DETAILED ACTION
Claims 1-20 are presented for examination
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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-8 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims do not fall within at least one of the four categories of patent eligible subject matter because the claims recited “One or more computer-readable media having a plurality of executable instructions embodied thereon”, and the specification is silent on " computer-readable media " as claimed excluding carrier wave and/or signal. Therefore, without an explicit definition of "a computer readable medium", an ordinary skill in the art would reasonably interpret "a computer readable medium" includes signal and/or carrier wave. Thus, the recited “computer-readable media” is not a process, a machine, a manufacture or a composition matter, as defined in 35 U.S.C. 101.
Accordingly, claims 1-8 fail to recite statutory subject matter under 35 U.S.C. 101.
Examiner suggests amending the above claims to add “non-transitory” to obviate the rejection.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 4, 7, 9, 10, 12, 16 and 18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by GUO et al. (US 2022/0405134 A1).
As to claim 1, GUO teaches one or more computer-readable media having a plurality of executable instructions embodied thereon, which, when executed by one or more processors, cause the one or more processors to perform a method comprising (Removable storage drive 514 may interact with a removable storage unit 518. Removable storage unit 518 includes a computer usable or readable storage device having stored thereon computer software (control logic) and/or data. According to an exemplary embodiment, secondary memory 510 may include other means, instrumentalities or other approaches for allowing computer programs and/or other instructions and/or data to be accessed by computer system 500; paragraphs [0065]-[0066]):
determining, based at least on incoming data traffic, a predicted incoming data processing
workload (Historical workload data 129 can be generated by operating a first set of one or more applications, e.g., application 127, at a first number of past time instances … monitor operator 135 can collect a first set of historical workload data 129 generated by operating the first set of one or more applications, e.g., application 127, at a first number of past time instances. The first set of historical workload data 129 can include a CPU usage, a memory utilization, a network bandwidth, a latency, a delay, or a throughput. The first set of historical workload data 129 can be generated at a first number of past time instances, which can include 5 past time instances; paragraphs [0021]-[0024]) for a service (services, applications; paragraphs [0015] and [0017]) of a cloud computing system (cloud resources; paragraph [0017]);
determining, based at least on the predicted incoming data processing workload and a
current configuration of the service comprising a number of computing resource instances of the
service, a predicted quality of service (QoS) metric of the service that is below a QoS metric
threshold (In some embodiments, workload forecasting operator 132 can predict probability parameters of a second set of future workload data for operating the second set of one or more applications, e.g., application 137, at a second number of future time instances; paragraph [0025]);
determining, based at least on applying the predicted incoming data processing workload
and the QoS metric threshold to a search algorithm, a corresponding number of computing resource instances of the service where a corresponding predicted QoS metric is above the QoS metric threshold (Workload forecasting operator 132 can predict the probability parameters based on recurrent neural networks (RNN). The second set of future workload data can follow a Gaussian distribution, a Poisson distribution, a binomial distribution, or some other probability distributions. The second set of future workload data can include a CPU usage, a memory utilization, a network bandwidth, a latency, a delay, or a throughput. The predicted probability parameters can include an average of the second set of future workload data, a standard deviation of the second set of future workload data, or a probability density function of the second set of future workload data. The second number of future time instances can include 5 future time instances. A first time instance and a second time instance of the second number of future time instances can be separated by 1 hour; paragraph [0025]); and
causing auto-scaling of the service based on the corresponding number of computing
resource instances (resource allocation scaler 233 can adjust resource allocation based on a fixed threshold value predictions made by workload forecasting operator 232. For example, resource allocation scaler 233 can adjust resource allocation using rules related to the fixed threshold value predictions, which may be based on infrastructure-level metrics, such as CPU utilization measured by the number of nodes. Processing operator 234 can operate applications, e.g., vSystem application, on the cluster of nodes 224, which is a Kubernates cluster. Resource allocation scaler 233 can scale up and down the number of nodes within the cluster of nodes 224 based on the usage of the workloads by various applications, e.g., System application. Resource allocation scaler 233 can scale up the number of nodes when a node resource usage is over the fixed threshold value. On the other hand, resource allocation scaler 233 can scale down the number of nodes when a node resource usage is below the fixed threshold value; paragraph [0031]).
