CN114915261A - Fault monitoring method and device for photovoltaic power station - Google Patents
Fault monitoring method and device for photovoltaic power station Download PDFInfo
- Publication number
- CN114915261A CN114915261A CN202210538164.4A CN202210538164A CN114915261A CN 114915261 A CN114915261 A CN 114915261A CN 202210538164 A CN202210538164 A CN 202210538164A CN 114915261 A CN114915261 A CN 114915261A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic power
- power station
- power
- data
- photovoltaic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000012806 monitoring device Methods 0.000 claims abstract description 9
- 230000014509 gene expression Effects 0.000 claims description 24
- 238000011161 development Methods 0.000 claims description 20
- 238000009825 accumulation Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000005316 response function Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 6
- 238000010248 power generation Methods 0.000 description 24
- 238000005070 sampling Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a fault monitoring method and a fault monitoring device for a photovoltaic power station, wherein the method comprises the following steps: acquiring output power data of a photovoltaic power station; obtaining a historical time sequence of the photovoltaic power station according to the output power data; establishing a grey prediction model according to the historical time sequence; obtaining a prediction power fitting data set of the photovoltaic power station according to the grey prediction model; processing the predicted power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a predicted power optimal fitting value of the photovoltaic power station; and judging whether the photovoltaic power station fails according to the predicted power optimal fitting value of the photovoltaic power station. The method and the device can provide accurate information reference for power grid dispatching to ensure the rationality of the power grid dispatching, thereby reducing the influence of photovoltaic access on the power grid, improving the stability and the safety of a power system and improving the quality of electric energy.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation, in particular to a fault monitoring method and a fault monitoring device for a photovoltaic power station.
Background
With the use of photovoltaic power generation in a power grid becoming more and more extensive, the influence of the stability of the photovoltaic power generation on the safety of the power grid is also paid more and more attention and researched, and particularly, because the power generation characteristics of a photovoltaic panel are influenced by multiple factors such as environment, temperature, illumination intensity and the like, the output power of a photovoltaic power station often shows larger fluctuation and randomness to cause frequent faults of the photovoltaic power station, so how to monitor the photovoltaic power station in real time and timely give early warning before the photovoltaic power station breaks down to ensure the power supply quality of the power grid is the key point of the research.
Disclosure of Invention
The invention aims to solve the technical problems and provides a fault monitoring method for a photovoltaic power station, which can provide accurate information reference for power grid dispatching to ensure the rationality of the power grid dispatching, thereby reducing the influence of photovoltaic access on the power grid, improving the stability and safety of a power system and improving the quality of electric energy.
The technical scheme adopted by the invention is as follows:
a fault monitoring method of a photovoltaic power station comprises the following steps: acquiring output power data of a photovoltaic power station; obtaining a historical time sequence of the photovoltaic power station according to the output power data; establishing a grey prediction model according to the historical time sequence; obtaining a prediction power fitting data set of the photovoltaic power station according to the grey prediction model; processing the predicted power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a predicted power optimal fitting value of the photovoltaic power station; and judging whether the photovoltaic power station fails or not according to the predicted power optimal fitting value of the photovoltaic power station.
According to an embodiment of the present invention, the determining whether the photovoltaic power station fails according to the best fit value of the predicted power of the photovoltaic power station specifically includes the following steps: calculating the relative residual error index of the output power of the photovoltaic power station according to the optimal fitting value of the predicted power; acquiring an output power reference index of the photovoltaic power station; judging whether the difference value of the output power relative residual error index and the output power reference index exceeds a prediction threshold value; and if so, judging that the photovoltaic power station fails.
According to one embodiment of the invention, the output power data is power data of the grid-connected gateway of the photovoltaic power station.
According to an embodiment of the present invention, the expression of the historical time series is:
X (0) ＝(x (0) (1),x (0) (2),...,x (0) (n))。
according to an embodiment of the present invention, the establishing a gray prediction model according to the historical time series specifically includes the following steps: generating a generation sequence according to the historical time sequence by adopting a primary accumulation algorithm; obtaining an adjacent mean value sequence according to the generated sequence; constructing a data matrix and a data vector according to the adjacent mean value sequence; calculating a development coefficient and a gray effect quantity required for establishing the gray prediction model according to the data matrix and the data vector; and determining the gray prediction model according to the development coefficient and the gray acting quantity.
According to an embodiment of the present invention, wherein,
the expression of the generated sequence is as follows:
X (1) ＝(x (1) (1),x (1) (2),...,x (1) (n))
wherein x is (1) (1)＝x (0) (1)，x (1) (2)＝x (0) (1)+x (0) (2)，...，x (1) (n)＝x (0) (n-1)+x (0) (n)；
The expression of the adjacent mean sequence is as follows:
Z (1) (k)＝(x (1) (k)+x (1) (k+1))/2
wherein k is 2, 3.
