DETAILED ACTION
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 06/12/2025 was filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1 and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Doshi et al (US Published Patent Application No. 20200134207, "Doshi"), in view of Weng et al (US Published Patent Application No. 20180146030, "Weng").
In regard to claim 1, Doshi teaches A data center system, comprising: (Doshi, paragraph 0037, “The edge cloud 110 is located much closer to the endpoint (consumer and producer) data sources 160 (e.g., autonomous vehicles 161, user equipment 162, business and industrial equipment 163, video capture devices 164, drones 165, smart cities and building devices 166, sensors and IoT devices 167, etc.) than the cloud data center 130.”)
a plurality of nodes; (Doshi, paragraph 0043, “FIG. 2 illustrates deployment and orchestration for virtual edge configurations across an edge-computing system operated among multiple edge nodes and multiple tenants.”)
an orchestrator node; and (Doshi, paragraph 0029, “For example, multi-tenant data protection techniques discussed herein relate to usage of PRMs in edge platforms, allowing developers to provide workload metadata (e.g., via SLOs from an orchestrator node) that describes inter-tenant and intra-tenant protection semantics ( e.g., secure keys and transformation functions), as well as express service level objectives/requirements in terms of Key Performance Indicators (KPis) that are meaningful to the developer/user, such as response time, jitter/determinism, latency, etc.”)
execute a Monte Carlo simulation using at least a portion of the data describing an elastic workload to obtain a workload configuration that distributes the elastic workload over a plurality of nodes; and (Doshi, paragraph 0158, “The workload metadata may include a machine-readable expression ( e.g. CDDL, ASN. 1, JSON, or other types of expressions) that maps the SLO objective into concrete KPis for executing the workload. The metadata interpreter 918 can further decompose the workloads into "functions". One type of function is a "homomorphic function" where the function can be applied to homomorphically encrypted data [an elastic workload to obtain a workload configuration that distributes the elastic workload over a plurality of nodes;]. In some aspects, the memory and compute resources used to perform the workload functions are isolated according to the SLA definition of "tenant" (i.e., the user/group agreeing to the terms of the SLA contract). Therefore, the shared memory configuration may be a resource reservation mechanism that associates the resource (possibly spanning multiple ECDs as seen in FIG. 11) with the tenant(s) under the SLA. The metadata interpreter 918 may perform the SLO decomposition (e.g., SLA----;,SLO----;, Workflow----;, Workload----;, Function----;,sub-routine----;, outer-loop----;,inner-loop----;,execution). In some aspects, there may be other functions that are not using homomorphic- encrypted data that operate on cleartext data. Other types of functions that may be specified by the SLO 922 include FaaS functions, Named Function Networking (NFN) functions, XasS, etc. Additional functions that may be specified by the SLO 922 include content encode/decode/ transcode, data storage/retrieval, financial computation functions, such as Monte Carlo simulations [Monte Carlo simulation], engineering applications/simulations, etc.”)
provide a workload configuration to the orchestrator node for managing the elastic workload across the plurality of nodes. (Doshi, paragraph 0158, “The workload metadata may include a machine-readable expression ( e.g. CDDL, ASN. 1, JSON, or other types of expressions) that maps the SLO objective into concrete KPis for executing the workload. The metadata interpreter 918 can further decompose the workloads into "functions". One type of function is a "homomorphic function" where the function can be applied to homomorphically encrypted data [managing the elastic workload across the plurality of nodes.]. In some aspects, the memory and compute resources used to perform the workload functions are isolated according to the SLA definition of "tenant" (i.e., the user/group agreeing to the terms of the SLA contract). Therefore, the shared memory configuration may be a resource reservation mechanism that associates the resource (possibly spanning multiple ECDs as seen in FIG. 11) with the tenant(s) under the SLA.” And paragraph 0159, “In an example embodiment, the PRM SMA 902 may receive multiple metadata structures from the orchestrator 904, wherein at least one of the metadata structures is separate from the workflow metadata but where the tenant isolation context is known and enforced by the PRM SMA 902.”)
However, Doshi does not explicitly teach a computing device configured to: receive data describing an elastic workload that is partitioned among multiple nodes;
Weng teaches a computing device configured to: receive data describing an elastic workload that is partitioned among multiple nodes; (Weng, paragraph 0065, “number of sites including this architecture can be deployed globally with communication traffic layers and operations (such as homepage, search, view-item, and sign-in) fully contained within each one, An extended example of this elastic architecture 700 is shown in FIG. 7. This architecture significantly improves traffic throughput, reduces cost, enhances efficient load balancing and high service availability, and boosts load balancing performance. GTM is also known as Global Server Load Balancing (GSLB) which is a mechanism to enable geographically distributed applications to scale and perform efficiently.”)
