Cloud infrastructure planning systems and methods can utilize artificial intelligence/machine learning agents for developing a plan of demand, plan of record, plan of execution, and plan of availability for developing cloud infrastructure plans that are more precise and accurate, and that learn from previous planning and deployments. Some agents include one or more of supervised, unsupervised, and reinforcement machine learning to develop accurate predictions and perform self-tuning alone or in conjunction with other agents.

A computer-implemented system and method identifies a network flow direction. The method includes observing, by a network flow monitor, a plurality of data packets as each data packet travels past a connection point. The method further includes identifying, from the plurality of data packets, a flow session, wherein the flow session comprises a source port, a source device, a destination device, a destination port, and a communication protocol. The method also includes, gathering, from the plurality of data packets, directional metadata. The method includes, comparing the source port and the destination port against a list of common destination ports. The method further includes determining, based on the plurality of data packets, a flow direction of the flow session. The method includes storing the flow session in a database.

Software performance can be automatically managed in a distributed computing environment. In one example, a system that can receive metrics information describing resource usage by a first instance of a service in a distributed computing environment. The system can also determine a quality-of-service (QoS) constraint for the service. The system can then modify a definition file based on the metrics information and the QoS constraint, the definition file being configured for deploying instances of the service in the distributed computing environment. The system can deploy a second instance of the service in the distributed computing environment using the modified definition file. As a result, the second instance can more closely satisfy the QoS constraint than the first instance.

Methods, apparatus, and processor-readable storage media for artificial intelligence-based redundancy management are provided herein. An example computer-implemented method includes obtaining telemetry data from one or more client devices within at least one system; predicting one or more hardware component failures in at least a portion of the one or more client devices within the at least one system by processing at least a portion of the telemetry data using a first set of one or more artificial intelligence techniques; determining, using a second set of one or more artificial intelligence techniques, one or more redundant hardware components for implementation in connection with the one or more predicted hardware component failures; and performing at least one automated action based at least in part on the one or more redundant hardware components.

Techniques of network configuration verification are disclosed herein. One example process includes, upon receiving a query to determine whether a packet from a first endpoint is reachable to a second endpoint in a virtual network, identifying a network path between the first endpoint to the second endpoint in a network graph. The network graph has nodes representing corresponding enforcement points of network policies in the virtual network and edges connecting pairs of the nodes. The example process can also include generating compound function representing conjoined individual constraints of the network policies at each of the nodes in the network graph along the identified network path, compiling the generated compound function into a Boolean formula, and solving the compiled Boolean formula to determine whether an assignment of values to packet fields of the packet exists such that all the conjoined individual constraints of the compound function can be satisfied.

A method of abstracting network resources in a mobile communications network includes: determining a service coverage area for a class of service, the class of service defined by service parameters; determining a set of tracking areas that fall at least partly within the service coverage area; selecting available network resources for tracking areas of the set of tracking areas, for providing the class of service in the tracking areas; defining an abstraction view of the selected network resources for the class of service in the service coverage area, the abstraction view having deliverable values of the service parameters within the set of tracking areas; and outputting a communication signal having an indication of the abstraction view.

A method for task offloading based on power control and resource allocation in the Industrial Internet of Things includes establishing a computing model for computation tasks at different offloading locations, constructing communication power control, resource allocation and computation offloading problems as a mixed integer non-linear programming model, solving them using a deep reinforcement learning algorithm to obtain an optimal strategy for offloading of the computation tasks, thus achieving communication power optimization and cross-domain resource allocation.

A computer implemented method of managing a predictive model of a communication network, wherein the predictive model is configured to identify and correct forthcoming failures in network devices based on data collected from the network devices. The method includes allocating network devices of the communication network into first and second clusters, disabling the predictive model in the first cluster, enabling the predictive model in the second cluster, collecting data from the first cluster, repeating said disabling, enabling and collecting with a new allocation of first and second clusters to continuously collect data with different allocation of first and second clusters, and outputting at least the data collected from the first cluster for analysis of the predictive model

Provided is acquiring communication information via communication or directly from an engineering DB (corresponding to one example “database”) in which the communication information related to communication devices constituting a plant network is defined; storing the acquired communication information; calculating, based on the stored communication information, a total communication amount of each of the communication devices supposed in communication executed in corresponding one of the communication devices; estimating, based on the total communication amount, an actual communication amount of each of the communication devices according to an arbitrary estimation condition specified by a user; determining at least presence/absence of a communication device whose actual communication amount exceeds communication capability of the communication device; and outputting a determined determination result to the user.

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.