Abstract: Techniques are disclosed for modularly creating a virtual representation of physical infrastructure of a computing environment. For example, a method comprises generating a virtual representation of physical components of a computing environment. The virtual representation is generated by enabling selection of templates from a pre-stored template database wherein the templates respectively represent the physical components, and by integrating the selected templates with one another to collectively represent the physical components. The method then manages the physical components via the virtual representation.

Abstract: Embodiments of systems and methods for automated identification of training datasets are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: receive a training dataset comprising a plurality of elements, tag an element of the training dataset with: (a) a first attribute representing a first characteristic detectable in the element, and (b) a second attribute representing a second characteristic not detectable in the element, and select a subset of the plurality of elements to train an Artificial Intelligence (AI) or Machine Learning (ML) model based, at least in part, upon the tag.

Abstract: Embodiments of systems and methods for model prediction confidence utilizing drift are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: identify drift with respect to an Artificial Intelligence (AI) or Machine Learning (ML) model; and adjust a confidence score of a prediction or inference produced by the AI/ML model based, at least in part, upon the drift.

Abstract: Embodiments of systems and methods for multi-observer, consensus-based ground truth are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: detect an observation overlap between two or more devices; identify a consensus between Artificial Intelligence (AI) or Machine Intelligence (ML) model inferences made based upon data received by the two or more devices; and in response to the identification, tag at least a subset of the data with a ground truth label.

Abstract: Embodiments of systems and methods for unsupervised data characterization utilizing drift are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: provide input data to an Artificial Intelligence (AI) or Machine Learning (ML) drift detector, where the AI/ML drift detector is associated with a characteristic undetectable in the input data; and receive a drift confidence score from the AI/ML drift detector.

Abstract: Embodiments of systems and methods for enhanced drift remediation with causal methods and online model modification are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: detect drift in an Artificial Intelligence (AI) or Machine Learning (ML) model configured to make a prediction or a causal reasoning graphical or structural inference based upon input data, identify a root cause of the drift, and tag the input data with an indication of the root cause.

Abstract: Techniques described herein relate to a method for deploying workflows. The method may include receiving, by a global orchestrator of a device ecosystem, a request to execute a workflow; decomposing, by the global orchestrator, the workflow into a plurality of workflow portions; executing, by the global orchestrator, a metaheuristic algorithm to generate a result comprising a plurality of domains of the device ecosystem in which to execute the plurality of workflow portions; and providing, by the global orchestrator, the plurality of workflow portions to respective local orchestrators of the plurality of domains based on the result of executing the metaheuristic algorithm.

Abstract: An information handling system includes a plurality of network nodes and a processor. The network nodes each include an optical link and a reflectometry analyzer. The reflection analyzers provide reflectometry results that each provide a characterization of physical properties of the associated optical link. The processor receives the reflectometry results, and, for each optical link, analyzes the reflectometry results to determine a fingerprint of the physical properties of the associated optical link. The processor further determines a status for each of the optical links based upon the associated fingerprints, and displays a map of the information handling system including each network node and the associated optical link, wherein the map provides an indication of the status for each of the optical links.

Abstract: An information handling system includes a plurality of network nodes and a processor. Each network node includes an optical link and a reflectometry analyzer. The reflection analyzers provide a plurality of reflectometry results that each provide a characterization of physical properties of the optical link. The processor receives the reflectometry results, analyzes the reflectometry results to define a fingerprint of the physical properties of the optical link, and determines a status for each of the optical links based upon the associated fingerprints. The status for each of the optical links includes one of a plurality of graded statuses. Each graded status represents a qualitative measure of the physical properties of the associated optical link. A first graded status represents a better qualitative measure than a second graded status. The processor further receives a request to route a data flow from a first one of the network nodes to a second one of the network nodes.

Abstract: A data communication network includes a network node and a processor. The network node includes an optical link and a reflectometry analyzer. The reflection analyzer provides a plurality of reflectometry results that each provide a characterization of physical and operational properties of the optical link at the time of the reflectometry result. The processor receives a first set of the reflectometry results, analyzes the first set of reflectometry results to define a fingerprint of the physical and operational properties of the optical link, receives a second set of the reflectometry results, compares the second set of reflectometry results with the fingerprint, and determines whether or not the optical link is secure based upon the comparison of the second set of reflectometry results with the fingerprint.

Abstract: A data communication network includes a plurality of network nodes and a processor. The network nodes each include an optical link and a reflectometry analyzer. The reflection analyzers provide reflectometry results that each provide a characterization of physical and operational properties of the associated optical link. The processor receives the reflectometry results from the reflectometry analyzers, and, for each optical link, analyzes the reflectometry results to determine a fingerprint of the physical and operational properties of the associated optical link. The processor further determines a status for each of the optical links based upon the associated fingerprints, and determines a first path between a first one of the network nodes and a second one of the network nodes based upon a first status of a first optical link in the first path and a second status of a second optical link in the path.

