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 .
Claim Objections
Claims 1-10 are objected to because of the following informalities of claim 1: “achieving, according to the obtained data of the centralized photovoltaic power station, point prediction of the distributed photovoltaic power station, through the optimal model of the corresponding weather”. The use of “achieving” with regard to “point prediction” makes the meaning of the limitation unclear. The examiner suggests changing the limitation to the following in order to make the meaning clearer: “obtaining according to the obtained data of the centralized photovoltaic power station, point prediction of the distributed photovoltaic power station, through the optimal model of the corresponding weather”.
Claims 2-10 inherit this issue and do not cure this deficiency. Therefore, claims 2-10 are also objected for the same reasons. Appropriate correction is required.
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 therefore, subject to the conditions and requirements of this title.
Claims 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception, an abstract idea, that does not amount to significantly more than the judicial exception.
The following is an analysis of independent claim 1 based on the 2019 Revised Patent Subject Matter Eligibility Guidance (2019 PEG).
Step 1, Statutory Category:
Yes: Claims 1 is directed to a method.
Step 2A Prong 1, Judicial Exception:
The Examiner submits that the following claim limitations constitute mental processes or generic computer functions, as the claims cover performance of the limitations of the human mind or a generic computer processor, given their broadest reasonable interpretation. Abstract ideas are bolded.
Claim 1 recites the following limitations:
A probability estimation method for photovoltaic power based on an optimized copula function, comprising the following steps:
classifying, according to historical photovoltaic power data obtained from a centralized photovoltaic power station and a distributed photovoltaic power station, weather types by a clustering method to obtain a plurality of weather types;
constructing, according to the cumulative distribution of the photovoltaic output obtained from photovoltaic data under different weather types, a plurality of copula function models for quantitatively representing the spatial correlation of the power of the centralized photovoltaic power station and the distributed photovoltaic power station, respectively;
evaluating the plurality of copula function models respectively for different weather, and obtaining a copula function model achieving the highest accuracy for predicting the photovoltaic power under the corresponding different weather as an optimal model;
achieving, according to the obtained data of the centralized photovoltaic power station, point prediction of the distributed photovoltaic power station, through the optimal model of the corresponding weather;
constructing, based on the relationship between an actual value and a value of point prediction of the distributed photovoltaic power station, a conditional probability model and obtaining, through the conditional probability model, the probability distribution of the power of the distributed photovoltaic power station and the conditional probability corresponding to the value of point prediction;
obtaining, based on a real value of the power of the centralized photovoltaic power station at the future moment and in combination with the above conditional probability model, a predicted value of the power generated by the distributed photovoltaic power station at the future moment.
The limitations classifying, according to historical photovoltaic power data obtained from a centralized photovoltaic power station and a distributed photovoltaic power station, weather types by a clustering method to obtain a plurality of weather types (relies on numerical algorithms/equations/values), constructing, according to the cumulative distribution of the photovoltaic output obtained from photovoltaic data under different weather types, a plurality of copula function models for quantitatively representing the spatial correlation of the power of the centralized photovoltaic power station and the distributed photovoltaic power station, respectively and constructing, based on the relationship between an actual value and a value of point prediction of the distributed photovoltaic power station, a conditional probability model and obtaining, through the conditional probability model, the probability distribution of the power of the distributed photovoltaic power station and the conditional probability corresponding to the value of point prediction (relies on numerical algorithms/equations/values), and achieving, according to the obtained data of the centralized photovoltaic power station, point prediction of the distributed photovoltaic power station, through the optimal model of the corresponding weather (relies on numerical algorithms/equations/values), obtaining, based on a real value of the power of the centralized photovoltaic power station at the future moment and in combination with the above conditional probability model, a predicted value of the power generated by the distributed photovoltaic power station at the future moment (relies on numerical algorithms/equations/values) are abstract ideas because they are directed towards mathematical formulas and equations.
The limitations evaluating the plurality of copula function models respectively for different weather, and obtaining a copula function model achieving the highest accuracy for predicting the photovoltaic power under the corresponding different weather as an optimal model (one can observe the numerical output of a model and perform analysis on said data using critical thinking and judgement) is an abstract idea because it is directed towards a mental process.
