Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Claims 1-14, 16, and 21-25 are pending. Claims 15, and 17-20 are canceled and claim 25 is newly added by Applicant.
Examiner Notes
Examiner cites particular paragraphs and/or columns and lines in the references as applied to Applicant’s claims for the convenience of the Applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested that, in preparing responses, the Applicant fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. The prompt development of a clear issue requires that the replies of the Applicant meet the objections to and rejections of the claims. Applicant should also specifically point out the support for any amendments made to the disclosure. See MPEP § 2163.06.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Objections
As per claim 22, Applicant is requested to amend the claim to differentiate between “power consumption” and “compute power consumption” recited in ll. 3-4. Applicant is requested to amend the claim to explain what “energy” means in ll. 4. If it is energy consumption then how would that be the same or different than compute power consumption, and power consumption? Applicant is requested to amend “task execution cost” to “an execution cost for the task”. Applicant is requested to amend the claim to explain what “time” means in ll. 4. Appropriate correction is required.
Response to Amendment - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 1-14, 16, and 21-25 are rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement.
As per claims 1-14, 16, and 21-25, they contain subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, at the time the application was filed, had possession of the claimed invention. The amendment filed 04/24/2026 introduces new matter into the claims. The added material which is not supported by the original disclosure is as follows: “wherein said predicted amount of work is predicted based on historical workload execution data”. Applicant is required to cancel the new matter in the reply to this Office Action.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 7-8, and 14-16 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino et al. (US 2012/0110585) (hereinafter Cosentino as previously cited) in view of Belady et al. (US 2006/0184287) (hereinafter Belady) in view of
Kaul (US 2023/0055276) (as provided in the Notice of References Cited dated 07/10/2025).
As per claim 1, Cosentino primarily teaches the invention as claimed including a system comprising:
a memory ([0022]); and
a processor in communication with said memory, said processor being configured to execute operations ([0022]) comprising:
receiving a request to execute a task from a user ([0036] execution agent enforces the execution of each job in response to a corresponding request received from the executor), wherein said task is associated with an executor ([0036] handler submits each job of the plan for execution as soon as possible on the corresponding execution server either defined statically or selected at run-time among the available execution servers having the required characteristics) based on an optimal amount of power to be used by an executor to execute said task (abstract execution scheme optimizes the energy consumed by the data-processing system to execute the data-processing jobs and claim 13 select a data-processing unit to execute each data-processing job to optimize the energy consumed according to the ambient temperature of the plurality of data-processing units);
executing said task with said executor ([0036] execution agent enforces the execution of each job in response to a corresponding request received from the executor); and
returning a response to said request to said user ([0036] return feedback information indicating the result of the execution which may include indicating whether the job has completed successfully, the actual duration of the job, or the like).
Cosentino does not explicitly teach:
provisioning said executor with resources to fulfill said request based on a predicted amount of work to execute a workload of said task by said executor,
wherein said executor is of said preferred executor type, and
wherein said predicted amount of work is predicted based on historical workload execution data.
However, Belady teaches:
provisioning said executor with resources to fulfill said request based on a predicted amount of work to execute a workload of said task by said executor ([0061] if the power management system predicts that over a relatively long time interval the workload placed on the system will be relatively constant, the power management system may be implemented to configure the system with little buffer e.g., not much more than the amount of resources needed to support the predicted workload are to be provisioned at full power; whereas if the power management system predicts that over a given time interval the workload placed on the system will be volatile/bursty, the power management system may be implemented to configure the system with a large buffer e.g., much more than the amount of resources needed to support the predicted workload are to be provisioned at full power to ensure sufficient resources to support spikes in the encountered workload)
wherein said predicted amount of work is predicted based on historical workload execution data ([0016], [0024], [0027], [0047], and [0060] predict future utilization of the resource based on the historical utilization data of the resource. That is, the power management system uses the historical utilization data to forecast upcoming utilization of the resource. Utilization monitor monitors the utilization of the servers and collects corresponding historical utilization data for each of the servers, and analyzes historical utilization data for each of the servers to predict future utilization thereof and controls the power of each of the resources).