According to an embodiment of the present invention, the obtaining of the predicted power fitting dataset of the photovoltaic power station according to the gray prediction model specifically includes the following steps: calculating the predicted power data of the photovoltaic power station according to the time response function of the grey prediction model; processing the predicted power data of the photovoltaic power station by adopting a primary accumulation and subtraction algorithm to obtain predicted power fitting data of the photovoltaic power station; and forming a predicted power fitting data set of the photovoltaic power station according to the predicted power fitting data of the photovoltaic power station.
According to an embodiment of the present invention, wherein,
the specific expression of the time response function of the gray prediction model is as follows:
the predicted power fitting data of the photovoltaic power station specifically comprises the following steps:
a fault monitoring device for a photovoltaic power plant, comprising: the acquisition module is used for acquiring output power data of the photovoltaic power station; the first data processing module is used for obtaining a historical time sequence of the photovoltaic power station according to the output power data; the modeling module is used for establishing a gray prediction model according to the historical time sequence; the second data processing module is used for obtaining a predicted power fitting data set of the photovoltaic power station according to the grey prediction model; a third data processing module for processing the predicted power fit data set using an ensemble Kalman filtering algorithm to obtain a predicted power best fit value for the photovoltaic power plant; and the fault judgment module is used for judging whether the photovoltaic power station has a fault according to the optimal fitting value of the predicted power of the photovoltaic power station.
According to an embodiment of the present invention, the fault determining module is configured to calculate a relative residual indicator of output power of the photovoltaic power station according to the best fit value of the predicted power, obtain a reference indicator of output power of the photovoltaic power station, determine whether a difference between the relative residual indicator of output power and the reference indicator of output power exceeds a prediction threshold, and if so, determine that the photovoltaic power station has a fault.
The invention has the following beneficial effects:
according to the invention, by predicting the output power of the photovoltaic power station, accurate information reference can be provided for power grid dispatching, so that the rationality of the power grid dispatching is ensured, the influence of photovoltaic access on the power grid can be reduced, in addition, the stability and the safety of a power system can be improved, and the power quality can be improved.
Drawings
FIG. 1 is a flow chart of a method of fault monitoring of a photovoltaic power plant in accordance with an embodiment of the present invention;
FIG. 2 is a detailed flow chart of a method for monitoring faults of a photovoltaic power plant according to an embodiment of the present invention;
fig. 3(a) is a line graph of predicted power generation and actual power generation of a photovoltaic power plant in the event of a fault according to an embodiment of the present invention;
fig. 3(b) is a line graph showing an absolute difference, a relative difference, and a threshold line between the predicted power generation amount and the actual power generation amount at the time of a failure of the photovoltaic power plant according to one embodiment of the present invention;
fig. 4 is a block diagram schematically illustrating a fault monitoring apparatus of a photovoltaic power plant 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.
Fig. 1 is a flowchart of a method for monitoring a fault of a photovoltaic power plant according to an embodiment of the present invention.
As shown in fig. 1, the method for monitoring faults of a photovoltaic power station according to the embodiment of the present invention includes the following steps:
and S1, acquiring output power data of the photovoltaic power station.
Specifically, the output power data of the photovoltaic power station can be collected through the intelligent electric meter. The intelligent electric meter can be a three-phase intelligent electric meter, and the output power data of the photovoltaic power station can be power data of a grid-connected gateway of the photovoltaic power station, namely power data input to a power grid by the photovoltaic power station.
And S2, obtaining the historical time sequence of the photovoltaic power station according to the output power data.
Specifically, the historical time sequence of the photovoltaic power station can be formed according to the power data of the grid-connected gateway of the photovoltaic power station, namely the power data input to the power grid by the photovoltaic power station. The expression of the historical time sequence of the photovoltaic power station can be as follows:
X (0) ＝(x (0) (1),x (0) (2),...,x (0) (n))。
and S3, establishing a gray prediction model according to the historical time sequence.
Specifically, a generation sequence can be generated according to a historical time sequence by adopting a one-time accumulation algorithm, an adjacent mean sequence can be obtained according to the generation sequence, a data matrix and a data vector can be further constructed according to the adjacent mean sequence, then a development coefficient and a gray acting amount required by the gray prediction model can be calculated according to the data matrix and the data vector, and finally the gray prediction model can be determined according to the development coefficient and the gray acting amount.
In one embodiment of the present invention, the sequence generation rule of the one-time accumulation algorithm is as follows:
x (1) (1)＝x (0) (1)，
x (1) (2)＝x (0) (1)+x (0) (2)，
，......，
x (1) (n)＝x (0) (n-1)+x (0) (n)。
further, a generation sequence may be generated according to the sequence generation rule of the one-time accumulation algorithm, and an expression of the generation sequence may be:
X (1) ＝(x (1) (1),x (1) (2),...,x (1) (n))
wherein x is (1) (1)＝x (0) (1)，x (1) (2)＝x (0) (1)+x (0) (2)，...，x (1) (n)＝x (0) (n-1)+x (0) (n)。
Further, the sequence X may be generated as described above (1) Performing adjacent mean generation to obtain an adjacent mean sequence, and the expression of the adjacent mean sequence may be:
Z (1) (k)＝(x (1) (k)+x (1) (k+1))/2
wherein k is 2, 3.
