Disclosed in some examples are methods, systems, and machine-readable mediums which determine jitter buffer delay by inputting jitter buffer and currently observed network status information to a machine learned model that is trained using a reinforcement learning (RL) method. The model maps these inputs to an action to compress, stretch, or hold the jitter buffer delay, which is used by a recipient computing device to optimize the jitter buffer delay. The model may be trained using a simulator that uses network traces of past real streaming sessions (e.g., communication sessions) of users. By training the model through reinforcement learning, the model learns to make better decisions through reinforcement in the form of reward signals that reflect the performance of each decision.

Aspects of the subject disclosure may include, for example, a processing system that performs operations including collecting encrypted network traffic flow data from user interaction with an application, deriving a first set of traffic feature vectors from the encrypted network traffic flow data collected, training a machine learning algorithm on the first set of traffic feature vectors to classify each traffic feature vector in the first set of traffic feature vectors as associated with a type of the application or not associated with the type of the application, and classifying whether an encrypted network traffic flow as the type of the application by applying the machine learning algorithm to a traffic feature vector of the encrypted network traffic flow. Other embodiments are disclosed.

Implementations described and claimed herein provide systems and methods for intelligent node type selection in a telecommunications network. In one implementation, a customer set is obtained for a communications node in the telecommunications network. The customer set includes an existing customer set and a new customer set. A set of customer events is generated for a node type of the communications node using a simulator. The set of customer events is generated by simulating the customer set over time through a discrete event simulation. An impact of the customer events is modeled for the node type of the communications node. The node type is identified from a plurality of node types for a telecommunications build based on the impact of the customer events for the node type.

Systems and methods for controlling operations of a computer system. The methods comprises: collecting, by at least one computing device, information about events occurring in the computer system; performing automated ontogenesis operations by the at least one computing device using the collected information to determine a context of a given situation associated with the computer system, define parameters for a plurality of different sets of actions that could occur in the context of the given situation, and simulate the sets of actions to generate predicted consequences resulting from the performance of certain behaviors by nodes of the computer system; and using the parameters of at least one of the predicted consequences to control operations of the computer system.

This document describes modeling and simulation techniques to select a cloud architecture profile based on correlations between application workloads and resource utilization. In some aspects, a method includes obtaining infrastructure data specifying utilization of computing resources of an existing computing system. Application workload data specifying tasks performed by one or more applications running on the existing computing system is obtained. One or more models are generated based on the infrastructure data and the application workload data. The model(s) define an impact on utilization of each computing resource in response to changes in workloads of the application(s). A workload is simulated, using the model(s), on a candidate cloud architecture profile that specifies a set of computing resources. A simulated utilization of each computing resource of the candidate cloud architecture profile is determined based on the simulation. An updated cloud architecture profile is generated based on the simulated utilization.

The present invention extends to methods, systems, and computer program products for tool registry for automating DevOps toolchains. Submission of a DevOps tool, authentication information, and tool configuration data is received from a user. Subsequently, the DevOps tool is selected for inclusion in a DevOps job. The DevOps tool including the authentication information and tool configuration data is automatically accessed from the tool registry. The DevOps tool is configured in accordance with the accessed authentication information and accessed tool configuration data as part of the DevOps job and for interaction with the one or more other DevOps tools. The DevOps job is deployed.

The present disclosure generally relates to systems, methods and software for quantitatively evaluating an improvement on an active communication network when an impairment, such as a developing impairment, is addressed by one or more repair options via proactive network maintenance.

In one embodiment, a device obtains an indication of a network event predicted by a routing engine for a network. The device initiates monitoring of one or more network paths associated with the network event, to determine one or more states of the network. The device makes a comparison between the one or more states of the network and a set of one or more constraints. The device provides a prediction cancelation notification to the routing engine, based on the comparison.

Systems and methods are provided for analyzing one or more root causes of service degradation events in a network or other environment. A method, according to one implementation, includes a step of monitoring a plurality of overlying services offered in an underlying infrastructure having a plurality of resources arranged with a specific topology. In response to detecting a negative impact on the overlying services during a predetermined time window and based on an understanding of the specific topology, the method further includes the step of identifying suspect components from the plurality of resources in the underlying infrastructure. The method also includes the step of obtaining status information with respect to the suspect components to determine a root cause of the negative impact on the overlying services.

Technologies are described for determining between synchronous and asynchronous modes for computing service requests. Computing service requests are received by a computing service from clients. The computing service dynamically determines whether to use synchronous mode or asynchronous mode for processing the computing service requests. The computing service makes the dynamic determination of which mode to use (synchronous or asynchronous) based on various criteria, which can include synchronous/asynchronous mode recommendations generated by machine learning models and/or synchronous/asynchronous mode recommendations generated by static rules.