CN116231624A - Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station - Google Patents
Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station Download PDFInfo
- Publication number
- CN116231624A CN116231624A CN202211567854.9A CN202211567854A CN116231624A CN 116231624 A CN116231624 A CN 116231624A CN 202211567854 A CN202211567854 A CN 202211567854A CN 116231624 A CN116231624 A CN 116231624A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic module
- output power
- model
- photovoltaic
- economic benefit
- 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
- 230000008901 benefit Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012360 testing method Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 12
- 238000010998 test method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000013112 stability test Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013479 data entry Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000005251 gamma ray Effects 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000015556 catabolic process Effects 0.000 description 5
- 238000006731 degradation reaction Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000001744 unit root test Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Power Engineering (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a photovoltaic module output power prediction method for evaluating the economic benefit of a photovoltaic power station. The method is beneficial to improving the accuracy of prediction and monitoring, simplifying the operation process, enabling the prediction process to be more efficient and reasonable, and further completing the effective evaluation of the economic benefit of the photovoltaic power station.
Description
Technical Field
The invention relates to the technical field of photovoltaic power station design and operation and maintenance evaluation, in particular to a photovoltaic module output power prediction method for evaluating economic benefits of a photovoltaic power station.
Background
With the rapid development of the photovoltaic power station industry and the rapid increase of the installed capacity of the photovoltaic, how to ensure the safe and stable operation of the whole photovoltaic power generation system is becoming more interesting. As a core component of the photovoltaic power generation system, the service life and the parameter performance of the photovoltaic module can be degraded along with the increase of the operation life of the photovoltaic power station and the influence of external weather factors, so that the stability and the reliability of the power generation of the photovoltaic power station are affected. Therefore, the power generation condition of the photovoltaic power station can be further judged by predicting the output power of the photovoltaic module, and meanwhile, the economic benefit of the photovoltaic power station is predicted and evaluated, so that the method has good engineering value and application value.
At present, the health management method of the photovoltaic module is mainly based on two types of degradation mechanisms and data driving, and the method based on the degradation mechanisms needs to know the internal structure and the power generation principle of the photovoltaic module, so that the requirements on technicians are quite high, and the method is difficult to popularize and apply; the method based on data driving is divided into two types, namely an intelligent algorithm and data modeling, wherein the intelligent algorithm generally needs a large amount of degradation data (generally needs 8-10 years) of the photovoltaic module, and the monitoring cost is too high; and the mathematical modeling method has complex modeling process and complex calculation.
The patent number is CN201610843720.3, and the method comprises the following steps: 1) Obtaining an optimal delay l and an optimal embedding dimension m of a photovoltaic output power time sequence by adopting a C-C method, and reconstructing a photovoltaic power time sequence phase space; 2) Determining a predicted central phase space point Pk according to the reconstructed photovoltaic power time sequence phase space in the step 1), selecting an adjacent phase space point Pkj corresponding to the predicted central phase space point, and calculating a weight Wj of the adjacent phase space point Pkj; 3) According to the weight Wj of the adjacent phase space point Pkj obtained in the step 2), a photovoltaic output weighted first-order local linear regression model is established, and a best linear fitting coefficient matrix is calculated; 4) And 3) calculating a photovoltaic output power predicted value according to the optimal linear fitting coefficient matrix obtained in the step 3). However, the prediction accuracy is not high, so that the calculation is inconvenient, and the economic benefit cannot be effectively evaluated.
Disclosure of Invention
The invention aims to provide a photovoltaic module output power prediction method for evaluating economic benefits of a photovoltaic power station, which is characterized in that a data acquisition device is used for acquiring real-time output voltage and output current of a photovoltaic module, and a third party database is used for processing the output voltage and the output current to obtain a short-term actually measured output power time sequence of the photovoltaic module. And further establishing a differential autoregressive moving average model (ARIMA), and defining the power of the photovoltaic module as an economic benefit failure threshold when the generating capacity gain of the photovoltaic module is lower than the operation and maintenance expenditure of the photovoltaic power station. And dividing the actually measured output power time sequence of the photovoltaic module into a training set and a testing set, further optimizing a prediction model, and then carrying out trend prediction on the output power of the photovoltaic module, thereby finally completing the economic benefit evaluation of the photovoltaic power station. The output power prediction method of the photovoltaic module is simple and reliable, the output power of the photovoltaic module can be accurately predicted, the economic benefit of the photovoltaic power station can be effectively evaluated, and the method has high application and popularization values.
In order to solve the technical problems, the invention adopts the following technical scheme: the photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station comprises the following steps:
s110, calculating output power of the photovoltaic module, namely, collecting output voltage and output current time sequences of the photovoltaic module, transmitting the content to a sample database of an intelligent calculation module by using a data acquisition card, and calculating voltage and current values at the same moment to calculate corresponding output power;
s120, extracting an output power time sequence of the photovoltaic module, wherein the output power time sequence of the photovoltaic module is obtained according to the corresponding output power extraction analysis;
s130, constructing an autoregressive moving average (ARMA) model, wherein the method specifically comprises the following steps of: checking sequence stability, determining model order, model residual error checking and model optimization;
s140, setting an economic benefit failure threshold of the photovoltaic module, evaluating the economic benefit of the photovoltaic power station, defining the power of the photovoltaic module as the economic benefit failure threshold when the generating capacity yield of the photovoltaic module is lower than the operation and maintenance expenditure of the photovoltaic power station, and setting the economic benefit failure threshold as follows: p (P) f ；
S150, an ARIMA model is imported for prediction, and the output power time sequence in S120 is imported into the ARIMA model which is built and optimized in S140 for trend prediction;
s160, evaluating the economic benefit of the photovoltaic power station, and evaluating the time period of the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module according to the economic benefit failure threshold of the photovoltaic module set in S140 and combining the prediction result of ARIMA in S150.