Further, the above-mentioned neighbor mean sequence Z can be used (1) (k) And constructing a data matrix B and a data vector Y, and calculating a development coefficient a and a gray action amount B required for establishing a gray prediction model according to the data matrix B and the data vector Y.
The specific expression of the data matrix B is as follows:
the specific expression of the data vector Y is:
the specific expressions of the development coefficient a and the gray effect amount b are as follows:
further, a gray prediction model, specifically a GM (1, 1) model, can be determined based on the above-described coefficient of development a and the amount of gray contribution b.
And S4, obtaining a prediction power fitting data set of the photovoltaic power station according to the grey prediction model.
Specifically, the predicted power data of the photovoltaic power station can be calculated according to a time response function of the grey prediction model, the predicted power data of the photovoltaic power station can be processed by adopting a one-time accumulation and subtraction algorithm to obtain predicted power fitting data of the photovoltaic power station, and then a predicted power fitting data set of the photovoltaic power station can be formed according to the predicted power fitting data of the photovoltaic power station.
In one embodiment of the present invention, the specific expression of the time response function of the gray prediction model is:
furthermore, the predicted power data of the photovoltaic power station, namely the output power value of the photovoltaic power station at the next moment, can be calculated according to the time response function.
In one embodiment of the present invention, the sequence generation rule of the one-time subtraction algorithm is as follows:
x (0) (1)＝x (1) (1)，
x (0) (2)＝x (1) (2)-x (1) (1)，
，......，
x (0) (n)＝x (1) (n)-x (1) (n- 1 )。
furthermore, the predicted power data of the photovoltaic power station can be processed according to the sequence generation rule of the primary accumulation and subtraction algorithm, namely the output power value of the photovoltaic power station at the next moment
So as to obtain the predicted power fitting data of the photovoltaic power station, namely the fitting value of the output power value of the photovoltaic power station at the next moment
And the fitting value
The specific expression of (A) is as follows:
in conclusion, the predicted power fitting data of a plurality of photovoltaic power stations, namely the output power fitting value of the photovoltaic power station at the next moment, can be generated by calling the gray prediction model for a plurality of times
For example, predicted power fit data for q photovoltaic power plants may be generated, i.e. the output power fit values for the photovoltaic power plants at the next moment in time
And fitting the predicted power fitting data of the q photovoltaic power stations, namely the output power fitting value of the photovoltaic power station at the next moment
Make up photovoltaic electricityThe predicted power of the station is fitted to the data set.
And S5, processing the predicted power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a predicted power optimal fitting value of the photovoltaic power station.
Specifically, the prediction power fitting data set can be processed by adopting an ensemble Kalman filtering algorithm to obtain a prediction power optimal fitting value of the photovoltaic power station at the next moment, so that the nonlinear characteristic of the time sequence of the prediction power fitting data of the photovoltaic power station can be adapted through the ensemble Kalman filtering algorithm, and the sampling noise and the background noise contained in the photovoltaic power station can be filtered.
More specifically, the covariance P of the predicted state error of the photovoltaic plant at the current time, e.g. k, may be first determined k a Covariance between predicted state error and observed error P k xy Observation error covariance P k y Then, an ensemble kalman filtering algorithm can be adopted to obtain a predicted power best-fit value of the photovoltaic power station at the next moment, for example, the moment k + 1.
Wherein the predicted state error covariance P of the photovoltaic plant at the current moment, e.g. at moment k k a Covariance between predicted state error and observed error P k xy Observation error covariance P k y The calculation formula is as follows:
wherein,
in order to predict the value of the state,
for the observed estimates, Q, R are the covariance of the model noise and the covariance of the metrology noise, respectively, and are both zero mean white noise.
And S6, judging whether the photovoltaic power station fails according to the predicted power optimal fitting value of the photovoltaic power station.
Specifically, the output power relative residual index of the photovoltaic power station can be calculated according to the optimal fitting value of the predicted power, the output power reference index of the photovoltaic power station can be obtained, whether the difference value of the output power relative residual index and the output power reference index exceeds a prediction threshold value or not can be judged, and if yes, the photovoltaic power station is judged to be in fault.
More specifically, the following formula can be used to calculate the output power relative residual indicator of the photovoltaic power plant:
wherein, delta (k +1) represents the output power relative residual index of the photovoltaic power station, x (0) (k +1) represents the photovoltaic power station outputting power data at the moment k +1,
and predicting the optimal power fitting value of the photovoltaic power station at the k +1 moment.
More specifically, the output power reference index δ of the photovoltaic plant ref The method can be used for obtaining the relative residual error index of the output power when the different types of faults occur in the photovoltaic power station and the output power when the photovoltaic power station normally operates.