Dashi and Weng are related to the same field of endeavor (i.e. workload balance). In view of the teachings of Weng, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Weng to Dashi before the effective filing date of the claimed invention in order to enhance the efficiency of load balancing. (Weng, paragraph 0065, “This architecture significantly improves traffic throughput, reduces cost, enhances efficient load balancing and high service availability, and boosts load balancing performance.”)
In regard to claim 17, the claim recites similar limitations as corresponding claim 1, and is rejected for similar reasons as claim 1 using similar teachings and rationale.
Doshi further teaches At least one non-transitory machine-readable medium including instructions, which when executed by a computing device, cause the computing device to perform operations comprising (Doshi, paragraph 0207, “Example 20 is at least one non-transitory machinereadable storage medium comprising instructions or stored data which may be configured into instructions, wherein the instructions, when configured and executed by a processing circuitry of an edge computing device operable in an edge computing system,”)
presenting the workload configuration. (Doshi, paragraph 0207, “cause the processing circuitry to perform operations that: obtain, from an orchestration provider, a workflow execution plan, the workflow execution plan including workload metadata defining a plurality of workloads associated with a plurality of edge service instances, the instances executing respectively on a plurality of edge computing devices within the edge computing system;”)
In regard to claim 19, the claim recites similar limitations as corresponding claim 1, and is rejected for similar reasons as claim 1 using similar teachings and rationale.
A method executed by a computing device, the method comprising: (Doshi, paragraoh 0226, “Example 39 is a method performed by an edge computing device operable in an edge computing system, comprising: obtaining, from an orchestration provider, a workflow execution plan, the”)
presenting the workload configuration. (Doshi, paragraph 0207, “cause the processing circuitry to perform operations that: obtain, from an orchestration provider, a workflow execution plan, the workflow execution plan including workload metadata defining a plurality of workloads associated with a plurality of edge service instances, the instances executing respectively on a plurality of edge computing devices within the edge computing system;”)
In regard to claim 15 and analogous claims 18 and 20, Doshi and Weng teach the system of claim 1.
Doshi further teaches wherein the workload configuration expresses a resource allocation plan for resources used during execution of the elastic workload. (Doshi, paragraph 0029, “The PRM SMA is further configured to use memory access configuration information within the workload metadata to implement decentralized shared memory models that edge PRMs expose to orchestrators as part of the resource scheduling and allocation steps.”)
In regard to claim 16, Doshi and Weng teach the system of claim 1.
Doshi further teaches wherein a virtual machine executes on at least one of the plurality of nodes, the virtual machine providing a plurality of tenants, wherein the workload configuration expresses a resource allocation plan for resources among the plurality of tenants during execution of the elastic workload. (Doshi, paragraph 0029, “The PRM SMA is further configured to use memory access configuration information within the workload metadata to implement decentralized shared memory models that edge PRMs expose to orchestrators as part of the resource scheduling and allocation steps. [a resource allocation plan for resources among the plurality of tenants during execution of the elastic workload.]” And paragraph 0043, “Specifically, FIG. 2 depicts coordination of a first edge node 222 and a second edge node 224 in an edge computing system 200, to fulfill requests and responses for various client endpoints 210 from various virtual edge instances. The virtual edge instances provide edge compute capabilities and processing in an edge cloud, with access to a cloud/data center 240 for higher-latency requests for websites, applications, database servers, etc. Thus, the edge cloud enables coordination of processing among multiple edge nodes for multiple tenants or entities. [wherein a virtual machine executes on at least one of the plurality of nodes, the virtual machine providing a plurality of tenants]”))
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Doshi, in view of Weng and in further view of Cao et al (US Published Patent Application No. 20170185452, "Cao").
In regard to claim 2, Doshi and Weng teach the system of claim 1.
However, Doshi and Weng do not explicitly teach wherein the data describing an elastic workload includes a distributed workload graph.
Cao teaches wherein the data describing an elastic workload includes a distributed workload graph. (Cao, paragraph 0115, “In S3, the central controller CC inquires the policy engine PE, which then divides the computation workload into two sub-workloads based on a predetermined policy. For example, the received computation workload may be compiled into a directed acyclic graph (DAG). In the DAG each vertex represents a task in the computation workload, while each edge represents data flowing between tasks and dependency between tasks.”)
Dashi, Weng and Cao are related to the same field of endeavor (i.e. workload balance). In view of the teachings of Cao, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Cao to Dashi and Weng before the effective filing date of the claimed invention in order to make sure the execution of the workload is sufficient. (Cao, paragraph 0057, “Therefore, in this disclosure, by "the storage node's computing capability is sufficient to execute the workload", it is meant after removing computing resources used for providing data services from the storage node's computing resources, remaining computing resources is sufficient to execute the workload.”)
