CN110059441B - Photovoltaic power station modeling method and photovoltaic power station model output correction method - Google Patents
Photovoltaic power station modeling method and photovoltaic power station model output correction method Download PDFInfo
- Publication number
- CN110059441B CN110059441B CN201910356832.XA CN201910356832A CN110059441B CN 110059441 B CN110059441 B CN 110059441B CN 201910356832 A CN201910356832 A CN 201910356832A CN 110059441 B CN110059441 B CN 110059441B
- Authority
- CN
- China
- Prior art keywords
- power generation
- data
- photovoltaic
- object model
- meteorological
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012937 correction Methods 0.000 title claims abstract description 17
- 238000010248 power generation Methods 0.000 claims abstract description 119
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Computer Hardware Design (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
Abstract
The application discloses a photovoltaic power station modeling method, which comprises the following steps: s1, acquiring historical meteorological data and historical power generation data of the photovoltaic power station; s2, establishing an identification data set and a sample data set of a meteorological parameter corresponding to a power generation parameter according to historical meteorological data and historical power generation data; s3, inputting the identification data set into identification software, and identifying a plurality of object models which take meteorological parameters as control variables and take power generation parameters as controlled variables; s4, inputting the meteorological data in the sample data set into each object model one by one; s5, calculating the deviation between the power generation data output by each object model and the corresponding actual power generation data in the sample data set; s6, selecting an object model with the minimum comprehensive deviation as an object model of the photovoltaic power station; the technical problems that an existing direct model prediction method and an existing indirect model prediction method are complex and troublesome when modeling of a photovoltaic power station is conducted are solved. The application also provides a photovoltaic power station model output correction method.
Description
Technical Field
The application relates to the technical field of photovoltaic power generation, in particular to a photovoltaic power station modeling method and a photovoltaic power station model output correction method.
Background
At present, most of power generation energy is from petrochemical fuel, and with the rapid development of social economy, the consumption of fossil energy is increased sharply, and the energy is combusted day by day to cause serious environmental pollution. Renewable energy sources such as solar energy and the like are pollution-free and have huge reserves, so that the renewable energy sources are generally regarded as important in all countries around the world for power generation.
In recent years, photovoltaic power generation technology is rapidly developed, a large-scale photovoltaic power station is connected to a power grid, and although the current unreasonable energy structure can be improved, photovoltaic power generation is intermittent, so that the probability of power system problems such as power quality and stability is increased undoubtedly. Therefore, it is necessary to establish a high-precision model capable of describing the dynamic response characteristics of power generation of the photovoltaic power station, and the model is used for power system analysis, power generation power prediction, equipment state evaluation, model-based controller design and the like.
The existing photovoltaic power station power generation model method mainly comprises a direct model prediction method and an indirect model prediction method. The direct model prediction method is mainly based on machine learning theory and method, including for example: support Vector Machines (SVMs), Support Vector Regression (SVR), Artificial Neural Networks (ANN), Genetic Algorithms (GA), markov chains, and hybrid algorithms, among others. The research ideas of the methods are simple, no specific requirements are placed on the internal details of the photovoltaic power station, the power conversion efficiency and the like, but the methods usually cause the structure of the established model to be complex. The indirect model prediction method is mainly used for establishing models of a power station, a photovoltaic conversion, a circuit, an inverter and the like according to the photovoltaic power generation mechanism, equipment conditions and the like, the method needs detailed technical data and data of power station equipment during modeling, the basic data collection is time-consuming, and the established photovoltaic power generation mechanism model is quite complex.
Disclosure of Invention
The application provides a photovoltaic power station modeling method, which solves the technical problems that the existing direct model prediction method and the existing indirect model prediction method are complex and troublesome when modeling a photovoltaic power station. The application also provides a photovoltaic power station model output correction method.
In view of the above, a first aspect of the present application provides a photovoltaic power plant modeling method, including:
s1, acquiring historical meteorological data and historical power generation data of the photovoltaic power station;
s2, establishing an identification data set and a sample data set of a meteorological parameter corresponding to a power generation parameter according to the historical meteorological data and the historical power generation data;
s3, inputting the identification data set into identification software, and identifying a plurality of object models which take the meteorological parameters as control variables and the power generation parameters as controlled variables;
s4, inputting the meteorological data in the sample data set into the object models one by one;
s5, calculating the deviation between the power generation data output by each object model and the corresponding actual power generation data in the sample data set;
and S6, selecting the object model with the minimum comprehensive deviation as the object model of the photovoltaic power station.