Further, the relative residual error index delta (k +1) of the output power of the photovoltaic power station and the reference index delta of the output power of the photovoltaic power station can be calculated ref The difference delta between the two indexes, and can judge the relative residual error index delta (k +1) of the output power and the reference index delta of the output power ref Whether the difference Δ δ between exceeds the prediction threshold ± δ th Wherein, if the output power is relative to the residual indicator delta (k +1) and the output power reference indicator delta ref The difference Δ δ between exceeds the prediction threshold ± δ th And then the photovoltaic power station can be judged to have faults.
The following will describe a specific flow of the method for monitoring faults of a photovoltaic power station according to an embodiment of the present invention with reference to fig. 2.
As shown in fig. 2, a specific flow of the method for monitoring faults of a photovoltaic power station according to the embodiment of the present invention is as follows:
s1, acquiring output power data of the photovoltaic power station;
s2, obtaining a historical time sequence of the photovoltaic power station according to the output power data;
s301, performing 1-AGO accumulation, namely generating a generation sequence according to the historical time sequence by adopting a primary accumulation algorithm;
s302, calculating a development coefficient a and a gray acting quantity B, namely obtaining an adjacent mean sequence according to the generated sequence, further constructing a data matrix B and a data vector Y according to the adjacent mean sequence, and then calculating the development coefficient a and the gray acting quantity B required by establishing a gray prediction model according to the data matrix B and the data vector Y;
s303, determining a gray prediction model GM (1, 1), namely determining the gray prediction model as a GM (1, 1) model according to the development coefficient a and the gray acting quantity b;
s401, calculating predicted power fitting data of the photovoltaic power station, specifically calculating the predicted power data of the photovoltaic power station according to a time response function of a gray prediction model, and processing the predicted power data of the photovoltaic power station by adopting a one-time accumulation and subtraction algorithm to obtain the predicted power fitting data of the photovoltaic power station;
s402, forming a predicted power fitting data set of the photovoltaic power stations, specifically, generating predicted power fitting data of the photovoltaic power stations by calling a gray prediction model for multiple times to form the predicted power fitting data set of the photovoltaic power stations;
s403, judging whether the number of elements in the predicted power fitting data set is q, if not, returning to the step S401, and if so, executing the step S5;
s5, processing the prediction power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a prediction power optimal fitting value of the photovoltaic power station;
s601, calculating a relative residual error index delta (k +1) of the output power of the photovoltaic power station;
s602, calculating an output power relative residual indicator delta (k +1) and an output power reference indicator delta ref The difference Δ δ therebetween;
s603, judging whether the difference delta exceeds a prediction threshold +/-δ th If not, returning to execute the step S602; if yes, go to step S604;
and S604, judging that the photovoltaic power station has faults.
The invention has the following beneficial effects:
according to the invention, by predicting the output power of the photovoltaic power station, accurate information reference can be provided for power grid dispatching, so that the rationality of the power grid dispatching is ensured, the influence of photovoltaic access on the power grid can be reduced, in addition, the stability and the safety of a power system can be improved, and the power quality can be improved.
The application effect of the fault monitoring method for the photovoltaic power station according to the embodiment of the invention will be specifically described below by taking a photovoltaic power station with installed capacity of 1MW as an example.
In an embodiment of the present invention, referring to fig. 3(a), historical output power data of a photovoltaic power station with an installed capacity of 1MW for three days, that is, historical first-day, historical second-day, and historical third-day power generation amount, may be obtained first, and a historical time series may be formed according to the historical output power data of the first two days, that is, the historical first-day and historical second-day power generation amount, so as to establish a corresponding gray prediction model, so as to obtain predicted power data of the third day, that is, predicted power generation amount of the third day. And setting a fault on the third day to reduce the power generation amount of the photovoltaic power station.
Further, a reference can be extracted from the failure diagnosis expert system as a prediction threshold line according to historical similar day data and the weather, environment and illumination conditions of the day, and a relative difference between the actual power generation amount and the predicted power generation amount of the third day, namely a relative residual indicator of the output power of the photovoltaic power station, and an absolute difference between the actual power generation amount and the predicted power generation amount of the third day, namely a reference indicator of the output power of the photovoltaic power station, can be calculated, as shown in fig. 3(b), so that it can be judged that the photovoltaic power station fails in the sampling point 133-157 period. Therefore, the method for monitoring the faults of the photovoltaic power station can accurately predict whether the photovoltaic power station has faults or not.
Corresponding to the fault monitoring method of the photovoltaic power station in the embodiment, the invention further provides a fault monitoring device of the photovoltaic power station.
As shown in fig. 4, the fault monitoring apparatus of the photovoltaic power plant according to the embodiment of the present invention includes an obtaining module 10, a first data processing module 20, a modeling module 30, a second data processing module 40, a third data processing module 50, and a fault determining module 60. The acquisition module 10 is used for acquiring output power data of the photovoltaic power station; the first data processing module 20 is configured to obtain a historical time sequence of the photovoltaic power station according to the output power data; the modeling module 30 is used for establishing a grey prediction model according to the historical time sequence; the second data processing module 40 is used for obtaining a prediction power fitting data set of the photovoltaic power station according to the grey prediction model; the third data processing module 50 is configured to process the predicted power fitting data set by using an ensemble kalman filter algorithm to obtain a predicted power best-fit value of the photovoltaic power station; the fault judgment module 60 is configured to judge whether the photovoltaic power station fails according to the best-fit value of the predicted power of the photovoltaic power station.
