learning, the objective function based on the received topology and the one or more flows F. The system can determine updated IGP metrics based on the optimization of the objective function. The IGP metrics for the metric domain may be updated with the updated IGP metrics.

A node device for forming a multi-hop network is provided. The node device is configured to avoid interference from coexisting interfering networks and includes a transceiver configured to receive and transmit data with respect to a Destination Oriented Directed Acyclic Graph (DODAG) Information Object message (DIO message), a memory configured to store computer executable programs including an interfered-node count (IC), single-rate link count (SLC), multi-rate link count (MLC), hop count (HP), path communication latency (PCL) and an interference efficient and multi-rate supported routing program CoM-RPL, and a processor configured to perform steps of the computer executable programs. The steps include determining if the received DIO message indicates a new DODAG or an existing DODAG. In this case, if a determined result in the determining indicates the new DODAG and no single-rate link and no interfered node on a path of multi-hop network, the node device joins DODAG network and the processor selects a sender of the DIO message as a default parent, computes a rank for itself, updates DIO message with its rank, IC, SLC, TRM, HP, PCL and transmits scheduled DIO messages based on transmission rate mode.

In one embodiment, a device obtains data regarding routing decisions made by a machine learning-based predictive routing engine for a network. The device determines, based on the data regarding the routing decisions, a behavior of the machine learning-based predictive routing engine. The device compares the behavior of the machine learning-based predictive routing engine to a behavioral policy for the machine learning-based predictive routing engine. The device adjusts operation of the machine learning-based predictive routing engine, when the behavior of the machine learning-based predictive routing engine violates the behavioral policy.

A node device for forming a multi-hop network is provided. The node device is configured to avoid interference from coexisting interfering networks and includes a transceiver configured to receive and transmit data with respect to a Destination Oriented Directed Acyclic Graph (DODAG) Information Object message (DIO message), a memory configured to store computer executable programs including an interfered-node count (IC), single-rate link count (SLC), multi-rate link count (MLC), hop count (HP), path communication latency (PCL) and an interference efficient and multi-rate supported routing program CoM-RPL, and a processor configured to perform steps of the computer executable programs. The steps include determining if the received DIO message indicates a new DODAG or an existing DODAG. In this case, if a determined result in the determining indicates the new DODAG and no single-rate link and no interfered node on a path of multi-hop network, the node device joins DODAG network and the processor selects a sender of the DIO message as a default parent, computes a rank for itself, updates DIO message with its rank, IC, SLC, TRM, HP, PCL and transmits scheduled DIO messages based on transmission rate mode.

An agent training method includes: obtaining environment information of a first agent and environment information of a second agent; generating first information based on the environment information of the first agent and the environment information of the second agent; and training the first agent by using the first information, so that the first agent outputs individual cognition information and neighborhood cognition information. The neighborhood cognition information of the first agent is consistent with neighborhood cognition information of the second agent.

A new approach is proposed to support firewall protection of dynamically introduced routes in an internal communication network. Under the proposed approach, all routes dynamically introduced into the internal communication network via a dynamic routing service are dynamically learned and tagged by a route collection engine. A dynamic network object is created, which is a software component configured to store a plurality of single IP addresses and/or IP address ranges of the dynamically learned routes in a dynamic routing network. A firewall engine of the internal communication network is configured to create one or more firewall rules referencing the dynamic network object and apply various security measures/policies to network data packets routed on the dynamically learned routes in the dynamic routing network based on IP address matching with the dynamic network object.

Provided are a method and device for packet forwarding. The method comprises: interface direction information and a routing table issued by a control plane are received, where a route in the routing table carries a routing direction identifier; when a packet is received from an interface, a forwarding plane determines the interface direction of an incoming interface of the packet according to the interface direction information, and determines a routing direction of the packet according to the routing direction identifier; if the interface direction of the incoming interface matches the routing direction, then the packet is forwarded; and if not, then the packet is discarded.

This application provides a model training-based communication method and apparatus, and a system, to effectively decrease a data amount of a parameter transmitted between the communication device and the central server. The method includes: The communication device determines a change amount of a first model parameter value. If the communication device determines, based on the change amount of the first model parameter value, that a first model parameter is stable, the communication device stops sending an update amount of the first model parameter value to the central server in a preset time period. The update amount of the first model parameter value is determined by the communication device based on user data in a process of performing model training. The communication device receives a second model parameter value sent by the central server.