Belady and Cosentino are both concerned with power/energy management in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady because it would provide a way to collect historical utilization data for resources in a data center, predict future utilization of the resources based on the historical utilization data, and selectively place one or more of the resources into a power-conserving mode based on the predicted future utilization. The power management system may resume full power to the resources sufficiently in advance of a predicted utilization of such resources so as not to negatively impact performance of the data center. Considering that electrical costs to a data center is often millions of dollars per year, the power management system may provide a significant cost savings to the data center without sacrificing performance of the data center.
Cosentino in view of Belady do not explicitly teach:
wherein said executor is of said preferred executor type.
However, Kaul teaches:
wherein said executor is of said preferred executor type ([0027] and [0034] workload processes have associated preference information which details the workload’s preferences to be executed on nodes of a particular type).
Kaul and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul because it would provide a way of identifying target nodes that are least likely to be upgraded such as target nodes with newest OS versions. By identifying a target node with the newest version of an OS, the workload execution manager can significantly increase availability of that node before a subsequent upgrade may be scheduled. This, in turn, can significantly reduce the service disruption to workloads caused by repeated relocation of those workloads since the likelihood of draining a node with the newest version of the OS is extremely low. Additionally, since newer versions of an OS are least likely to be unstable, identifying nodes with the newest version of an OS can provide increased stability in the environment for executable workloads. Moreover, by minimizing workload service disruptions, the workload execution manager can improve stability of executing workloads within the cloud computing environment, providing increased efficiency in management of cloud computing resources overall.
As per claim 7, Cosentino further teaches wherein the response comprises one or more of a calculation, a search result, a computation, an answer to a question, and a confirmation of a success ([0036] return feedback information indicating the result of the execution which may include indicating whether the job has completed successfully, the actual duration of the job, or the like).
As per claim 8, it has similar limitations as claim 1 and is therefore rejected using the same rationale.
As per claim 14, it has similar limitations as claim 7 and is therefore rejected using the same rationale.
As per claim 15, Kaul teaches wherein said executor comprises a plurality of nodes (abstract identify a set of eligible nodes of the plurality of nodes for executing the workload process).
As per claim 16, it has similar limitations as claim 1 and is therefore rejected using the same rationale.
Claims 2 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Thomas (US 10,616,078) (as previously cited).
As per claim 2, Cosentino in view of Belady in view of Kaul do not explicitly teach obtaining usage data associated with a plurality of executors, wherein said usage data is associated with a usage pattern.
However, Thomas teaches obtaining usage data associated with a plurality of executors, wherein said usage data is associated with a usage pattern (fig. 2, blocks 210-250 monitor compute resources usage, store usage data in a data store, analyze stored usage data to determine a usage pattern of the resources).
Thomas and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Thomas because it would provide for a profiling service that can use pre-determined baseline usage patterns for a type of resource. For example, the baseline usage pattern for a type of resource can be supplied through a database having fields populated by an administrator of the distributed environment. The pre-determined baseline usage patterns for a type of resource can be based on historical usage patterns or desired usage patterns. Using pre-determined baseline usage patterns for a type of resource may reduce the computing overhead associated with frequently calculating running baseline usage patterns for a type of resource.
As per claim 9, it has similar limitations as claim 2 and is therefore rejected using the same rationale.
Claims 3 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Thomas in view of Desikachari et al. (US 2015/0310139) (Desikachari as previously cited).
As per claim 3, Cosentino in view of Belady in view of Kaul in view of Thomas do not explicitly teach wherein said executor is associated with a resource selection model, and wherein said resource selection model is based on said usage pattern.
However, Desikachari teaches wherein said executor is associated with a resource selection model, and wherein said resource selection model is based on said usage pattern (fig. 4 and [0022]-[0023] generate a model for a resource based on a selected set of usage patterns).
