DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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.
The Information Disclosure Statement, filed 11 January 2024 has been fully considered by the examiner. A signed copy is attached.
Acknowledgement is made of the preliminary amendment to the claims, specification and abstract filed on 12 July 2023, and the application is being examined on the basis of the amended disclosure.
Claims 1-20 are pending.
Claims 1-20 are rejected, grounds follow.
Priority
Application’s status as a 35 USC 371 national stage application of PCT application PCT/CN2022/120325 is acknowledged.
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Claim Objections
Claim 20 is objected to because of the following informalities:
Apparent missing words “each of” in claim 20 line 6 (“wherein [each of] the data acquisition device is”) where the antecedent basis is “a plurality of data acquisition devices”.
Appropriate correction is required.
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.
Claim(s) 1-2, 4, 7-8, 14, and 18-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al., Medium and Long Term Wind Power Generation Forecasting Method Cases on Deep Learning, Guangdong Electric Power, Vol. 34, No. 6, Pages 73-78 (June 2021) (hereafter “Zhu”, pagination and citations to English Translation provided by Applicant, IFW Copy 11 January 2024) in view of Stenneth et al., US Pg-Pub 2016/0092615.
Regarding Claim 1, Zhu teaches:
A prediction method of wind power output, (see Page 2 “power generation prediction model” Page 1 “wind farm”) comprising: periodically acquiring an initial meteorological data set corresponding to each received time node; (see page 3, “Continuous random variables X and Y represent meteorological data and historical wind power, respectively” page 10 “Among them, the monthly information in the data is used as a node input in the time series of the network.”)
wherein each of the initial meteorological data sets comprises initial meteorological data corresponding to at least one meteorological element on a one-to-one basis, (e.g. Page 6 “The core idea of the model is to use daily wind [speed*], temperature, pressure, air humidity, and altitude information of the wind farm to predict monthly and annual power generation”, *nb. see page 5) and the initial meteorological data comprises initial meteorological sub-data of at least one dimension of the meteorological element corresponding thereto; (individual readings from sub-stations at each farm, see page 6 “Embed and represent multidimensional daily data such as meteorological information collected from meteorological stations and wind farm areas, and construct daily feature vectors.”)
determining an instantaneous wind energy density corresponding to the latest received time node; (see pages 4-5 “The effective wind energy density, wind energy size, and air density are used to represent the potential characteristics of wind energy, and the effective wind energy density is defined: [as a function of wind speed, humidity, temperature]”)
performing rolling averaging calculation (Page 6 “The neural network is used to represent the daily feature vector as the monthly feature vector on a monthly basis”) on the instantaneous wind energy density (Page 6 “Vector representation of multidimensional monthly features, as shown in Figure 1. Among them, the potential characteristics of wind energy are represented by effective wind energy density,”) to obtain an average wind energy density within a target time period; (e.g. monthly, see page 6).
wherein the target time period comprises the latest received time node; (see Page 12, “use the data from the last year as the test set and the rest as the training set.”)
and inputting the smoothed meteorological data set and the average wind energy density in the target time period as input features into a wind power output predictive model, so that the wind power output predictive model outputs a wind power output predictive value of the target time period. (see Page 9, “in the formula: h (t+1) is the predicted result at the current time; [h (t+1) h(t+2) ... h (t+l2)] is the predicted vector for the current 12 month electricity generation; H (t), h (t-1),..., h (t-n) are the monthly power generation forecast results at the previous time x (t), x (t-1), ... , x (t-n) are the inputs of the previous time, namely the monthly feature fusion vector; n is the current number of input network nodes.”)
Zhu differs from the claimed invention in that:
Zhu does not clearly articulate: identifying abnormal sub-data from each latest initial meteorological sub-data after acquiring the latest initial meteorological data set corresponding to the latest received time node;
smoothing the identified abnormal sub-data to obtain a smoothed meteorological data set when the abnormal sub-data is identified, and taking the latest initial meteorological data set as a smoothed meteorological data set when the abnormal sub-data is not identified;
However Stenneth teaches a smoothing process for weather data which identifies abnormal sub-data from a data set ([0048] “The smoothing process may remove outlier weather data from the station to station location based model plot. The outlier weather data may be discarded by an outlier removal algorithm”) and smooths the data (see [0054] “the weather data used for display or control of control system functions may be an average of the weather station data from the weather stations which satisfied the threshold.”) or, when data is not abnormal, takes the initial data as the smoothed data ([0053] “The weather data which satisfies the confidence threshold, e.g. greater than 60%, may be considered valid and weather data which fails to satisfy the threshold, e.g. less than 60%, may be considered invalid.” See also [0069] “Other possible smoothing algorithm may be functions of the standard error from mean, confidence intervals, clustering techniques, or the like. The weather data which satisfies the determined attribute difference may be discarded and removed from the station to station location based model.”)
