Abstract: Aspects of the present disclosure relate to sustainability-aware computing device behavior management. In examples, a sustainability platform obtains sustainability information associated with an energy grid, as may be provided by a data provider. The sustainability platform may provide a sustainability forecast, which may be received and cached by a computing device. The computing device may use the sustainability forecast to manage various device functionality, such that functionality may be performed during one or more times that are identified to have a comparatively lower environmental impact, thereby deferring device energy consumption during a time forecasted to have a higher environmental impact. The sustainability forecast cached by the computing device may be updated on a periodic basis or in response to determining that the location of the computing device (and, potentially, the associated energy grid) has changed, among other examples.

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

Abstract: In examples, a device configuration is evaluated according to a set of conservation rules, such that one or more configuration recommendations may be generated. A configuration recommendation may be presented to a user of the computing device, such that the user may accept or reject the recommendation. If the recommendation is rejected, the recommendation may be presented to the user at a later time. In another example, a sustainability forecast may be obtained by the computing device, which may include estimated characteristics for an associated energy grid. The sustainability forecast may be presented to a user, thereby enabling the user to consider whether it may be preferable to use the computing device in one or more time periods that have a comparatively lower estimated environmental impact. A sustainability utilization metric may also be generated that is indicative of an estimated past environmental impact of the device.

Abstract: Aspects of the present disclosure relate to sustainability-aware computing device behavior management. In examples, a sustainability platform obtains sustainability information associated with an energy grid, as may be provided by a data provider. The sustainability platform may provide a sustainability forecast, which may be received and cached by a computing device. The computing device may use the sustainability forecast to manage various device functionality, such that functionality may be performed during one or more times that are identified to have a comparatively lower environmental impact, thereby deferring device energy consumption during a time forecasted to have a higher environmental impact. The sustainability forecast cached by the computing device may be updated on a periodic basis or in response to determining that the location of the computing device (and, potentially, the associated energy grid) has changed, among other examples.

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

Abstract: Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.