CN112766573A - Power generation data prediction method and device and electronic equipment - Google Patents
Power generation data prediction method and device and electronic equipment Download PDFInfo
- Publication number
- CN112766573A CN112766573A CN202110075094.9A CN202110075094A CN112766573A CN 112766573 A CN112766573 A CN 112766573A CN 202110075094 A CN202110075094 A CN 202110075094A CN 112766573 A CN112766573 A CN 112766573A
- Authority
- CN
- China
- Prior art keywords
- power station
- target
- power
- benchmark
- generation data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a method and a device for predicting power generation data and electronic equipment. Namely, when the target power station to be subjected to power generation data prediction is a power station without communication equipment or with frequent communication equipment failure, the power generation data of the target power station can be predicted by using the historical power generation data of the corresponding target benchmarking power station, so that the prediction of the power generation data of the power station without communication equipment or with frequent communication equipment failure is realized, and the power generation control of the power station is further realized. Furthermore, the method and the device can also determine the target benchmark power station of the target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station so as to assist in the prediction of the power generation data of the target power station.
Description
Technical Field
The invention relates to the field of data prediction, in particular to a method and a device for predicting power generation data and electronic equipment.
Background
The distributed photovoltaic technology is a new energy technology, can meet the energy demand, reduce the greenhouse effect and simultaneously improve the reliability of a power supply. In order to realize the distributed photovoltaic technology, distributed photovoltaic power stations need to be dispersedly arranged at different places.
In the operation process of the distributed photovoltaic power station, power generation control needs to be performed, and in order to realize the power generation control of the distributed photovoltaic power station, power generation data of the distributed photovoltaic power station needs to be predicted and power generation control needs to be performed based on the predicted power generation data. When power generation prediction is performed, for a power station without communication equipment or with frequent faults of the communication equipment, the controller cannot acquire historical power generation data of the power station through the communication equipment, and further cannot realize prediction of the power generation data of the power station and cannot realize power generation control of the power station.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for predicting power generation data, and an electronic device, so as to solve the problems that, for a power station in which no communication device is installed or a communication device frequently fails, the power generation data of the power station cannot be predicted and the power generation control of the power station cannot be realized.
In order to solve the technical problems, the invention adopts the following technical scheme:
a prediction method of power generation data is applied to a controller, and comprises the following steps:
under the condition that a target power station to be subjected to power generation data prediction does not have a corresponding target benchmark power station, determining the benchmark power station corresponding to the target power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station;
and predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Optionally, determining the target power station corresponding to the target power station includes:
obtaining a target power station within a preset distance range and belonging to the same area as the target power station, and determining the target power station as a candidate target power station;
acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and screening effective benchmark power stations from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and effective power station screening rules, and determining the effective benchmark power stations as the corresponding benchmark power stations of the target power station.
Optionally, determining a target benchmarking power station corresponding to the target power station from the benchmarking power stations based on the average output data and preset benchmarking power station screening rules, including:
acquiring output data of a single acquisition time interval of each benchmark power station;
calculating an average output coefficient of each benchmarking power station based on the output data and the power station attribute information of the benchmarking power stations;
and screening out the benchmark power station with the maximum average output coefficient, and determining the benchmark power station as a target benchmark power station corresponding to the target power station.
Optionally, predicting the power generation data of the target power station according to the historical power generation data of the target benchmarking power station includes:
predicting linear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a first linear data prediction model;
predicting nonlinear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a second linear data prediction model;
and integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
Optionally, in a case that the target power station has a corresponding target benchmarking power station, the method further includes:
acquiring actual average output power and predicted average output power of each preset time interval of a target benchmark power station of the target power station;
calculating a deviation value of the actual average output power and the predicted average output power;
judging whether the deviation value is larger than a preset threshold value or not;
if the average value of the power values of the target benchmarking power station is larger than the preset average output power, determining the average value of the power values of the target benchmarking power station in the preset time interval every day before the current moment, and determining the abnormal detection result of the target power station based on the comparison result of the average value and the actual average output power.