Preferably, the S3 specifically includes:
and inputting the identification data set into identification software to identify a plurality of object models which take the meteorological parameters as control variables, take the power generation parameters as controlled variables and take the model structures as second-order plus pure lag object models SOPDT structures.
Preferably, the S5 specifically includes:
calculating the deviation 2-norm of the power generation data output by each object model and the corresponding actual power generation data in the sample data set;
the S6 specifically includes:
and selecting the object model with the minimum comprehensive deviation 2-norm as the object model of the photovoltaic power station.
Preferably, said S6 is followed by:
discretizing an object model of the photovoltaic power plant;
storing the discretized object model of the photovoltaic power plant in a computer.
Preferably, the discretizing of the object model of the photovoltaic power plant specifically comprises:
discretizing an object model of the photovoltaic power plant by a transformation calculation of a zero-order keeper.
Preferably, the S2 specifically includes:
carrying out time synchronization processing on each meteorological data in the historical meteorological data and each power generation data in the historical power generation data, compiling the meteorological data and the power generation data into a uniform time scale, and forming a data set with the same time label;
and selecting a meteorological parameter and a power generation parameter from the data set to form an identification data set and a sample data set.
Preferably, the time synchronization processing of each meteorological data in the historical meteorological data and each power generation data in the historical power generation data is performed, the time synchronization processing is compiled into a uniform time scale, and the data set with the same time tag is formed, and then the method further includes:
and eliminating the part of the data set with the power generation power of 0 value at night time period.
Preferably, the meteorological parameters specifically include: illumination intensity, ambient temperature, humidity and wind speed; the power generation parameters specifically comprise active power, reactive power and photovoltaic backboard temperature.
Preferably, the S1 specifically includes:
historical meteorological data are obtained from a meteorological system, and historical power generation data of a photovoltaic power station are obtained from a data acquisition monitoring system SCADA of the photovoltaic power station.
The second aspect of the present application provides a photovoltaic power plant model output correction method, including:
pre-establishing a meteorological parameter-first object model of generated power, a photovoltaic backboard temperature-second object model of generated power and a meteorological parameter-third object model of photovoltaic backboard temperature of a photovoltaic power station;
the first object model is established by taking meteorological parameters as control variables and power generation power as controlled variables according to any one of the photovoltaic power station modeling methods provided by the first aspect;
the second object model is established by taking the temperature of a photovoltaic back plate as a control variable and the generated power as a controlled variable with reference to any one of the photovoltaic power station modeling methods provided by the first aspect;
the third object model is established by taking the meteorological parameters as control variables and the photovoltaic back panel temperature as controlled variables according to any one of the photovoltaic power station modeling methods provided by the first aspect;
the generated power is active power or reactive power;
acquiring new meteorological data and power generation data corresponding to the photovoltaic power station;
inputting the new meteorological data into the first object model and the third object model respectively to obtain the predicted power generation output by the first object model and the predicted photovoltaic backboard temperature output by the third object model;
calculating a temperature deviation between the predicted photovoltaic backplane temperature and an actual photovoltaic backplane temperature in the power generation data;
inputting the temperature deviation into the second object model to obtain the power generation deviation output by the second object model;
and adding the generated power deviation and the predicted generated power to obtain the corrected predicted generated power.
According to the technical scheme, the method has the following advantages:
the application provides a photovoltaic power station modeling method, which comprises the following steps: s1: acquiring historical meteorological data and historical power generation data of a photovoltaic power station; s2: establishing an identification data set and a sample data set of a meteorological parameter corresponding to a power generation parameter according to historical meteorological data and historical power generation data; s3: inputting the identification data set into identification software, and identifying a plurality of object models which take meteorological parameters as control variables and take power generation parameters as controlled variables; s4: inputting all meteorological parameters in the sample data set into all object models one by one; s5: calculating the deviation between the power generation parameters output by each object model and the corresponding actual power generation parameters in the sample data set; s6: and selecting the object model with the minimum comprehensive deviation as the object model of the photovoltaic power station.