In the above method for predicting output power of a photovoltaic module for evaluating economic benefit of a photovoltaic power station, in step S110, the calculating the corresponding output power according to the voltage and current values at the same time is as follows:
P＝I*U
wherein P represents output power, I represents current at the same time, and U represents voltage at the same time.
In the above method for predicting output power of a photovoltaic module for evaluating economic benefit of a photovoltaic power station, in step S120, the output power time sequence of the photovoltaic module obtained by extracting and analyzing according to the corresponding output power is as follows:
P t ＝{p 0 ,p 1 ,p 2 ,…,p t }
and t is the cut-off time of the obtained time sequence of the photovoltaic module, the output power sample database of the photovoltaic module is 1 year, and the time sequence data takes 12 hours as a sequence interval.
In the aforementioned photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power station, in step S130, the ARMA model is defined as follows:
wherein, p represents the order of the autoregressive coefficient, and q is the order of the moving average coefficient; gamma ray i Represents the autocorrelation coefficient, θ i Represents the partial autocorrelation coefficient, x t Representing the current value, epsilon, of the time series t Representing the function error, μ representing the compensation constant term; the hysteresis value of the stationary time series obtained after the difference is further added to the present value and hysteresis of the random error termThe model created by fitting regression of values is called the differential autoregressive moving average model (ARIMA), and the created ARIMA model is ARIMA (p, q, d).
In the above method for predicting output power of a photovoltaic module for evaluating economic benefit of a photovoltaic power station, in step S130, the sequence stationarity check is as follows: performing stability test on a photovoltaic module output power time sequence of 1 year in a sample database by using an ADF test method; when the result of the test is 0, rejecting the original hypothesis and confirming that the time series data is not stable; when the test result is 1, the original assumption is accepted, and the time sequence data is confirmed to be stable; when the time sequence data is not stable, the time sequence is considered to be subjected to first-order difference and then stability test is carried out, if the time sequence data is stable after the first-order difference, d in ARIMA (p, q, d) is set to be 1, if the time sequence data is not stable, high-order difference operation is continued until the time sequence data is stable, and finally the value of d is determined according to the difference order.
In the above method for predicting output power of a photovoltaic module for assessing economic benefit of a photovoltaic power station, in step S130, the determined model order is: after obtaining a stable photovoltaic module output power time sequence, calculating an autocorrelation coefficient and a partial autocorrelation coefficient according to the sequence data sample, and further determining an important order of a model according to the properties of the autocorrelation coefficient and the partial autocorrelation coefficient, wherein the autocorrelation coefficient of the original sequence sample is calculated according to the following formula:
in the formula ,ρk Represents the autocorrelation coefficient, x t Representing the current value of the time series, m t Representing the mean of the sequence; the partial autocorrelation coefficients of the original sequence samples can be further calculated based on the autocorrelation coefficients, namely:
wherein ,
wherein D is determinant of coefficient matrix, D k Is a determinant formed by converting the kth vector in D into an autocorrelation coefficient vector on the right of the equal sign.
In the foregoing photovoltaic module output power prediction method for evaluating economic benefits of a photovoltaic power station, in step S130, the model residual error check is: performing residual testing on the model, including a residual signal and a DW (Durbin-Watson) testing method, wherein the residual signal is obtained by subtracting a residual signal of a model fitting signal from an original sequence sample, if the residual signal is randomly normally distributed and is not self-correlated, the residual signal is a section of white noise signal, and useful signals in the original sequence data are extracted into an ARIMA model for analysis and prediction; the DW test method tests the first-order autocorrelation of the residual in the time series regression fit, assuming the residual is r t The first order linear autocorrelation equation is:
x t ＝ρx t-1 +v t
in the formula ,xt Representing the current value of the time series, x t-1 Representing the value immediately preceding the time series, ρ representing the correlation coefficient, v t Representing the correction coefficient;
x when ρ=0 t Without first order linear correlation, DW test passes constructing statistics:
the approximate relation between DW and rho is established for the intermediate quantity through residual error, and the random term x can be judged t And due to the autocorrelation of (a):
DW≈2(1-ρ)
i.e. the closer the calculated value of DW is to 2, the less there is a first order correlation in the residual.
In the aforementioned photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power plant, in step S130, the model is optimized as follows: training and learning the established ARIMA model by adopting an actual measurement output power time sequence of the photovoltaic module for 1 year, wherein the time sequence interval is 12 hours, and the sequence data entry of 1 year is 730 data points; and dividing the time sequence into 80% as a training set and 20% as a test set, training the ARIMA model according to the change trend of the first 584 data points, and testing the model by using the last 146 data points.