Stenneth is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired weather data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of abnormal time-series sub-data and smoothing of the abnormal data can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Stenneth which discard outlier (i.e. abnormal) data points and average remaining high confidence data points in order to smooth the data set for weather data; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because determining that the data is valid allows for more accurate adjustment of control systems, minimizing unnecessary adjustments due to inaccurate or irrelevant weather data, as suggested by Stenneth ([0080] “The determination of valid weather data using the station to station location based model allows for more accurate weather determinations for control system 102… minimizing unnecessary activation or adjustments due to inaccurate or irrelevant weather data.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 2, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu further teaches:
wherein the performing rolling averaging calculation on the instantaneous wind energy density to obtain an average wind energy density within a target time period comprises: rolling the first-time window along the time axis to align the first-time window with the target time period; (see Page 6, the monthly data is a rolled average of the time-window comprising the “j” number of days in each month”)
and averaging a plurality of instantaneous wind energy densities in a first-time window to obtain an average wind energy density in the target time period. (i.e. the plurality of daily wind energy density calculations (see page 5) averaged by the fusion process over the daily feature set, see page 6. Function for calculating energy density from the feature vector is integral (e.g. an averaging of instantaneous values) over a continuous function, see pages 3-4)
Regarding Claim 4, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Stenneth further teaches:
wherein the identifying abnormal sub-data from each latest initial meteorological sub-data after acquiring the latest initial meteorological data set corresponding to the latest received time node comprises: rolling a second time window along a time axis so that the second time window comprises the latest received time node after acquiring the latest initial meteorological data set corresponding to the latest received time node; ([0038] “Historical weather data may include … or any other time period which may be useful for determining historical weather data correlations. In some instances the historical data may include current weather data.”)
performing normal normalization processing (interpreted as including, inter alia, standard deviation calculations) on the initial meteorological sub-data which belongs to the same dimension of the same meteorological element (e.g. comparing temperature to temperature, see [0043] “In line 1 of the algorithm weather attributes a.sub.1, e.g. temperature, visibility, precipitation, or the like, a model is created”) and is a non-null value in the second time window to obtain a normal normalization value corresponding to each latest initial meteorological sub-data; ([0048] “smoothing algorithms may be functions of the standard error from mean, confidence intervals, clustering techniques, or the like”)
and determining the latest initial meteorological sub-data for which the normal normalized value ([0048] “an algorithm which removes or discards weather data based on a function of the standard deviation of attribute difference or error “) is not within the preset value range to be the abnormal sub-data. ([0052] “The control system 102 may compare the attribute errors of the candidate weather stations 106 to a predetermined attribute error threshold. For example, the control system 102 may have a predetermined temperature error threshold of 10 degrees Celsius, and the control system 102 may determine that the weather data from weather stations 106 which satisfies the predetermined temperature error threshold, e.g. is less than or equal to 10 degrees Celsius, is valid or has high confidence, and weather data from weather stations which fail to meet the predetermined temperature threshold, e.g. is greater than 10 degrees Celsius, is not valid or has low confidence.”)
Stenneth is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired weather data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of abnormal time-series sub-data and smoothing of the abnormal data can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Stenneth which discard outlier (i.e. abnormal) data points and average remaining high confidence data points in order to smooth the data set for weather data; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because determining that the data is valid allows for more accurate adjustment of control systems, minimizing unnecessary adjustments due to inaccurate or irrelevant weather data, as suggested by Stenneth ([0080] “The determination of valid weather data using the station to station location based model allows for more accurate weather determinations for control system 102… minimizing unnecessary activation or adjustments due to inaccurate or irrelevant weather data.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 7, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Stenneth further teaches:
wherein the periodically acquiring an initial meteorological data set corresponding to each received time node comprises: periodically acquiring an initial meteorological data predictive set corresponding to each received time node; wherein the initial meteorological data predictive set is predicted based on a historical initial meteorological data truth value set corresponding to at least one historical received time node. ([0038] “The control system 102 may request and receive historic weather data, including weather station locations, from a candidate weather station 106 and other weather stations 106 associated with a weather provider. Historical weather data may include weather data from the respective weather station over a predetermined period, such as one week, one month, six months, one year five years, ten years, or any other time period which may be useful for determining historical weather data correlations.”)