According to the method, only historical meteorological data and historical power generation data are used as basic modeling data, and then technical means such as identification of identification software and screening of models are used, so that the object model of the photovoltaic power station with meteorological parameters as control variables and power generation parameters as controlled variables can be obtained, a complex model structure (direct model prediction method) established by a machine learning method is not needed, and a large amount of photovoltaic power station equipment parameter information (indirect model prediction method) is not needed to be collected by mechanism modeling. When the model is applied, the corresponding predicted power generation parameters of the photovoltaic power station can be obtained by inputting meteorological parameters, and the power generation characteristics of the photovoltaic power station can be embodied.
Drawings
FIG. 1 is a flow chart of a photovoltaic power plant modeling method provided in a first embodiment of the present application;
FIG. 2 is a flow chart of a photovoltaic power plant modeling method provided in a second embodiment of the present application;
FIG. 3 is a flow chart of a photovoltaic power plant model output correction method according to a third embodiment of the present application;
FIG. 4 is a calculation flowchart of an application example of the photovoltaic power plant model output correction method provided by the present application;
fig. 5 is a comparison diagram of the prediction effect of the application example of the photovoltaic power station model output correction method provided by the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions of the present application will be clearly and completely described below with reference to the drawings in the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all 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 application.
The photovoltaic power station modeling method is different from an existing direct model prediction method and an existing indirect model prediction method, and both the simplicity degree of modeling and the accuracy of a modeled model can be guaranteed.
Referring to fig. 1, fig. 1 is a flowchart of a photovoltaic power plant modeling method according to a first embodiment of the present application, where the method includes:
According to the method, basic data required by photovoltaic power station modeling mainly comprise historical meteorological data and historical power generation data. The historical meteorological data comprises various meteorological parameters such as illumination intensity, ambient temperature, humidity, wind speed and the like, and the meteorological data corresponding to the meteorological parameters can be read through a meteorological system. Historical power generation data also includes various power generation parameters such as active power, reactive power, photovoltaic backplane temperature, and the like. The power generation Data corresponding to the power generation parameters can be read from a Data Acquisition And monitoring system (Supervisory Control And Data Acquisition SCADA) of the photovoltaic power station.
It should be noted that the meteorological parameters and power generation parameters mentioned in the present application refer to a certain data category, and the meteorological data and power generation data mentioned refer to specific data under a certain category, for example, two power generation data under one power generation parameter for 50kW and 70 kW.
102, establishing an identification data set and a sample data set of a meteorological parameter corresponding to a power generation parameter according to historical meteorological data and historical power generation data.
A meteorological parameter, such as any of light intensity, ambient temperature, humidity, wind speed, etc., may be selected from the historical meteorological data. One power generation parameter may be selected from the historical power generation data, and the power generation parameter may be any one of active power, reactive power, photovoltaic backplane temperature, and the like. And processing the corresponding meteorological data and power generation data according to the selected meteorological parameters and power generation parameters to establish an identification data set and a sample data set.
It should be noted that the data in the identification data set is used for identifying the model, and the data in the sample data set is used for screening the model, but the identification data set and the specific data in the sample data set may be partially repeated.
Through the identification software, the input identification data set is identified, and a plurality of object models with meteorological parameters as control variables and power generation parameters as controlled variables can be obtained.
And 104, inputting the meteorological data in the sample data set into each object model one by one.
After obtaining a plurality of object models, an optimal one needs to be selected from the object models. In a specific implementation, each object model in the meteorological data in the sample data set needs to receive its input, and the obtained output can be compared with the actual power generation data in the sample data set, and the corresponding deviation can be calculated.
Each of the meteorological data in the sample data set is input to each of the object models as described above, and thus, for each of the object models, a plurality of deviations corresponding to a plurality of inputs can be obtained. And through comparison and analysis of the deviation between the object models, selecting the object model with the minimum comprehensive deviation from the object models, and taking the object model as the object model of the photovoltaic power station. Reference models for power prediction, robust control, device state detection, and the like
And 106, selecting the object model with the minimum comprehensive deviation as the object model of the photovoltaic power station.