Desikachari and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Thomas in view of Desikachari because it would provide for a way of intelligently determining approximate resource consumptions by various transactions comprising an application and scaling infrastructure components accordingly based on maximum expected load which results in a more optimal allocation of resources for implementing the application. This may be done with respect to adding resources to facilitate application growth, and may be similarly employed to remove extra or unnecessary resources to decrease application capacity if desired.
As per claim 10, it has similar limitations as claim 3 and is therefore rejected using the same rationale.
Claims 4 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Thomas in view of Cronin (US 2023/0211691) (as previously cited).
As per claim 4, Cosentino in view of Belady in view of Kaul in view of Thomas do not explicitly teach wherein a lifecycle of said executor is based on said usage data.
However, Cronin teaches wherein a lifecycle of said executor is based on said usage data ([0166] build different ML models based on system usage data to extend the lifecycle).
Cronin and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Thomas in view of Cronin because it would provide a way for pre-allocating slots in hosts for a particular user account what may not be deemed necessary to ensure host availability for that user account and, reserving the host slots would otherwise waste resources as no other user accounts could use the slots. Alternatively, rather than not creating the allocation upon determining that the fleet of hosts is likely to be widely available for executing virtual machines, a capacity management system may create the allocation but set the start time later rather than earlier to reduce the amount of time that the slots are unavailable for use by other users. Upon expiration of the end time, the allocation is considered invalid and the allocated slots in the specified hosts can be used to launch virtual machines for any user accounts.
As per claim 11, it has similar limitations as claim 4 and is therefore rejected using the same rationale.
Claims 5 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Ramaswamy et al. (US 2023/0081488) (hereinafter Ramaswamy as previously cited).
As per claim 5, Cosentino in view of Belady in view of Kaul do not explicitly teach wherein a type of said executor type is one of a serverless type, a microservice type, and a mixed service type.
However, Ramaswamy teaches wherein a type of said executor type is one of a serverless type, a microservice type, and a mixed service type ([0034] a backend can be a mix of Microservices and Serverless functions).
Ramaswamy and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Ramaswamy because it would provide for a canvas system which can be optimized for scale and development speed. The canvas system can use different kinds of databases that are the best fitting for the specified use cases and use an amalgamation of all of these to get the best performance at scale while still being cost-effective.
As per claim 12, it has similar limitations as claim 5 and is therefore rejected using the same rationale.
Claims 6 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Gupta et al. (US 11,500,663) (hereinafter Gupta as previously cited).
As per claim 6, Cosentino in view of Belady in view of Kaul do not explicitly teach converting said executor from a first executor type to a second executor type.
However, Gupta teaches converting said executor from a first executor type to a second executor type (col. 7, ll. 17-32 reconfiguring servers to execute different types of virtual machines).
Gupta and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Gupta because it would provide a way for pre-allocating slots in hosts for a particular user account what may not be deemed necessary to ensure host availability for that user account and, reserving the host slots would otherwise waste resources as no other user accounts could use the slots. Alternatively, rather than not creating the allocation upon determining that the fleet of hosts is likely to be widely available for executing virtual machines, a capacity management system may create the allocation but set the start time later rather than earlier to reduce the amount of time that the slots are unavailable for use by other users. Upon expiration of the end time, the allocation is considered invalid and the allocated slots in the specified hosts can be used to launch virtual machines for any user accounts.
As per claim 13, it has similar limitations as claim 6 and is therefore rejected using the same rationale.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Blanding et al. (US 9,515,905) (hereinafter Blanding as previously cited) in view of Karri et al. (US 2023/0071278) (hereinafter Karri as previously cited).
As per claim 21, Cosentino in view of Belady in view of Kaul do not explicitly teach wherein said optimal amount of power is based on a user priority, wherein said user priority is selected from the group consisting of minimizing resource consumption, minimizing an execution cost, and using minimal resources to complete said task within a defined period of time.