In the above method for predicting output power of a photovoltaic module for assessing economic benefit of a photovoltaic power station, in step S150, the introducing ARIMA model predicts as follows: importing the output power time sequence of the photovoltaic module in the step S120 into the step S140, and establishing and optimizing an ARIMAA model to conduct trend prediction to obtain the trend of the change of the output power time sequence of the photovoltaic module after the moment t as follows:
P t * ＝{p t+1 ,p t+2 ,p t+3 ,…,p t+m ,…}
wherein ,Pt+1 Representing the predicted sequence value at the first moment, and m represents m time periods of the output power prediction of the photovoltaic module by the ARIMA model.
In the above method for predicting output power of a photovoltaic module for evaluating economic benefit of a photovoltaic power station, in step S160, the economic benefit of the photovoltaic power station is evaluated according to the economic benefit failure threshold of the photovoltaic module set in S140, and when the sequence variation trend of the output power of the photovoltaic module at a certain point after the t moment has the following relationship with the economic benefit failure threshold of the photovoltaic module in combination with the prediction result of S150 ARIMA:
P t+m ≥P f
in the formula ,Pt+m Representing the predicted sequence value at the mth instant.
The time period for evaluating the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module is as follows:
T P ＝(t+m)-t＝m
wherein m is the time period from the prediction 0 moment to the economic benefit failure threshold value of the photovoltaic module.
Compared with the prior art, the invention has the following advantages:
1) The invention is based on the real-time output voltage and output current of the photovoltaic module which are acquired in real time by the data acquisition device and transmitted to the database, and the database obtains the data sequence of the short-term actual measurement output power of the photovoltaic module through data processing such as rejection, interpolation, average and the like. The whole process is simple, efficient and reasonable.
2) According to the invention, the traditional and complicated photovoltaic module health management method based on degradation mechanism, mathematical modeling, intelligent algorithm and the like is abandoned, and the photovoltaic module output power prediction method based on time sequence is provided from the practical engineering application point of view, and the output power of the photovoltaic module is further predicted by further importing the constructed ARIMA model through setting the failure threshold of the economic benefit of the photovoltaic module, so that the effective evaluation of the economic benefit of the photovoltaic power station is finally completed. The method is simple in principle, easy to implement and quite high in prediction accuracy.
3) The ARIMA model constructed by the invention ensures the stability of the output power time sequence of the photovoltaic module through differential operation, and the model is required to be further identified and residual error checked after each parameter of the model is ensured. In the optimization stage, the actual measurement output power time sequence of the photovoltaic module for 1 year is divided into 80% as a training set, 20% as a test set, and the ARIMA model is determined to be successfully optimized when the maximum error between the data value and the true value of the test set is not more than 0.2%, so that the optimized model can be used for predicting the future output power of the photovoltaic module.
4) The photovoltaic module output power prediction method constructed by the invention has excellent portability, and a specific model can be constructed to predict the photovoltaic module output power and further complete the effective evaluation of the photovoltaic power station economic benefit by only changing the functional parameters of the photovoltaic module and the corresponding photovoltaic module economic benefit failure threshold aiming at different photovoltaic power station projects. The innovation point of the invention is that: and processing the output voltage and the output current acquired in real time through a database to obtain a short-term actually measured output power time sequence of the photovoltaic module, establishing a differential autoregressive moving average model, defining an economic benefit failure threshold value, carrying out trend prediction on the output power of the photovoltaic module, and completing economic benefit assessment of the photovoltaic power station.
Drawings
FIG. 1 is a flow chart of a photovoltaic module output power prediction method for assessing the economic benefit of a photovoltaic power plant of the present invention;
FIG. 2 is a flow chart of output power prediction of a photovoltaic module according to the present invention;
FIG. 3 is a schematic diagram of a 570Wp photovoltaic module output power time series according to the present invention;
FIG. 4 is a schematic diagram of a first-order differential time sequence of the output power of the 570Wp photovoltaic module of the invention;
FIG. 5 is a graph of the output power first order differential time series ACF of the present invention;
FIG. 6 is a graph of the PACF of the present invention with output power first order differential time series;
FIG. 7 is a table of the time series model scaling criteria of the present invention;
FIG. 8 is a graph of the training test results of the ARIMA model of the present invention;
FIG. 9 is a graph of the ARIMA model predicted outcome of the present invention;
the invention is further described below with reference to the drawings and the detailed description.
