Abstract: Energy aware data prefetching is disclosed. Data stored in a source storage may be retrieved or prefetched to a target storage based on a prefetching time predicted or estimated by an awareness engine. The awareness engine may include models configured to predict the prefetching time so that the prefetching time accounts for a cost and/or source of energy. The prefetching operation is performed at the prefetching time. The models of the awareness engine may also be configured to recommend a source for the prefetching operation from among multiple potential sources for the prefetching operation in an energy aware manner.

Abstract: One example method includes receiving, from a DCF (data confidence fabric) including a node that comprises a data source of an edge environment, a confidence score concerning a data stream associated with the data source, correlating the confidence score to a compliance level of the edge environment with regard to a specified requirement for the edge environment, generating, based on the confidence score and compliance information, an audit report that identifies a connection between the confidence score and the compliance level, and for a value of a performance gap between the compliance level and a required compliance level, associated with the specified requirement, that meets or exceeds a threshold, identifying a remedial action which, when implemented in the edge environment, causes a reduction of the performance gap to a value below the threshold.

Abstract: Energy aware data encryption operations are disclosed. An awareness engine includes models configured to generate a recommendation that includes an encryption time and/or an encryption model. When the encryption operation is a data at rest encryption operation, the data is encrypted in accordance with the recommendation and stored at the storage system. When the encryption operation is a data in motion encryption operation, the data is encrypted and transmitted to a target storage system in accordance with the recommendation. At the target storage system, the encrypted may be stored in an encrypted form or decrypted and stored. The recommendations are configured to account for energy considerations including energy cost and/or energy source.

Abstract: One example method includes receiving, by a TEA (trustworthy energy awareness) module, a request from a storage controller to identify a most energy-efficient storage array, as among a plurality of storage arrays, on which to store a set of data, determining, by the TEA module based on energy efficiency information and user constraints, the most energy efficient storage array, and identifying, by the TEA module to the storage controller, the most energy efficient storage array.

Abstract: Routing data in a data confidence fabric network. A confidence fabric adds confidence information to data delivered through the data confidence fabric network. A route is selected by considering inputs that include the trust insertion capabilities of nodes in potential routes, resource usage of nodes in the potential routes, and/or historical delivery times for the potential routes. One of the potential routes is selected as a selected route. The selected route may be based on best anticipated delivery time in view of the inputs.

Abstract: One example method includes generating respective confidence vectors for respective hops associated with a data confidence fabric (DCF), and each hop is associated with one or more trust insertion technologies, identifying a deviation from one of the confidence vectors, generating a waterfall visualization that identifies a location in the DCF, and a type, of the deviation, automatically identifying a remediation action concerning the deviation, and automatically implementing the remediation action in a node of the DCF.

Abstract: Energy aware data compression is disclosed. A storage array may receive data from a client to be compressed. The storage array may request information from a compression awareness engine that is configured to estimate compression times in the context of energy source and energy cost. The storage array makes a decision to compress the data based on the estimates or response received from the compression awareness engine. The data is then compressed and stored in the storage array.

Abstract: One example method includes formulating a hypothesis for development of computing model, annotating the hypothesis with ethics metadata, storing the hypothesis and the ethics metadata, in association with each other, in a ledger, performing ‘n’ phases of a development lifecycle for the computing model, annotating each of the ‘n’ phases with ethics metadata specific to the phase, updating the ledger to include the ‘n’ phases and the ethics metadata respectively associated with each of the ‘n’ phases, and calculating an ethics confidence score for the computing model.

Abstract: Enhancing privacy-preserving data aggregation with a data confidence fabric or confidence scores. Data points ingested into a data confidence fabric are associated with a confidence score. The confidence score is generated as trust insertion technologies are applied to the data points. The confidence score reflects a trustworthiness of the data and reflects how the data points are trusted. When aggregating the data points into aggregated data, the data points are aggregated in a manner that accounts for their confidence scores. This lessens the impact of data points that have comparatively low confidence scores in the aggregated data.

Abstract: One example method includes receiving, at a node of a data confidence fabric, a data stream, prepending, by the node, a data confidence fabric header to the data stream so as to create a prepended data stream, and the data confidence fabric header includes confidence metadata relating to the data stream, and transmitting, by the node, the prepended data stream to another node of the data confidence fabric. The confidence metadata includes metadata about hardware and/or software associated with the data in the data stream.