However, Blanding teaches wherein said optimal amount of power is based on a user priority (col. 4, ll. 66 to col. 5, ll. 7 specify relative priorities of workloads and execution environments), wherein said user priority is selected from the group consisting of minimizing resource consumption, minimizing an execution cost (col. 3, ll. 23-28 minimize resource cost and energy consumption).
Blanding and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Blanding because it would provide for automatic management of multiple scale out workloads so as to minimize the computing resources and hence the related energy consumption required to achieve the performance targets established for the workloads. Automatic management provides for reduced cost and better matching of resources to actual demand as compared to manual management. Automatic management of heterogeneous resources (e.g., use of both virtual and physical execution environment) provides more flexibility than managing only homogeneous resources (e.g., only virtual machines) as well as potential for a better match between required and available resources. Automatic management of heterogeneous workloads from a single resource pool provides more efficiency in use of computing resources as opposed to using separate pools for each workload, and thus reduces energy consumption by the computer system.
Cosentino in view of Belady in view of Kaul in view of Blanding do not explicitly teach using minimal resources to complete said task within a defined period of time.
However, Karri teaches using minimal resources to complete said task within a defined period of time ([0013] optimization criteria seeks to minimize the amount of computational resources to allocate to process the execution paths within required available times to execute the activity steps).
Karri and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Blanding in view of Karri because it would provide for an optimization criteria to minimize execution time by selecting a group of execution paths that completes execution in a minimum time. If the optimization criteria is to minimize processor/memory resource allocation to conserve computational resources, then the resource allocation selects the group of execution paths that minimizes the processor/memory resource allocation and completes execution of the activity steps in the required available times for the activity steps.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Eastep et al. (US 2016/0188380) (hereinafter Eastep) in view of Gmach et al. (US 2013/0268940) (hereinafter Gmach as previously cited) in view of Fellenstein et al. (US 2006/0149714) (hereinafter Fellenstein as previously cited).
As per claim 22, Cosentino in view of Belady in view of Kaul do not explicitly teach wherein said provisioning said executor with resources to fulfill said request is based on a factor selected from the group consisting of an average amount of response to process workloads, an average amount of work done to process a workload by said executor, an average cost for workload services, and a total cost for all available workload services.
However, Eastep teaches wherein said provisioning said executor with resources to fulfill said request is based on a factor selected from the group consisting of an average amount of response to process workloads, an average amount of work done to process a workload by said executor ([0060]-[0061] progress meters of nodes may report average work completed and/or to be completed across cores of the nodes and based on that information the allocation of resources applied to the nodes may be appropriately modified).
Eastep and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Eastep because to it would provide a way to reduce total waiting times for task execution by reallocating computational resources at work on a task. Waiting times at a core level may be reduced overall by speeding up slower cores while slowing down faster cores to allow threads and/or cores to arrive at a global synchronization barrier in relatively less mean time. Core (and/or processor) frequency may be varied over a range by altering the amount of power that may be fed to the core (and/or processor). In a situation where power resources may be limited, faster thread processing times may be obtained by shifting power away from cores that are faster than the average of the cores employed, and toward cores that are slower than the average of the cores employed. In some circumstances, it may be advantageous to redirect power away from cores that are slower than average to other cores that are even slower. Progress meters provide data that may be used to regularly adjust power to cores, thereby relatively reducing waiting times at synchronization points. Power shifting may also reduce power consumed in the course of processing a given job. Advantageously, the overall speed with which a parallel processing job is to be completed may be relatively increased. In addition, total amount of power necessary to complete the job may be relatively reduced. Thus, reducing the relative power consumed by the cores may result in less heat generated at the cores, which may allow relatively less intensive use of air conditioning systems in facilities to provide additional further power savings.
Cosentino in view of Belady in view of Kaul in view of Eastep do not explicitly teach an average cost for workload services, and a total cost for all available workload services.