Stenneth is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired weather data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of abnormal time-series sub-data and smoothing of the abnormal data can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Stenneth which discard outlier (i.e. abnormal) data points and average remaining high confidence data points in order to smooth the data set for weather data; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because determining that the data is valid allows for more accurate adjustment of control systems, minimizing unnecessary adjustments due to inaccurate or irrelevant weather data, as suggested by Stenneth ([0080] “The determination of valid weather data using the station to station location based model allows for more accurate weather determinations for control system 102… minimizing unnecessary activation or adjustments due to inaccurate or irrelevant weather data.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 8, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Stenneth further teaches:
wherein the periodically acquiring an initial meteorological data set corresponding to each received time node comprises: periodically acquiring an initial meteorological data truth value set corresponding to each received time node. (e.g. [0071] “the apparatus 200 may include means, such as a processor 202, a communications interface 206, or the like, configured to receive current weather data and station to station location based models associated with a plurality of candidate weather stations. The current weather data and station to station location based models may be received periodically or in response to a weather query.”)
Stenneth is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired weather data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of abnormal time-series sub-data and smoothing of the abnormal data can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Stenneth which discard outlier (i.e. abnormal) data points and average remaining high confidence data points in order to smooth the data set for weather data; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because determining that the data is valid allows for more accurate adjustment of control systems, minimizing unnecessary adjustments due to inaccurate or irrelevant weather data, as suggested by Stenneth ([0080] “The determination of valid weather data using the station to station location based model allows for more accurate weather determinations for control system 102… minimizing unnecessary activation or adjustments due to inaccurate or irrelevant weather data.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 14, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu further teaches:
wherein the meteorological elements comprise wind speed, gas density, gas pressure and air temperature. (e.g. Page 6 “The core idea of the model is to use daily wind [speed*], temperature, pressure, air humidity, and altitude information of the wind farm to predict monthly and annual power generation”, *nb. see page 5)
Regarding Claim 18, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu further teaches:
An electronic device, comprising a processor, a memory and a program stored on the memory and executable on the processor, which when executed by the processor, implementing the steps of the prediction method of wind power output according to claim 1. (Zhu teaches a computer-implemented algorithm, therefore at least rendering obvious the operation of the same on an electronic device.)
Alternatively, Stenneth teaches the same (see Stenneth fig. 2, depicting an electronic device including a processor, memory and [0061] “instructions stored in the memory 204 or otherwise accessible to the processor.”)
Regarding Claim 19, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu further teaches:
A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the prediction method of wind power output according to claim 1. (Zhu teaches a computer-implemented algorithm, therefore at least rendering obvious the operation of the same stored on a non-transitory computer-readable storage medium.)
Alternatively, Stenneth teaches the same (see Stenneth fig. 2, depicting an electronic device including a non-transitory media [0058] “The memory may be non-transitory and may include, for example, one or more volatile and/or non-volatile memories.”)
Claim(s) 3 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu in view of Stenneth, further in view of Wang et al., US Pg-Pub 2016/0025070.
Regarding Claim 3, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu in view of Stenneth further teaches:
wherein the smoothed meteorological sub-data in the smoothed meteorological data set comprises at least a smoothed wind speed and a smoothed air density, […] and the determining the instantaneous wind energy density corresponding to the latest received time node comprises: determining the instantaneous wind energy density corresponding to the latest received time node according to the smooth wind speed and the smooth air density […] corresponding to the latest received time node. (see pages 4-5 “The effective wind energy density, wind energy size, and air density are used to represent the potential characteristics of wind energy, and the effective wind energy density is defined: [as a function of wind speed, humidity and temperature]” nb. where humidity and temperature are used to measure air density. See Page 4.)
The combination differs from the claimed invention in that:
Neither reference clearly articulates the data set being taken at a hub of the fan nor determining the energy at the hub of the fan.