The above is a detailed description of the photovoltaic power plant modeling method provided by this embodiment. According to the method provided by the embodiment, only historical meteorological data and historical power generation data are used as basic modeling data, and then the object model of the photovoltaic power station with meteorological parameters as control variables and power generation parameters as controlled variables can be obtained through technical means such as identification software identification and model screening, and a complex model structure (direct model prediction method) established by a machine learning method is not needed, and a large amount of photovoltaic power station equipment parameter information (indirect model prediction method) is not needed to be collected by mechanism modeling. When the model is applied, the corresponding predicted power generation parameters of the photovoltaic power station can be obtained by inputting meteorological parameters, and the power generation characteristics of the photovoltaic power station can be embodied.
Referring to fig. 2, fig. 2 is a flowchart of a photovoltaic power plant modeling method according to a second embodiment of the present application, where the method includes:
This step can be seen in step 101 of the first embodiment described above.
In order to establish the identification data set and the sample data set, the historical meteorological data and the historical power generation data need to be preprocessed and synchronized in time, so that the meteorological data and the power generation data correspond in time.
And step 203, eliminating the part of the data set with the power generation power of 0 value in the night time period.
Useless data are removed, and the influence of the useless data on the accuracy of the model is prevented.
For example, the illumination intensity and the active power may be selected to form an illumination intensity-active power identification data set and a sample data set, and other meteorological parameters or power generation parameters may also be selected.
In this embodiment, the structure of the identified model is defined, and the identified model structure needs to conform to a second-order plus pure hysteresis object model (SOPDT) structure. In particular, the SOPDT structure is in the form of:
the identification software can identify each parameter under the condition of selecting the structure, thereby obtaining the object model.
And step 206, inputting the meteorological data in the sample data set into each object model one by one.
This step may be referred to as step 104 in the first embodiment described above.
And step 207, calculating the deviation 2-norm of the power generation data output by each object model and the corresponding actual power generation data in the sample data set.
In calculating the deviation between the predicted value and the actual value output by the object model, the present embodiment calculates the 2-norm of the deviation.
The deviation 2-norm is calculated as follows:
||Ek||2=||Yij-Xk||2。
wherein E iskAs deviation of the kth object model, YijIs the numerical value, X, of the corresponding actual power generation data in the sample data setkAnd generating data output for the object model.
And 208, selecting the object model with the minimum comprehensive deviation 2-norm as the object model of the photovoltaic power station.
This step may be referred to as step 106 in the first embodiment described above.
And 209, discretizing an object model of the photovoltaic power station through the transformation calculation of the zero-order retainer.
The object model of the SOPDT structure obtained above is a continuous model, which can be discretized by a zero-order holder.
The expression for the zeroth order keeper is as follows:
after transformation calculation, a corresponding discretization model can be obtained:
y(k)=[d2*y(k-1)+d1*y(k-2)+n1*u(k-1)+n2*u(k-2)+n3*u(k-3)]/d3
parameter n in the above1、n2、n3、d1、d2And d3And can be obtained by a typical discretization calculation program.
Of course, besides the zero-order retainer, there are various types of retainers that can realize discretization of the model, so that in practical application, a proper retainer can be selected according to needs.
And 210, storing the discretized object model of the photovoltaic power station in a computer.
The above is a detailed description of the photovoltaic power plant modeling method provided by this embodiment. According to the method provided by the embodiment, only historical meteorological data and historical power generation data are used as basic modeling data, and then the object model of the photovoltaic power station with meteorological parameters as control variables and power generation parameters as controlled variables can be obtained through technical means such as identification software identification and model screening, and a complex model structure (direct model prediction method) established by a machine learning method is not needed, and a large amount of photovoltaic power station equipment parameter information (indirect model prediction method) is not needed to be collected by mechanism modeling. When the model is applied, the corresponding predicted power generation parameters of the photovoltaic power station can be obtained by inputting meteorological parameters, and the power generation characteristics of the photovoltaic power station can be embodied.
After modeling is completed, the model is usually fixed, but after the photovoltaic power station runs for a long time, due to factors such as equipment characteristic drift, inaccurate meteorological parameters and environmental condition influence, the deviation between the output of the model and the actual condition is gradually increased, and the accuracy of the model is gradually reduced.
In view of the above problems, the present application further provides a method for correcting photovoltaic power plant model output, which may be seen from fig. 3, where fig. 3 is a flowchart of a method for correcting photovoltaic power plant model output according to a third embodiment of the present application, and the method needs to pre-establish three object models of a photovoltaic power plant, which are a first object model of meteorological parameters-generated power, a second object model of photovoltaic backplane temperature-generated power, and a third object model of meteorological parameters-photovoltaic backplane temperature.