Detailed Description
Example 1 of the present invention: the photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station, as shown in fig. 1, comprises the following steps:
s110, calculating output power of the photovoltaic module, namely, collecting output voltage and output current time sequences of the photovoltaic module, transmitting the content to a sample database of an intelligent calculation module by using a data acquisition card, and calculating voltage and current values at the same moment to calculate corresponding output power;
s120, extracting an output power time sequence of the photovoltaic module, wherein the output power time sequence of the photovoltaic module is obtained according to the corresponding output power extraction analysis;
s130, constructing an autoregressive moving average (ARMA) model, wherein the method specifically comprises the following steps of: checking sequence stability, determining model order, model residual error checking and model optimization;
s140, setting an economic benefit failure threshold of the photovoltaic module, evaluating the economic benefit of the photovoltaic power station, defining the power of the photovoltaic module as the economic benefit failure threshold when the generating capacity yield of the photovoltaic module is lower than the operation and maintenance expenditure of the photovoltaic power station, and setting the economic benefit failure threshold as follows: p (P) f ；
S150, an ARIMA model is imported for prediction, and the output power time sequence in S120 is imported into the ARIMA model which is built and optimized in S140 for trend prediction;
s160, evaluating the economic benefit of the photovoltaic power station, and evaluating the time period of the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module according to the economic benefit failure threshold of the photovoltaic module set in S140 and combining the prediction result of ARIMA in S150. In this embodiment, the device for predicting output power of a photovoltaic module includes a photovoltaic module, a data acquisition card, a voltage sensor, a current sensor, and an intelligent computing module. The voltage sensor and the current sensor are respectively used for collecting output voltage and output current of the photovoltaic module, the data acquisition card is used as a data transmission medium to transmit the output voltage and output current signals of the photovoltaic module to the intelligent computing module of the upper computer, the intelligent computing module is further used for computing to obtain output power of the photovoltaic module based on the Python platform, and the residual service life of the photovoltaic module is predicted based on the ARIMA model. Specifically, in step S110, the output power of the photovoltaic module is calculated first, and the corresponding output power is calculated according to the voltage and current values at the same time, where the output power is as follows:
P＝I*U
wherein P represents output power, I represents current at the same time, and U represents voltage at the same time. The voltage sensor and the current sensor respectively collect the output voltage and the output current of the photovoltaic module at the same moment, collect the output voltage and the output current time sequence of the photovoltaic module and transmit the output voltage and the output current time sequence to a sample database of the intelligent computing module through the data collection card, calculate the corresponding output power according to the voltage and the current value at the same moment, and further extract and analyze the data of the calculated output power to obtain the output power time sequence of the photovoltaic module in the step S120:
P t ＝{p 0 ,p 1 ,p 2 ,…,p t }
in this embodiment, in order to ensure accuracy of a prediction result, a photovoltaic module output power sample database is set to be 1 year, and time sequence data is set to be a sequence interval of 12 hours. Specifically, as shown in fig. 3, the 570Wp photovoltaic module of a manufacturer has a one-year time sequence data, the 570Wp photovoltaic module has a sequence interval of 12 hours, and the database obtains a photovoltaic module short-term actually measured output power data sequence through data processing such as rejection, interpolation, averaging and the like, so that the whole process is simple, efficient and reasonable.
In the above embodiment, the economic failure threshold of the photovoltaic module is set. The operation period of a general photovoltaic power station is 25 years, and the power of a photovoltaic module also can be attenuated year by year. The invention aims to further evaluate the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module, so that the power of the photovoltaic module is defined as the economic benefit failure threshold when the generating capacity gain of the photovoltaic module is lower than the operation and maintenance expenditure of the photovoltaic power station.
Example 2 of the present invention: the photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station is as shown in fig. 1:
in step S130, an autoregressive moving average (ARMA) model is constructed, and the ARMA model is defined as follows:
wherein, p represents the order of the autoregressive coefficient, and q is the order of the moving average coefficient; gamma ray i Represents the autocorrelation coefficient, θ i Representing the deviationAutocorrelation coefficient, x t Representing the current value, epsilon, of the time series t Representing the function error, μ representing the compensation constant term; the model established by fitting and regressing the hysteresis value of the stationary time sequence obtained after the differentiation and the present value and hysteresis value of the random error term is called a differential autoregressive moving average model (ARIMA), and the established ARIMA model is ARIMA (p, q, d). In practical application, most of random event time sequence data are non-stationary, and a differential stationary sequence can be obtained after differential operation is performed on the sequence. Based on this idea, an autoregressive model, a moving average model, and a difference operation are combined, and a model constructed by fitting and regressing a hysteresis value of a stationary time series obtained after the difference, a present value of a random error term, and a hysteresis value is called a differential autoregressive moving average model (ARIMA). The differential autoregressive moving average model is compared with the autoregressive moving average model, so that differential operation on the original sequence data is increased. The model therefore needs to determine not only the order p of the autoregressive coefficients and the order q of the moving average coefficients, but also the order d of the differences, i.e. the ARIMA model constructed is ARIMA (p, q, d).
And constructing an autoregressive moving average (ARMA) model includes: and (5) checking sequence stability, determining model order, checking model residual errors and optimizing the model. Specifically, the sequence stationarity check is: and carrying out stability test on the photovoltaic module output power time sequence of 1 year in the sample database by using an ADF test method, wherein the ADF test method is unit root test, namely whether unit roots exist in the test sequence or not, because the existence of the unit roots is a non-stable time sequence. If the result of the test is 0, rejecting the original assumption, wherein the time series data is not stable; if the result of the test is 1, the original assumption is accepted, and the time series data is stable, and the next step can be performed. When the time sequence data is not stable, the stability of the time sequence is checked after the time sequence is considered to be subjected to first-order difference, if the data is stable after the first-order difference, d in ARIMA (p, q, d) is set to be 1, if the data is not stable, high-order difference operation is continued until the data is stable, and finally, the value of d is determined according to the number of the difference. The result of performing the stationarity check on the photovoltaic module output power time sequence in step S120 according to the method is 0, so the data is unstable, and the result after performing the first-order difference on the data is shown in fig. 4. And similarly, carrying out stability verification on the first-order differential time sequence of the 570Wp photovoltaic module output power by using an ADF (automatic frequency correction) test method, and receiving an original assumption if the result is found to be 1, wherein the first-order differential time sequence data is stable. The value of the parameter d in the constructed ARIMA model is set to 1. The method of the embodiment abandons the traditional and complicated photovoltaic module health management method based on degradation mechanism, mathematical modeling, intelligent algorithm and the like, and from the practical engineering application point of view, the method further introduces the constructed ARIMA model to predict the output power of the photovoltaic module by setting the failure threshold of the economic benefit of the photovoltaic module, and finally completes the effective evaluation of the economic benefit of the photovoltaic power station. The method is simple in principle, easy to implement and quite high in prediction accuracy.