Claims 3-6 are rejected under 35 U.S.C. 103 as being unpatentable over Doshi, in view of Weng and in further view of Dasgupta et al (US Published Patent Application No. 20090241117, "Dasgupta").
In regard to claim 3, Doshi and Weng teach the system of claim 1.
However, Doshi and Weng do not explicitly teach wherein the computing device is configured to determine a goal for the elastic workload.
Dasgupta teaches wherein the computing device is configured to determine a goal for the elastic workload. (Dasgupta, paragraph 0034, “A job scheduler can, for example, include sophisticated matching logic for finding the suitable candidate resources for job execution, and a knob for controlling performance goals [determine a goal]. Also, a job scheduler may not, for example, control job flow [elastic workload] orchestration.”)
Dashi, Weng and Dasgupta are related to the same field of endeavor (i.e. workload balance). In view of the teachings of Dasgupta, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Dasgupta to Dashi and Weng before the effective filing date of the claimed invention in order to ensure efficiency with workflow. (Dasgupta, paragraph 0104, “As noted above, jobs and data-sets should be managed in close coordination with each other, both statically and at run-time, to ensure efficient execution of data-intensive grid workflows.”)
In regard to claim 4, Doshi, Weng and Dasgupta teach the system of claim 3.
Dasgupta further teaches wherein to determine the goal, the computing device is configured to: initiate an artificial intelligence subsystem to create a model for the elastic workload, and use the model to determine the goal. (Dasgupta, paragraph 0034, “A job scheduler can, for example, include sophisticated matching logic for finding the suitable candidate resources for job execution, and a knob for controlling performance goals [use the model to determine the goal]. Also, a job scheduler may not, for example, control job flow orchestration [a model for the elastic workload].”)
Dashi, Weng and Dagupta are combinable for the same rationale as set forth above with respect to claim 3.
In regard to claim 5, Doshi, Weng and Dasgupta teach the system of claim 3.
Dasgupta further teaches wherein the goal is an efficiency target. (Dasgupta, paragraph 0085, “Having selected a job to move, one can identify a target compute and/or data queue for the job. In case of a compute, it is the queue where the compute job incurs minimum execution time, queue wait time, and data transfer time (if any).”)
Dashi, Weng and Dagupta are combinable for the same rationale as set forth above with respect to claim 3.
In regard to claim 6, Doshi, Weng and Dasgupta teach the system of claim 5.
Dasgupta further teaches wherein the efficiency target represents a combination of compute, queuing, and buffering efficiencies. (Dasgupta, paragraph 0117, “An IFS can also dynamically adapt flows at runtime. The integrated component can be a buffering queue maintained for each resource, and the IFS holds all jobs submitted by the orchestrator to that resource. The IFS can also maintain scheduler mappings for the resource and dispatch jobs to the resource in accordance to the computed schedule.”)
Dashi, Weng and Dagupta are combinable for the same rationale as set forth above with respect to claim 3.
Claims 7-14 are rejected under 35 U.S.C. 103 as being unpatentable over Doshi, in view of Weng and Dasgupta, in further view of Cao et al (US Published Patent Application No. 20170185452, "Cao").
In regard to claim 7 and analogous claim 14, Doshi, Weng and Dasgupta teach the system of claim 3.
However, Doshi, Weng and Dasgupta do not explicitly teach wherein to execute the Monte Carlo simulation, the computing device is configured to: deconstruct the data describing the elastic workload to obtain a first sub-workload and a second sub-workload; identify an insufficient sub-workload from the first sub-workload and the second sub-workload; and determine a workload configuration that satisfies the goal by substituting the insufficient sub-workload.
Cao teaches wherein to execute the Monte Carlo simulation, the computing device is configured to: deconstruct the data describing the elastic workload to obtain a first sub-workload and a second sub-workload; (Cao, paragraph 0055, “In some embodiments, the one or more sub-workloads at least include a first sub-workload.”)
identify an insufficient sub-workload from the first sub-workload and the second sub-workload; and (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload, dispatch the first sub-workload to computing node 220.”)
determine a workload configuration that satisfies the goal by substituting the insufficient sub-workload. (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload, dispatch the first sub-workload to computing node [substituting the insufficient sub-workload] 220.” And paragraph 0060, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes part of the computation workload and dispatching unit 320 is further configured to dispatch the first sub-workload to storage node 230 in response to determining the computing capability of storage node 230 is sufficient to execute the first sub-workload.”)
Dashi, Weng, Dasgupta and Cao are related to the same field of endeavor (i.e. workload balance). In view of the teachings of Dasgupta, it would have been obvious for a person with ordinary skill in the art to apply the teachings of Dasgupta to Dashi and Weng before the effective filing date of the claimed invention in order to make sure the execution of the workload is sufficient. (Cao, paragraph 0057, “Therefore, in this disclosure, by "the storage node's computing capability is sufficient to execute the workload", it is meant after removing computing resources used for providing data services from the storage node's computing resources, remaining computing resources is sufficient to execute the workload.”)