It can be understood that all three object models are established according to the photovoltaic power plant modeling method provided by the application. The first object model and the third object model are corresponding object models with meteorological parameters as control variables and power generation parameters (power generation power and photovoltaic backboard temperature both belong to power generation parameters) as controlled variables, and can be directly established according to the photovoltaic power station modeling method provided by the application.
However, the control variable and the controlled variable of the second object model are power generation parameters, so when the photovoltaic power station modeling method provided by the application is applied, some appropriate adjustments need to be made when the identification data set and the sample data set are established, but the modeling idea is still consistent, namely, the model is obtained through identification, screening and other means.
The generated power can be active power or reactive power.
After the pre-operation is finished, the output correction of the photovoltaic power station model comprises the following steps:
301, acquiring new meteorological data and power generation data corresponding to the photovoltaic power station.
It should be noted that the new meteorological data is different from the historical meteorological data, is closer to the current in time, and is therefore suitable for correcting the model.
And 302, inputting new meteorological data into the first object model and the third object model respectively to obtain the predicted power generation power output by the first object model and the predicted photovoltaic backboard temperature output by the third object model.
The first object model takes meteorological parameters as control variables and takes generated power as controlled variables, and the third object model takes the meteorological parameters as control variables and takes the temperature of the photovoltaic backboard as the controlled variables. After new meteorological data is input, the predicted power generation power output by the first object model and the predicted photovoltaic backboard temperature output by the third object model can be obtained.
And calculating the temperature deviation between the predicted photovoltaic backboard temperature output by the third object model and the actual photovoltaic backboard temperature.
And step 304, inputting the temperature deviation into the second object model to obtain the power generation deviation output by the second object model.
With the second object model, the deviation of the temperature can be converted into the deviation of the generated power.
And 305, adding the generated power deviation and the predicted generated power to obtain the corrected predicted generated power.
And correcting the predicted generating power model output by the first object model through the generating power deviation to obtain the predicted values of the photovoltaic generating power of various time scales.
The above is a detailed description of the photovoltaic power station model output correction method provided by the present application. In the method, a first object model of meteorological parameters-generated power, a second object model of photovoltaic backboard temperature-generated power and a third object model of meteorological parameters-photovoltaic backboard temperature are pre-established, and when the correction is carried out, the output deviation of the third object model (namely the deviation between the predicted photovoltaic backboard temperature and the actual temperature) is converted into the deviation on the generated power through the second object model, so that the output of the first object model can be corrected, various influences on the prediction model due to factors such as equipment characteristic drift, inaccurate meteorological parameters, environmental condition influence and the like are eliminated, and the accuracy of generated power prediction is improved.
The application example of the photovoltaic power station model output correction method is further provided, and reference may be made to fig. 4, and fig. 4 shows a calculation flow chart of the application example of the photovoltaic power station model output correction method provided by the application.
In this application example, the discretization calculation formula of the third object model is as follows:
yA-T(k)=[dA-T2*y(k-1)+dA-T1*y(k-2)+nA-T1*u(k-1)+nA-T2*u(k-2)+nA-T3*u(k-3)]/dA-T3。
the discretization calculation for the first object model is:
yA-MW(k)=[dA-MW2*y(k-1)+dA-MW1*y(k-2)+nA-MW1*u(k-1)+nA-MW2*u(k-2)+nA-MW3*u(k-3)]/dA-MW3。
the discretization calculation for the second object model is:
yT-MW(k)=[dT-MW2*y(k-1)+dT-MW1*y(k-2)+nT-MW1*u(k-1)+nT-MW2*u(k-2)+nT-MW3*u(k-3)]/dT-MW3
in the above formula: n isA-T1,nA-T2,nA-T3,dA-T1,dA-T2,dA-T3Parameters of a discrete model that is a third object model; n isT-MW1,nT-MW2,nT-MW3,dT-MW1,dT-MW2,dT-MW3Parameters of a discrete model that is a second object model; n isA-MW1,nA-MW2,nA-MW3,dA-MW1,dA-MW2,dA-MW3Parameters of a discrete model that is a first object model.