Next, the model order is determined. The determined model order is: after a stable photovoltaic module output power time sequence is obtained, an autocorrelation coefficient and a partial autocorrelation coefficient of the photovoltaic module output power time sequence can be calculated according to the sequence data sample, and the important order of the model is further determined according to the properties of the autocorrelation coefficient and the partial autocorrelation coefficient, wherein the autocorrelation coefficient of the original sequence sample is calculated according to the following formula:
in the formula ,ρk Represents the autocorrelation coefficient, x t Representing the current value of the time series, m t Representing the mean of the sequence; the partial autocorrelation coefficients of the original sequence samples can be further calculated based on the autocorrelation coefficients, namely:
wherein ,
wherein D is determinant of coefficient matrix, D k Is a determinant formed by converting the kth vector in D into an autocorrelation coefficient vector on the right of the equal sign. By D and D k The results of calculating ACF and PACF are shown in FIGS. 5 and 6, wherein ACF is the autocorrelation coefficient and PACF is the partial autocorrelation coefficient. And then, combining with the order criteria of the time sequence model order criteria table shown in fig. 7, it can be determined that the autocorrelation order p and the moving average order q of the ARIMA model are 3 and 3, respectively, so that the constructed ARIMA (p, q, d) model is ARIMA (3, 1).
And then performing model residual error check, wherein the model residual error check is as follows: performing residual testing on the model, including a residual signal and a DW (Durbin-Watson) testing method, wherein the residual signal is obtained by subtracting a residual signal of a model fitting signal from an original sequence sample, if the residual signal is randomly normally distributed and is not self-correlated, the residual signal is a section of white noise signal, and useful signals in the original sequence data are extracted into an ARIMA model for analysis and prediction; the DW test method tests the first-order autocorrelation of the residual in the time series regression fit, assuming the residual is r t The first order linear autocorrelation equation is:
x t ＝ρx t-1 +v t
in the formula ,xt Representing the current value of the time series, x t-1 Representing the value immediately preceding the time series, ρ representing the correlation coefficient, v t Representing the correction coefficient;
x when ρ=0 t Without first order linear correlation, DW test passes constructing statistics:
the approximate relation between DW and rho is established for the intermediate quantity through residual error, and the random term x can be judged t And due to the autocorrelation of (a):
DW≈2(1-ρ)
i.e. the closer the calculated value of DW is to 2, the less there is a first order correlation in the residual. As a result of the calculation using the equation (10), dw= 1.9514, which is very close to 2, it is found that there is almost no first-order correlation in the residual signal. In summary, the residual signals conform to random normal distribution and are independent of each other, so that the fixed order of the ARIMA model conforms to the modeling standard.
Finally, model optimization is performed. Through the above, an applicable ARIMA model can be obtained, but the model still needs to be checked by establishing a check standard according to actual conditions, if the model does not pass the check, the model needs to be modeled again, various possibilities can be fully considered by the model after the check passes the check, different parameter variables are further set to fit a plurality of models, and finally, the model with the optimal performance is selected from all the fitted models passing the check. Training and learning the established ARIMA model by adopting an actual measurement output power time sequence of the photovoltaic module for 1 year, wherein the time sequence interval is 12 hours, and the sequence data entry of 1 year is 730 data points; and dividing the time sequence into 80% as a training set and 20% as a test set, training the ARIMA model according to the change trend of the first 584 data points, and testing the model by using the last 146 data points. As a result, as shown in fig. 8, the actual value in the test set is almost identical to the predicted value in the test set, and the maximum prediction error is only 0.105%, and does not exceed the prescribed maximum error upper limit, which indicates that the built model has excellent effect and rather high prediction accuracy, and can be used for predicting the future output power of the photovoltaic module. The ARIMA model ensures the stability of the output power time sequence of the photovoltaic module through differential operation, and the model is required to be further identified and residual error checked after each parameter of the model is ensured. And determining that the ARIMA model is successfully optimized when the maximum error between the data value and the true value of the test set is not more than 0.2%, wherein the optimized model can be used for predicting the future output power of the photovoltaic module.
Example 3 of the present invention: the photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station is as shown in fig. 1: in step S150, the introducing ARIMA model predicts as follows: importing the output power time sequence of the photovoltaic module in the step S120 into the step S140, and establishing and optimizing an ARIMA model to conduct trend prediction to obtain the trend of the change of the output power time sequence of the photovoltaic module after the moment t as follows:
P t * ＝{p t+1 ,p t+2 ,p t+3 ,…,p t+m ,…}
wherein ,Pt+1 Representing the predicted sequence value at the first moment, and m represents m time periods of the output power prediction of the photovoltaic module by the ARIMA model. The final prediction result is shown in fig. 8.