However, Gmach teaches an average cost for workload services ([0040] a best average effective cost for each workload using a cloud service to be serviced by virtual machines).
Gmach and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Eastep in view of Gmach because it would allow a service user i.e., a customer to decide how best to have workloads hosted by apportioning costs that are least sensitive to workload placement decisions and by providing robust and repeatable cost estimates. The resulting system could compare the costs of hosting a workload in virtualized and non-virtualized environments, separate workloads into categories including those that should be virtualized and those that should not, and determine the amount of physical resources to cost-effectively host a set of workloads.
Cosentino in view of Belady in view of Kaul in view of Eastep in view of Gmach do not explicitly teach a total cost for all available workload services.
However, Fellenstein teaches a total cost for all available workload services ([0081] determine the total hardware and software costs for use of the available grid resources for the grid job and to identify the lowest cost resources available).
Fellenstein and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Eastep in view of Gmach in view of Fellenstein because it would provide for a grid catalog and storage subsystem of grid services that manages the storage and distribution of software images for efficient resource building facilitates grid services such that a user may specify preferred performance levels for a resource management service to distribute jobs to maintain preferred performance levels within the grid execution environment. A grid dynamic build service can build the resource nodes identified as the most cost effective.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Stefani et al. (US 11,170,309) (hereinafter Stefani as previously cited).
As per claim 23, Cosentino in view of Belady in view of Kaul do not explicitly teach wherein said provisioning said executor with said resources to fulfill said request is responsive to said executor having inadequate available resources to execute said task.
However, Stefani teaches wherein said provisioning said executor with said resources to fulfill said request is responsive to said executor having inadequate available resources to execute said task (col. 12, ll. 37-48 provision additional computing resources when processing resources available for use drops below a threshold value).
Stefani and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Stefani because it would provide for an efficient machine learning model inference routing system in a machine learning service feedback processing system that collectively allow for adjusting the routing of inferences based on machine learning model accuracy, performance, demand, and/or the like. This could enable the performance of shadow testing, support ensemble machine learning models, and improve existing machine learning models using feedback data.
Claim 24 is rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Tan et al. (US 2018/0032375) (hereinafter Tan as previously cited).
As per claim 24, Cosentino in view of Belady in view of Kaul do not explicitly teach wherein said executor is selected to execute said task based on an impact of said executor executing said task.
However, Tan teaches wherein said executor is selected to execute said task based on an impact of said executor executing said task ([0020] when multiple computing frameworks can execute a same sub-task, a target computing framework is selected from the multiple computing frameworks according to operation time and resource consumption, to execute a sub-task, so as to improve the data processing efficiency and working performance of a system).
Tan and Cosentino are both concerned with task execution in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Tan because when multiple computing frameworks can execute a same task, a target computing framework can be selected from the multiple computing frameworks according to operation time and resource consumption, to execute a sub-task, so as to improve the data processing efficiency and working performance of the system. APIs that are in different computing frameworks and that execute a same type of task are encapsulated using a preset programming language, to generate a unified API, so as to shield differences between programming languages, greatly reduce a programming threshold for a developer, and improve flexibility and adaptability of each computing framework.
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over Cosentino in view of Belady in view of Kaul in view of Tiwari (US 2020/0409814).
As per claim 25, Cosentino in view of Belady in view of Kaul teach: wherein said optimal amount of power is determined based on a factor selected from the group consisting of overall system efficiency (Belady [0005] and [0032] load resources for most cost and power efficient solution), power consumption (Belady [0032] power management system varies the power consumption of the resources and varies the power supplies to maintain an optimum load on the power supplies), compute power consumption (Belady [0032] power management system varies the power consumption of the resources and varies the power supplies to maintain an optimum load on the power supplies), energy (Cosentino [0027] reduce/optimize energy consumed), task execution cost (Cosentino [0044] and [0076] cost of executing jobs and cost of operating data processing system), and time (Cosentino [0027] find the best time to operate and cool computers of the data-processing system. This can make any free-cooling systems more effective and/or to optimize the use of heat produced by the data-processing system for other applications).