However, Wang teaches a wind turbine farm (see [0003]) which uses data from tower anemometers ([0003] “anemometer tower data”) including wind speed and air density measurements and calculations taken at the hub of each fan ([0034] “constructing wind speed conversion function of each wind direction sector by extrapolating the wind speed of each of the plurality of anemometer towers to a height of each hub of wind turbine”) and determining energy at the hub of each fan (see e.g. [0049-0050] “the power curve can be calibrated by following formula {omitted for brevity} wherein P.sub.correct is the calibrated wind power; P.sub.0 is the wind power according to theoretical power curve; ρ.sub.0 is the standard air density; V.sub.0 is the original wind speed; V.sub.correct is the wind speed after the correction; ρ is the measured average density.”)
Wang and Zhu are analogous art because it is from the same field of endeavor as the claimed invention and other references of predicting wind power generation in wind farm installations.
Accordingly, Examiner finds 1) the prior art contained a device (method, or product, etc.) which differed from the claimed device by the substitution of some components (step, element, etc.) with other components – the teachings of Zhu which differed from the claimed invention by recording meteorological data at an unspecified location in each wind field; 2) the substituted components and their functions were known in the art – as exemplified by Wang, which teaches recording meteorological data at the hub of the fan on the wind turbine mast; 3) one of ordinary skill in the art before the effective filing date of the application could have substituted one known element for another, and the results of the substitution would have been predictable at least because Wang teaches that measuring at the hub is suitable for collecting data that may be used to estimate wind power density (See Wang [0049]-[0051]). And accordingly the substitution would have been obvious to one having ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.B).
Regarding Claim 20, Zhu in view of Stenneth teaches all of the limitations of parent claim 18,
Stenneth further teaches:
A plurality of data acquisition devices and a control device (see fig. 1) the data acquisition devices are communicatively connected to the control device, and the control device is communicatively connected to the electronic device; (see e.g. fig. 2, communication interface 206, and fig. 1)
and the control device is configured to generate an initial meteorological data set according to each of the original meteorological sub-data, and transmit the initial meteorological data set to the electronic device according to a preset time interval, so that the electronic device performs wind power output prediction; and each of the initial meteorological data sets corresponds to a received time node received by the electronic device. (e.g. [0071] “the apparatus 200 may include means, such as a processor 202, a communications interface 206, or the like, configured to receive current weather data and station to station location based models associated with a plurality of candidate weather stations. The current weather data and station to station location based models may be received periodically or in response to a weather query.”)
The combination differs from the claimed invention in that:
The references do not clearly articulate wherein the data acquisition devices are provided in a wind power station,
wherein the data acquisition device is configured to acquire original meteorological sub-data in the wind power station and to transmit the original meteorological sub-data to the control device;
However, Wang teaches a wind turbine farm (see [0003]) which acquires the wind data from a plurality of data acquisition devices - tower anemometers ([0003] “anemometer tower data”) for transmission to a control device (see e.g. [0015] “first step, selecting a plurality of anemometer towers in a wind farm, and analyzing historical data acquired by the plurality of anemometer towers;”)
Wang and Zhu are analogous art because it is from the same field of endeavor as the claimed invention and other references of predicting wind power generation in wind farm installations.
Accordingly, Examiner finds 1) the prior art contained a device (method, or product, etc.) which differed from the claimed device by the substitution of some components (step, element, etc.) with other components – the teachings of Zhu which differed from the claimed invention by recording meteorological data at an unspecified location in each wind field; 2) the substituted components and their functions were known in the art – as exemplified by Wang, which teaches recording meteorological data at the hub of the fan on the wind turbine mast; 3) one of ordinary skill in the art before the effective filing date of the application could have substituted one known element for another, and the results of the substitution would have been predictable at least because Wang teaches that measuring at the hub is suitable for collecting data that may be used to estimate wind power density (See Wang [0049]-[0051]). And accordingly the substitution would have been obvious to one having ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.B).
Claim(s) 5 and 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu in view of Stenneth, further in view of Huo et al., Application of Two-Directional Time Series Models to Replace Missing Data Journal of Environmental Engineering, ASCE, pp 435-443 (Apr. 2010) (hereafter Huo)
Regarding Claim 5, Zhu in view of Stenneth teaches all of the limitations of parent claim 4,
The combination differs from the claimed invention in that:
Neither reference clearly articulates: determining a null value in each of the latest initial meteorological sub-data within the second time window as the abnormal sub-data.