A prediction device of power generation data, which is applied to a controller, the prediction device comprises:
the power station determining module is used for determining a target benchmark power station corresponding to a target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
the data determination module is used for determining a target benchmark power station corresponding to the target power station from the benchmark power stations and acquiring historical power generation data of the target benchmark power station based on the average output data and preset benchmark power station screening rules;
and the data prediction module is used for predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Optionally, the power station determination module includes:
the power station acquisition submodule is used for acquiring the benchmark power station which is within the preset distance range of the target power station and belongs to the same area with the target power station, and determining the benchmark power station as a standby benchmark power station;
the information acquisition submodule is used for acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and the power station determining submodule is used for screening an effective benchmark power station from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and an effective power station screening rule, and determining the effective benchmark power station as the benchmark power station corresponding to the target power station.
Optionally, the data determining module includes:
the data acquisition submodule is used for acquiring the output data of a single acquisition time interval of each benchmark power station;
the coefficient calculation submodule is used for calculating the average output coefficient of each benchmark power station based on the output data and the power station attribute information of the benchmark power stations;
and the power station screening submodule is used for screening the benchmark power station with the maximum average output coefficient and determining the benchmark power station as the target benchmark power station corresponding to the target power station.
Optionally, the data prediction module comprises:
the first prediction submodule is used for predicting linear power generation data of the target power station based on historical power generation data of the target benchmark power station and a first linear data prediction model;
the second prediction submodule is used for predicting the nonlinear power generation data of the target power station based on the historical power generation data of the target benchmark power station and a second linear data prediction model;
and the data integration submodule is used for integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that a target power station to be subjected to power generation data prediction does not have a corresponding target benchmark power station, determining the benchmark power station corresponding to the target power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station;
and predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method and a device for predicting power generation data and electronic equipment. In other words, when the target power station to be subjected to power generation data prediction is a power station without communication equipment or with frequent communication equipment failure, the power generation data of the target power station can be predicted by using the historical power generation data of the corresponding target benchmarking power station, so that the prediction of the power generation data of the power station without communication equipment or with frequent communication equipment failure is realized, and the power generation control of the power station is further realized. Furthermore, the method and the device can also determine the target benchmark power station of the target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station so as to assist in the prediction of the power generation data of the target power station.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting power generation data according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for predicting power generation data according to another embodiment of the present invention;
FIG. 3 is a flow chart of a method for predicting power generation data according to another embodiment of the present invention;
FIG. 4 is a schematic diagram of a prediction scenario of power generation data according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a power generation data prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Since the beginning of the 21 st century, energy problems have again attracted attention from countries around the world. The demand for chemical fuels such as petroleum, coal, natural gas and the like is rising rapidly, so that people are prompted to consider more influences of resource problems on sustainable development and pay attention to influences of human activities on global climate change. The distributed photovoltaic technology is a new energy technology, can meet the energy demand, reduce the greenhouse effect and simultaneously improve the reliability of a power supply. Distributed photovoltaic power plants are therefore an important solution to the world's energy problem.
The distributed photovoltaic power station has the characteristics of small scale, scattered deployment and numerous equipment, however, the distributed photovoltaic power station brings many difficulties to the operation and maintenance work of the power station.
Taking a photovoltaic power generation system for 100 users included in an exemplary system as an example, some power stations are not provided with communication equipment or frequently fail to communicate with each other, and remote equipment, such as a controller, cannot remotely acquire historical power generation data of the power station through the communication equipment, so that prediction of the power generation data of the power station and power generation control of the power station cannot be realized.
In order to solve the technical problem, the inventor finds that intelligent operation and maintenance of a photovoltaic power station or a power station with incomplete data obtained in real-time monitoring or a power station with frequent communication faults can be realized by adopting a virtual acquisition mode and power generation amount prediction through remote monitoring. Specifically, when the target power station for which the power generation data is to be predicted is a power station in which no communication device or a communication device frequently fails, the power generation data of the target power station can be predicted by using the historical power generation data of the target benchmarking power station corresponding to the target power station, so that the power generation data of the power station in which no communication device or a communication device frequently fails is predicted, and the power generation control of the power station is further realized. Furthermore, the method and the device can also determine the target benchmark power station of the target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station so as to assist in the prediction of the power generation data of the target power station.