In regard to claim 8 and analogous claim 11, Doshi, Weng, Dasgupta and Cao teach the system of claim 7.
Cao further teaches wherein the insufficient sub-workload is a lower compute efficient sub-workload of the first sub-workload and the second sub-workload. (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload, dispatch the first sub-workload to computing node 220. For example, after computing resources used for providing data services are removed from computing resources 240 of storage node 230, if the amount of remaining computing resources is less than the amount of required computing resources for executing the first subworkload, then dispatching the first sub-workload to storage node 230 will harm storage node 230 in providing normal data services.”)
Dashi, Weng, Dagupta and Cao are combinable for the same rationale as set forth above with respect to claim 7.
In regard to claim 9, Doshi, Weng, Dasgupta and Cao teach the system of claim 7.
Cao further teaches wherein the insufficient sub-workload is a lower networking efficient sub-workload of the first sub-workload and the second sub-workload. (Cao, paragraph 0058, “The amount of required computing resources ( e.g. the number of CPU life cycles) for executing all or part of the computation workload may be estimated, and then it is determined whether, after removing computing resources used for providing data services from computing resources 240 of storage node [lower networking efficient sub-workload] 230, the amount of remaining computing resources (e.g. the number of CPU life cycles) is greater than the amount of required computing resources or not.” And paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload, dispatch the first sub-workload to computing node 220. For example, after computing resources used for providing data services are removed from computing resources 240 of storage node 230, if the amount of remaining computing resources is less than the amount of required computing resources for executing the first subworkload, then dispatching the first sub-workload to storage node 230 will harm storage node 230 in providing normal data services.”)
Dashi, Weng, Dagupta and Cao are combinable for the same rationale as set forth above with respect to claim 7.
In regard to claim 10, Doshi, Weng, Dasgupta and Cao teach the system of claim 7.
Cao further teaches wherein the insufficient sub-workload is a lower storage efficient sub-workload of the first sub-workload and the second sub-workload. (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload, dispatch the first sub-workload to computing node 220. For example, after computing resources used for providing data services are removed from computing resources 240 of storage node 230, if the amount of remaining computing resources is less than the amount of required computing resources [a lower storage efficient sub-workload] for executing the first subworkload, then dispatching the first sub-workload to storage node 230 will harm storage node 230 in providing normal data services.”)
Dashi, Weng, Dagupta and Cao are combinable for the same rationale as set forth above with respect to claim 7.
In regard to claim 12, Doshi, Weng, Dasgupta and Cao teach the system of claim 7.
Cao further teaches wherein the insufficient sub-workload is a less secure sub-workload of the first sub-workload and the second sub-workload. (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload [insufficient sub-workload is a less secure, examiner would like to point out that the workload being insufficient makes the workloads less secure due to making the baseline weak.], dispatch the first sub-workload to computing node 220. For example, after computing resources used for providing data services are removed from computing resources 240 of storage node 230, if the amount of remaining computing resources is less than the amount of required computing resources for executing the first subworkload, then dispatching the first sub-workload to storage node 230 will harm storage node 230 in providing normal data services.”)
Dashi, Weng, Dagupta and Cao are combinable for the same rationale as set forth above with respect to claim 7.
In regard to claim 13, Doshi, Weng, Dasgupta and Cao teach the system of claim 7.
Cao further teaches wherein the insufficient sub-workload is a less trusted sub-workload of the first sub-workload and the second sub-workload. (Cao, paragraph 0059, “In some embodiments, if the predetermined policy indicates dividing the computation workload based on the computing capability, the first sub-workload includes all of the computation workload and dispatching unit 320 is further configured to: in response to determining the computing capability of storage node 230 is insufficient to execute the first sub-workload [insufficient sub-workload is a less trusted, examiner would like to point out that with an insufficient workload, it is less trusted due to it not being able to satisfy.], dispatch the first sub-workload to computing node 220. For example, after computing resources used for providing data services are removed from computing resources 240 of storage node 230, if the amount of remaining computing resources is less than the amount of required computing resources for executing the first subworkload, then dispatching the first sub-workload to storage node 230 will harm storage node 230 in providing normal data services.”)
Dashi, Weng, Dagupta and Cao are combinable for the same rationale as set forth above with respect to claim 7.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SKYLAR K VANWORMER whose telephone number is (703)756-1571. The examiner can normally be reached M-F 6:00am to 3:00 pm.
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) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Usmaan Saeed can be reached at (571) 272-4046. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/S.K.V./Examiner, Art Unit 2146
/USMAAN SAEED/Supervisory Patent Examiner, Art Unit 2146
Prosecution Insights