Example 4 of the present invention: the photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station is as shown in fig. 1: in step S160, the step of evaluating the economic benefit of the photovoltaic power station is based on the economic benefit failure threshold of the photovoltaic module set in step S140, and in combination with the prediction result of S150ARIMA, when the sequence change trend of the output power of the photovoltaic module at a certain point of time after the t moment has the following relationship with the economic benefit failure threshold of the photovoltaic module:
P t+m ≥P f
in the formula ,Pt+m Representing the predicted sequence value at the mth instant.
The time period for evaluating the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module is as follows:
T P ＝(t+m)-t＝m
wherein m is the time period from the prediction 0 moment to the economic benefit failure threshold value of the photovoltaic module. In this embodiment, referring to fig. 9, the black solid line represents the time series data of the output power of the original photovoltaic module, and the small dotted line is a 95% confidence interval. The large dashed line represents the future sequence value of the photovoltaic module output power time sequence predicted by the ARIMA model. Analysis shows that the photovoltaic module output power time series reaches the failure threshold 560Wp at 1470 th data point, and if the time series is calculated from 730 th data point as a starting point, the time period for estimating the economic benefit of the photovoltaic power station by predicting the photovoltaic module output power is 740 data points, namely 370 days. Because the method has portability, a specific model can be constructed to predict the output power of the photovoltaic module and further complete the effective evaluation of the economic benefit of the photovoltaic power station by only changing the functional parameters of the photovoltaic module and the corresponding economic benefit failure threshold of the photovoltaic module aiming at different photovoltaic power station projects.
The working principle of one embodiment of the invention is as follows: firstly, calculating output power of the photovoltaic module, transmitting acquired data results at the same moment to a sample database, calculating in the sample database, extracting and analyzing the corresponding output power to obtain an output power time sequence of the photovoltaic module, and setting time sequence data to be at sequence intervals of 12 hours. An autoregressive moving average (ARMA) model is built based on the output power time sequence of the extracted photovoltaic module, a model built by fitting regression of a hysteresis value of a stable time sequence obtained after difference and a current value and a hysteresis value of a random error term is called an autoregressive moving average differential model (ARIMA), and the built ARIMA model is ARIMA (p, q, d). And the accuracy and the effectiveness of the model are maintained through sequence stability verification, model order determination, model residual error verification and model optimization. Setting an economic benefit failure threshold of the photovoltaic module, and carrying out stability test on the output power time sequence of the photovoltaic module for 1 year in the sample database by using an ADF test method; when the result of the test is 0, rejecting the original hypothesis and confirming that the time series data is not stable; when the test result is 1, the original assumption is accepted, and the time sequence data is confirmed to be stable; when the time sequence data is not stable, carrying out stability test after carrying out first-order difference on the time sequence, if the time sequence data is stable after the first-order difference, setting d in ARIMA (p, q, d) as 1, if the time sequence data is not stable, continuing to carry out high-order difference operation until the time sequence data is stable, and finally determining the value of d according to the difference order to establish and optimize an ARIMA model for trend prediction, wherein the trend prediction is used for evaluating the economic benefit of the photovoltaic power station. And (3) leading the values into an ARIMA model for prediction, and finally evaluating the economic benefit of the photovoltaic power station. The whole process is simple, efficient and reasonable, the implementation is easy, the prediction accuracy is quite high, the optimized model can be used for predicting the future output power of the photovoltaic module, a specific model is constructed for predicting the output power of the photovoltaic module, and the effective evaluation of the economic benefit of the photovoltaic power station is further completed.
Claims (10)
1. The photovoltaic module output power prediction method for evaluating the economic benefit of the photovoltaic power station is characterized by comprising the following steps of:
s110, calculating output power of the photovoltaic module, namely, collecting output voltage and output current time sequences of the photovoltaic module, transmitting the content to a sample database of an intelligent calculation module by using a data acquisition card, and calculating voltage and current values at the same moment to calculate corresponding output power;
s120, extracting an output power time sequence of the photovoltaic module, wherein the output power time sequence of the photovoltaic module is obtained according to the corresponding output power extraction analysis;
s130, constructing an autoregressive moving average (ARMA) model, wherein the method specifically comprises the following steps of: checking sequence stability, determining model order, model residual error checking and model optimization;
s140, setting an economic benefit failure threshold of the photovoltaic module, evaluating the economic benefit of the photovoltaic power station, defining the power of the photovoltaic module as the economic benefit failure threshold when the generating capacity yield of the photovoltaic module is lower than the operation and maintenance expenditure of the photovoltaic power station, and setting the economic benefit failure threshold as follows: p (P) f ；
S150, an ARIMA model is imported for prediction, and the output power time sequence in S120 is imported into the ARIMA model which is built and optimized in S140 for trend prediction;
s160, evaluating the economic benefit of the photovoltaic power station, and evaluating the time period of the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module according to the economic benefit failure threshold of the photovoltaic module set in S140 and combining the prediction result of ARIMA in S150.
2. The method for predicting output power of a photovoltaic module for assessing economic benefit of a photovoltaic power plant according to claim 1, wherein in the step S110, the calculating the corresponding output power according to the voltage and current values at the same time is:
P＝I*U
wherein P represents output power, I represents current at the same time, and U represents voltage at the same time.