However, Huo teaches a time-series smoothing algorithm (see Page 436, section Flow Diagram of Two-Directional ES and Two Directional ES with white noise methods, “TES and TESWN methods are developed to replace routinely missing values”) for missing data in a time-series (See Page, bottom of first column. “Any method developed must preserve the original data and replace missing data in a way that reflects the overall pattern of the time series”)
Huo is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired time-series data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of missing data values as the abnormal time-series sub-data for subsequent smoothing can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Huo which identify null data points as the abnormal points and calculate replacement values in order to smooth the data set; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because Huo teaches that missing data must be replaced in order to use the data as input to a process simulation model, (Huo 235 “To use existing operational data as an input to a process simulation model, the missing data
must be replaced.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 6, Zhu in view of Stenneth teaches all of the limitations of parent Claim 1,
Stenneth further teaches:
rolling a third time window along a time axis for any one of the identified abnormal sub-data, so that the third time window comprises the received time node corresponding to the abnormal sub-data and a plurality of received time nodes preceding the received time node corresponding to the abnormal sub-data; ([0038] “In some instances the historical data may include current weather data.”)
replacing each abnormal sub-data with a corresponding new value to obtain a smoothed meteorological data set. ([0076] “The weather data average may be a weighted average of the weather data. The weights for the weighted average may be based on the attribute error. In an example embodiment, the weighted average for each weather station weather data may be inversely proportional to the respective attribute error.” )
Zhu in view of Stenneth differs from the claimed invention in that:
neither reference clearly articulates averaging on initial meteorological sub-data which belongs to the same dimension of the same meteorological element as the abnormal sub-data in the third time window to obtain a new value corresponding to the abnormal sub-data;
However, Huo teaches a time-series smoothing algorithm (see Page 436, section Flow Diagram of Two-Directional ES and Two Directional ES with white noise methods, “TES and TESWN methods are developed to replace routinely missing values”) for missing data in a time-series (See Page, bottom of first column. “Any method developed must preserve the original data and replace missing data in a way that reflects the overall pattern of the time series”) which uses a weighted average of the time-series data of a given parameter to obtain a new value corresponding to the abnormal (i.e. missing) data (see Page 438 “This TES method, which is designed to represent both
forward and backward autocorrelations in the time series, can decrease the difference above caused by different directions. To execute the method, first, generate a full data set using the ANO method. Second, forecast the missing values using an ES algorithm
(in this paper, Holt’s linear trend ES) in the forward direction (forward ES). Next, forecast the missing values using an ES algorithm in the backward direction (backward ES). The final replacement values for the missing data points are determined by
averaging the forward and backward ES estimates.)
Huo is analogous art because it is from a related field of endeavor of weather-based control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the acquired time-series data.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting system of Zhu, upon which the identification of missing data values as the abnormal time-series sub-data for subsequent smoothing can be viewed as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Huo which identify null data points as the abnormal points and calculate replacement values in order to smooth the data set; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because Huo teaches that missing data must be replaced in order to use the data as input to a process simulation model, (Huo 235 “To use existing operational data as an input to a process simulation model, the missing data
must be replaced.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Claim(s) 9-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu in view of Stenneth, further in view of Chen et al., Chinese Patent Application Publication CN 110245801 (citations to machine translation submitted 11 January 2024).
Regarding Claim 9, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
Zhu further teaches:
wherein before the periodically acquiring an initial meteorological data set corresponding to each received time node, the method further comprises: acquiring a plurality of first sample sets; (see Page 12 “In the dataset of four wind farms, use the data from the last year as the test set and the rest as the training set.”)
wherein the first sample set includes a smooth meteorological data set sample (n.b. examiner notes that Stenneth is relied upon to teach the features related to smoothing) corresponding to each historical received time node in a historical time period, (see page 6, e.g. “monthly feature vector” constructed from “daily” time nodes.) an average wind energy density sample in the historical time period, (see pages 3-6 describing the meteorological data in the data set, including Temperature, Pressure, Humidity, wind speed, etc.) and a wind power output truth value sample in the historical time period; (see e.g. Page 12, “Wi is the actual monthly electricity generation”)
Zhu differs from the claimed invention in that:
Zhu does not appear to clearly articulate: constructing a boosting model;
Nor training the boosting model according to the plurality of first sample sets to obtain a trained boosting model; and generating the wind power output predictive model according to the trained boosting model.
However, Chen teaches a power load prediction method which includes constructing a boost model (XGBoost, see abstract) training the model according the training set to obtain a trained boost model (see pages 7-9, particularly page 9 “S500, training… the XGBoost prediction model separately using the training set”) and generating output of the predictive model according to the trained boosting model (see page 10 “the power load is predicted by using a combined mining model based on the LSTM prediction model and the XGBoost prediction model.”)