Specifically, on the basis of the above, another embodiment of the present invention provides a method for predicting power generation data, which is applied to a controller, and the controller in this embodiment may be the above-mentioned remote controller. Referring to fig. 1, the prediction method of power generation data may include:
s11, under the condition that the target power station to be subjected to power generation data prediction does not have a corresponding target benchmarking power station, determining the benchmarking power station corresponding to the target power station, and determining the average output data of each benchmarking power station.
The benchmark power station is a power station from which the controller can acquire power generation data.
In practical application, for a target power station, the target power station is not provided with communication equipment or has frequent faults of the communication equipment, and if the target power station is a power station which needs to perform power generation data prediction, it needs to be determined whether a corresponding benchmarking power station exists.
And if the target benchmarking power station is corresponding, directly using the historical power generation data of the target benchmarking power station to predict the power generation data, and taking the predicted result as the power generation prediction result of the target power station. If the target benchmarking power station does not correspond to the target benchmarking power station, the corresponding target benchmarking power station needs to be determined firstly, then the historical power generation data of the target benchmarking power station are used for predicting the power generation data, and the predicted result is used as the power generation prediction result of the target power station.
In practical application, referring to fig. 2, determining the target power station corresponding to the target power station may include:
and S21, acquiring the target power station within the preset distance range and belonging to the same area with the target power station, and determining the target power station as a candidate target power station.
In practical application, in order to realize data virtual acquisition of a communication fault frequent power generation station with incomplete data, an intelligent algorithm is used for preprocessing missing data. Based on the photovoltaic power generation system of more than 100 users included in the exemplary system, the virtual access of the power station is realized by adopting a virtual acquisition algorithm without realizing remote monitoring. The virtual collection algorithm in this embodiment refers to determining and using historical power generation data of a benchmarking power station.
Firstly, a target power station is searched for a benchmark power station which realizes remote monitoring within the range of 1km multiplied by 1km, and the spatial distance can be maximally expanded to 3km multiplied by 3km according to specific conditions. Then, effective benchmarking power stations of grids in the same area as the power station to be tested are screened out, and the power stations are called alternative benchmarking power stations. Here, 1km × 1km or 3km × 3km in the present embodiment is referred to as a preset distance range.
And S22, acquiring historical power generation data and power station attribute information of each candidate benchmarking power station.
In this embodiment, historical power generation data of each alternative benchmarking power station, such as data of at least one month of power station daily power generation, daily peak power, and the like, is obtained.
In addition, it is also necessary to obtain power station attribute information of the candidate benchmarking power station, such as installed capacity of the power station.
And S23, screening effective benchmarking power stations from the alternative benchmarking power stations based on the historical power generation data, the power station attribute information and effective power station screening rules, and determining the effective benchmarking power stations as benchmarking power stations corresponding to the target power stations.
Specifically, whether the installed capacity of the power station registered by the alternative benchmarking power station is correct or not is judged according to the historical maximum power detection of the screened effective power station, namely C is less than 1000Pwpcos θ/H, wherein: c denotes the installed capacity of the power station, PwpScreening the maximum daily peak power in the month, theta, the installation inclination angle of the photovoltaic array and H, the maximum horizontal irradiance corresponding to the maximum peak power, and if C is less than 1000Pwpcos theta/H, the installed capacity of the power station registered by the power station is correct, the alternative benchmarking power station is effective, and the alternative benchmarking is electrifiedAnd the station is used as a benchmark power station, otherwise, an incorrect alternative benchmark power station is rejected.
S12, determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station.
In practical application, the number of the determined benchmark power stations may be more than one, at the moment, one benchmark power station needs to be screened out from a plurality of benchmark power stations and determined as a target benchmark power station, and the number of the target benchmark power stations corresponding to the target power station to be detected is guaranteed to be unique.
In practical applications, referring to fig. 3, the "determining a target benchmarking power station corresponding to the target power station from the benchmarking power stations based on the average output data and preset benchmarking power station screening rules" may include:
and S31, acquiring the output data of the single acquisition time interval of each benchmark power station.
In practical application, the average output data of each benchmarking power station refers to a certain instantaneous actual output and installed capacity of the benchmarking power station within a time interval T.
And S32, calculating the average output coefficient of each benchmark power station based on the output data and the power station attribute information of the benchmark power station.
The average output coefficient of the benchmark power station refers to the average output coefficient in a single acquisition time interval T, and the calculation process of the average output coefficient is as follows:
calculating the average output coefficient of the benchmark power station within a single acquisition time interval T according to the installed capacity of the power station
Where Pi is the instantaneous actual output at a time interval T of the ith benchmarking power station.
And S33, screening out the benchmark power station with the maximum average output coefficient, and determining the benchmark power station as the target benchmark power station corresponding to the target power station.
Specifically, ranking is carried out according to the sequence of the average output coefficient values from large to small, and the benchmark power station with the largest average output coefficient is screened out and used as the target benchmark power station.
And S13, predicting the power generation data of the target power station according to the historical power generation data of the target benchmarking power station.
In practical applications, the controller uses a hybrid model of SARIMA and SVR to predict the theoretical average output power of the plant. The SARIMA model is a first linear data prediction model and is used for fitting a linear part of the average output power value, the SVR model is a second linear data prediction model and is used for making up non-linear errors caused by a plurality of complex factors, and simultaneous data auxiliary prediction of a target benchmarking power station is used.
When the power generation data of the target power station is predicted according to the historical power generation data of the target benchmark power station, the specific implementation process is as follows:
1) predicting linear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a first linear data prediction model;
2) predicting nonlinear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a second linear data prediction model;
3) and integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
Specifically, the predicted power generation amount of the target power station to be measured at the time t is assumed to be YtThen Y ist＝Lt+NtWherein L istIs a linear part of the predicted value of the power generation, is fitted based on the historical power generation data of the target benchmarking power station using a SARIMA model, NtThe target benchmark power station is a nonlinear part of the generated energy predicted value, and the SVR model predicts the generated energy based on the historical generated data of the target benchmark power station.
The SARIMA model is one of the most widely used univariate time series data prediction methods at present, and the formula can be written as phip(B)Φp(Bs)(1-B)d(1-Bs)DYt＝θq(B)ΘQ(Bs)at. Where B is the post-shift operator, atIs a mean of 0 and a variance of
White noise sequence of (Y)tRepresenting the predicted value of the generated energy at the moment t, (1-B)dAnd (1-B)s)DRespectively representing normal and seasonal difference operators, phip(B) And phip(Bs) Representing conventional and seasonal AR polynomials, θ, respectivelyq(B) And ΘQ(Bs) Representing the conventional and seasonal MA polynomials, respectively.
SVR is a linear regression model that focuses on finding a flat hyperplane that approximates the data. Similar to the ordinary linear regression, it has the formula
Where f (x) is a predicted value,
is the input data, WTIs a one-dimensional weight term and b is an offset. The purpose of SVR is to minimize the empirical risk, i.e., minimize
In an implementation manner of the present invention, the data accuracy of the SARIMA + SVR model is verified through experiments, specifically, refer to fig. 4. In fig. 4, the difference between the actual power generation amount data and the predicted data is small, and thus it can be seen that the accuracy of the SARIMA + SVR model in the present invention is high.
The above embodiment describes that, in a scenario where a target power station to be measured does not have a corresponding target benchmarking power station, the target benchmarking power station is determined first, and then the historical power generation data of the target benchmarking power station is used, and the power generation data is predicted based on the two models.
In another implementation manner of the invention, if the target power station to be tested has a corresponding target benchmarking power station, historical power generation data of the target benchmarking power station is used, and power generation data is predicted based on the two models.
In conclusion, the performance of the intelligent operation and maintenance system of the existing distributed photovoltaic power station is greatly enhanced through the virtual acquisition and the fusion prediction model of SARIMA and SVR. In addition, the operation and maintenance system adopting the method provided by the invention overcomes the defects of the traditional virtual acquisition algorithm and the prediction model in accuracy through the machine learning fusion model on the premise of high processing speed in the operation and maintenance task of the photovoltaic power station, and optimizes the overall performance. The method can be applied to the operation of the power grid in a real scene, the performance of the virtual acquisition and prediction model is superior, and the intelligent operation and maintenance system has strong generalization while having the capability of solving complex problems.
In another implementation mode of the invention, the actual power generation data of the target power station can be acquired under the scene that the target power station to be detected has the corresponding target benchmarking power station.
After prediction is carried out, the predicted average output power P 'of each preset time interval in the target power station T-1 day to be detected can be determined, specifically, the predicted average output power of each preset time interval can be obtained through the predicted power generation amount, in addition, the actual average output power P of each preset time interval can also be obtained, and when the predicted average output power P' is obtained, the actual average output power P of each preset time interval can be obtained
The difference between the actual power and the theoretical power is large, the power station may not work normally, and the operation condition of the power station needs to be further judged. Firstly, historical operating power data of the power station at the same moment are obtained, and the average value of the data is calculated. The current actual power is then compared to the historical average power at the same time. And if the relative error of the actual power is less than 30%, the actual power fluctuates in a normal range, and the power station operates normally. If the relative error of the actual power is larger than 30%, the operation condition of the power station is early warned, so that technicians can know the abnormal condition of the power station in time.
Therefore, under the condition that the target power station has a corresponding target benchmarking power station, the method further comprises the following steps: acquiring actual average output power and predicted average output power of each preset time interval of a target benchmark power station of the target power station; calculating a deviation value of the actual average output power and the predicted average output power; judging whether the deviation value is larger than a preset threshold value or not; if the average value of the power values of the target benchmarking power station is larger than the preset average output power, determining the average value of the power values of the target benchmarking power station in the preset time interval every day before the current moment, and determining the abnormal detection result of the target power station based on the comparison result of the average value and the actual average output power.
Alternatively, on the basis of the above embodiment of the method for predicting power generation data, another embodiment of the present invention provides a prediction apparatus of power generation data, which is applied to a controller, and with reference to fig. 5, the prediction apparatus may include:
the power station determining module 11 is configured to determine a target benchmarking power station corresponding to a target power station in which power generation data is to be predicted, and determine average output data of each benchmarking power station, when the target power station does not have the corresponding target benchmarking power station; the benchmark power station is a power station from which the controller can obtain power generation data;
the data determining module 12 is configured to determine a target benchmark power station corresponding to the target power station from the benchmark power stations and acquire historical power generation data of the target benchmark power station based on the average output data and preset benchmark power station screening rules;
and the data prediction module 13 is used for predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Further, the power station determination module includes:
the power station acquisition submodule is used for acquiring the benchmark power station which is within the preset distance range of the target power station and belongs to the same area with the target power station, and determining the benchmark power station as a standby benchmark power station;
the information acquisition submodule is used for acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and the power station determining submodule is used for screening an effective benchmark power station from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and an effective power station screening rule, and determining the effective benchmark power station as the benchmark power station corresponding to the target power station.
Further, the data determination module includes:
the data acquisition submodule is used for acquiring the output data of a single acquisition time interval of each benchmark power station;
the coefficient calculation submodule is used for calculating the average output coefficient of each benchmark power station based on the output data and the power station attribute information of the benchmark power stations;
and the power station screening submodule is used for screening the benchmark power station with the maximum average output coefficient and determining the benchmark power station as the target benchmark power station corresponding to the target power station.
Further, the data prediction module comprises:
the first prediction submodule is used for predicting linear power generation data of the target power station based on historical power generation data of the target benchmark power station and a first linear data prediction model;
the second prediction submodule is used for predicting the nonlinear power generation data of the target power station based on the historical power generation data of the target benchmark power station and a second linear data prediction model;
and the data integration submodule is used for integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
Further, still include:
the power acquisition module is used for acquiring the actual average output power and the predicted average output power of each preset time interval of the target benchmark power station of the target power station;
the deviation calculation module is used for calculating deviation values of the actual average output power and the predicted average output power;
the judging module is used for judging whether the deviation value is larger than a preset threshold value or not;
and the abnormality detection module is used for determining the average value of the power values of the target benchmarking power station in the preset time interval every day before the current moment if the average value is larger than the preset time interval, and determining the abnormality detection result of the target power station based on the comparison result of the average value and the actual average output power.
In this embodiment, when a target power station for which power generation data prediction is to be performed does not have a corresponding target benchmarking power station, the target benchmarking power station corresponding to the target power station is determined, and power generation data of the target power station is predicted according to historical power generation data of the target benchmarking power station. In other words, when the target power station to be subjected to power generation data prediction is a power station without communication equipment or with frequent communication equipment failure, the power generation data of the target power station can be predicted by using the historical power generation data of the corresponding target benchmarking power station, so that the prediction of the power generation data of the power station without communication equipment or with frequent communication equipment failure is realized, and the power generation control of the power station is further realized. Furthermore, the method and the device can also determine the target benchmark power station of the target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station so as to assist in the prediction of the power generation data of the target power station.
It should be noted that, for the working processes of each module and sub-module in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.
Optionally, on the basis of the above embodiment of the method and apparatus for predicting power generation data, another embodiment of the present invention provides an electronic device, including: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that a target power station to be subjected to power generation data prediction does not have a corresponding target benchmark power station, determining the benchmark power station corresponding to the target power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station;
and predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Further, determining the target power station corresponding to the target power station comprises:
obtaining a target power station within a preset distance range and belonging to the same area as the target power station, and determining the target power station as a candidate target power station;
acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and screening effective benchmark power stations from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and effective power station screening rules, and determining the effective benchmark power stations as the corresponding benchmark power stations of the target power station.
Further, based on the average output data and preset benchmarking power station screening rules, determining a target benchmarking power station corresponding to the target power station from the benchmarking power stations, including:
acquiring output data of a single acquisition time interval of each benchmark power station;
calculating an average output coefficient of each benchmarking power station based on the output data and the power station attribute information of the benchmarking power stations;
and screening out the benchmark power station with the maximum average output coefficient, and determining the benchmark power station as a target benchmark power station corresponding to the target power station.
Further, predicting the power generation data of the target power station according to the historical power generation data of the target benchmarking power station comprises the following steps:
predicting linear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a first linear data prediction model;
predicting nonlinear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a second linear data prediction model;
and integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
Further, under the condition that the target power station has a corresponding target benchmarking power station, the method further comprises the following steps:
acquiring actual average output power and predicted average output power of each preset time interval of a target benchmark power station of the target power station;
calculating a deviation value of the actual average output power and the predicted average output power;
judging whether the deviation value is larger than a preset threshold value or not;
if the average value of the power values of the target benchmarking power station is larger than the preset average output power, determining the average value of the power values of the target benchmarking power station in the preset time interval every day before the current moment, and determining the abnormal detection result of the target power station based on the comparison result of the average value and the actual average output power.
In this embodiment, when a target power station for which power generation data prediction is to be performed does not have a corresponding target benchmarking power station, the target benchmarking power station corresponding to the target power station is determined, and power generation data of the target power station is predicted according to historical power generation data of the target benchmarking power station. In other words, when the target power station to be subjected to power generation data prediction is a power station without communication equipment or with frequent communication equipment failure, the power generation data of the target power station can be predicted by using the historical power generation data of the corresponding target benchmarking power station, so that the prediction of the power generation data of the power station without communication equipment or with frequent communication equipment failure is realized, and the power generation control of the power station is further realized. Furthermore, the method and the device can also determine the target benchmark power station of the target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station so as to assist in the prediction of the power generation data of the target power station.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A prediction method of power generation data, applied to a controller, the prediction method comprising:
under the condition that a target power station to be subjected to power generation data prediction does not have a corresponding target benchmark power station, determining the benchmark power station corresponding to the target power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station;
and predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
2. The prediction method of claim 1, wherein determining the benchmarking power station corresponding to the target power station comprises:
obtaining a target power station within a preset distance range and belonging to the same area as the target power station, and determining the target power station as a candidate target power station;
acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and screening effective benchmark power stations from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and effective power station screening rules, and determining the effective benchmark power stations as the corresponding benchmark power stations of the target power station.
3. The prediction method of claim 1, wherein determining a target benchmarking power station corresponding to the target power station from the benchmarking power stations based on the average output data and preset benchmarking power station screening rules comprises:
acquiring output data of a single acquisition time interval of each benchmark power station;
calculating an average output coefficient of each benchmarking power station based on the output data and the power station attribute information of the benchmarking power stations;
and screening out the benchmark power station with the maximum average output coefficient, and determining the benchmark power station as a target benchmark power station corresponding to the target power station.
4. The prediction method of claim 1, wherein predicting the power generation data of the target utility from historical power generation data of the target benchmarking utility comprises:
predicting linear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a first linear data prediction model;
predicting nonlinear power generation data of the target power station based on historical power generation data of the target benchmarking power station and a second linear data prediction model;
and integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
5. The prediction method of claim 1, further comprising, in the case where the target power station has a corresponding target benchmarking power station:
acquiring actual average output power and predicted average output power of each preset time interval of a target benchmark power station of the target power station;
calculating a deviation value of the actual average output power and the predicted average output power;
judging whether the deviation value is larger than a preset threshold value or not;
if the average value of the power values of the target benchmarking power station is larger than the preset average output power, determining the average value of the power values of the target benchmarking power station in the preset time interval every day before the current moment, and determining the abnormal detection result of the target power station based on the comparison result of the average value and the actual average output power.
6. A prediction apparatus for power generation data, applied to a controller, the prediction apparatus comprising:
the power station determining module is used for determining a target benchmark power station corresponding to a target power station under the condition that the target power station to be subjected to power generation data prediction does not have the corresponding target benchmark power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
the data determination module is used for determining a target benchmark power station corresponding to the target power station from the benchmark power stations and acquiring historical power generation data of the target benchmark power station based on the average output data and preset benchmark power station screening rules;
and the data prediction module is used for predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
7. The prediction apparatus of claim 6 wherein the power station determination module comprises:
the power station acquisition submodule is used for acquiring the benchmark power station which is within the preset distance range of the target power station and belongs to the same area with the target power station, and determining the benchmark power station as a standby benchmark power station;
the information acquisition submodule is used for acquiring historical power generation data and power station attribute information of each alternative benchmarking power station;
and the power station determining submodule is used for screening an effective benchmark power station from the alternative benchmark power stations based on the historical power generation data, the power station attribute information and an effective power station screening rule, and determining the effective benchmark power station as the benchmark power station corresponding to the target power station.
8. The prediction apparatus of claim 7, wherein the data determination module comprises:
the data acquisition submodule is used for acquiring the output data of a single acquisition time interval of each benchmark power station;
the coefficient calculation submodule is used for calculating the average output coefficient of each benchmark power station based on the output data and the power station attribute information of the benchmark power stations;
and the power station screening submodule is used for screening the benchmark power station with the maximum average output coefficient and determining the benchmark power station as the target benchmark power station corresponding to the target power station.
9. The prediction device of claim 6, wherein the data prediction module comprises:
the first prediction submodule is used for predicting linear power generation data of the target power station based on historical power generation data of the target benchmark power station and a first linear data prediction model;
the second prediction submodule is used for predicting the nonlinear power generation data of the target power station based on the historical power generation data of the target benchmark power station and a second linear data prediction model;
and the data integration submodule is used for integrating the linear power generation data and the nonlinear power generation data to obtain the power generation data of the target power station.
10. An electronic device, comprising: a memory and a processor;
wherein the memory is used for storing programs;
the processor calls a program and is used to:
under the condition that a target power station to be subjected to power generation data prediction does not have a corresponding target benchmark power station, determining the benchmark power station corresponding to the target power station, and determining average output data of each benchmark power station; the benchmark power station is a power station from which the controller can obtain power generation data;
determining a target benchmark power station corresponding to the target power station from the benchmark power stations based on the average output data and preset benchmark power station screening rules, and acquiring historical power generation data of the target benchmark power station;