3. The method for predicting output power of a photovoltaic module for assessing economic benefit of a photovoltaic power plant according to claim 2, wherein in the step S120, the output power time sequence of the photovoltaic module obtained according to the corresponding output power extraction analysis is:
P t ＝{p 0 ,p 1 ,p 2 ,…,p t }
and t is the cut-off time of the obtained time sequence of the photovoltaic module, the output power sample database of the photovoltaic module is 1 year, and the time sequence data takes 12 hours as a sequence interval.
4. A photovoltaic module output power prediction method for assessing economic efficiency of a photovoltaic power plant according to claim 3, wherein in step S130, the ARMA model is defined as follows:
wherein, p represents the order of the autoregressive coefficient, and q is the order of the moving average coefficient; gamma ray i Represents the autocorrelation coefficient, θ i Represents the partial autocorrelation coefficient, x t Representing the current value, epsilon, of the time series t Representing the function error, μ representing the compensation constant term; the model established by fitting and regressing the hysteresis value of the stationary time sequence obtained after the differentiation and the present value and hysteresis value of the random error term is called a differential autoregressive moving average model (ARIMA), and the established ARIMA model is ARIMA (p, q, d).
5. The photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power plant according to claim 4, wherein in step S130, the sequence stationarity check is: performing stability test on a photovoltaic module output power time sequence of 1 year in a sample database by using an ADF test method; when the result of the test is 0, rejecting the original hypothesis and confirming that the time series data is not stable; when the test result is 1, the original assumption is accepted, and the time sequence data is confirmed to be stable; when the time sequence data is not stable, the time sequence is considered to be subjected to first-order difference and then stability test is carried out, if the time sequence data is stable after the first-order difference, d in ARIMA (p, q, d) is set to be 1, if the time sequence data is not stable, high-order difference operation is continued until the time sequence data is stable, and finally the value of d is determined according to the difference order.
6. The photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power plant according to claim 5, wherein in step S130, the determined model order is: after a stable photovoltaic module output power time sequence is obtained, calculating an autocorrelation coefficient and a partial autocorrelation coefficient according to the sequence data sample, and further determining an important order of a model according to the properties of the autocorrelation coefficient and the partial autocorrelation coefficient, wherein the autocorrelation coefficient of the original sequence sample is calculated according to the following formula:
in the formula ,ρk Represents the autocorrelation coefficient, x t Representing the current value of the time series, m t Representing the mean of the sequence;
the partial autocorrelation coefficients of the original sequence samples can be further calculated based on the autocorrelation coefficients, namely:
wherein ,
wherein D is determinant of coefficient matrix, D k Is a determinant formed by converting the kth vector in D into an autocorrelation coefficient vector on the right of the equal sign.
7. The photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power plant according to claim 6, wherein in step S130, the model residual check is: performing residual testing on the model, including a residual signal and a DW (Durbin-Watson) testing method, wherein the residual signal is obtained by subtracting a residual signal of a model fitting signal from an original sequence sample, if the residual signal is randomly normally distributed and is not self-correlated, the residual signal is a section of white noise signal, and useful signals in the original sequence data are extracted into an ARIMA model for analysis and prediction; the DW test method tests the first-order autocorrelation of the residual in the time series regression fit, assuming the residual is r t The first order linear autocorrelation equation is:
x t ＝ρx t-1 +v t
in the formula ,xt Representing the current value of the time series, x t-1 Representing the value immediately preceding the time series, ρ representing the correlation coefficient, v t Representing the correction coefficient;
x when ρ=0 t Without first order linear correlation, DW test passes constructing statistics:
the approximate relation between DW and rho is established for the intermediate quantity through residual error, and the random term x can be judged t And due to the autocorrelation of (a):
DW≈2(1-ρ)
i.e. the closer the calculated value of DW is to 2, the less there is a first order correlation in the residual.
8. The photovoltaic module output power prediction method for assessing economic efficiency of a photovoltaic power plant of claim 7, wherein in step S130, the model is optimized as: training and learning the established ARIMA model by adopting an actual measurement output power time sequence of the photovoltaic module for 1 year, wherein the time sequence interval is 12 hours, and the sequence data entry of 1 year is 730 data points; and dividing the time sequence into 80% as a training set and 20% as a test set, training the ARIMA model according to the change trend of the first 584 data points, and testing the model by using the last 146 data points.
9. The photovoltaic module output power prediction method for assessing economic benefit of a photovoltaic power plant according to claim 1, wherein in step S150, the introducing ARIMA model predicts as: importing the output power time sequence of the photovoltaic module in the step S120 into the step S140, and establishing and optimizing an ARIMA model to conduct trend prediction to obtain the trend of the change of the output power time sequence of the photovoltaic module after the moment t as follows:
P t * ＝{p t+1 ,p t+2 ,p t+3 ,…,p t+m ,…}
wherein ,Pt+1 Representing the predicted sequence value at the first moment, and m represents m time periods of the output power prediction of the photovoltaic module by the ARIMA model.
10. The method for predicting output power of a photovoltaic module according to claim 1, wherein in step S160, the economic benefit of the photovoltaic module is evaluated according to the economic benefit failure threshold of the photovoltaic module set in S140, and in combination with the prediction result of S150ARIMA, when there is a relationship between the sequence variation trend of the output power of the photovoltaic module at a point of time after the t moment and the economic benefit failure threshold of the photovoltaic module:
P t+m ≥P f
in the formula ,Pt+m Representing the predicted mth instantSequence values.