In an embodiment of the present invention, the obtaining module 10 may collect output power data of the photovoltaic power station through a smart meter. The intelligent electric meter can be a three-phase intelligent electric meter, and the output power data of the photovoltaic power station can be power data of a grid-connected gateway of the photovoltaic power station, namely power data input to a power grid by the photovoltaic power station.
In an embodiment of the present invention, the first data processing module 20 may be specifically configured to form a historical time sequence of the photovoltaic power plant according to power data of a grid-connected gateway of the photovoltaic power plant, that is, power data input by the photovoltaic power plant to a power grid.
The expression of the historical time sequence of the photovoltaic power station can be as follows:
X (0) ＝(x (0) (1),x (0) (2),...,x (0) (n))。
in an embodiment of the present invention, the modeling module 30 may specifically adopt a one-time accumulation algorithm to generate a generation sequence according to the historical time sequence, and may obtain an adjacent mean sequence according to the generation sequence, and further may construct a data matrix and a data vector according to the adjacent mean sequence, and then may calculate a development coefficient and a gray acting amount required for establishing a gray prediction model according to the data matrix and the data vector, and finally may determine the gray prediction model according to the development coefficient and the gray acting amount.
In one embodiment of the present invention, the sequence generation rule of the one-time accumulation algorithm is as follows:
x (1) (1)＝x (0) (1)，
x (1) (2)＝x (0) (1)+x (0) (2)，
，......，
x (1) (n)＝x (0) (n-1)+x (0) (n)。
further, a generation sequence may be generated according to the sequence generation rule of the one-time accumulation algorithm, and an expression of the generation sequence may be:
X (1) ＝(x (1) (1),x (1) (2),...,x (1) (n))
wherein x is (1) (1)＝x (0) (1)，x (1) (2)＝x (0) (1)+x (0) (2)，...，x (1) (n)＝x (0) (n-1)+x (0) (n)。
Further, the sequence X may be generated as described above (1) Performing adjacent mean generation to obtain an adjacent mean sequence, and the expression of the adjacent mean sequence may be:
Z (1) (k)＝(x (1) (k)+x (1) (k+1))/2
wherein k is 2, 3.
Further, the above-mentioned neighbor mean sequence Z can be used (1) (k) And constructing a data matrix B and a data vector Y, and calculating a development coefficient a and a gray action amount B required for establishing a gray prediction model according to the data matrix B and the data vector Y.
The specific expression of the data matrix B is as follows:
the specific expression of the data vector Y is:
the specific expressions of the development coefficient a and the gray effect amount b are as follows:
further, a gray prediction model, specifically a GM (1, 1) model, can be determined based on the above-described coefficient of development a and the amount of gray contribution b.
In an embodiment of the present invention, the second data processing module 40 may specifically calculate the predicted power data of the photovoltaic power station according to a time response function of the gray prediction model, may process the predicted power data of the photovoltaic power station by using a first-order accumulation and subtraction algorithm to obtain predicted power fitting data of the photovoltaic power station, and may then form a predicted power fitting data set of the photovoltaic power station according to the predicted power fitting data of the photovoltaic power station.
In one embodiment of the present invention, the specific expression of the time response function of the gray prediction model is:
furthermore, the predicted power data of the photovoltaic power station, namely the output power value of the photovoltaic power station at the next moment, can be calculated according to the time response function.
In one embodiment of the present invention, the sequence generation rule of the one-time subtraction algorithm is as follows:
x (0) (1)＝x (1) (1)，
x (0) (2)＝x (1) (2)-x (1) (1)，
，......，
x (0) (n)＝x (1) (n)-x (1) (n-1)。
further, photovoltaic electricity can be processed according to the sequence generation rule of the one-time subtraction algorithmPredicted power data of a station, i.e. the output power value of a photovoltaic power station at the next moment
So as to obtain the predicted power fitting data of the photovoltaic power station, namely the output power value of the photovoltaic power station at the next moment
Fitting value of
And the fitting value
The specific expression of (A) is as follows:
in conclusion, the predicted power fitting data of a plurality of photovoltaic power stations, namely the output power fitting value of the photovoltaic power station at the next moment, can be generated by calling the gray prediction model for a plurality of times
For example, predicted power fitting data of q photovoltaic power stations, i.e. output power fitting values of photovoltaic power stations at the next moment in time, are generated
And fitting the predicted power fitting data of the q photovoltaic power stations, namely the output power fitting value of the photovoltaic power station at the next moment
And forming a prediction power fitting data set of the photovoltaic power station.