As to claim 2, GUO teaches the media of claim 1, wherein determining the predicted incoming data processing workload further comprises:
using a hierarchal time-series forecasting method to predict the predicted incoming data
processing workload based on the incoming data traffic (Monitoring operator 235 can be used to monitor the resources used by the cluster of nodes 224 and monitor the workload of system applications, and provide the workload dataset 238 for training time series prediction module 254. Time series prediction module 254 can support workload forecasting operator 232 to offer a solution of on-demand resources based on the user-defined strategy; paragraph [0035]).
As to claim 4, GUO teaches the media of claim 1, wherein determining the predicted incoming data processing workload further comprises: determining the predicted incoming data processing workload based on at least one of an upstream service or external data of a tenant (In some embodiments, some raw time series dataset may be of the form: {“start”: “2020-06-30 12:00:00”, “target”: [110, 98, 90, . . . ], “dynamic_feat”: [[100, 83, 76, . . . ],[80.1,78.3,75.5, . . . ], [0,1,0, . . . ]]}, which can be generated by concomitant variables module 253. The keyword “start” can be of the format “YYYY-MM-DD HH:MM: SS”, representing the start time. The time series data can be sampled once an hour; paragraph [0039]).
As to claim 7, GUO teaches the media of claim 1, wherein the search algorithm optimizes the corresponding number of computing resource instances of the service based on the predicted incoming data processing workload and the QoS metric threshold using a brute-force configuration search (paragraph [0032]).
As to claim 9, see rejection of claim 1 above
GUO teaches a computer-implemented method (claim 1).
As to claim 10, see rejection of claim 2 above.
As to claim 12, see rejection of claim 4.
As to claim 16, see rejection of claim 1 above.
GUO teaches further teaches computing system comprising: a processor; and a non-transitory computer-readable medium having stored thereon instructions that when executed by the processor, cause the processor to perform operations (A computing system, comprising: at least one processor coupled to the storage device; a workload forecasting operator operated by the at least one processor; claim 13 and Removable storage drive 514 may interact with a removable storage unit 518. Removable storage unit 518 includes a computer usable or readable storage device having stored thereon computer software (control logic) and/or data. According to an exemplary embodiment, secondary memory 510 may include other means, instrumentalities or other approaches for allowing computer programs and/or other instructions and/or data to be accessed by computer system 500; paragraphs [0065]-[0066]).
As to claim 18, see rejection of claim 4 above.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
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 3, 5, 6, 8, 11, 13-15, 17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over GUO et al. (US 2022/0405134 A1) in view of Burgin et al. (US 11,656,912 B1).
As to claim 3, GUO teaches the media of claim 1, wherein determining the predicted incoming data processing workload further comprises:
accessing the incoming data traffic comprising a data source level corresponding to the
incoming data traffic to each data source of a plurality of data sources and services (paragraph [0025]), and determining the predicted incoming data processing workload using a reconciliation approach for corresponding predictions of the data source and service level (paragraph [0026]).
