Abstract: There is disclosed in one example a computer apparatus, including: a hardware platform including a central processor unit (CPU) and a memory; and instructions encoded within the memory to instruct the CPU to: enumerate a plurality of running processes, and associate resource demands with the running processes; predict a resource starvation condition for at least one process; rank the plurality of running processes according to a dynamic ranking algorithm, wherein the ranking algorithm includes user engagement as an input for ranking a process; and according to the ranking and a safeguard algorithm, deallocate resources from a process ranked lower than the at least one process and assign the deallocated resources to the at least one process to mitigate the predicted resource starvation condition.

Abstract: Systems, methods and computer-readable media are provided for receiving an indication to suspend a first event associated with a first resource indicator that is stored in a first data file associated with a first resource management software utilized by a first entity. A second indication to suspend the first event is determined to be provided by a second entity utilizing a second resource management software, the second indication to suspend the first event indicating a modification to both the first data file associated with a first resource management software and a second data file associated with the second resource management software. The first data file is reconciled by instructing the first resource management software to modify the first resource indicator in the first data file so as to correspond to a modification to a second resource indicator associated with the second data file.

Abstract: 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.

Abstract: A resource allocation method comprises using resources with a used resource quantity of a machine learning system to execute a first experiment which has a first minimum resource demand, receiving an experiment request associated with a target dataset, deciding a second experiment according to the target dataset, deciding a second minimum resource demand of the second experiment, allocating resources with a quantity equal to the second minimum resource demand for an execution of the second experiment when a total resource quantity of the machine learning system meets a sum of the first minimum resource demand and the second minimum resource demand and a difference between the total resource quantity and the used resource quantity meets the second minimum resource demand, determining that the machine learning system has an idle resource, and selectively allocating said the idle resource for at least one of the first experiment and the second experiment.

Abstract: At a managed control plane service, constituent services and operational requirements of an application are identified. In response to an end-user request directed to the application, contents of an inter-service request are generated at a resource selected by the managed control plane service for a first constituent service, and a response to the message is generated at another resource selected for a second constituent service. Tasks to be performed for the operational requirements are initiated by the managed control plane service.

Abstract: There is provided method of centralized control of event messages for accessing services by processes that generate event messages, comprising: monitoring event messages from an event broker server of a distributed event streaming technology service monitoring a central event dataset storing the event messages streamed over a network from the processes for accessing the services, counting a number of event messages for combination(s) of event attribute(s) according to set(s)-of-rules, dynamically generating a lock that includes instructions for blocking the event messages having the certain combination of event attributes(s) in response to the number reaching a threshold for a certain combination of event attribute(s), and dynamically providing the lock to each process that generates event messages having the combination of event attribute(s), wherein each process is configured for implementing the lock for locally blocking the event messages having the certain combination of event attribute(s).

Abstract: A method of processing data for a deep learning system driven by a plurality of heterogeneous resources is provided. The method includes, when a first task including at least one of a plurality of operations is to be performed, receiving first path information indicating a first computing path for the first task. The first computing path includes a sequence of operations included in the first task and a driving sequence of resources for performing the operations included in the first task. The method further includes setting data representation formats of the resources for performing the operations included in the first task based on data representation information and the first path information. The data representation information indicates an optimized data representation format for each of the plurality of heterogeneous resources.

Abstract: The present disclosure relates to a gateway device supporting integral processing of APIs with security function, and a method of operating the gateway device. In more detail, the present disclosure relates to a gateway device for integrally processing APIs with a security function, the gateway device supporting a security function that notifies of a security danger when a problem is generated by analyzing logs in the process of API calling and responding and supporting a security function that increases security for a new environment in which calling of several API servers and responding are repeated in a gateway by applying a function of integrally processing a plurality of API functions by registering the API functions into a unit API service to the gateway, and a method of operating the gateway device.

Abstract: A method of managing task offloading to edge servers in a multi-access edge computing (MEC) system includes receiving, by a task broker implemented at a host management level of the MEC system, a task offloading request from a UE application, analyzing, by the task broker, resource requirements of a task of the task offloading request and running a forecasting mechanism that determines whether the task offloading request will eventually be dropped or not by a system management level of the MEC system. The task broker, based on the determination of the forecasting mechanism, either rejects or provisionally admits the task offloading request.

Abstract: A computer implemented method is provided that includes using historic migration data to label key performance indicators (KPIs) in a migration model including a scale that indicates a level of successful migration to a remote provider. Employing the migration model to predict successful migration of a local application having one or more of said one or more of local key performance indicators for the local application. Migrating the local application to a remote provider when the model to predict successful migration indicates a greater than threshold value for successful migration.

Abstract: Techniques are provided for scheduling multiple jobs on one or more cloud computing instances, which provide the ability to select a job for execution from among a plurality of jobs, and to further select a designated instance from among a plurality of cloud computing instances for executing the selected job. The job and the designated instance are each selected based on a probability distribution that a cost of executing the job on the designated instance does not exceed the budget. The probability distribution is based on several factors including a cost of prior executions of other jobs on the designated instance and a utility function that represents a value associated with a progress of each job. By scheduling select jobs on discounted cloud computing instances, the aggregate utility of the jobs can be maximized or otherwise improved for a given budget.

Abstract: Task permissions for software services can be set in a distributed computing environment according to some examples described herein. In one example, a system can determine software services that are included in software products deployable to a user account of a distributed computing environment. The system can determine task permissions to be set in the user account for allowing the software services to execute tasks in the distributed computing environment. The system can generate a list of task permissions by consolidating the task permissions based on predefined rules. The system can then transmit an output indicating the list of task permissions for causing the user account to be configured based on the list of task permissions, to permit the software services to execute the tasks in the distributed computing environment.

Abstract: Systems and methods are provided for managing dynamically allocated storage and processing units. The systems and methods include operations for determining, a usage pattern having a peak usage portion and a low usage portion; reserving a first collection of units on a dynamic unit allocation system during the peak usage portion; detecting a transition from the peak usage portion to the low usage portion; in response to detecting the transition, instructing the dynamic unit allocation system to reduce the first collection of units to reserve a second collection of units corresponding to a second amount of the low usage portion; selecting asynchronous tasks that consume a set of units greater than the second collection of units; and during a period of time that the dynamic unit allocation system is reducing the first collection of units, causing the asynchronous tasks to be executed by the dynamic allocation system.

Abstract: Reliability monitoring can be performed for compute instances in a cluster with auto-scaling capability. Such monitoring can analyze state information for various instances, such as spot instances, to determine when an interruption or termination is to occur. An impact assessor can determine the impact on performance due to any such interruption or termination, and if necessary to maintain at least a minimum level of performance then an action performer can obtain additional or alternate instances, which may be of a different type, to make up for lost capacity. Any tasks being performed can be migrated to the newly-allocated instances without any failures or significant impact on performance, and the previously-utilized instances can be released corresponding to the termination or interruption.

Abstract: Systems and methods for quality of service management are provided. According to one embodiment, a non-transitory computer-readable medium comprises instructions that when executed by the processing resource cause the processing resource to collect, from a plurality of volumes on a per-volume basis, one or more real-time performance metrics for one or more compute processes executing on the one or more computer systems, generate an inertial parameter for one or more volumes in the plurality of volumes, and generate an instruction that cause a processor to use the real-time performance metrics and the inertial parameter to determine whether to transfer responsibility for a compute process on a first storage server node to a second storage server node.

Abstract: A method and an apparatus for processing a transaction in a blockchain network, a related device, and storage medium are disclosed. The method includes the following. A transaction submission request in a form of readable data field is obtained, and the data field in the transaction submission request is processed. If a target field exists during processing the data field, a virtual machine is called to execute logical codes corresponding to the target field. According to a code execution result from the virtual machine and a processing result of the data field, a processing result of the transaction submission request is determined.

Abstract: Technologies and techniques for a mobile end device to offload computing from the mobile end device to at least one edge computer and/or at least one cloud computer. Resource information may be obtained from the at least one edge computer and/or at least one cloud computer. Application information may be obtained from at least one system application in the mobile end device, and A computing capacity may be assigned for the at least one system application in the mobile end device to the at least one edge computer and/or the at least one cloud computer.

Abstract: A cooling-power-consumption-based workload allocation system includes a workload allocation system coupled to at least one client device and a plurality of server devices. The workload allocation system receives a first workload request that identifies a first workload from the at least one client device, and determines a first workload priority of the first workload relative to a second workload priority of each second workload being performed by the plurality of server devices. Based on the first workload priority of the first workload relative to the second workload priority of each second workload and a cooling-power-utilization-efficiency ranking of each of the plurality of server devices, the workload allocation system identifies a first server device included in the plurality of server devices for performing the first workload, and causes the first server device to perform the first workload.

Abstract: A method is provided for managing applications for sensors. In one embodiment, the method includes loading a plurality of applications and links for communicating with a plurality of sensors on a platform having an interface for entry of a requested use case; and copying a configuration from a grouping of application instances being applied to a first sensor performing in a function comprising of the requested use case. The method may further include applying the configuration for the grouping of application instances to a second set of sensors to automatically conform the plurality of sensors on the platform to perform the requested use case.

Abstract: A computer implemented method implemented on an allocation computing unit for distributing a pre-defined workflow comprising a nonempty set of workflow components, the workflow components being ordered in a directed acyclic precedence graph, onto a set of general purpose computing units comprising at least two general purpose computing units.