A computer implemented method of adapting a configuration of a software defined network to improve a measure of network performance towards an objective measure of performance, the network including a plurality of network nodes communicating via the network, the method including each node applying an evolutionary algorithm to generate a candidate adjusted configuration for the network and, responsive to a determination that the candidate provides an improvement to the measure of network performance, the node storing the candidate in a distributed database accessible to the nodes for access by other nodes; each node accessing candidate adjusted configurations in the distributed database and determining a performance of the network provided by each accessed candidate, wherein each node records the determined performance provided by a candidate in the database in association with the candidate, such that a candidate adjusted configuration providing a greatest improvement to the measure of network performance is selected by the nodes for adapting the configuration of the network.

A system and method of managing a network that includes assets are described. The method includes modeling the network as a directed graph with each of the assets represented as a node and determining alternative paths to each node from each available corresponding source of the node. The method also includes computing upstream robustness of each node, computing upstream robustness of the network, and computing downstream criticality of each node. Managing the network and each asset of the network is based on the upstream robustness and the downstream criticality of each node.

For example, a network management device performs a method. The network management device collects network data of a current network. Then, the network management device generates a simulation network based on the network data of the current network. When there is a network change requirement, the simulation network can be changed based on a simulation change instruction, to obtain data of a changed simulation network. The network management device obtains a connectivity simulation result based on the data of the changed simulation network and a connectivity simulation input parameter. The network data of the current network is collected, so that restoration is performed and an independent simulation network is additionally generated. The simulation network is changed and the network data generated by the changed simulation network and the connectivity simulation input parameter are used to perform connectivity simulation.

A multi-layer network planning system can determine a set of regenerator sites (“RSs”) that have been found to cover all paths among a set of nodes of an optical layer of a multi-layer network and can determine a set of candidate RSs in the optical layer for use by the links between a set of nodes of an upper layer, wherein each RS can be selected as a candidate RS for the links. The system can determine a binary path matrix for the links between the set of nodes of the upper layer. The system can determine a min-cost matrix that includes a plurality of min-cost paths. The system can determine a best RS from the set of candidate RSs and can move the best RS from the set of candidate RSs into the set of RSs for the links. The system can then update the binary path matrix.

A system, method, and computer program product for identifying location-specific faults are provided. Some embodiments may include receiving first device status data associated with a first computing device and the first device status data may comprise first location-indicative data indicative of a location. Some embodiments may include comparing the first device status data with second device status data associated with one or more second computing devices and the second device status data may comprise second location-indicative data indicative of the location. In some embodiments, based on the comparison of the first device status data and the second device status data, determining that the first computing device is affected by one or more of a device-specific fault or a location-specific fault. Some embodiments may include causing information regarding the device-specific fault or the location-specific fault to be displayed via a graphical user interface.

A method includes obtaining input features based on network traffic received during a time window. The method also includes generating multiple network service type predictions about the network traffic during the time window using a machine learning (ML) classification system operating on the input features. The method also includes storing the multiple network service type predictions in different time steps in a first-in first-out (FIFO) buffer and generating decisions about a presence of each of multiple service types in the network traffic using a voting algorithm. The method also includes reducing fluctuations in the generated decisions using a logic-based stabilizer module to generate a final network service type decision.

Methods are provided for recommending actions to improve operability of a network. In one implementation, a method includes acknowledging a plurality of subnetworks in a whole network, each subnetwork including multiple nodes and being represented by a tunnel group having multiple end-to-end tunnels through the subnetwork. The method also includes selecting a first group of subnetworks from the plurality of subnetworks and generating a Reinforcement Learning (RL) agent for each subnetwork of the first group. Each RL agent is based on observations of end-to-end metrics of the end-to-end tunnels of the respective subnetwork. The observations are independent of specific topology information of the subnetwork. Also, the method includes training a global model based on the RL agents of the first group of subnetworks and applying the global model to an Action Recommendation Engine (ARE) configured for recommending actions that can be taken to improve a state of the whole network.

A system includes a network of multiple network domains, each network domain includes a software defined network (SDN) controller. Each SDN controller includes a network interface circuitry, a processor and a memory. The network interface circuitry provides a communicative coupling with at least one domain of the multiple network domains. The memory includes instructions that when executed by the processor, performs a network update comprising adding links, subtracting links or reporting a status of links in at least one network domain upon receiving a network update request, and performs sending and receiving the network update request to a second SDN controller, where the network update request is part of real-time publish/subscribe protocol, the sending network update request includes a publish message having a specified topic and a set of QoS attributes, and the receiving a network update request includes subscribing to the specified topic and the set of QoS attributes.

In some aspects, a server device may identify one or more services of a cloud infrastructure via a management layer. The server device may determine service information and configuration information for the one or more services. The server device may generate an environment model based at least in part on the service information and the configuration information, the environment model providing information on relationship between one or more components of the cloud infrastructure. The server device may determine one or more threats to the one or more services based at least in part on analyzing the environment model and accessing a threat information database. The server device may generate a threat model that lists the one or more threats to the one or more services. The server device may generate one or more recommendations for the cloud infrastructure based at least on the threat model.

Techniques for monitoring network connectivity using machine learning are provided. A plurality of historical connectivity records is received, and a first machine learning model type, of a plurality of machine learning model types, is selected based on the plurality of historical connectivity records. A machine learning model, of the first machine learning model type, is trained based on the plurality of historical connectivity records, where the machine learning model learns to generate forecasted connectivity records based on the training.