GUO does not teach accessing the incoming data traffic comprising a tenant level corresponding to the incoming data traffic to each tenant of a plurality of tenants, and a service level corresponding to the incoming data traffic to the service (A data monitoring service collects monitoring and operational data in the form of logs, metrics, and events, related to virtually any type of computing resource of a service provider network 100. In some embodiments, metrics collected by a data monitoring service from compute instances of various compute instance pools 110 can be used by a capacity tracking service 130 and capacity forecasting and scheduling service 138 to determine an amount of compute capacity from compute instance pool(s) 110 used by each of various workloads (for example, workloads associated with tenants A-N) over time and to make predictions about future resource usage patterns by various workloads and tenants. In some embodiments, metrics may be collected and stored separately for each workload, for example, where each workload can be associated with a separate “namespace” used to identify the workload's metrics by a capacity tracking service 130 and capacity forecasting and scheduling service 138; col. 9, line 57 – col. 10, lines 7 and col. 9, lines 4-8); and determining the predicted incoming data processing workload using a reconciliation approach for corresponding predictions of the tenant level and the service level (“a capacity forecasting and scheduling service 138 can provide various GUIs that display information indicating historical capacity usage by the user's workloads and scheduled usage of capacity in the future, and further enable users to make modifications to proposed capacity schedules”; col. 13, lines 50-55 and “to make predictions about future resource usage patterns by various workloads and tenants. In some embodiments, metrics may be collected and stored separately for each workload, for example, where each workload can be associated with a separate “namespace” used to identify the workload's metrics by a capacity tracking service 130 and capacity forecasting and scheduling service 138”; col. 9, line 67 – col. 10, line 7).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to apply the teaching of Burgin to the system of GUO because both are directed to auto scaling resources of the service given the historical data, and Burgin teaches a method that allows user to conditionally making request to terminate unused resources, thus, improve the resource utilization of the system.
As to claim 5, GUO as modified by Burgin teaches the media of claim 1, wherein determining the predicted QoS metric further comprises: using a queuing model that models an arrival process and a service process of the incoming data traffic based on the number of computer resource instances of the service using probability distributions to determine the predicted QoS metric (see Burgin: As indicated above, one example of a computing workload source 120 is a batch processing service 122. A batch processing service 122 generally enables users to execute queues or batches of compute jobs without manual intervention. In some embodiments, a batch processing service 122 uses other services of a service provider network 100 to execute compute jobs. For example, depending on the specifics of the compute jobs to be executed, a batch processing service 122 can use one or more compute instances provided by a hardware virtualization service 102, execute one or more container instances using a container execution service 128 (which in turn uses compute instances provided by a hardware virtualization service 102), use one or more databases provided by a database service, or use any other types of computing resources or combinations thereof. A batch processing service 122 enables users to specify various types of compute jobs desired for execution by the batch processing service 122. In response to receiving new compute job requests, the batch processing service 122 uses various processes to plan, schedule, and execute the requested compute jobs by provisioning a quantity and type of compute resources (for example, CPU-optimized or memory-optimized compute instances) based on the estimated resource requirements of the compute jobs submitted; col. 7, lines 27-50).
As to claim 6, GUO as modified by Burgin does not teach wherein determining the predicted QoS metric further comprises: using Histogram-Based Gradient Boosting Regression Tree (HGBR) to determine the predicted QoS metric.
However, GUO teaches using RNN (recurrent neural network) to determine predicted QoS metric (paragraph [0025]-[0026]).
Burgin teaches a capacity forecasting and scheduling service 138 can generate predictions of compute instance pool capacity usage using any of a variety of different techniques including autoregressive models, machine learning (for example, based on recurrent neural networks (RNNs) or other time series forecasting models), or other forms of predictive modeling and probabilistic forecasting known to those of skill in the art. In some embodiments, a capacity forecasting and scheduling service 138 uses a separate machine learning (ML) service of the service provider network 100 to create ML-based models of capacity usage of various compute instance capacity pools 110. The training of such models, for example, can be based on using windows (e.g., 2 weeks) of historic time series data, where the models can be updated over time (or completely regenerated) as more data becomes available. In some embodiments, capacity usage predictions can be probabilistic and used to provide users with an indication of how likely future scheduled uses of compute capacity are to be satisfied based on historic trends (col. 12, lines 23-43).
Given the teaching of GUO and Burgin above, especially Burgin indicates different types of models/NN to predict the QoS, it would have been obvious to one of ordinary skill in the art that the system of GUO as modified by Burgin could use using Histogram-Based Gradient Boosting Regression Tree (HGBR) to determine the predicted QoS metric.
