Abstract: Examples are described herein for monitoring power source usage of a computing device, including a battery and another power source, over time. In various examples, time periods of this monitored time may be added to a time count based on their immediately previous or immediately subsequent time periods satisfying a condition. The time count may be used to track periods of time during which certain power source usage factors are present that may lead to or may indicate the presence of battery swelling. After a time period is added to the time count, the updated time count can be compared to a time count threshold, and a user of the computing device may be warned based on the comparison. The threshold and warning may be selected to warn a user of potential present or future swelling of the battery.

Abstract: In an example in accordance with the present disclosure, a computing device is described. The computing device includes a database with a thermal dataset acquired during usage of a device. The computing device also includes a processor which trains a neural network to determine suitability of the device for a user of the device based on the thermal dataset. The neural network includes 1) an encoder trained to transform the thermal dataset to a first embedding vector, 2) a compression/decompression component trained to generate a second embedding vector that minimizes a difference from the thermal dataset based on the first embedding vector, and 3) a decoder trained to generate a second thermal dataset from the second embedding vector.

Abstract: An example of a computer-readable medium storing machine-readable instructions. The instructions may cause the processor to receive thermal data for a device and apply anomaly models to the thermal data to produce grades. Grades for a device may be combined into a system thermal grade and corrective actions identified to improve the system thermal grade.

Abstract: An example of a server including a communication interface to receive telemetry data from a plurality of client devices. The telemetry data is to indicate a health of a client device from the plurality of client devices. The server further includes a prediction engine to process the telemetry data to determine the health of the client device with a prediction model to identify a hardware issue at the client device. The server also includes a diagnostic evaluator in communication with the prediction engine. The diagnostic evaluator is to request a local confirmation of the hardware issue from the client device upon identification of the hardware issue by the prediction engine. The local confirmation is determined at the client device via a diagnostic engine. The server also includes a reporter to report the hardware issue upon receipt of the local confirmation.

Abstract: A system may comprise a database to collect telemetry data corresponding to a particular component of a device. The system may further comprise a controller coupled to the database. The controller may receive telemetry data for the particular component from the database. The controller may further determine a plurality of metrics for the particular component based on the telemetry data, wherein the plurality of metrics is determined for a plurality of suppliers and select a particular supplier of the plurality of suppliers based on the determined plurality of metrics.

Abstract: An example of a non-transitory computer-readable medium to store machine-readable instructions to be executed by a processor. The instructions may cause the processor to create a first knowledge graph to represent a computer system at a first time. The first knowledge graph may include a first set of entries to represent a first set of components of the computer system. The instructions may cause the processor to create a second knowledge graph to represent the computer system at a second time after the first time. The instructions may cause the processor to compare the second knowledge graph with the first knowledge graph and perform a corrective action based on the comparison.

Abstract: In various examples, a plurality of data points indicative of a history of a battery may be obtained and analyzed based on a causal model to predict a future safety threat event of the battery. The causal model may include a plurality of nodes linked by edges. Each node may represent an event and each edge may represent an observed cause-effect relationship between an event represented by one node of the causal model and another event represented by another node of the causal model. One of the nodes of the causal model may represent the future safety threat event of the battery.

Abstract: An example of a computer-readable medium to store machine-readable instructions. The instructions may cause a processor to update a machine learning model based on first confidential data set. The machine learning model may have been previously trained based on a training data set distinct from the confidential data set. The instructions may cause the processor to apply the machine learning model after the update to a second confidential data set.

Abstract: An example of a computer-readable medium storing machine-readable instructions. The instructions may cause the processor to receive thermal data for a device and apply anomaly models to the thermal data to produce grades. Grades for a device may be combined into a system thermal grade and corrective actions identified to improve the system thermal grade.

Abstract: An example of an apparatus including a memory storage unit to store a local set of troubleshooting solutions. The apparatus further an administration engine to communicate with a first network. The administration engine is to manage a service subscription. The apparatus also includes a communication interface to communicate with a peer device. The peer device is part of a second network separate from the first network. The apparatus also includes an authentication engine to authenticate the peer device to establish a link with the peer device to access a peer set of troubleshooting solutions. In addition, the apparatus includes a diagnostic engine to collect diagnostic data to identify an issue. The diagnostic engine selects a solution from the local set of troubleshooting solutions and the peer set of troubleshooting solutions based on the diagnostic data. The apparatus includes a repair engine to implement the solution.

Abstract: An example method of collecting an n-component subset of resource usage data descriptive of usage of resources of a device or a system includes normalizing a set of resource usage data. Normalizing the set of resource usage data includes comparing usage of a first resource by a first component with usage of the first resource by other components.

Abstract: An example of a server including a communication interface to receive telemetry data from a plurality of client devices. The telemetry data is to indicate a health of a client device from the plurality of client devices. The server further includes a prediction engine to process the telemetry data to determine the health of the client device with a prediction model to identify a hardware issue at the client device. The server also includes a diagnostic evaluator in communication with the prediction engine. The diagnostic evaluator is to request a local confirmation of the hardware issue from the client device upon identification of the hardware issue by the prediction engine. The local confirmation is determined at the client device via a diagnostic engine. The server also includes a reporter to report the hardware issue upon receipt of the local confirmation.

Abstract: In an example, a method includes monitoring, by at least one processor, a computing system. An alert related to the computing system may be generated based on a threshold value. An analysts handling of the alert may be monitored and, based on the analysts handling of the alert, the threshold value for generating alerts may be adjusted.

Abstract: In some examples, a computing device can determine a data state from telemetry data received from a plurality of client devices, determine a state change using the data state determined from the telemetry data, determine, using the state change, a potential cause of a fault of a component of a client device of the plurality of client devices, where the potential cause of the fault is determined in response to receiving a support inquiry from the client device, and display a timeline of state changes, where the timeline includes the determined state change of the client device.

Abstract: A system may comprise a database to collect telemetry data corresponding to a particular component of a device. The system may further comprise a controller coupled to the database. The controller may receive telemetry data for the particular component from the database. The controller may further determine a plurality of metrics for the particular component based on the telemetry data, wherein the plurality of metrics is determined for a plurality of suppliers and select a particular supplier of the plurality of suppliers based on the determined plurality of metrics.

Abstract: A system for monitoring the thermal health of an electronic device is described. The system includes a predictor to predict an expected temperature of the electronic device using a model. The system also includes a computation manager to compute a difference between an actual temperature of the electronic device and the expected temperature, compute a z-score of the difference, and map the z-score to a thermal health grade for the electronic device.

Abstract: In some examples, a computing device can determine a data state from telemetry data received from a plurality of client devices, determine a state change using the data state determined from the telemetry data, determine, using the state change, a potential cause of a fault of a component of a client device of the plurality of client devices, where the potential cause of the fault is determined in response to receiving a support inquiry from the client device, and display a timeline of state changes, where the timeline includes the determined state change of the client device.