In an embodiment of the present invention, the third data processing module 50 may specifically adopt an ensemble kalman filtering algorithm to process the predicted power fitting data set to obtain a predicted power best-fit value of the photovoltaic power station at the next time, so that the time-series nonlinear characteristic of the predicted power fitting data of the photovoltaic power station can be adapted by the ensemble kalman filtering algorithm, and thus, the sampling noise and the background noise contained in the time-series nonlinear characteristic can be filtered out.
More specifically, the covariance P of the predicted state error of the photovoltaic plant at the current time, e.g. k, may be first determined k a Covariance between predicted state error and observed error P k xy Observation error covariance P k y Then, an ensemble kalman filtering algorithm can be adopted to obtain a predicted power best-fit value of the photovoltaic power station at the next moment, for example, the moment k + 1.
Wherein the predicted state error covariance P of the photovoltaic plant at the current moment, e.g. at moment k k a Covariance between predicted state error and observed error P k xy Observation error covariance P k y The calculation formula is as follows:
wherein,
in order to predict the value of the state,
for the observed estimates, Q, R are the covariance of the model noise and the covariance of the metrology noise, respectively, and are both zero mean white noise.
In an embodiment of the present invention, the fault determining module 60 may be specifically configured to calculate a relative residual indicator of the output power of the photovoltaic power station according to the best fit value of the predicted power, obtain a reference indicator of the output power of the photovoltaic power station, and then determine whether a difference between the relative residual indicator of the output power and the reference indicator of the output power exceeds a prediction threshold, if so, determine that the photovoltaic power station has a fault.
More specifically, the following formula can be used to calculate the output power relative residual indicator of the photovoltaic power plant:
wherein, delta (k +1) represents the output power relative residual index of the photovoltaic power station, x (0) (k +1) represents the photovoltaic power station outputting power data at the moment k +1,
and predicting the optimal power fitting value of the photovoltaic power station at the k +1 moment. .
More specifically, the output power reference index δ of the photovoltaic plant ref The method can be used for obtaining the relative residual error index of the output power when the different types of faults occur in the photovoltaic power station and the output power when the photovoltaic power station normally operates.
Further, the relative residual error index delta (k +1) of the output power of the photovoltaic power station and the reference index delta of the output power of the photovoltaic power station can be calculated ref The difference delta between the two indexes can be judged, and the relative residual error index delta (k +1) of the output power and the reference index delta of the output power can be judged ref Whether the difference Δ δ between exceeds the prediction threshold ± δ th Wherein, if the output power is relative to the residual index delta (k +1) and the output power reference index delta ref The difference Δ δ between exceeds the prediction threshold ± δ th And then the photovoltaic power station can be judged to have faults.
The specific operation of the fault monitoring device for a photovoltaic power plant according to the embodiment of the present invention will be described with reference to fig. 2.
As shown in fig. 2, the specific working process of the fault monitoring device of the photovoltaic power station according to the embodiment of the present invention is as follows:
s1, acquiring output power data of the photovoltaic power station;
s2, obtaining a historical time sequence of the photovoltaic power station according to the output power data;
s301, performing 1-AGO accumulation, namely generating a generation sequence according to the historical time sequence by adopting a primary accumulation algorithm;
s302, calculating a development coefficient a and a gray acting quantity B, namely obtaining an adjacent mean sequence according to the generated sequence, further constructing a data matrix B and a data vector Y according to the adjacent mean sequence, and then calculating the development coefficient a and the gray acting quantity B required by establishing a gray prediction model according to the data matrix B and the data vector Y;
s303, determining a gray prediction model GM (1, 1), namely determining the gray prediction model as a GM (1, 1) model according to the development coefficient a and the gray acting quantity b;
s401, calculating predicted power fitting data of the photovoltaic power station, specifically calculating the predicted power data of the photovoltaic power station according to a time response function of a gray prediction model, and processing the predicted power data of the photovoltaic power station by adopting a one-time accumulation and subtraction algorithm to obtain the predicted power fitting data of the photovoltaic power station;
s402, forming a predicted power fitting data set of the photovoltaic power stations, specifically, generating predicted power fitting data of the photovoltaic power stations by calling a gray prediction model for multiple times to form the predicted power fitting data set of the photovoltaic power stations;
s403, judging whether the number of elements in the predicted power fitting data set is q, if not, returning to the step S401, and if so, executing the step S5;
s5, processing the predicted power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a predicted power optimal fitting value of the photovoltaic power station;
s601, calculating a relative residual error index delta (k +1) of the output power of the photovoltaic power station;
s602, calculating an output power relative residual indicator delta (k +1) and an output power reference indicator delta ref The difference Δ δ therebetween;
s603, judging whether the difference value delta exceeds the prediction threshold value +/-delta th If not, returning to execute the step S602; if yes, go to step S604;
and S604, judging that the photovoltaic power station has faults.
The invention has the following beneficial effects:
according to the invention, by predicting the output power of the photovoltaic power station, accurate information reference can be provided for power grid dispatching, so that the rationality of the power grid dispatching is ensured, the influence of photovoltaic access on the power grid can be reduced, in addition, the stability and the safety of a power system can be improved, and the power quality can be improved.