Step 2A Prong 2, Integration into a Practical Application:
Claim 1 recites additional limitations of a distributed and centralized photovoltaic power station that would fall under general field of use, specifically generally linking (see MPEP § 2106.05(h)).
Step 2B, Significantly More:
When considered individually or in combination, the additional limitations and elements of Claim 1 do not amount to significantly more than the judicial exceptions for the same reasons above as to why the additional limitations do not integrate the abstract idea into a practical application.
The additional limitations identified as general field of use above are carried over and also do not provide significantly more than the abstract idea. See MPEP § 2106.05(h).
Therefore, considering the claim limitations in combination as a whole make Claim 1 ineligible under 35 U.S.C. 101.
Claims 2, 3, and 7 only recited limitations that fall under the judicial exception of “mental processes/ mathematical relationship” and then “generally linking” to a technical field, as per MPEP 2106.05(h). Also, claim 2 recites obtaining data which is insignificant extra-solution activity in the form of mere data gathering activity as per MPEP 2106.05(g). Therefore, they remain ineligible for the same reasons as set forth for Claim 1.
Claim 4 depends on claim 3 and recites limitation that is directed to a field of use since it is generally linking the math data values to what they represent (weather features).
Claims 5-6 are dependent on Claim 1 and only recite limitations that specify mathematical relationships/equations for use in Claim 1 and 5. Therefore, they remain ineligible for the same reasons as set forth for Claim 1.
Claim 8 depends on claims 1 and 7. Claim 8 only recites limitations directed towards an abstract idea that do not cure the issues of Claims 1 and 7. Therefore, claim 8 remains ineligible for the same reason as set forth for Claims 1 and 7 above.
Claim 9 is dependent on Claim 1 and only recite limitations directed towards an abstract idea that do not cure the issues of Claim 1. In addition, claim 9 adds generic computer components as mere instructions to apply the exception as per MPEP 2106.05(f). Therefore, claim 9 remains ineligible for the same reason as set forth for Claim 1.
Claim 10 is dependent on Claim 1 and only recite limitations directed towards an abstract idea that do not cure the issues of Claim 1 In addition, claim 10 recites power generation units, a power station, and a power grid with PV inverters and transformers, which are field of use limitation as per MPEP 2106.05(h). Therefore, claim 10 remains ineligible for the same reason as set forth for Claim 1.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 5-7, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over He (Short-Term Power Load Forecasting with Deep Belief Network and Copula Models), in view of Li (Optimal Power Flow Calculation Considering Large-Scale Photovoltaic Generation Correlation), in view of Khatib (Grid Impact Assessment of Centralized and Decentralized Photovoltaic-Based Distribution Generation: A Case Study of Power Distribution Network with High Renewable Energy Penetration), in view of Cheng (Ultra Short-term Output Forecasting of Distributed Photovoltaic Power Station Based on Feature Extraction), in view Cao (Probabilistic Estimation of Wind Power Ramp Events: A Data-Driven Optimization Approach), in view of An (A Probabilistic Ensemble Prediction Method for PV Power in the Nonstationary Period ), in view of Sulaiman (Artificial neural network versus linear regression for predicting Grid-Connected Photovoltaic system output), in further view of Liu (An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data).