Abstract: Techniques described herein relate to a method for distributed data management. The method may include making a first determination that data is written to a data structure of storage of a data host; obtaining, based on the first determination, data information associated with the data; making a second determination of intent corresponding to the data; generating a global name and metadata corresponding to the data, wherein the metadata comprises the intent; and publishing the global name and the metadata to a global name repository.

Abstract: Techniques described herein relate to a method for using pipeline data for deploying workflows. The method may include determining that a pipeline testing trigger occurred for a workflow; decomposing a pipeline testing manifest of the workflow; generating a testing execution plan using the decomposed workflow; adding instrumentation to the testing execution plan; determining that the instrumented testing execution plan is valid; deploying computing devices within a CI/CD pipeline ecosystem for performing the instrumented testing execution plan; capturing deployment logs; initiating telemetry capture; executing pipeline testing of the workflow based on the instrumented testing execution plan; generating a pipeline deployment information set based on the pipeline testing; and providing the pipeline deployment information set to an orchestrator of a production device ecosystem.

Abstract: Techniques described herein relate to a method for deploying workflows. The method may include receiving, by a global orchestrator of a device ecosystem, a request to execute a workflow; decomposing, by the global orchestrator, the workflow into a plurality of workflow portions; executing, by the global orchestrator, a metaheuristic algorithm to generate a result comprising a plurality of domains of the device ecosystem in which to execute the plurality of workflow portions; and providing, by the global orchestrator, the plurality of workflow portions to respective local orchestrators of the plurality of domains based on the result of executing the metaheuristic algorithm.

Abstract: A system for processing data is disclosed that includes an artificial intelligence (AI) model operating on a processor and configured to process an incoming data set to generate a data output. An AI model anomaly detection system operating on the processor and configured to receive the incoming data set and the data output and to generate an anomaly detection as a function of the incoming data set and the data output. An AI model anomaly analysis system operating on the processor and configured to receive the anomaly detection and the incoming data set and to generate AI model anomaly data. An AI model anomaly mitigation system operating on the processor and configured to receive the AI model anomaly data and to generate AI model anomaly correction data.

Abstract: Techniques described herein relate to a method for performing data services. The method may include receiving, from a monitor agent, a global name and metadata corresponding to data written to a data structure of storage of a data host; performing a services assessment using the global name, the metadata, and a data service policy rule to obtain at least one data service to perform on the data; and performing the at least one data service based on the services assessment.

Abstract: A method, comprising: obtaining a data item that is associated with an IoT device, the IoT device including one or more of a sensor, an actuator, or an energy source; obtaining, from a blockchain-based attestation system, a trust score that is associated with the data item, the trust score being generated by using a consensus-building mechanism that is provided by the blockchain-based attestation system; when the trust score satisfies a predetermined condition, using the data item; and when the trust score fails to satisfy the predetermined condition, discarding the data item, wherein the IoT device is configured to operate as a node in the blockchain-based attestation system, and the blockchain-based attestation system includes one or more other IoT devices that are part of the same IoT device network as the IoT device.

Abstract: An information handling system includes a plurality of network nodes and a processor. Each network node includes an optical link and a reflectometry analyzer. The reflection analyzers provide a plurality of reflectometry results that each provide a characterization of physical properties of the optical link. The processor receives the reflectometry results, analyzes the reflectometry results to define a fingerprint of the physical properties of the optical link, and determines a status for each of the optical links based upon the associated fingerprints. The status for each of the optical links includes one of a plurality of graded statuses. Each graded status represents a qualitative measure of the physical properties of the associated optical link. A first graded status represents a better qualitative measure than a second graded status. The processor further receives a request to route a data flow from a first one of the network nodes to a second one of the network nodes.

Abstract: A data communication network includes a plurality of network nodes and a processor. The network nodes each include an optical link and a reflectometry analyzer. The reflection analyzers provide reflectometry results that each provide a characterization of physical and operational properties of the associated optical link. The processor receives the reflectometry results from the reflectometry analyzers, and, for each optical link, analyzes the reflectometry results to determine a fingerprint of the physical and operational properties of the associated optical link. The processor further determines a status for each of the optical links based upon the associated fingerprints, and determines a first path between a first one of the network nodes and a second one of the network nodes based upon a first status of a first optical link in the first path and a second status of a second optical link in the path.

Abstract: A data communication network includes a network node and a processor. The network node includes an optical link and a reflectometry analyzer. The reflection analyzer provides a plurality of reflectometry results that each provide a characterization of physical and operational properties of the optical link at the time of the reflectometry result. The processor receives a first set of the reflectometry results, analyzes the first set of reflectometry results to define a fingerprint of the physical and operational properties of the optical link, receives a second set of the reflectometry results, compares the second set of reflectometry results with the fingerprint, and determines whether or not the optical link is secure based upon the comparison of the second set of reflectometry results with the fingerprint.