The time period for evaluating the economic benefit of the photovoltaic power station by predicting the output power of the photovoltaic module is as follows:
T P ＝(t+m)-t＝m
wherein m is the time period from the prediction 0 moment to the economic benefit failure threshold value of the photovoltaic module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211567854.9A CN116231624A (en) | 2022-12-07 | 2022-12-07 | Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211567854.9A CN116231624A (en) | 2022-12-07 | 2022-12-07 | Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116231624A true CN116231624A (en) | 2023-06-06 |
Family
ID=86588096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211567854.9A Pending CN116231624A (en) | 2022-12-07 | 2022-12-07 | Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116231624A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116562916A (en) * | 2023-07-12 | 2023-08-08 | 国网安徽省电力有限公司经济技术研究院 | Economic benefit analysis and evaluation system for photovoltaic direct-current power distribution system |
| CN118174381A (en) * | 2024-05-14 | 2024-06-11 | 国网浙江省电力有限公司 | Distributed power station dynamic topology optimization method based on space-time correlation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103996073A (en) * | 2014-05-06 | 2014-08-20 | 国家电网公司 | Photometric-network real-time-correction self-learning ARMA model photovoltaic power prediction method |
| CN105137242A (en) * | 2015-09-09 | 2015-12-09 | 南京航空航天大学 | Single-phase photovoltaic inverter on-line state monitoring and residual life prediction method |
| CN109388863A (en) * | 2018-09-21 | 2019-02-26 | 国网天津市电力公司 | A kind of distributed photovoltaic power output power forecasting method based on ARIMA model |
| CN113256027A (en) * | 2021-06-22 | 2021-08-13 | 南京邮电大学 | Human resource allocation method based on cargo quantity |
-
2022
- 2022-12-07 CN CN202211567854.9A patent/CN116231624A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103996073A (en) * | 2014-05-06 | 2014-08-20 | 国家电网公司 | Photometric-network real-time-correction self-learning ARMA model photovoltaic power prediction method |
| CN105137242A (en) * | 2015-09-09 | 2015-12-09 | 南京航空航天大学 | Single-phase photovoltaic inverter on-line state monitoring and residual life prediction method |
| CN109388863A (en) * | 2018-09-21 | 2019-02-26 | 国网天津市电力公司 | A kind of distributed photovoltaic power output power forecasting method based on ARIMA model |
| CN113256027A (en) * | 2021-06-22 | 2021-08-13 | 南京邮电大学 | Human resource allocation method based on cargo quantity |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116562916A (en) * | 2023-07-12 | 2023-08-08 | 国网安徽省电力有限公司经济技术研究院 | Economic benefit analysis and evaluation system for photovoltaic direct-current power distribution system |
| CN116562916B (en) * | 2023-07-12 | 2023-10-10 | 国网安徽省电力有限公司经济技术研究院 | Economic benefit analysis and evaluation system for photovoltaic direct-current power distribution system |
| CN118174381A (en) * | 2024-05-14 | 2024-06-11 | 国网浙江省电力有限公司 | Distributed power station dynamic topology optimization method based on space-time correlation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116231624A (en) | Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station | |
| CN104866926B (en) | Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis | |
| CN106803137A (en) | Urban track traffic AFC system enters the station volume of the flow of passengers method for detecting abnormality in real time | |
| CN111738348B (en) | Power data anomaly detection method and device | |
| CN112100574A (en) | Resampling-based AAKR model uncertainty calculation method and system | |
| CN110738346A (en) | batch electric energy meter reliability prediction method based on Weibull distribution | |
| CN110852906B (en) | Method and system for identifying electricity stealing suspicion based on high-dimensional random matrix | |
| CN113742932A (en) | Method for predicting and diagnosing faults of gearbox of wind turbine generator | |
| CN113672606A (en) | Oil chromatography monitoring data quality evaluation method | |
| CN114330120B (en) | 24-Hour PM prediction based on deep neural network2.5Concentration method | |
| CN109598052A (en) | Intelligent electric meter life cycle prediction technique and device based on correlation analysis | |
| CN114372344B (en) | Quantitative identification method for subsynchronous oscillation damping characteristic influence factors | |
| CN112560916B (en) | Wind power tower barrel overturning intelligent diagnosis method based on tilt angle sensor information | |
| CN117405971B (en) | Power acquisition digitization method based on flow automation | |
| CN117192063A (en) | Water quality prediction method and system based on coupled Kalman filtering data assimilation | |
| CN112098066A (en) | High-voltage shunt reactor fault diagnosis method and system based on gate control circulation unit | |
| CN116128690B (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| CN116957534A (en) | Method for predicting replacement number of intelligent electric meter | |
| CN115577854A (en) | Quantile regression wind speed interval prediction method based on EEMD-RBF combination | |
| CN110895624A (en) | Method for testing consistency of degraded data of accelerated storage and natural storage based on maximum entropy spectrum estimation | |
| CN111210278A (en) | Coal industry stock price prediction method based on time series | |
| CN110889083A (en) | Accelerated storage and natural storage degradation data consistency checking method based on window spectrum estimation | |
| CN114254516B (en) | Parameter probability uncertainty modeling method under deleted data | |
| CN118071168B (en) | Comprehensive energy management system | |
| CN115062829A (en) | Atmospheric water vapor estimation method based on multipath mixed neural network atmospheric water vapor estimation model |
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 |