He teaches:
evaluating the plurality of copula function models respectively for different weather (Page 3: Data of the power load, electricity price, temperature, and other related parameters are collected from an urbanized area in Texas, United States. The length of the dataset covers a whole year period from January 2013 to January 2014. In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting. Classical neural network (NN), support vector regression machine (SVR), extreme learning machine (ELM), and classical deep belief network (DBN) are considered for the comparative analysis to evaluate the forecasting performance of the proposed method)
He does not teach:
classifying, according to historical photovoltaic power data obtained from a centralized photovoltaic power station and a distributed photovoltaic power station, weather types by a clustering method to obtain a plurality of weather types;
constructing, according to the cumulative distribution of the photovoltaic output obtained from photovoltaic data under different weather types, a plurality of copula function models for quantitatively representing the spatial correlation of the power of the centralized photovoltaic power station and the distributed photovoltaic power station, respectively;
and obtaining a copula function model achieving the highest accuracy for predicting the photovoltaic power under the corresponding different weather as an optimal model;
achieving, according to the obtained data of the centralized photovoltaic power station, point prediction of the distributed photovoltaic power station, through the optimal model of the corresponding weather;
constructing, based on the relationship between an actual value and a value of point prediction of the distributed photovoltaic power station, a conditional probability model
obtaining, through the conditional probability model, the probability distribution of the power of the distributed photovoltaic power station and the conditional probability corresponding to the value of point prediction;
obtaining, based on a real value of the power of the centralized photovoltaic power station at the future moment and in combination with the above conditional probability model, a predicted value of the power generated by the distributed photovoltaic power station at the future moment.
However, Li teaches:
classifying, according to historical photovoltaic power data obtained from a centralized photovoltaic power station, (Page 6: This paper uses the actual data of a large-scale centralized photovoltaic power station in a province as an example, intercepting the photovoltaic output from May to July 2018 for simulation…. Therefore, considering different weather conditions, the optimal classification number of power stations in the province is 6)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the historical photovoltaic data of Li “intercepting photovoltaic output from May to July 2018” with the Copula model evaluation of He “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” for “the comparative analysis to evaluate the forecasting performance of the proposed method” as outlined by He.
Khatib teaches:
and a distributed photovoltaic power station (Page 15: The paper also proposes a comparison based on grid assessment results between centralized and decentralized photovoltaic-based distributed generation.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the decentralized photovoltaic generation of Khatib with the historical photovoltaic data of He as modified above “This paper uses the actual data of a large-scale centralized photovoltaic power station in a province as an example, intercepting the photovoltaic output from May to July 2018 for simulation” for “the comparative analysis to evaluate the forecasting performance of the proposed method” as outlined by He as modified above.
Cheng teaches:
weather types by a clustering method to obtain a plurality of weather types; (Page 4: In order to cope with the complicated and changeable weather conditions, the clustering analysis method is adopted to classify the weather characteristics into four main categories: sunny day, cloudy day, rainy day, and foggy day, and then the historical data of multiple photovoltaic outputs with the same photovoltaic output type is grouped into data sequences with highly similar photovoltaic output characteristics.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the clustering method applied to weather types of Cheng “the clustering analysis method is adopted to classify the weather characteristics” with the historical photovoltaic power of He as modified above “intercepting the photovoltaic output from May to July 2018 for simulation” in order to “cope with the complicated and changeable weather conditions” as described by Cheng.
He further teaches:
Constructing a plurality of copula function models for quantitatively representing the spatial correlation of the power (Page 1: Hence, in order to gain more accuracy forecasting results of peak load forecasting, Copula models are introduced to build the correlation between power load verses real electricity price and power load verses temperature.)
Cheng further teaches:
Constructing a plurality of … functions according to the cumulative distribution of the photovoltaic output obtained from photovoltaic data under different weather types (Page 4: In order to cope with the complicated and changeable weather conditions, the clustering analysis method is adopted to classify the weather characteristics into four main categories: sunny day, cloudy day, rainy day, and foggy day, and then the historical data of multiple photovoltaic outputs with the same photovoltaic output type is grouped into data sequences with highly similar photovoltaic output characteristics.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the photovoltaic output grouping of Cheng “same photovoltaic output type is grouped into data sequences with highly similar photovoltaic output characteristics” with the Copula models of He as modified above in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Khatib further teaches:
A comparison of the centralized photovoltaic power station and the distributed photovoltaic power station, respectively; (Page 15: The paper also proposes a comparison based on grid assessment results between centralized and decentralized photovoltaic-based distributed generation.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the copula models of He as modified above “Copula models are introduced to build the correlation” with the centralized and distributed photovoltaic power stations of Khatib “between centralized and decentralized photovoltaic-based distribution generation” in order to perform analysis and prediction of the stations as outlined by Khatib “the decentralized PV systems were found to affect the power quality negatively more than the centralized system.”