After correction, the prediction accuracy of the model is ensured. As shown in fig. 5, fig. 5 is a comparison graph of the predicted effect of the application example of the photovoltaic power station model output correction method provided by the present application, and it can be seen that the matching degree between the predicted power generation output by the model and the actual photovoltaic power generation power is very high.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that, in this application, "at least one" means one or more, "a plurality" means two or more. "and/or" is used to describe the association relationship of the associated object, indicating that there may be three relationships, for example, "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b and c may be single or plural.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (1)
1. A photovoltaic power station model output correction method is characterized by comprising the following steps:
pre-establishing a first object model of meteorological parameters-generated power, a second object model of photovoltaic backboard temperature-generated power and a third object model of meteorological parameters-photovoltaic backboard temperature of a photovoltaic power station based on a photovoltaic power station modeling method;
the first object model is established by taking meteorological parameters as control variables and power generation power as controlled variables according to the photovoltaic power station modeling method;
the second object model is established by taking the temperature of a photovoltaic back plate as a control variable and the generated power as a controlled variable by referring to the photovoltaic power station modeling method;
the third object model is established by taking the meteorological parameters as control variables and the photovoltaic backboard temperature as controlled variables according to the photovoltaic power station modeling method;
the generated power is active power or reactive power;
acquiring new meteorological data and power generation data corresponding to the photovoltaic power station;
inputting the new meteorological data into the first object model and the third object model respectively to obtain the predicted power generation output by the first object model and the predicted photovoltaic backboard temperature output by the third object model;
calculating a temperature deviation between the predicted photovoltaic backplane temperature and an actual photovoltaic backplane temperature in the power generation data;
inputting the temperature deviation into the second object model to obtain the power generation deviation output by the second object model;
adding the generated power deviation and the predicted generated power to obtain corrected predicted generated power;
the photovoltaic power station modeling method comprises the following steps:
s1, acquiring historical meteorological data from a meteorological system, and acquiring historical power generation data of the photovoltaic power station from a data acquisition monitoring System (SCADA) of the photovoltaic power station;
s2, establishing an identification data set and a sample data set of meteorological parameters corresponding to a power generation parameter according to the historical meteorological data and the historical power generation data, specifically comprising the steps of carrying out time synchronization processing on each meteorological data in the historical meteorological data and each power generation data in the historical power generation data, compiling into a uniform time scale, forming a data set with the same time label, and eliminating a part of the data set with the power generation power value of 0 at night; selecting a meteorological parameter and a power generation parameter from the data set to form an identification data set and a sample data set; the meteorological parameters specifically include: illumination intensity, ambient temperature, humidity and wind speed; the power generation parameters specifically comprise active power, reactive power and photovoltaic backboard temperature;
s3, inputting the identification data set into identification software, and identifying a plurality of object models which take the meteorological parameters as control variables, take the power generation parameters as controlled variables and take the model structures as second-order plus pure lag object models SOPDT structures;
s4, inputting the meteorological data in the sample data set into the object models one by one;
s5, calculating the deviation 2-norm of the power generation data output by each object model and the corresponding actual power generation data in the sample data set;
s6, selecting the object model with the minimum comprehensive deviation 2-norm as the object model of the photovoltaic power station;
discretizing an object model of the photovoltaic power plant by transformation calculation of a zero-order keeper;
storing the discretized object model of the photovoltaic power plant in a computer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910356832.XA CN110059441B (en) | 2019-04-29 | 2019-04-29 | Photovoltaic power station modeling method and photovoltaic power station model output correction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910356832.XA CN110059441B (en) | 2019-04-29 | 2019-04-29 | Photovoltaic power station modeling method and photovoltaic power station model output correction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110059441A CN110059441A (en) | 2019-07-26 |
