International Business Machines Corporation

Kyndryl, Inc.

Braulio Gabriel Dumba

Sai Zeng

Jun Duan

Manish Mahesh Modh

Emrah Zarifoglu

Matthew X Staffelbach

Umar Mohamed Iyoob

Andrew John Anderson

Liang Liu

Alexei A Karve

Muhammed Fatih Bulut

Abdulhamid Adebowale Adebayo

Nerla Jean-Louis

Ubaid Ullah Hafeez

Gloire Rubambiza

An edge site maintains a plurality of rendezvous nodes to which a plurality of Internet of Things (IoT) devices are communicatively coupled, where the plurality of rendezvous nodes are also communicatively coupled to an edge hub in the edge site. A cached model is maintained at the edge hub, where the cached model enables the edge site to stay operational in an event of a failure of a cloud hub to which the edge hub is communicatively coupled.

Scalable mechanisms for workload management in edge computing

A method for scheduling services in a computing environment includes receiving a service scheduling request corresponding to the computing environment and identifying a resource pool and a set of compliance requirements corresponding to the computing environment. The method continues by identifying target resources within the resource pool, wherein target resources are resources which meet the set of compliance requirements, and subsequently identifying a set of available target resources, wherein available target resources are target resources with scheduling availability. The method further includes analyzing the set of available target resources to determine a risk score for each available target resource and selecting one or more of the set of available target resources according to the determined risk scores. The method continues by scheduling a service corresponding to the service scheduling request on the selected one or more available target resources.

Compliance aware application scheduling

A computer-implemented method, system and computer program product for maximizing system scalability while guaranteeing enforcement of service level objectives. A request is received to access a backend database in a hierarchy of backend databases that includes heterogenous computing resources with a dynamic range of performance. Upon receiving the request, a reinforcement learning based filter determines if the request's frequency of access exceeds a cutoff frequency. If the received request is not filtered, but instead, is passed through the filter, then one of the backend databases in the hierarchy is selected. Such a selection is made by a load balancer that is trained using reinforcement learning to select the optimal backend database taking into consideration the storage size and speed of the backend databases as well as taking into consideration the user-specified service level objective to be met by the request to guarantee enforcement of such a service level objective.

Maximizing system scalability while guaranteeing enforcement of service level objectives

A computer-implemented method for managing one or more operations of a workload includes selecting a resource type for workload management on a platform. One or more operations of the selected resource to be managed are identified. A reconciliation time for execution of each of the identified operations is determined. A reconciliation period between two consecutive reconciliations is determined for each of the identified operations. A minimum number of processes for workload management of a given set of the operations on resources is calculated, and the determined minimum number of processes is deployed to manage the workload.

Scalable operators for automatic management of workloads in hybrid cloud environments

A machine learning assessment system is provided. The system identifies multiple datasets and multiple machine learning (ML) modeling algorithms based on the client profile. The system assesses a cost of data collection for each dataset of the multiple datasets. The system assesses a performance metric for each ML modeling algorithm of the multiple modeling algorithms. The system recommends a dataset from the multiple datasets and an ML modeling algorithm from the multiple ML modeling algorithm based on the assessed costs of data collection for the multiple datasets and the assessed performance metrics for the multiple ML modeling algorithms.

Efficiency driven data collection and machine learning modeling recommendation

A system, computer program product, and method to deriving a cost model and dynamic adjustment of the derived model responsive to dynamic modification of one or more of the resources in a hybrid shared resource environment. Resources and corresponding configuration information are collected while monitoring runtime utilization of resource performance. As changes to the resources are discovered, the changes are subject to an assessment. A hybrid cost model is derived and configured to account for the one or more resources. The derived hybrid cost model is leveraged to conduct a multi-dimensional resource evaluation of the assessed changed configuration information. Responsive to the multi-dimensional evaluation, a generated resource utilization optimization of the one or more resources is selectively implemented.

Growing community of inventors

White Plains, NY, United States of America

Braulio Gabriel Dumba