Cao teaches:
and obtaining a copula function model achieving the highest accuracy for predicting the photovoltaic power under the corresponding different weather as an optimal model; (Page 2: The OpSDA is applied to conduct the probabilistic wind power ramp forecasting based on the generated scenarios under different weather and time conditions. By considering the stochastic correlation of different wind ramp features (magnitude, rate, start-time and duration), [24] investigates a conditional probabilistic wind power ramp forecasting model based on Copula theory. The Gaussian mixture model (GMM) and Bayesian information criterion are applied to fit and choose the optimal copula model for improved accuracy in prediction.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the optimal model of Cao “choose the optimal copula model” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” for “improved accuracy in prediction” as outlined by Cao.
An teaches:
Achieving point prediction of the distributed photovoltaic power station (Page 1: an optimization algorithm named Non-dominated Sorting Genetic Algorithm-II is applied for integrating and optimizing the results of the point forecast and probabilistic forecast. The proposed model is tested using two photovoltaic outputs and weather data measured from a grid-connected photovoltaic system. The results show that the proposed model outperforms conventional forecast methods to predict short-term photovoltaic power outputs and associated uncertainties.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the point prediction of An “optimizing the results of the point forecast” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Li further teaches:
according to the obtained data of the centralized photovoltaic power station (Page 6: This paper uses the actual data of a large-scale centralized photovoltaic power station)
Cao further teaches:
through the optimal model of the corresponding weather; (Page 3: The first one only requires a point forecast and the mean-absolute deviation of forecast error and takes the unimodality of forecast error distribution into account; the second one needs an arbitrary number of historical realizations of wind power data. Both models are data-driven and give rise to computationally tractable convex optimization problems, which could be solved via off-the-shelf solvers... Page 2: investigates a conditional probabilistic wind power ramp forecasting model based on Copula theory. The Gaussian mixture model (GMM) and Bayesian information criterion are applied to fit and choose the optimal copula model for improved accuracy in prediction.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the optimal model of Cao “applied to fit and choose the optimal copula model for improved accuracy in prediction” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Sulaiman teaches:
constructing a conditional probability model (Page 1: This paper presents a classically trained Multi-Layer Feedforward Neural Network (MLFNN) technique for predicting the output from a Grid-Connected Photovoltaic (GCPV) system. In the proposed MLFNN, the selection of the training parameters was conducted using a series of prescribed steps. The MLFNN utilized solar irradiance (SI) and module temperature (MT) as its inputs and AC kWh energy as its output. When compared with the linear regression method, the MLFNN offered superior performance by producing lower prediction error.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine with conditional probability model of Sulaiman “When compared with the linear regression method, the MLFNN offered superior performance by producing lower prediction error” with the Copula models of He as modified above “Copula models are introduced to build the correlation between power load verses real electricity price and power load verses temperature” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
An teaches:
based on the relationship between an actual value and a value of point prediction of the distributed photovoltaic power station (Page 1: an optimization algorithm named Non-dominated Sorting Genetic Algorithm-II is applied for integrating and optimizing the results of the point forecast and probabilistic forecast. The proposed model is tested using two photovoltaic outputs and weather data measured from a grid-connected photovoltaic system. The results show that the proposed model outperforms conventional forecast methods to predict short-term photovoltaic power outputs and associated uncertainties.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the point prediction of An “optimizing the results of the point forecast” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Liu teaches:
Obtaining the probability distribution of the power of the distributed photovoltaic power station (Page 1: Various PV power output prediction algorithms have been proposed up to present. Multiple linear regression [5], [6] was used to study the solar power output characteristics, combining with weather data and solar radiation data. However, SVM algorithms were originally proposed for classification problems, as for nonlinear regression problems such as PV power forecasting, it is not easy to choose suitable kernel functions and increase training speed during its quadratic programming process [13]. Researchers also have combined SVM algorithms with other regression methods, so as to get more accurate estimations for short term PV forecasting)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the probability distribution of Liu “Multiple linear regression [5], [6] was used to study the solar power output characteristics, combining with weather data and solar radiation data” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Cao further teaches:
the conditional probability corresponding to the value of point prediction; (Page 3: The first one only requires a point forecast and the mean-absolute deviation of forecast error and takes the unimodality of forecast error distribution into account; the second one needs an arbitrary number of historical realizations of wind power data. Both models are data-driven and give rise to computationally tractable convex optimization problems, which could be solved via off-the-shelf solvers...)
