Kyndryl, Inc.

International Business Machines Corporation

Laxmikantha Sai Nanduru

Clea Anne Zolotow

Pritpal Arora

Anil Kumar Narigapalli

Sarbajit Kumar Rakshit

Florian Graf

Anthony M Hunt

Venkateswarlu Basyam

Sean Thomas Fornash

Jigar Navanitrai Kapasi

Petra Kopp

Srilakshmi Surapaneni

Sathis Kumar Duraisamy

Seema Nagar

Tedrick Neal Northway

John Valentine Delaney

Bernhard Julius Klingenberg

Pramod Vadayadiyil Raveendran

James E Olson

Steven Joseph Kurtz

Gavin Charles O'Reilly

Arvind Viswanathan

Mihai Criveti

Rudolph C Baron

James S Bennett

Richard J Baird

Dennis M Carden

Vladimir V Danilevich

Tomasz Gola

Shankar Balasubramanian

Mark Vincent Chitti

A method of mitigating risks in a service level agreement (SLA), including: identifying relationships between an infrastructure and an application associated with the SLA; identifying changes to a technological environment of the SLA based on collected data associated with the SLA and the identified relationships, the collected data including the infrastructure and the application; establishing a baseline for a service level objective (SLO) of the SLA by analyzing the collected data of the infrastructure and the application; determining risk impact to the SLA based on an assessment of requirements to the SLO and the changes to the technological environment of the SLA; generating a solution option for the SLA by applying an explainable artificial intelligence (XAI) model based on processing the risk impact with the baseline in the XAI model; and updating the SLA based on the solution option.

Risk mitigation in service level agreements

Computer systems that use artificial intelligence to predict strategies, scenarios and or game plans for sports games that are already in progress. In some embodiments a feedback loop is used so that the artificial intelligence takes into account events occurring in and/or around the game as they occur to provide updated predictions.

Artificial intelligence assisted sports strategy predictor

An approach for providing solutions to ad in the process recovery in manufacturing systems to resume manufacturing activity is disclosed. The outcome of the approach can include the following advantages, minimizing waste, reducing cost of recovery, and increasing efficiency in a manufacturing process. The approach includes collecting initial factory data; identifying and categorizing one or more shop floor activities; determining initial recovery process; creating a digital twin copy of the factory; performing one or more initial simulation scenarios; generating factory improvement plan; and executing factory improvement plan.

AI-enabled process recovery in manufacturing systems using digital twin simulation

A tool for providing contextual policy-based computer vision control. The tool identifies one or more camera devices in an environment. The tool determines a plurality of vision areas in a field of view within the environment. The tool determines one or more contextual policies for the plurality of vision areas in the field of view. The tool determines one or more vision augmentations for the plurality of vision areas based, at least in part, on an aggregate computer vision capability of the one or more camera devices in the environment and the one or more contextual policies for the plurality of vision areas in the field of view. The tool applies the one or more vision augmentations to at least one of the one or more camera devices in the environment.

Contextual policy-based computer vision control

A computer-implemented method, according to one embodiment, includes logically partitioning a storage system into a plurality of compartment constructs, and mapping hosts in communication with the storage system to the compartment constructs, thereby enabling interoperability among the hosts and the compartment constructs. The interoperability of the hosts and the compartment constructs is analyzed, and the interoperability is based on storage software and/or firmware versions being run by the hosts. The method further includes defining, based on the analysis, risk profiles for applications run on the hosts, and determining, based on the risk profiles, recommendations for assignment and mapping of the hosts with the compartment constructs. Ownership of storage objects is assigned to the compartment constructs based on the recommendations. Each of the storage objects define a logical partition of one of the hosts and a logical partition of a storage volume of the storage system.

Dynamically assigning storage objects to compartment constructs of a storage system to reduce application risk

Mitigating the impact of data center thermal environmental issues on production applications includes retrieving, by a computer, from a centralized repository first data corresponding to I/O and processing activities of an infrastructure component executing one or more applications, second data corresponding to an application-to-infrastructure map, and third data corresponding to a business priority of the one or more applications. Based on the first data and the second data, the one or more applications are mapped to heat generation values of the infrastructure component, and based on the mapping a thermal load of the one or more applications on the infrastructure component is determined using data analytics. Using the third data, the computer identifies an execution priority for the one or more applications, generates a correlative mapping between the execution priority and the thermal load of the one or more applications, and generates a resolution plan based on the correlative mapping.