As to claim 8, GUO as modified by Burgin teaches the media of claim 1, wherein the search algorithm optimizes the corresponding number of computing resource instances of the service based on the predicted incoming data processing workload and the QoS metric threshold (see GUO: Workload forecasting operator 132 can predict the probability parameters based on recurrent neural networks (RNN). The second set of future workload data can follow a Gaussian distribution, a Poisson distribution, a binomial distribution, or some other probability distributions. The second set of future workload data can include a CPU usage, a memory utilization, a network bandwidth, a latency, a delay, or a throughput. The predicted probability parameters can include an average of the second set of future workload data, a standard deviation of the second set of future workload data, or a probability density function of the second set of future workload data. The second number of future time instances can include 5 future time instances. A first time instance and a second time instance of the second number of future time instances can be separated by 1 hour; paragraph [0025]).
GUO as modified by Burgin does not teach using a combinatorial search algorithm comprising at least one of a hill climbing algorithm, a beam search algorithm, a simulated annealing algorithm, a genetic algorithm, or an open-loop control and oscillation algorithm.
However, Burgin teaches a capacity forecasting and scheduling service 138 can generate predictions of compute instance pool capacity usage using any of a variety of different techniques including autoregressive models, machine learning (for example, based on recurrent neural networks (RNNs) or other time series forecasting models), or other forms of predictive modeling and probabilistic forecasting known to those of skill in the art. In some embodiments, a capacity forecasting and scheduling service 138 uses a separate machine learning (ML) service of the service provider network 100 to create ML-based models of capacity usage of various compute instance capacity pools 110. The training of such models, for example, can be based on using windows (e.g., 2 weeks) of historic time series data, where the models can be updated over time (or completely regenerated) as more data becomes available. In some embodiments, capacity usage predictions can be probabilistic and used to provide users with an indication of how likely future scheduled uses of compute capacity are to be satisfied based on historic trends (col. 12, lines 23-43).
Given the teaching of GUO and Burgin above, especially Burgin indicates different types of models/NN are used to optimizes the corresponding number of computing resource instances of the service, it would have been obvious to one of ordinary skill in the art that the system of GUO as modified by Burgin could use using a combinatorial search algorithm comprising at least one of a hill climbing algorithm, a beam search algorithm, a simulated annealing algorithm, a genetic algorithm, or an open-loop control and oscillation algorithm.
As to claim 11, see rejection of claim 3 above.
As to claim 13, see rejection of claim 5 above.
As to claim 14, see rejection of claim 6 above.
As to claim 15, see rejection of claim 8 above.
As to claim 17, see rejections of claims 2-3 above.
As to claim 19, see rejections of claims 5-6 above.
As to claim 20, see rejection of claim 8 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Van De Groenendaal et al. (US 2018/0026904 A1) teaches technologies for allocating resources within a self-managed node.
Grushka et al. (US 2023/0259408 A1) teaches computing resource prediction for optimizing resource utilization and computing workload density.
Park et al. (An Autoscaling System Based on Predicting the Demand for Resources and Responding to Failure in Forecasting) teaches a framework that includes algorithms that periodically monitor resource requirements and dynamically adjust resource provisioning to match the actual demand is proposed.
Shariffdeen et al. (Workload and Resource Aware Proactive Auto-Scaler for PaaS Cloud) teaches inteliScaler, a proactive and cost-aware auto-scaling solution to address these issues by combining a predictive model, cost model, and a smart killing feature. An ensemble workload prediction mechanism is introduced based on time series and machine learning techniques for making accurate predictions on drastically different workload patterns. Utility of the solution is demonstrated using both simulations and empirical evaluations using Apache Stratos PaaS (deployed on the AWS EC2), as well as RUBiS and real-world workload traces. Results show significant QoS improvements and cost reductions by inteliScaler compared to a typical reactive and threshold-based PaaS auto-scaling solution.
Thome (Automatically Scaling Exadata Cloud Service Based on Workload (Part 1) and (Part 2) teaches in Part 1, the concepts of building an autoscaling script and part 2 covers a proof of concept, with some sample code and test results.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DIEM K CAO whose telephone number is (571)272-3760. The examiner can normally be reached Monday-Friday 8:00am-4:00pm.
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, April Blair can be reached at 571-270-1014. 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.
/DIEM K CAO/Primary Examiner, Art Unit 2196
DC
August 7, 2026