through the conditional probability model (Page 3: …investigates a conditional probabilistic wind power ramp forecasting model based on Copula theory. The Gaussian mixture model (GMM) and Bayesian information criterion are applied to fit and choose the optimal copula model for improved accuracy in prediction.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the point prediction “only requires a point forecast and the mean-absolute deviation of forecast error and takes the unimodality of forecast error distribution into account “and conditional probability model of Cao “investigates a conditional probabilistic wind power ramp forecasting model based on Copula theory” with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Liu further teaches:
Obtaining a predicted value of the power (Page 1: There are two commonly used objectives for PV forecasting at present: one is to predict the environmental parameters relevant to the PV system, such as solar radiation [1], then to calculate the active power outputs with respect to solar radiation, ambient temperature, and other parameters, using predefined mathematical models. The other is to predict the active power outputs of PV directly)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the predicted value of Liu “to predict the active power outputs of PV directly” with the with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” for “improved accuracy in prediction” as outlined by Cao.
Cao further teaches:
generated by the distributed photovoltaic power station at the future moment (Page 15: The paper also proposes a comparison based on grid assessment results between centralized and decentralized photovoltaic-based distributed generation.)
based on a real value of the power of the centralized photovoltaic power station at the future moment and in combination with the above conditional probability model (Page 2: By considering the stochastic correlation of different wind ramp features (magnitude, rate, start-time and duration), [24] investigates a conditional probabilistic wind power ramp forecasting model based on Copula theory. The Gaussian mixture model (GMM) and Bayesian information criterion are applied to fit and choose the optimal copula model for improved accuracy in prediction)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the decentralized power station and real value of centralized power station of Cao with the Copula model evaluation of He as modified above “In this section, the deep belief network (DBN) embedded with Copula parameters is applied to conduct the day-ahead and week-ahead forecasting” in order to “gain more accuracy forecasting results of peak load forecasting” as outlined by He as modified above.
Regarding Claim 2:
Cheng teaches:
obtaining historical photovoltaic power data (Page 2: The measurement data of meteorological stations and the historical data of photovoltaic power stations are taken as the input of the model, and the power at a certain time in the future is taken as the output)
performing data cleaning; (Page 3: Therefore, the original data needs to be nondimensionalized, and the processing method adopts the averaging method)
obtaining meteorological data in the corresponding period of the historical photovoltaic power data (Page 2: The measurement data of meteorological stations and the historical data of photovoltaic power stations are taken as the input of the model, and the power at a certain time in the future is taken as the output)
determining, based on correlation analysis, clustering elements to cluster the weather to obtain the plurality of weather types. (Page 4: In order to cope with the complicated and changeable weather conditions, the clustering analysis method is adopted to classify the weather characteristics into four main categories: sunny day, cloudy day, rainy day, and foggy day, and then the historical data of multiple photovoltaic outputs with the same photovoltaic output type is grouped into data sequences with highly similar photovoltaic output characteristics.)
Regarding Claim 3,
Cheng teaches:
determining meteorological factors affecting the photovoltaic output as the clustering elements; (Page 4: In order to cope with the complicated and changeable weather conditions, the clustering analysis method is adopted to classify the weather characteristics into four main categories: sunny day, cloudy day, rainy day, and foggy day, and then the historical data of multiple photovoltaic outputs with the same photovoltaic output type is grouped into data sequences with highly similar photovoltaic output characteristics. When forecasting the photovoltaic output, the weather type and meteorological characteristics are known according to the weather forecast, and then the forecasting model related to various weather types is selected.)
