Abstract: In some implementations, a method is provided. The method includes receiving captured packet traffic, the captured packet traffic including a plurality of packets transmitted over a network. One or more communication patterns for each of one or more levels in a network stack are detected based on metadata of the captured packet traffic, each communication pattern indicating communication between two components in the network. The method further includes generating a topology of the network in view of the one or more communication patterns detected for each of the one or more levels in the network stack.

Abstract: Software performance can be predicted based on different system configurations. In one example, a computing device can receive historical datasets associated with copies of a software application executed by a group of computing environments during a prior timespan. Each historical dataset can indicate respective changes during the prior timespan to at least one performance characteristic of one of the copies of the software application executed by one of the computing environments in the group. Each computing environment in the group can being configured differently than the other computing environments in the group. The computing device can also convert the historical datasets into training data for a machine-learning model, and train the machine-learning model. This can yield a trained machine-learning model configured to generate a forecast of the performance characteristic for the software application over a future timespan.

Abstract: In some implementations, a method is provided. The method includes receiving captured packet traffic, the captured packet traffic including a plurality of packets transmitted over a network. One or more communication patterns for each of one or more levels in a network stack are detected based on metadata of the captured packet traffic, each communication pattern indicating communication between two components in the network. The method further includes generating a topology of the network in view of the one or more communication patterns detected for each of the one or more levels in the network stack.

Abstract: Anomalies can be identified within a network. For example, a system can automatically detect anomalous network-activity using a machine-learning model that can analyzing how network configurations change over time. The machine-learning model may detect anomalies by comparing current and anticipated rates of change and/or types of topological changes in the network.

Abstract: Software performance can be predicted based on different system configurations. In one example, a computing device can receive historical datasets associated with copies of a software application executed by a group of computing environments during a prior timespan. Each historical dataset can indicate respective changes during the prior timespan to at least one performance characteristic of one of the copies of the software application executed by one of the computing environments in the group. Each computing environment in the group can being configured differently than the other computing environments in the group. The computing device can also convert the historical datasets into training data for a machine-learning model, and train the machine-learning model. This can yield a trained machine-learning model configured to generate a forecast of the performance characteristic for the software application over a future timespan.

Abstract: In some implementations, a method is provided. The method includes receiving captured packet traffic, the captured packet traffic including a plurality of packets transmitted over a network. One or more communication patterns for each of one or more levels in a network stack are detected based on metadata of the captured packet traffic, each communication pattern indicating communication between two components in the network. The method further includes generating a topology of the network in view of the one or more communication patterns detected for each of the one or more levels in the network stack.

Abstract: Anomalies can be identified within a network. For example, a system can automatically detect anomalous network-activity using a machine-learning model that can analyzing how network configurations change over time. The machine-learning model may detect anomalies by comparing current and anticipated rates of change and/or types of topological changes in the network.