Chen is analogous art because it is from a related field of endeavor of Power Grid control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the accuracy of the forecasting model.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting LSTM system of Zhu, upon which the addition of a trained boosting model can be seen as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Chen, which augment an LSTM forecasting model with a trained boosting model; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because Chen teaches that the performance of a combined model incorporating both an LSTM and a boosting model results in improved forecast accuracy (see Chen Page 10, “it can be seen that the combined mining model has a higher prediction accuracy”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Regarding Claim 10, Zhu in view of Stenneth, further in view of Chen teaches all of the limitations of parent claim 9,
Chen further teaches:
wherein the training the boosting model according to the plurality of first sample sets to obtain a trained boosting model comprises: training the boosting model by a cross-validation method according to the plurality of first sample sets to obtain a trained boosting model. (see Page 3, “Determining the weights of the LSTM prediction model and the XGBoost prediction model based on prediction errors of the LSTM prediction model” Page 3 “trained using error backpropagation algorithms and cross-validation methods”).
Regarding Claim 11, Zhu in view of Stenneth, further in view of Chen teaches all of the limitations of parent claim 9,
Zhu further teaches:
wherein before inputting the smoothed meteorological data set and the average wind energy density within the target time period as input features into a wind power output predictive model, so that the wind power output predictive model outputs a wind power output predictive value of the target time period, the method further comprises: acquiring a historical wind power output truth value (see e.g. Page 12, “Wi is the actual monthly electricity generation”) corresponding to each received time node in the target time period; (see page 6, e.g. “monthly feature vector” and Page 12 “In the dataset of four wind farms, use the data from the last year as the test set and the rest as the training set.”)
wherein the inputting the smoothed meteorological data set (nb. Stenneth is relied upon to teach the features related to smoothing) and the average wind energy density within the target time period as input features into a wind power output predictive model, so that the wind power output predictive model outputs a wind power output predictive value of the target time period, comprises: inputting the historical wind power output truth value, the smoothed meteorological data set, and the average wind energy density within the target time period as input features into a wind power output predictive model, (See Page 9 “This article first extracts daily features from the raw data of wind farms, and then trains the entire network model (including the monthly feature fusion model of wind farms and the power generation prediction model) to obtain a trained prediction model.”) so that the wind power output predictive model outputs a wind power output predictive value of the target time period. (see Page 9, “in the formula: h (t+1) is the predicted result at the current time; [h (t+1) h(t+2) ... h (t+l2)] is the predicted vector for the current 12 month electricity generation; H (t), h (t-1),..., h (t-n) are the monthly power generation forecast results at the previous time x (t), x (t-1), ... , x (t-n) are the inputs of the previous time, namely the monthly feature fusion vector; n is the current number of input network nodes.” Nb. examiner notes that the trained model is an LSTM model, see Pages 7-8).
Regarding Claim 12, Zhu in view of Stenneth, further in view of Chen teaches all of the limitations of parent claim 11,
Zhu further teaches:
wherein before generating the wind power output predictive model according to the trained boosting model, the method further comprises: acquiring a plurality of second sample sets; wherein the second sample set comprises a historical wind power output truth value sample corresponding to each historical received time node in the historical time period; (see e.g. Page 12, “Wi is the actual monthly electricity generation”)
constructing a time series model; (e.g. the LSTM model, which is a time-series model, see e.g. Page 7 “LSTM neural networks have long-term memory function and can effectively utilize the long-term dependence of limited data samples. …The main idea is to use special neurons to store and transmit information for a long time, in order to obtain permanent memory, capture long-term dependencies, slow down the speed of information loss in time series, and increase the advantages of deep computing.”
training the time series model according to the plurality of second sample sets to obtain a trained time series model; (see Page 9, particularly “This article first extracts daily features from the raw data of wind farms, and then trains the entire network model (including the monthly feature fusion model of wind farms and the power generation prediction model) to obtain a trained prediction model.”)
and Chen further teaches:
and the generating the wind power output predictive model according to the trained boosting model comprises: stacking and fusing the trained boosting model and the trained time series model, to obtain the wind power output predictive model. (see page 10 “the power load is predicted by using a combined mining model based on the LSTM prediction model and the XGBoost prediction model.”)
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu in view of Stenneth and Chen, further in view of Haemel et al., US Pg-Pub 2020/0027210.