Li teaches:
according to the determined clustering elements, the weather is clustered using a k-means algorithm. (Page 6: The paper uses the k-means clustering method to analyze the fluctuation of PV output, and then substitutes the history PV output data and other information of the power plants into the LSTM model, so as to obtain the predicted output of large-scale PV power plant clusters in the province.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the k-means algorithm for clustering of Li “paper uses the k-means clustering method to analyze the fluctuation of PV output” with the meteorological factors of Cheng “When forecasting the photovoltaic output, the weather type and meteorological characteristics are known according to the weather forecast” so as to “obtain the predicted output of large-scale PV power plant clusters in the province” as outlined by Li.
Regarding Claim 5,
He teaches:
a Frank Copula function model and a hybrid Copula function model, the hybrid Copula function model being a weighted sum of the Frank Copula function model and other models in an Archimedean Copula function cluster model. (Among several parametric Copula models, two Copula families, the Ellipse Copula and Archimedean Copula family are frequently used. The Ellipse Copula family includes Gaussian Copula and Student-t Copula. The Archimedean Copula family includes Gumbel Copula, Clayton Copula, and Frank Copula. Among Archimedean Copulas, only the Gumbel Copula model reflects the upper tail dependence with high sensitivity. The Clayton Copula is suitable for modeling the lower tail dependence. For Ellipse families, both Student-t Copula and Gaussian Copula model are symmetric. Student-t Copula models both lower tail and upper tail dependence. The Frank Copula model evaluates concordance between two highly associated variables with heavily-tailed distributions. The Gaussian Copula does not model tail dependence.)
Regarding claim 6:
Li teaches:
obtaining, according to the cumulative distribution of the photovoltaic output, a correlation coefficient value under each weather type, (Page 3: The spatial correlation characteristics of photovoltaic output are affected by two spatial scales: large-scale weather and small-scale weather. Large-scale weather mainly affects the overall attenuation, while small-scale weather affects fluctuations. The similar fluctuations in photovoltaic output indicate that the geographical environment and weather conditions of the power station are similar, and the spatial correlation of photovoltaic output is high.)
He further teaches:
establishing the Frank Copula function model; (Page 2: Among several parametric Copula models, two Copula families, the Ellipse Copula and Archimedean Copula family are frequently used. The Ellipse Copula family includes Gaussian Copula and Student-t Copula. The Archimedean Copula family includes Gumbel Copula, Clayton Copula, and Frank Copula)
constructing, based on other functions in an Archimedean Copula function cluster other than a Frank Copula function, a Copula function cluster model corresponding to each weather (Page 2: Among several parametric Copula models, two Copula families, the Ellipse Copula and Archimedean Copula family are frequently used. The Ellipse Copula family includes Gaussian Copula and Student-t Copula. The Archimedean Copula family includes Gumbel Copula, Clayton Copula, and Frank Copula)
weighting and summing the Copula function cluster model and the Frank Copula function model according to weights to obtain an optimized hybrid Copula function model. (Page 2: Among several parametric Copula models, two Copula families, the Ellipse Copula and Archimedean Copula family are frequently used. The Ellipse Copula family includes Gaussian Copula and Student-t Copula. The Archimedean Copula family includes Gumbel Copula, Clayton Copula, and Frank Copula)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine the establishing Fank Copula model “The Archimedean Copula family includes Gumbel Copula, Clayton Copula, and Frank Copula”, constructing Archimedean Copula models “the Ellipse Copula and Archimedean Copula family are frequently used”, and “coupled Copula model “Archimedean Copula family are frequently used. The Ellipse Copula family includes Gaussian Copula and Student-t Copula” with the coefficient photovoltaic output of Li “the spatial correlation of photovoltaic output is high” in order to better predict photovoltaic output “The similar fluctuations in photovoltaic output indicate that the geographical environment and weather conditions of the power station are similar, and the spatial correlation of photovoltaic output is high”.