Abstract: One example method includes, in a node of a data confidence fabric (DCF), the node comprising hardware, obtaining, when available, a static confidence score for a lowermost layer of an infrastructure of the node, after a workload is orchestrated to the node, obtaining, when available, a workload confidence score, when the static confidence score and the workload confidence score are available, aggregating the static confidence score and the workload confidence score together to obtain an overall infrastructure confidence score, and applying, by the node, the overall infrastructure confidence score to data passing through the node.

Abstract: One example method includes monitoring confidence scores received from an edge entity in an edge environment, and the edge entity comprises hardware and/or software, comparing a change in the confidence scores with a threshold permissible confidence score change, when a magnitude of the change is above a threshold permissible change, identifying the edge entity, or a system/device monitored by the edge entity, as a possibly malfunctioning entity, identifying a corrective action for the edge entity, and implementing, and/or causing implementation of, the corrective action.

Abstract: Time sensitive networking with data confidence is disclosed. Data ingested into a data confidence network is associated with annotations and/or confidence scores based on trust insertion technologies applied to the data. When time sensitive networking is applied, the annotations and confidence score reflect the application or use of time sensitive networking. Applications may determine whether to use or have confidence in the data based on the confidence score and/or annotations related to the use of time sensitive networking.

Abstract: A proxy or sidecar configured to connect an application to a data confidence fabric is discloses. The sidecar is configured to perform functions related to the transmission of data. As the sidecar intercepts communications to/from an associated application, the sidecar determines which of several functions to perform related to the transmission of data. In addition, the sidecar ensures that data confidence related operations and trust functions, as specified by the application, are applied to the data. Further, the sidecar identifies lineage when data is changed by an application.

Abstract: A distributed ledger is configured with a global topic whose identifier is publicized and well known. The global topic stores information about trust providers including topic identifiers and smart contract identifiers. Requestors can query the global topic to retrieve the information of specific trust providers. Once the information of the specific trust providers is known, the requestors can publish or write annotations and transactions to the distributed ledger. By associating the entries in the global topic with timestamps, requestors can reconfigure themselves automatically with updated trust provider information whenever a write to the distributed ledger fails.

Abstract: One example method includes connecting a digital wallet of a customer to an agent of a data confidence fabric, receiving, from an application, a request for performance of a trust function, by the data confidence fabric, with respect to customer data, processing the customer data by applying the trust function to the customer data, returning the customer data, after the processing, to the agent, creating annotations for the customer data, based on the trust function that was applied, upon successful execution of a smart contract, transferring a fee from the digital wallet to a trust provider associated with the data confidence fabric, and providing the processed customer data to another entity.

Abstract: A computing system may identify data provided by a plurality of edge nodes that is to be used in training or updating a machine learning (ML) model. The computing system may identify a confidence score associated with the data provided by a plurality of edge nodes. The computing system may place the data provided by the plurality of edge nodes that is determined to have a high confidence score into a first queue. The computing system may place the data provided by the plurality of edge nodes that is determined to have a low confidence score into a second queue. The computing system may use the data placed into the first queue and/or the second queue to train or update the ML model.

Abstract: Invoking smart contracts in data confidence fabrics is disclosed. Trust functions are applied to data that is ingested into and/or flowing in a data confidence fabric. When a trust function is applied, a smart contract is invoked. The smart contract is configured to publish annotations to a distributed ledger that reflect the confidence information added by the trust function and to perform payment as a service such that the trust provider is paid. Publishing the annotations to a distributed ledger may be coupled or uncoupled to performing payment as a service.

Abstract: A data confidence fabric for generating data confidence scores for a build pipeline is disclosed. Confidence scores are generated for data or jobs in a build pipeline. The scores may be combined into a final confidence score that reflects a confidence in the artifact generated by the pipeline and in the pipeline. A user or infrastructure may or may not perform the artifact based on the associated confidence score.

Abstract: A data confidence fabric that is network topology aware is disclosed. When data is able to be transmitted over one of multiple communication channels, confidence information related to the transmission of the data over a selected communication channel is associated with the data. Events, such as failover, are also reflected in the confidence information and confidence score of the data. The confidence information and/or confidence scores allow applications to determine how to trust data in a manner that accounts for the transmission path.