Regarding Claim 13, Zhu in view of Stenneth, further in view of Chen teaches all of the limitations of parent claim 12,
The combination differs from the claimed invention in that:
None of the references clearly articulates: re-training the wind power output predictive model according to a plurality of new first sample sets and a plurality of new second sample sets to update the wind power output predictive model after the plurality of new first sample sets and the plurality of new second sample sets are acquired.
However, Haemel teaches an LSTM model (see [0040] “the machine learning models used by the system 200 may include… Long/Short Term Memory (LSTM)”) which may be retrained according to new data including new ground truths, ([0083 “model training 114 may include retraining or updating an initial model 604 (e.g., a pre-trained model) using new training data (e.g., new input data, such as the customer dataset 606, and/or new ground truth data associated with the input data).”)
Haemel is analogous art because it is from a related field of endeavor of Power Grid control systems and reasonably pertinent to the same problem confronted by Applicant of how to ensure high-confidence in the accuracy of the forecasting model.
Accordingly examiner finds 1) the prior art contained a “base” device (method, or product) upon which the claimed invention can be seen as an “improvement” – the wind power forecasting LSTM system of Zhu, upon which the addition retraining the model can be seen as an improvement; 2) the prior art contained a “comparable” device (method, or product that is not the same as the base device) that has been improved in the same way as the claimed invention – the teachings of Haemel, which retrain an LSTM forecasting model with a new second data set; 3) one of ordinary skill in the art before the effective filing date of the application could have applied the known “improvement” technique in the same way to the “base” device (method or product) and the results would have been predictable to one having ordinary skill in the art at least because Haemel teaches that retraining can re-tune an extant model for a new data set in less time than generating a new model from scratch (Haemel [0083] “As such, the initial model 604 may have previously fine-tuned parameters (e.g., weights and/or biases) that remain from prior training, so training or retraining 114 may not take as long or require as much processing as training a model from scratch.”) and the improvement would therefore be obvious to one of ordinary skill in the art before the effective filing date of the application (see MPEP 2143.I.C).
Claim(s) 15-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu in view of Stenneth, further in view of Wang, further in view of Well-Known Practice as Exemplified by Pal et al., US Pg-Pub 2011/0153096 and Pyle et al., US Pg-pub 2012/0185414.
Regarding Claim 15, Zhu in view of Stenneth teaches all of the limitations of parent claim 1,
The combination differs from the claimed invention in that:
Neither reference clearly teaches the latest initial meteorological sub-data comprises at least the latest initial wind speed at the hub of the fan,
Nor monitoring the initial wind speed at the hub of the fan acquired each time starting from the latest received time node after acquiring the latest initial meteorological data set corresponding to the latest received time node when the latest initial wind speed at the hub of the fan is less than a first preset wind speed or greater than a second preset wind speed; wherein the first preset wind speed is less than the second preset wind speed;
Nor performing warning according to the each acquired initial wind speed at the hub of the fan monitored in a preset period of time.
However, Wang teaches a wind turbine farm (see [0003]) which uses data from tower anemometers ([0003] “anemometer tower data”) including wind speed and air density measurements and calculations taken at the hub of each fan ([0034] “constructing wind speed conversion function of each wind direction sector by extrapolating the wind speed of each of the plurality of anemometer towers to a height of each hub of wind turbine”) and determining energy at the hub of each fan (see e.g. [0049-0050] “the power curve can be calibrated by following formula {omitted for brevity} wherein P.sub.correct is the calibrated wind power; P.sub.0 is the wind power according to theoretical power curve; ρ.sub.0 is the standard air density; V.sub.0 is the original wind speed; V.sub.correct is the wind speed after the correction; ρ is the measured average density.”)
Wang and Zhu are analogous art because it is from the same field of endeavor as the claimed invention and other references of predicting wind power generation in wind farm installations.
Accordingly, Examiner finds 1) the prior art contained a device (method, or product, etc.) which differed from the claimed device by the substitution of some components (step, element, etc.) with other components – the teachings of Zhu which differed from the claimed invention by recording meteorological data at an unspecified location in each wind field; 2) the substituted components and their functions were known in the art – as exemplified by Wang, which teaches recording meteorological data at the hub of the fan on the wind turbine mast; 3) one of ordinary skill in the art before the effective filing date of the application could have substituted one known element for another, and the results of the substitution would have been predictable at least because Wang teaches that measuring at the hub is suitable for collecting data that may be used to estimate wind power de