Regarding Claim 7,
He teaches:
an optimal Copula model corresponding to each weather type is selected from a Frank Copula model and an optimized hybrid Copula function model by comparing correlation coefficients and an error evaluation index under different weather. (Pages 2-3: This method combines the co-movement analysis from Copula model with layer-wise pre-training-based deep belief network. At first, the raw time series power load data are normalized with Box-Cox transformation. Next, two deterministic parameters as electricity price and temperature are selected to construct Gumbel-Hougaard Copula model to investigate the upper-tail dependence with the power load. By computing the Value-at-Risk (VaR) of the constructed Copula models, two binary parameters can be created as peak load indicators and used as input parameters. After that, two deep belief networks (DBNs) are constructed independently to forecasting the day-ahead and week-ahead power load. Consequently, three evaluation metrics, namely mean absolute percentage error (MAPE) and root mean square error (RMSE) assess the performance of the proposed method.)
Regarding Claim 9,
Cao teaches:
a processor and a memory, the processor reading a computer program in the memory for executing the probability estimation method for photovoltaic power based on an optimized copula function according to claim 1. (Page 2: As an important technique, detecting wind power ramp event has been studied by many researchers. Reference [6] proposes a two-stage method to detect and categorize large wind ramps based on the wind farm data from the Wind Power Prediction Tool (WPPT) in Australia. A classifier model is developed in [7] based on support vector machine (SVM) to address the one-step and multi-step ahead classification of wind power ramp events. In [8], an optimal detection technique is proposed to identify wind ramps for large time series. A family of scoring functions with ramp definitions is given and a dynamic programming recursion is applied to detect ramp events. In [9], a swinging door algorithm (SDA) is applied to identify ramp events from historical data. This method requires only one parameter in its definition, and has significant advantages in computational efficiency and robustness against noisy data.)
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over He (Short-Term Power Load Forecasting with Deep Belief Network and Copula Models), in view of Li (Optimal Power Flow Calculation Considering Large-Scale Photovoltaic Generation Correlation), in view of Khatib (Grid Impact Assessment of Centralized and Decentralized Photovoltaic-Based Distribution Generation: A Case Study of Power Distribution Network with High Renewable Energy Penetration), in view of Cheng (Ultra Short-term Output Forecasting of Distributed Photovoltaic Power Station Based on Feature Extraction), in view Cao (Probabilistic Estimation of Wind Power Ramp Events: A Data-Driven Optimization Approach), in view of An (A Probabilistic Ensemble Prediction Method for PV Power in the Nonstationary Period ), in view of Sulaiman (Artificial neural network versus linear regression for predicting Grid-Connected Photovoltaic system output), in further view of Liu (An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data), further in view of Gates (THE ENERGY ENVIRONMENT IN WHICH WE LIVE).
Regarding Claim 4, modified He teaches all of the limitations of the parent claims, but does not teach the limitations of claim 4.
Gates teaches:
meteorological factors comprise an atmospheric pressure, relative humidity and radiancy (Page 20: The transpiration rate will depend upon the stomatal control, availability of water through the root system, and the vapor pressure gradient between the leaf and the surrounding air. Hence, the vapor pressure of the air also enters into the final adjustment of the line CD. Climates are described in terms of the radiant heat load on a plant or animal and not just in meteorological terminology with parameters such as air temperature, relative humidity, precipitation, wind, etc.).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine modified He with Gates since all references are directed to similar technological field and Gates’ specific factors would improve understanding of the meteorological factors of pressure, humidity, and radiancy (Gates, Page 20).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over He (Short-Term Power Load Forecasting with Deep Belief Network and Copula Models), in view of Li (Optimal Power Flow Calculation Considering Large-Scale Photovoltaic Generation Correlation), in view of Khatib (Grid Impact Assessment of Centralized and Decentralized Photovoltaic-Based Distribution Generation: A Case Study of Power Distribution Network with High Renewable Energy Penetration), in view of Cheng (Ultra Short-term Output Forecasting of Distributed Photovoltaic Power Station Based on Feature Extraction), in view Cao (Probabilistic Estimation of Wind Power Ramp Events: A Data-Driven Optimization Approach), in view of An (A Probabilistic Ensemble Prediction Method for PV Power in the Nonstationary Period ), in view of Sulaiman (Artificial neural network versus linear regression for predicting Grid-Connected Photovoltaic system output), in further view of Liu (An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data), further in view of Ziane (Photovoltaic output power performance assessment and forecasting: Impact of meteorological variables).