Data analytics for mitigation of data center thermal issues

Application consistent dataset recovery using a cognitive control plane is provided. Sequence and timestamp of snapshots of volumes in a consistency group across heterogenous storage components corresponding to an application are recorded to facilitate operational recovery of application consistent datasets for the application. The cognitive control plane establishes a framework to manage, monitor, analyze, and update the consistency group and metadata to facilitate application consistent data recovery. A set of snapshots needed for the operational recovery of the application consistent datasets for the application is identified by mapping the sequence and timestamp of the snapshots of the volumes in the consistency group across the heterogenous storage components corresponding to the application in response to the computer determining that the operational recovery of the application consistent datasets for the application has been requested. The operational recovery of the application consistent datasets for the application is performed using the set of snapshots.

Cognitive control plane for application consistent datasets

A method for optimizing device-to-device communication protocol selection in an edge computing environment is provided. The method includes: receiving a request for a service from a user device, wherein the computing system is one of plural edge computing devices in an edge computing environment; determining computational tasks performed in providing the service; selecting, using a machine learning model, a set of the edge computing devices to perform the computational tasks and communication protocols for the set of the edge computing devices to use while performing the computational tasks, wherein the machine learning model is configured to select the set of the edge computing devices and the communication protocols based on minimizing a time to perform the computational tasks; and sending instructions to perform the computational tasks, thereby causing the set of the edge computing devices to perform the service in response to the request from the user device.

Optimizing device-to-device communication protocol selection in an edge computing environment

Policy deviations for distributed computing environments are detected and recorded an immutable ledger of transaction provenance from end to end transactions performed in the distributed computing environment. From the immutable ledger, persona data for transaction types is plotted as an bipartite graph. Edge weights of the bipartite graphs are correlated to trust levels between personas from the persona data and the transaction types from the immutable ledger. Trust levels from the edge weights are correlated to rules illustrating when the transaction provenance indicate a policy deviation in the distributed computing environment. The rules are then employed to detect in real time end to end provenance when a policy deviation in the distributed computing environment is occurring. An alert of policy deviations may be sent to stakeholders for the distributed computing environment.

Provenance based identification of policy deviations in cloud computing environments

A computer directs activity within a computer storage subsystem. The computer identifies a computer operating environment including a computer, and a storage subsystem connected to a group of storage devices. The compute receives metadata representing current and historic performance metrics of said computer operating environment. The computer identifies a first device associated with a first behavior profile governed by a power law distribution, and a second device associated with a second behavior profile governed by a normal distribution. The computer trains Machine Learning (ML) models based on the behavior profiles. The computer establishes Device Performance Rules based on the ML models. The computer forecasts time-based storage system requirements based, at least in part on the Device Performance Rules. The computer prefetches data to a cache component based, at least in part on said forecasted system requirements, in accordance with a time reference available to said computer.

Analytics-driven direction for computer storage subsystem device behavior

An embodiment for cognitively aligning data protection (DP) and disaster recovery (DR) policies is provided. The embodiment may include ingesting a variety of data associated with one or more applications into a repository. The embodiment may also include executing differential analysis on the data and changes to the data to identify differences between the data and the changes to the data. The changes to the data may be obtained by periodically polling internal and external data sources. The embodiment may also include translating the differences between the data and the changes to the data into an updated SLA. The embodiment may further include in response to determining that the differences between the data and the changes to the data warrant a change in the current DP and DR policies, generating one or more recommendations to modify the current DP and DR policies and/or create new DP and DR policies.

Cognitive data protection and disaster recovery policy management

Methods and systems for datacenter migrations are disclosed. A method includes: virtualizing, by a computing device, servers in a source environment; installing, by the computing device, an isolation firewall to isolate a target environment from the source environment; installing, by the computing device, shared services in the target environment; installing, by the computing device, monitoring and management tools in the virtualized servers in the source environment; replicating, by the computing device, between the source environment and the target environment; and cutting over, by the computing device, from the source environment to the target environment by switching a route advertisement from the source datacenter to the target datacenter.

Big bang approach in datacenter migrations

Methods, computer program products, and systems are presented. The methods include, for instance: input data from the source environment, including application hosting data of each server in the source environment and one or more cloud type of the source environment. Candidate cloud types for target platform are listed and servers of the source environment are screened for eligibility for the migration. The target platform is selected by applying preconfigured selection rules on the application hosting data of each eligible server in the source environment. Migration recommendations for each eligible server in the source environment, including selected cloud type corresponding to the target platform, are produced.

Cognitive cloud migration optimizer

A set of workloads to be migrated is identified. A constraint on optimization of the set of workloads is determined. A subset of workloads to be migrated is selected from the set of workloads. A model is constructed, using traffic information corresponding to the set of workloads. The model includes a representation of a relationship between a first workload and a second workload in the subset of workloads. The model is solved to cause generation of a set of optimal flow values. A schedule for a migration wave is constructed. The schedule complies with the constraint on optimization of the set of workloads.

Growing community of inventors

R K Puram Post, India

Laxmikantha Sai Nanduru