Cosentino in view of Belady in view of Kaul do not explicitly teach a power usage effectiveness of said workload executed by said preferred executor type.
However, Tiwari teaches a power usage effectiveness of said workload executed by said preferred executor type ([0018] and [0024] power usage effectiveness).
Tiwari and Cosentino are both concerned with energy/power management in computing environments and are therefore combinable/modifiable. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Cosentino in view of Belady in view of Kaul in view of Tiwari because it would provide a way of optimizing power usage effectiveness (PUE) within a data center using predictive analytics tools to identify a plurality of parameters required to compute data power usage effectiveness at various loads within a data center, determine, using a dynamic design of experiments approach, the largest number of possible combinations of the identified parameters and generate an optimal curve of power utilization incentives versus power utilization misses at each operational point based on which data center parameters can be automatically adjusted to optimize, in a real-time fashion, the power usage effectiveness and reduce associated penalties. Therefore, the resulting system would have the capacity to improve the power usage in data center facilities by managing data center operations cognitively using calibratable and dynamic curves developed from real-time estimation of power utilization incentives and power utilization misses
Response to Arguments
All of Applicant’s arguments have been considered. Applicant's arguments on pg. 11-12 are not persuasive and the examiner’s rebuttal appears below. Applicant’s remaining arguments not specifically mentioned below have been considered, but are moot because the new ground of rejection necessitated by Applicant’s amendments does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
In the Remarks on pg. 11-12, Applicant argues that the prior art references adjust resources reactively in response to runtime utilization or threshold violations. The examiner respectfully traverses. Cosentino in at least the following passages explicitly states: “The above-described solution uses a proactive approach, where energy consumed by the data-processing system is anticipated to optimize the energy consumption of the data-processing system” [0027], “the power cap can be estimated from information extracted from the workload database and ambient temperature information extracted from the monitoring log” [0038], “For each job, the energy required to execute the job on the corresponding execution server is estimated at block 406” [0041], “the performance monitor calculates a power function P(t), which models a trend of the processing power of the execution server over time during the execution window W” [0050], “The plan arranges the jobs in the desired sequence according to their run cycles, expected durations, and execution constraints, by taking into account the power cap of the corresponding execution servers.” [0056], and “A test is then performed at block 444 to verify whether the plan can be executed according to the power caps of the execution servers”, [0057]. Hence, contrary to Applicant’s allegation, Cosentino very clearly teaches a proactive and not a reactive approach. Belady also is directed to predicting future resource utilization (see at least Belady abstract). Thus, for at least the reasons provided above, Applicant’s arguments are unpersuasive and the rejections are sustained.
Finally, it should be noted that the examiner has previously attempted multiple times to propose suggested amendments to Applicant and collaborate with the Applicant to reach an agreement. However, Applicant has consistently declined the examiner’s recommendations.
Citation of Relevant Prior Art
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
Ueda (US 2012/0254443) disclose scaling up resources based on an average value of response performance triggering the scale-up.
Jacobson et al. (US 2014/0282605) disclose a data processing engine may be selected upon determining that the data processing engine best satisfies predefined criteria, such as one or more of speed, efficiency, resource consumption, job execution success rate, user-specified execution time constraints, etc.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Adam Lee whose telephone number is (571) 270-3369. The examiner can normally be reached on M-TH 8AM-5PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Pierre Vital can be reached on 571-272-4215. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center. Status information for published applications may be obtained from Patent Center. Status information for unpublished applications is available through Patent Center for authorized users only. Should you have questions about access to Patent Center, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, Applicant is encouraged to use the USPTO Automated Interview Request (AIR) Form at https://www.uspto.gov/patents/uspto-automated-interview-request-air-form.
/Adam Lee/Primary Examiner, Art Unit 2198 May 5, 2026
Prosecution Insights