Regarding Claim 8, modified He teaches all of the limitations of the parent claims, but does not teach the limitations of claim 8.
Ziane teaches:
a Pearson correlation coefficient (Page 5: In our case, we performed the selection based on the Pearson correlation coefficient between the features and using one feature when multiple ones are highly correlated, and prioritizing the most correlated feature with the target over the others.)
a determination coefficient R2 (Page 7: To assess the developed models’ performance and compare regression methods to each other, we chose from classical statistical indicators, six statistical parameters; Max Error (ME), Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Median Absolute Error (MedAE) and Determination Coefficient R2)
error evaluation index is a root mean square error. (Page 7: To assess the developed models’ performance and compare regression methods to each other, we chose from classical statistical indicators, six statistical parameters; Max Error (ME), Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Median Absolute Error (MedAE) and Determination Coefficient R2)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s claimed invention to combine modified He with Ziane since all references are directed to similar technological field and Ziane’s coefficients and error evaluation index would improve performance of the overall system (Ziane, Pages 5 and 7).
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over He (Short-Term Power Load Forecasting with Deep Belief Network and Copula Models), in view of Li (Optimal Power Flow Calculation Considering Large-Scale Photovoltaic Generation Correlation), in view of Khatib (Grid Impact Assessment of Centralized and Decentralized Photovoltaic-Based Distribution Generation: A Case Study of Power Distribution Network with High Renewable Energy Penetration), in view of Cheng (Ultra Short-term Output Forecasting of Distributed Photovoltaic Power Station Based on Feature Extraction), in view Cao (Probabilistic Estimation of Wind Power Ramp Events: A Data-Driven Optimization Approach), in view of An (A Probabilistic Ensemble Prediction Method for PV Power in the Nonstationary Period ), in view of Sulaiman (Artificial neural network versus linear regression for predicting Grid-Connected Photovoltaic system output), in further view of Liu (An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data), further in view of Rakhshani (Integration of Large Scale PV-Based Generation into Power Systems: A Survey).
Regarding Claim 10, He, Li, Cheng, Cao, Khatib, Liu, Sulaiman, and An teach all the limitations of Claim 1.
Rakhshani teaches:
a plurality of power generation units (Page 2: The impact of large-scale PV based generation units are the focus of many strategic researches on the integration of renewable energy [7,8]. A PV-based power generation unit usually works in the grid connected mode.)
a centralized photovoltaic power station or a distributed photovoltaic power station in each power generation unit being each connected to a power grid through a corresponding photovoltaic inverter and transformer (Page 2: The impact of large-scale PV based generation units are the focus of many strategic researches on the integration of renewable energy [7,8]. A PV-based power generation unit usually works in the grid connected mode.)
It would have been obvious for one of ordinary skill in the art before the effective filing date of the Applicant’s invention to combine the power grid connection of HE “A PV-based power generation unit usually works in the grid connected mode” with the power generation plants “the power generation of grid-connected PV plants is increasing continuously all over the world” and power units “The impact of large-scale PV based generation units” of Rakhshani in order to better understand renewable energy “focus of many strategic researches on the integration of renewable energy” as outlined by Rakhshani (Page 2).
He further teaches:
wherein the probability estimation method for photovoltaic power based on an optimized copula function according to claim 1 is used for estimating the photovoltaic power. (Page 1: Hence, in order to gain more accuracy forecasting results of peak load forecasting, Copula models are introduced to build the correlation between power load verses real electricity price and power load verses temperature.)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAYDEN JAMES DANSEREAU whose telephone number is (571)270-5754. The examiner can normally be reached Monday-Friday (7:30am-5:00pm) ET.
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, Rehana Perveen can be reached at (571)272-3676. 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.
/HAYDEN JAMES DANSEREAU/Examiner, Art Unit 2189
/REHANA PERVEEN/Supervisory Patent Examiner, Art Unit 2189
Prosecution Insights