The application effect of the fault monitoring device of the photovoltaic power station according to the embodiment of the present invention will be specifically described below by taking a photovoltaic power station with an installed capacity of 1MW as an example.
In an embodiment of the present invention, referring to fig. 3(a), historical output power data of a photovoltaic power station with an installed capacity of 1MW for three days, that is, historical first-day, historical second-day, and historical third-day power generation amount, may be obtained first, and a historical time series may be formed according to the historical output power data of the first two days, that is, the historical first-day and historical second-day power generation amount, so as to establish a corresponding gray prediction model, so as to obtain predicted power data of the third day, that is, predicted power generation amount of the third day. And setting a fault on the third day to reduce the power generation amount of the photovoltaic power station.
Further, a reference can be extracted from the failure diagnosis expert system as a prediction threshold line according to historical similar day data and the weather, environment and illumination conditions of the day, and a relative difference between the actual power generation amount and the predicted power generation amount of the third day, namely a relative residual indicator of the output power of the photovoltaic power station, and an absolute difference between the actual power generation amount and the predicted power generation amount of the third day, namely a reference indicator of the output power of the photovoltaic power station, can be calculated, as shown in fig. 3(b), so that it can be judged that the photovoltaic power station fails in the sampling point 133-157 period. Therefore, the fault monitoring device of the photovoltaic power station can accurately predict whether the photovoltaic power station has faults or not.
In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The meaning of "plurality" is two or more unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Claims (10)
1. A fault monitoring method of a photovoltaic power station is characterized by comprising the following steps:
acquiring output power data of a photovoltaic power station;
obtaining a historical time sequence of the photovoltaic power station according to the output power data;
establishing a grey prediction model according to the historical time sequence;
obtaining a prediction power fitting data set of the photovoltaic power station according to the grey prediction model;
processing the predicted power fitting data set by adopting an ensemble Kalman filtering algorithm to obtain a predicted power optimal fitting value of the photovoltaic power station;
and judging whether the photovoltaic power station fails or not according to the predicted power optimal fitting value of the photovoltaic power station.
2. The method for monitoring the faults of the photovoltaic power station as claimed in claim 1, wherein the step of judging whether the photovoltaic power station has faults or not according to the best fit value of the predicted power of the photovoltaic power station specifically comprises the following steps:
calculating the relative residual error index of the output power of the photovoltaic power station according to the optimal fitting value of the predicted power;
acquiring an output power reference index of the photovoltaic power station;
judging whether the difference value of the output power relative residual error index and the output power reference index exceeds a prediction threshold value;
and if so, judging that the photovoltaic power station fails.
3. The method of claim 1 wherein the output power data is power data from a grid-tie gateway of the photovoltaic power plant.
4. The method of monitoring faults in a photovoltaic plant of claim 1 wherein the expression of the historical time series is:
X (0) ＝(x (0) (1),x (0) (2),...,x (0) (n))。
5. the method for monitoring faults of a photovoltaic power plant according to claim 1, wherein the establishing of the grey prediction model according to the historical time series specifically comprises the following steps:
generating a generation sequence according to the historical time sequence by adopting a primary accumulation algorithm;
obtaining an adjacent mean value sequence according to the generated sequence;
constructing a data matrix and a data vector according to the adjacent mean value sequence;
calculating a development coefficient and a gray effect quantity required for building the gray prediction model according to the data matrix and the data vector;
and determining the gray prediction model according to the development coefficient and the gray acting quantity.
6. The method for fault monitoring of a photovoltaic power plant of claim 5 wherein,
the expression of the generated sequence is as follows:
X (1) ＝(x (1) (1),x (1) (2),...,x (1) (n))
wherein x is (1) (1)＝x (0) (1)，x (1) (2)＝x (0) (1)+x (0) (2)，...，x (1) (n)＝x (0) (n-1)+x (0) (n)；
The expression of the adjacent mean sequence is as follows:
Z (1) (k)＝(x (1) (k)+x (1) (k+1))/2
wherein k is 2, 3.
7. The method for monitoring faults of a photovoltaic power plant of claim 1, wherein the obtaining of the predicted power fitting dataset of the photovoltaic power plant from the grey prediction model specifically comprises the steps of:
calculating the predicted power data of the photovoltaic power station according to the time response function of the grey prediction model;
processing the predicted power data of the photovoltaic power station by adopting a primary accumulation and subtraction algorithm to obtain predicted power fitting data of the photovoltaic power station;
and forming a predicted power fitting data set of the photovoltaic power station according to the predicted power fitting data of the photovoltaic power station.