CN110059441B true CN110059441B (en) | 2022-07-19 |
Family
ID=67321729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910356832.XA Active CN110059441B (en) | 2019-04-29 | 2019-04-29 | Photovoltaic power station modeling method and photovoltaic power station model output correction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110059441B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112835941A (en) * | 2020-12-31 | 2021-05-25 | 佛山职业技术学院 | Photovoltaic power station component model selection system and method thereof |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学(保定) | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
CN103593577A (en) * | 2013-11-25 | 2014-02-19 | 河海大学常州校区 | Photovoltaic power generation system output power modeling and estimation method |
CN105512775A (en) * | 2016-02-01 | 2016-04-20 | 北京交通大学 | Method for power prediction of photovoltaic power generation system |
CN107766990A (en) * | 2017-11-10 | 2018-03-06 | 河海大学 | A kind of Forecasting Methodology of photovoltaic power station power generation power |
CN108268963A (en) * | 2016-12-30 | 2018-07-10 | 中国电力科学研究院 | A kind of photovoltaic power short term prediction method for reviewing one's lessons by oneself positive test |
CN109558632A (en) * | 2018-10-26 | 2019-04-02 | 国网江西省电力有限公司电力科学研究院 | A kind of photovoltaic module parameter identification method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5439450B2 (en) * | 2011-09-13 | 2014-03-12 | 株式会社東芝 | Power generation prediction apparatus and method |
CN105184404B (en) * | 2015-08-31 | 2018-12-18 | 中国科学院广州能源研究所 | Output power classification forecasting system suitable for photovoltaic system Life cycle |
US11545830B2 (en) * | 2017-01-18 | 2023-01-03 | Board Of Regents, The University Of Texas System | Systems and methods of hierarchical forecasting of solar photovoltaic energy production |
-
2019
- 2019-04-29 CN CN201910356832.XA patent/CN110059441B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学(保定) | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
CN103593577A (en) * | 2013-11-25 | 2014-02-19 | 河海大学常州校区 | Photovoltaic power generation system output power modeling and estimation method |
CN105512775A (en) * | 2016-02-01 | 2016-04-20 | 北京交通大学 | Method for power prediction of photovoltaic power generation system |
CN108268963A (en) * | 2016-12-30 | 2018-07-10 | 中国电力科学研究院 | A kind of photovoltaic power short term prediction method for reviewing one's lessons by oneself positive test |
CN107766990A (en) * | 2017-11-10 | 2018-03-06 | 河海大学 | A kind of Forecasting Methodology of photovoltaic power station power generation power |
CN109558632A (en) * | 2018-10-26 | 2019-04-02 | 国网江西省电力有限公司电力科学研究院 | A kind of photovoltaic module parameter identification method |
Non-Patent Citations (1)
Title |
---|
A Power Prediction System for Photo-Voltaic Power Plants;Li XiaoFeng, et al.;《2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2)》;20181220;正文第1-6页 * |
Also Published As
Publication number | Publication date |
---|---|
CN110059441A (en) | 2019-07-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Andryushkevich et al. | Composition and application of power system digital twins based on ontological modeling | |
Kusiak et al. | Short-term prediction of wind farm power: A data mining approach | |
CN109002915B (en) | Photovoltaic power station short-term power prediction method based on Kmeans-GRA-Elman model | |
CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
CN111815035B (en) | Fusion form clustering and TCN-attribute short-term load prediction method | |
CN110929953A (en) | Photovoltaic power station ultra-short term output prediction method based on cluster analysis | |
CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
CN109376951B (en) | Photovoltaic probability prediction method | |
CN105404937A (en) | Photovoltaic plant short-term power prediction method and system | |
CN110705771B (en) | Method and device for predicting and optimizing generation power of new energy of regional power grid | |
CN116245033B (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
Anuradha et al. | Analysis of solar power generation forecasting using machine learning techniques | |
CN113052389A (en) | Distributed photovoltaic power station ultra-short-term power prediction method and system based on multiple tasks | |
CN110059441B (en) | Photovoltaic power station modeling method and photovoltaic power station model output correction method | |
Huang et al. | Parameter identification for photovoltaic models using an improved learning search algorithm | |
CN108198268A (en) | A kind of production equipment data scaling method | |
Jimenez et al. | The role of artificial intelligence in Latin Americas energy transition | |
CN113240217A (en) | Photovoltaic power generation prediction method and device based on integrated prediction model | |
KR20190071174A (en) | Method and system for short-term wind speed prediction based on pressure data | |
CN112508278A (en) | Multi-connected system load prediction method based on evidence regression multi-model | |
CN113361737A (en) | Abnormity early warning method and system for photovoltaic module | |
CN113408924B (en) | Planning method of park comprehensive energy system based on statistical machine learning | |
Salgado et al. | Hybrid fuzzy clustering neural networks to wind power generation forecasting | |
CN114638396A (en) | Photovoltaic power prediction method and system based on neural network instantiation | |
CN112215383A (en) | Distributed photovoltaic power generation power prediction method and system |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |