Abstract: In some embodiments, operating data may be collected from a set of enterprise system devices via a cloud-based services architecture. The operating data may be processed, for example, via requests handled by analytic microservices. A deployment platform may create code instances of actively deployed analytic microservices and identify an existing deployed analytic microservice as being associated with a feature update, the existing deployed analytic microservice being associated with a set of pending requests. The deployment platform may create a new code instance of the identified analytic microservice and arrange for the existing deployed analytic microservice to process the set of pending requests while the new code instance handles newly received requests. The deployment platform may then determine that the existing deployed analytic microservice has completely processed the set of pending requests and retire the existing deployed analytic microservice such that it is replaced by the new code instance.

Abstract: In some embodiments, a cloud-based services architecture may receive operating data associated with a set of assets from a set of enterprise system devices. The cloud-based services architecture may then process the received operating data. A plurality of computing platforms may execute instance runs of a plurality of analytics, with each instance run being associated with an industrial asset. A distributed cache may be shared by the plurality of analytic instance runs executing on the plurality of computing platforms. An orchestration run-time execution engine may maintain an overall count value that represents a number of analytic instance runs currently utilizing the distributed cache. Note that the distributed cache may be emptied when the overall count value indicates that no analytic instance runs are still utilizing the distributed cache.

Abstract: In some embodiments, a cloud-based services architecture may receive operating data from a set of enterprise system devices. The cloud-based services architecture may include a tenant-specific space and an orchestration run-time execution service to manage creation and execution of a first and a second custom analytic model in the tenant-specific space. Moreover, the first analytic model may be customized to run as a service having: (i) some of the received operational data as an input, and (ii) a result of a first analytics process as an output. The second analytic model may be customized to run as a service having: (i) the output of the first analytic model as an input, and (ii) a result of a second analytics process as an output. According to some embodiments, the input of the second analytic model is received from the first analytic model without leaving the tenant-specific space.

Abstract: In some embodiments, operating data may be collected from a set of enterprise system devices via a cloud-based services architecture. The operating data may be processed, for example, via requests handled by analytic microservices. A deployment platform may create code instances of actively deployed analytic microservices and identify an existing deployed analytic microservice as being associated with a feature update, the existing deployed analytic microservice being associated with a set of pending requests. The deployment platform may create a new code instance of the identified analytic microservice and arrange for the existing deployed analytic microservice to process the set of pending requests while the new code instance handles newly received requests. The deployment platform may then determine that the existing deployed analytic microservice has completely processed the set of pending requests and retire the existing deployed analytic microservice such that it is replaced by the new code instance.