8. The method of monitoring faults of a photovoltaic power plant of claim 7 wherein,
the specific expression of the time response function of the gray prediction model is as follows:
the predicted power fitting data of the photovoltaic power station specifically comprises the following steps:
9. a fault monitoring device of a photovoltaic power station, comprising:
the acquisition module is used for acquiring output power data of the photovoltaic power station;
the first data processing module is used for obtaining a historical time sequence of the photovoltaic power station according to the output power data;
the modeling module is used for establishing a grey prediction model according to the historical time sequence;
the second data processing module is used for obtaining a predicted power fitting data set of the photovoltaic power station according to the grey prediction model;
a third data processing module for processing the predicted power fit data set using an ensemble Kalman filtering algorithm to obtain a predicted power best fit value for the photovoltaic power plant;
and the fault judgment module is used for judging whether the photovoltaic power station has a fault according to the optimal fitting value of the predicted power of the photovoltaic power station.
10. The device for monitoring the faults of the photovoltaic power stations as claimed in claim 9, wherein the fault judging module is configured to calculate a relative residual index of the output power of the photovoltaic power station according to the best fit value of the predicted power, obtain a reference index of the output power of the photovoltaic power station, judge whether a difference value between the relative residual index of the output power and the reference index of the output power exceeds a prediction threshold, and if so, judge that the photovoltaic power station has a fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210538164.4A CN114915261A (en) | 2022-05-17 | 2022-05-17 | Fault monitoring method and device for photovoltaic power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210538164.4A CN114915261A (en) | 2022-05-17 | 2022-05-17 | Fault monitoring method and device for photovoltaic power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114915261A true CN114915261A (en) | 2022-08-16 |
Family
ID=82768834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210538164.4A Pending CN114915261A (en) | 2022-05-17 | 2022-05-17 | Fault monitoring method and device for photovoltaic power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114915261A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116418293A (en) * | 2023-04-21 | 2023-07-11 | 攀枝花中电光伏发电有限公司 | Photovoltaic power station intelligent diagnosis system based on big data of Internet of things |
| CN118040910A (en) * | 2024-04-12 | 2024-05-14 | 国网山东省电力公司菏泽供电公司 | Online monitoring method for energy storage abnormal state of micro-grid in remote area |
| CN118677035A (en) * | 2024-08-26 | 2024-09-20 | 国网浙江省电力有限公司诸暨市供电公司 | Power regulation and control method and system for photovoltaic power station |
-
2022
- 2022-05-17 CN CN202210538164.4A patent/CN114915261A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116418293A (en) * | 2023-04-21 | 2023-07-11 | 攀枝花中电光伏发电有限公司 | Photovoltaic power station intelligent diagnosis system based on big data of Internet of things |
| CN116418293B (en) * | 2023-04-21 | 2024-02-27 | 攀枝花中电光伏发电有限公司 | Photovoltaic power station intelligent diagnosis system based on big data of Internet of things |
| CN118040910A (en) * | 2024-04-12 | 2024-05-14 | 国网山东省电力公司菏泽供电公司 | Online monitoring method for energy storage abnormal state of micro-grid in remote area |
| CN118677035A (en) * | 2024-08-26 | 2024-09-20 | 国网浙江省电力有限公司诸暨市供电公司 | Power regulation and control method and system for photovoltaic power station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114915261A (en) | Fault monitoring method and device for photovoltaic power station | |
| CN109146093B (en) | Power equipment field investigation method based on learning | |
| CN102930356B (en) | short-term load forecasting method based on meteorological factor sensitivity | |
| EP2537222B1 (en) | Energy generating system and control thereof | |
| Leva et al. | PV module fault diagnosis based on microconverters and day-ahead forecast | |
| CN102737286A (en) | Online risk analysis system and method for regional power grid | |
| CN102708411A (en) | Method for evaluating risk of regional grid on line | |
| CN113988273A (en) | Ice disaster environment active power distribution network situation early warning and evaluation method based on deep learning | |
| CN102426674A (en) | Power system load prediction method based on Markov chain | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN115528817A (en) | Intelligent power distribution and utilization system, method, medium, equipment and terminal for user side | |
| US11451053B2 (en) | Method and arrangement for estimating a grid state of a power distribution grid | |
| CN103246939A (en) | Security and stability margin based on-line identification method for power network operating safety risk incidents | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| CN116845878B (en) | Electric load prediction method for micro-grid | |
| KR20200119371A (en) | Sunlight generation integrated management system based on model and method thereof | |
| CN116341919B (en) | Data and model combined driving safety risk assessment and early warning method | |
| CN117674420A (en) | Power station operation state monitoring system and method based on multivariate time sequence prediction | |
| CN117477558A (en) | Prediction method and system based on power grid load | |
| US11551323B2 (en) | Ensuring safe servicing in a low-voltage network of the electric power distribution system | |
| CN105958474B (en) | Dynamic capacity increasing method and system for power transmission line for power grid regulation and control system | |
| CN115310839A (en) | Photovoltaic power station dust deposition early warning assessment method and system | |
| CN114912671A (en) | Weather type sudden drought early warning method based on weather forecast | |
| CN116704735B (en) | Hydropower station intelligent alarm method, system, terminal and storage medium | |
| CN117200223A (en) | Day-ahead power load prediction method and device |
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 |