and predicting the power generation data of the target power station according to the historical power generation data of the target benchmark power station.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110075094.9A CN112766573A (en) | 2021-01-20 | 2021-01-20 | Power generation data prediction method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110075094.9A CN112766573A (en) | 2021-01-20 | 2021-01-20 | Power generation data prediction method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112766573A true CN112766573A (en) | 2021-05-07 |
Family
ID=75703463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110075094.9A Pending CN112766573A (en) | 2021-01-20 | 2021-01-20 | Power generation data prediction method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112766573A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757681A (en) * | 2023-08-16 | 2023-09-15 | 武汉联动设计股份有限公司 | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
| CN117113267A (en) * | 2023-10-25 | 2023-11-24 | 杭州海兴泽科信息技术有限公司 | Prediction model training method based on big data and photovoltaic power generation performance detection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184399A (en) * | 2015-08-27 | 2015-12-23 | 许继集团有限公司 | Power prediction method for photovoltaic power plant |
| CN108256697A (en) * | 2018-03-26 | 2018-07-06 | 电子科技大学 | A kind of Forecasting Methodology for power-system short-term load |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111614316A (en) * | 2020-06-16 | 2020-09-01 | 国网电子商务有限公司 | Photovoltaic system power generation state monitoring method and device |
-
2021
- 2021-01-20 CN CN202110075094.9A patent/CN112766573A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184399A (en) * | 2015-08-27 | 2015-12-23 | 许继集团有限公司 | Power prediction method for photovoltaic power plant |
| CN108256697A (en) * | 2018-03-26 | 2018-07-06 | 电子科技大学 | A kind of Forecasting Methodology for power-system short-term load |
| CN110929953A (en) * | 2019-12-04 | 2020-03-27 | 国网山东省电力公司电力科学研究院 | Photovoltaic power station ultra-short term output prediction method based on cluster analysis |
| CN111614316A (en) * | 2020-06-16 | 2020-09-01 | 国网电子商务有限公司 | Photovoltaic system power generation state monitoring method and device |
Non-Patent Citations (1)
| Title |
|---|
| 刘龙龙: "基于 SARIMA 与 SVR 的短期电力负荷预测", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 12, pages 1 - 19 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757681A (en) * | 2023-08-16 | 2023-09-15 | 武汉联动设计股份有限公司 | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
| CN116757681B (en) * | 2023-08-16 | 2023-11-28 | 武汉联动设计股份有限公司 | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
| CN117113267A (en) * | 2023-10-25 | 2023-11-24 | 杭州海兴泽科信息技术有限公司 | Prediction model training method based on big data and photovoltaic power generation performance detection method |
| CN117113267B (en) * | 2023-10-25 | 2024-02-09 | 杭州海兴泽科信息技术有限公司 | Prediction model training method based on big data and photovoltaic power generation performance detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garcia Marquez et al. | A comprehensive review of artificial intelligence and wind energy | |
| US10962576B2 (en) | Estimation of shading losses for photovoltaic systems from measured and modeled inputs | |
| CN104268678B (en) | A kind of petrochemical equipment preventative maintenance method based on dynamic reliability | |
| CN111614316B (en) | Photovoltaic system power generation state monitoring method and device | |
| US20180046924A1 (en) | Whole-life-cycle power output classification prediction system for photovoltaic systems | |
| CN112766573A (en) | Power generation data prediction method and device and electronic equipment | |
| KR102063383B1 (en) | Integrated management system and method of distributed energy resource | |
| CN110649883B (en) | Cleaning method and device and computer equipment | |
| CN108448625B (en) | Fan cut-in wind speed calculation method based on data driving | |
| CN104091289A (en) | Large-scale power distribution network N-1 rapid verification method based on wiring mode rules | |
| CN116865258A (en) | Hierarchical distributed power supply intelligent power grid construction method | |
| CN102800030A (en) | Comprehensive reliability interactive iteration assessment method for regional power grid relay protection equipment | |
| CN113011477B (en) | Cleaning and completing system and method for solar irradiation data | |
| US20210351612A1 (en) | Solar inverter power output communications methods, and related computer program products | |
| JP3245325U (en) | Solar power plant cluster monitoring system | |
| CN112083279B (en) | Electric power automation distributed information acquisition system and method | |
| CN111030594B (en) | Photovoltaic power station fault detection method and system and storage medium | |
| CN113268894B (en) | Thermal power production data management method and system based on data center station | |
| CN114442543A (en) | Computer monitoring method suitable for early warning of hydropower station fault | |
| CN114139897A (en) | Emergency response setting method for power grid fault system | |
| CN113642937B (en) | Operation and maintenance scheduling method and device for fan cluster, electronic equipment and storage medium | |
| Jiang et al. | Security-constrained unit commitment with flexible uncertainty set for wind power generation | |
| CN114070198B (en) | Fault diagnosis method and device for distributed photovoltaic power generation system and electronic equipment | |
| CN112564100B (en) | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater | |
| KR102524158B1 (en) | Method and device for providing solutions for managing solar power plants based on digital twin |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |