CN117952240A - Photovoltaic power generation amount prediction method and device - Google Patents
Photovoltaic power generation amount prediction method and device Download PDFInfo
- Publication number
- CN117952240A CN117952240A CN202211329473.7A CN202211329473A CN117952240A CN 117952240 A CN117952240 A CN 117952240A CN 202211329473 A CN202211329473 A CN 202211329473A CN 117952240 A CN117952240 A CN 117952240A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic power
- power generation
- generation amount
- weather
- confidence interval
- 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
- 238000010248 power generation Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000005484 gravity Effects 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 2
- 230000015654 memory Effects 0.000 description 14
- 238000005315 distribution function Methods 0.000 description 7
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001747 exhibiting effect Effects 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Abstract
The invention relates to the field of photovoltaic power generation amount prediction, in particular to a photovoltaic power generation amount prediction method and device. The method comprises the following steps: 1) Determining a plurality of historical time periods similar to meteorological parameters of the predicted time period, and acquiring photovoltaic power generation level data corresponding to each historical time period; 2) Determining the distribution condition of the photovoltaic power generation level data obtained in the step 1); 3) Determining a confidence interval of the photovoltaic power generation level data according to the set confidence; 4) And (3) calculating a confidence interval of the photovoltaic power generation amount according to the confidence interval of the photovoltaic power generation level data and the photovoltaic power starting capacity obtained in the step (3), wherein the calculated confidence interval of the photovoltaic power generation amount is a result of photovoltaic power generation amount prediction in a prediction time period. The method solves the problem of low prediction precision of the photovoltaic power generation amount.
Description
Technical Field
The invention relates to a photovoltaic power generation amount prediction method and device, and belongs to the field of photovoltaic power generation amount prediction.
Background
Photovoltaic power generation gradually becomes the main stream choice of a newly-added power supply by virtue of the advantages of green cleaning, low pollution and the like. However, due to the strong dependence of the photovoltaic power generation on the meteorological environment, the output of the photovoltaic power generation has very strong randomness and fluctuation, and further, the photovoltaic power generation also provides new challenges for safe and stable operation of a power system. In recent years, as more and more new energy power stations start to be built and connected, the duty ratio of the new energy power generation amount is gradually increased, and the demands for the prediction diversity and accuracy of the new energy power generation amount are rapidly increased.
Along with the grid connection of a large number of photovoltaic stations, the influence of the fluctuation and randomness of the photovoltaic power generation on the large-scale photovoltaic grid-connected power generation is more and more serious, and the prediction of the photovoltaic power generation is very important.
The Chinese patent application with the application publication number of CN108921339A discloses a genetic support vector machine photovoltaic power interval prediction method based on quantile regression, a data sample is obtained by extracting solar radiation values, temperature values and photovoltaic power of historical data, a prediction model is constructed, and high-precision photovoltaic deterministic prediction power is obtained, but the method has a complex prediction process and only considers three conditions of sunny days, cloudy days and rainy days when weather types are classified.
The Chinese patent application with the application publication number of CN104021427A discloses a factor analysis-based method for predicting the daily power generation capacity of a grid-connected photovoltaic power station, which considers weather data such as historical conventional weather observation values, but the accuracy of prediction is not high due to the fact that the number of weather factors considered by the method is small.
Disclosure of Invention
The invention aims to provide a photovoltaic power generation amount prediction method and device, which are used for solving the problem of low photovoltaic power generation amount prediction precision.
In order to achieve the above object, the present invention provides a method comprising:
the invention provides a photovoltaic power generation amount prediction method, which comprises the following steps:
1) Determining a plurality of historical time periods similar to meteorological parameters of the predicted time period, and acquiring photovoltaic power generation level data corresponding to each historical time period;
2) Determining the distribution condition of the photovoltaic power generation level data obtained in the step 1);
3) Determining a confidence interval of the photovoltaic power generation level data according to the set confidence;
4) And (3) calculating a confidence interval of the photovoltaic power generation amount according to the confidence interval of the photovoltaic power generation level data and the photovoltaic power starting capacity obtained in the step (3), wherein the calculated confidence interval of the photovoltaic power generation amount is a result of photovoltaic power generation amount prediction in a prediction time period.
The beneficial effects are that: the historical time period similar to the meteorological parameters of the prediction time period is acquired, the fact that the data in the acquired overall sample is closer to real data is guaranteed, the data abnormality caused by the photovoltaic power generation capacity is eliminated through the related calculation of the photovoltaic power generation capacity and the photovoltaic power generation capacity, the reliability of the data is guaranteed, a distribution model is further constructed, the distribution function confidence interval can be obtained through the distribution model and the significant level to be determined, the photovoltaic power generation capacity confidence interval is obtained through the distribution function confidence interval and the photovoltaic power generation capacity calculation, the prediction of the photovoltaic power generation capacity is completed, and the predicted data is more accurate.
Further, in step 1), the following method is adopted to determine a plurality of historical time periods similar to the meteorological parameters of the predicted time periods:
The method comprises the steps of obtaining weather parameters of a plurality of historical time periods, carrying out normalization processing on the obtained weather parameter data, calculating information entropy values of all weather parameters according to the normalized data, calculating index proportion matrixes of all weather parameters according to the information entropy values of all weather parameters, calculating similarity of all historical time periods and predicted time periods according to the calculated index proportion matrixes, the weather parameter data of all the historical time periods and the weather parameter data of the predicted time periods, and selecting a plurality of previous historical time periods with larger similarity as a plurality of historical time periods similar to the weather parameters of the predicted time periods.
Further, the index specific gravity matrix is:
dj＝1-ej
Wherein d j is information utility value, w j is index specific gravity matrix, and e j is information entropy value.
Further, the information entropy value of each meteorological parameter is:
wherein e j is the information entropy value, y ij is the specific gravity of the ith time point under the jth factor, X ij is the value normalized by the factor j on the ith weather day.
Further, the meteorological parameters include at least two of total radiation, solar time, average wind speed, average temperature, relative humidity, and atmospheric transparency.
Further, the calculation formula of the similarity of the weather parameters between the predicted time period and each historical time period is as follows:
Where n represents the total number of weather indicators considered, i represents the ith weather indicator, w i represents the weight of the ith weather indicator, x i represents the ith weather indicator data in the predicted time period, and y i represents the ith weather indicator data in the historical time period.
The beneficial effects are that: the method has the advantages that richer parameters are obtained, the reliability of model construction is guaranteed, the acquired data are more similar to weather in a prediction time period through calculation of weight of each parameter and calculation of similarity of weather parameters in the prediction time period and each historical time period, calculation of similar days is completed, and accuracy of prediction results is guaranteed. Through the calculation of the Euclidean distance, the completion of the selection of the similar days is realized, and the accuracy of the selection of the similar days is ensured.
Further, in the step 3), the distribution condition of the photovoltaic power generation level data is enabled to meet t distribution, and then the confidence interval of the photovoltaic power generation level data is determined according to a confidence interval calculation method of the t distribution;
The confidence interval for confidence 1-a is:
Wherein, Can be obtained by querying a t distribution fractional number t α (n) table,/>S 2 is the sample variance, n is the total sample, and a is the significant level.
The beneficial effects are that: by acquiring each parameter in the formula, the calculation of the distribution function confidence interval with the confidence degree of 1-a is realized, and the calculation of the photovoltaic power generation capacity is ensured.
Further, the calculation method of the photovoltaic power generation amount in the photovoltaic power generation amount confidence interval comprises the following steps: and taking the confidence interval of the data at the photovoltaic power generation level as the photovoltaic power generation level, wherein the photovoltaic power generation amount is equal to the confidence interval of the data at the photovoltaic power generation level multiplied by the photovoltaic power-on capacity.
The beneficial effects are that: the calculation of the confidence interval of the photovoltaic power generation amount is completed by acquiring the confidence interval of the obtained distribution function and the photovoltaic power starting capacity, and the prediction of the photovoltaic power generation amount is realized.
The invention also provides a photovoltaic power generation amount prediction device, which comprises a processor, wherein the processor is used for executing program instructions to realize the photovoltaic power generation amount prediction method.
The beneficial effects are that: the photovoltaic power generation amount prediction method can be realized through the device, and the photovoltaic power generation amount can be accurately predicted.
Drawings
FIG. 1 is a schematic illustration of confidence intervals and confidence levels of the present invention;
fig. 2 is a flowchart of a photovoltaic power generation amount prediction method of the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
Method embodiment:
the result of photovoltaic power generation predicted by the invention is a confidence interval, and firstly, a confidence interval theory is introduced simply.
As shown in fig. 1, which is a schematic diagram of confidence intervals and confidence levels, the curve represents a distribution function F constructed by sample statistics, the area enclosed by the distribution function and the x-axis is 100%, the confidence interval is a section interval [ θ 1,θ2 ] on the x-axis, and the corresponding confidence is the area enclosed by the distribution curve F, x axis and x=θ 1、x＝θ2. Confidence interval refers to an estimated interval of an overall parameter constructed from sample statistics, exhibiting a degree of confidence that the true value of this parameter falls around the measured value (the inferred value).
Let θ be an unknown parameter of the population X, determine from sample X 1、X2、X3、…、Xn that two statistics θ1＝θ1(X1、X2、X3、…、Xn),θ2＝θ2(X1、X2、X3、…、Xn)., if there is a random interval [ θ 1,θ2 ], satisfy for a given 0 < α < 1:
P{θ1≤θ≤θ2}＝1-α
Then the term interval [ θ 1,θ2 ] is a confidence interval with θ confidence of 1- α, θ 1、θ2 is a confidence lower limit and a confidence upper limit, respectively, 1- α is a confidence, and α is a significant level.
When the standard deviation of the population is unknown and the sample capacity is small, the standard deviation of the population can be replaced by the standard deviation of the sample, and the upper limit and the lower limit of the future photovoltaic power generation amount are approximately estimated by adopting t distribution. The specific theory of t distribution is presented below.
Assuming that the number of overall samples is n, when the variance σ 2 of the overall X is unknown, and the sample variance S 2 is used to replace σ 2, the random variable T obeys the T distribution with the degree of freedom of n-1, namely:
Wherein, Mu is a mathematical expectation, S 2 is a sample variance, n is a total sample amount, n-1 is a degree of freedom, and T is a random variable.
Given a significant level α, there are:
Further comprises the following steps:
the confidence interval for the mathematical expectation mu confidence of 1-alpha is
For this purpose, the average value, variance and t distribution of each time period are calculated by using the historical data of the photovoltaic power generation amountThe upper and lower limits of the photovoltaic power generation amount in the predicted time period can be obtained by the values of (a) and (b) and the values of (b) and (b) brought into the formula.
The following describes in detail a photovoltaic power generation amount prediction method according to the present invention based on the above theory.
The implementation flow of the invention is shown in fig. 2, and specifically comprises the following steps:
1. A time scale is determined.
And determining a predicted time scale of the photovoltaic power generation amount according to actual requirements, such as one day, one week or one month.
2. A population sample is established.
According to the determined photovoltaic power generation quantity prediction time scale, searching a total sample formed by corresponding historical data, wherein the adopted method is a similar daily method, and the specific method is that an entropy method and Euclidean distance are adopted to search a time period similar to weather conditions in a predicted time period in the historical data so as to form the total sample of confidence interval prediction.
The method comprises the following steps of:
Because photovoltaic power generation is primarily affected by weather factors, weather factors are primarily considered when selecting similar days. For the total photovoltaic power generation amount in a certain period of time, the following indexes are mainly used as reference standards selected on similar days: total radiation, solar time, average wind speed, average temperature, relative humidity, atmospheric transparency. However, the influence of each factor on the photovoltaic power generation power is different, and the weight of each influence factor needs to be determined, so that the history day most similar to the predicted solar-air condition is found from the history data.
The weight coefficient of each meteorological factor is calculated by adopting an entropy method, and the weight coefficient of each index is calculated by adopting the entropy method based on the data distribution condition completely, so that the influence of human factors is avoided. The entropy method is to obtain a weight coefficient by sorting, calculating and analyzing an actual sample set, the method accords with actual data distribution, and the weight coefficient affecting all factors of photovoltaic power generation weather is calculated by adopting the entropy method, and the method comprises the following specific steps:
1) And (5) normalizing the index data.
Because the dimension and the magnitude difference of each factor of the weather are large, each index data needs to be normalized to a designated interval, and the specific formula is as follows:
Wherein: x j is the value of the jth factor, x max is the maximum value of the jth factor in the meteorological data set, x min is the minimum value of the jth factor in the meteorological data set, and x ij is the value of the jth factor after standardization treatment of the ith meteorological day.
2) And calculating an index specific gravity matrix.
Calculating the specific gravity y ij of the ith time point under the jth factor according to the result of the step 1, wherein the specific formula is as follows:
And calculating an information entropy value and an information utility value d. The information entropy value e j of the jth factor can be calculated according to y ij, and the specific formula is as follows:
Wherein:
Next, the information utility value d j of the j-th index is calculated, and the specific formula is as follows:
dj＝1-ej。
The index specific gravity matrix is:
3) And calculating the Euclidean distance.
Euclidean metric (also known as euclidean distance) is a commonly used distance definition that refers to the true distance between two points in an n-dimensional space, or the natural length of a vector (i.e., the distance of the point from the origin). The calculation formula is as follows:
Specifically, the Euclidean distance calculation formula is as follows in combination with the scene selected by the similar days of the generated energy:
Wherein: n represents the total number of considered weather indicators, i represents the ith weather indicator, w i represents the weight of the ith weather indicator, x i represents the ith weather indicator data in the predicted period, and y i represents the ith weather indicator data in the historical period.
And calculating Euclidean distance between each meteorological index in the predicted time period and each meteorological index in the historical time period according to the method to determine the similarity between the predicted time period and each historical time period, and further selecting the first plurality of historical time periods with the smallest Euclidean distance, namely the maximum similarity, as the similarity days.
If the prediction period is a certain period in summer, in the photovoltaic power generation historical data, according to a method selected by a similar day, continuous one week, in which weather data such as temperature and irradiance are similar to weather data in the prediction period, is searched, and photovoltaic power generation amount X i 'in the week is taken as one sample in the whole body, and the method is used for searching sample data as much as possible to form the whole body sample [ X 1′、X2′、X3′、…、Xn' ].
3. Sample data preprocessing.
Considering that the starting capacity of the new energy may change (such as overhaul, electricity limiting, or power station extension, etc.) in the statistical period and the prediction period of the historical data, the power generation level of the photovoltaic power generation is used as a statistical sample of the photovoltaic power generation prediction, and the confidence interval of the power generation level is used for converting the confidence interval of the photovoltaic power generation in the prediction target time period. The photovoltaic power generation level calculation method is as follows:
photovoltaic power generation level = photovoltaic power generation/photovoltaic power on capacity
Obtaining a sample [ X 1、X2、X3、…、Xn ] after pretreatment of sample data
Furthermore, if the ageing of the photovoltaic modules and other technical updates are taken into account, corresponding conversions are possible.
4. And establishing a sample data distribution model.
According to the t distribution theory introduced above, a t distribution model is built by combining the samples after pretreatment. Namely:
5. and calculating a distribution function confidence interval.
The significant level α determined according to the actual requirement, if α=0.05, is:
Further comprises the following steps:
The confidence interval for the mathematical expectation mu confidence of 0.95 is
Where n is the total number of samples,Is the mean value of sample data [ X 1、X2、X3、…、Xn ], S is the sample standard deviation,/>Can be obtained by looking up a t distribution quantile t α (n) table. The confidence interval of the mathematical expectation mu of the t distribution can be calculated after the data are brought in.
6. And calculating a photovoltaic power generation amount confidence interval.
Confidence interval of mathematical expectation μ according to the calculated t distribution Assuming that the confidence interval calculated after the parameters are brought is [ theta 1,θ2 ], according to the process of preprocessing the original data in the step 3, converting the obtained confidence interval to obtain a real power generation confidence interval, the specific method is as follows:
Photovoltaic power generation = photovoltaic power generation level x photovoltaic power on capacity
Assuming that the starting capacity in the predicted period is C, a confidence interval of 0.95 of the final photovoltaic power generation amount is [ cθ 1,Cθ2 ] can be obtained according to the above formula. The calculated confidence interval of the photovoltaic power generation amount is the result of photovoltaic power generation power prediction.
Device example:
The embodiment of the invention relates to a photovoltaic power generation amount prediction device, which comprises a memory, a processor and an internal bus, wherein the processor and the memory are communicated with each other and data interaction is completed through the internal bus. The memory comprises at least one software functional module stored in the memory, and the processor executes various functional applications and data processing by running the software programs and the modules stored in the memory to realize the photovoltaic power generation amount prediction method in the method embodiment of the invention.
The processor may be a microprocessor MCU, a programmable logic device FPGA, or other processing device. The memory may be various memories for storing information by using electric energy, such as RAM, ROM, etc.; the magnetic storage device can also be various memories for storing information by utilizing a magnetic energy mode, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a bubble memory, a U disk and the like; various memories for optically storing information, such as CDs, DVDs, etc.; of course, other types of memory are also possible, such as quantum memory, graphene memory, etc.
The invention provides a photovoltaic power generation amount prediction method and device, which combine confidence interval theory and photovoltaic power generation amount to predict photovoltaic power generation amount in a future period. The predicted outcome is a confidence interval for the power generation at a given confidence, meaning that the photovoltaic power generation in the future for a period of time will fall within the confidence interval with a certain probability. The confidence interval of the photovoltaic power generation capacity is accurately predicted, the power grid can be assisted to conduct long-time scale dispatching supply and demand balance, a user is helped to reduce assessment, and the auxiliary decision can be conducted on the photovoltaic station construction investment benefit.
Claims (9)
1. The photovoltaic power generation amount prediction method is characterized by comprising the following steps of:
1) Determining a plurality of historical time periods similar to meteorological parameters of the predicted time period, and acquiring photovoltaic power generation level data corresponding to each historical time period;
2) Determining the distribution condition of the photovoltaic power generation level data obtained in the step 1);
3) Determining a confidence interval of the photovoltaic power generation level data according to the set confidence;
4) And (3) calculating a confidence interval of the photovoltaic power generation amount according to the confidence interval of the photovoltaic power generation level data and the photovoltaic power starting capacity obtained in the step (3), wherein the calculated confidence interval of the photovoltaic power generation amount is a result of photovoltaic power generation amount prediction in a prediction time period.
2. The method of claim 1, wherein the step 1) includes determining a plurality of historical time periods similar to the weather parameters of the predicted time period by:
The method comprises the steps of obtaining weather parameters of a plurality of historical time periods, carrying out normalization processing on the obtained weather parameter data, calculating information entropy values of all weather parameters according to the normalized data, calculating index proportion matrixes of all weather parameters according to the information entropy values of all weather parameters, calculating similarity of all historical time periods and predicted time periods according to the calculated index proportion matrixes, the weather parameter data of all the historical time periods and the weather parameter data of the predicted time periods, and selecting a plurality of previous historical time periods with larger similarity as a plurality of historical time periods similar to the weather parameters of the predicted time periods.
3. The photovoltaic power generation amount prediction method according to claim 2, wherein the index specific gravity matrix is:
dd＝1-ej
Wherein d j is information utility value, j w is index specific gravity matrix, and e j is information entropy value.
4. The method for predicting photovoltaic power generation amount according to claim 2, wherein the information entropy value of each meteorological parameter is:
wherein e j is the information entropy value, y ij is the specific gravity of the ith time point under the jth factor, X ij is the value normalized by the factor j on the ith weather day.
5. The method of claim 2, wherein the meteorological parameters include at least two of total radiation, solar time, average wind speed, average temperature, relative humidity, and atmospheric transparency.
6. A photovoltaic power generation amount prediction method according to claim 3, wherein the calculation formula of the similarity of the weather parameter of the prediction period and each of the history periods is:
Where n represents the total number of weather indicators considered, i represents the ith weather indicator, w i represents the weight of the ith weather indicator, x i represents the ith weather indicator data in the predicted time period, and y i represents the ith weather indicator data in the historical time period.
7. The photovoltaic power generation amount prediction method according to claim 1, wherein in the step 3), the distribution condition of the photovoltaic power generation level data is made to satisfy the t distribution, and further the confidence interval of the photovoltaic power generation level data is determined according to the confidence interval calculation method of the t distribution;
The confidence interval for confidence 1-a is:
Wherein, Can be obtained by querying a t distribution fractional number t α (n) table,/>S 2 is the sample variance, n is the total sample, and a is the significant level.
8. The photovoltaic power generation amount prediction method according to claim 7, characterized in that the calculation method of the photovoltaic power generation amount located in the photovoltaic power generation amount confidence interval is: and taking the confidence interval of the data at the photovoltaic power generation level as the photovoltaic power generation level, wherein the photovoltaic power generation amount is equal to the confidence interval of the data at the photovoltaic power generation level multiplied by the photovoltaic power-on capacity.
9. A photovoltaic power generation amount prediction apparatus comprising a processor for executing program instructions to implement the photovoltaic power generation amount prediction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211329473.7A CN117952240A (en) | 2022-10-27 | 2022-10-27 | Photovoltaic power generation amount prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211329473.7A CN117952240A (en) | 2022-10-27 | 2022-10-27 | Photovoltaic power generation amount prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117952240A true CN117952240A (en) | 2024-04-30 |
Family
ID=90798880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211329473.7A Pending CN117952240A (en) | 2022-10-27 | 2022-10-27 | Photovoltaic power generation amount prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117952240A (en) |
-
2022
- 2022-10-27 CN CN202211329473.7A patent/CN117952240A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| CN111369070B (en) | Multimode fusion photovoltaic power prediction method based on envelope clustering | |
| CN108932557A (en) | A kind of Short-term Load Forecasting Model based on temperature cumulative effect and grey relational grade | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN110601250B (en) | Method for evaluating stability of static voltage of access point based on new energy power station | |
| CN103473621A (en) | Wind power station short-term power prediction method | |
| CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN110866633B (en) | Micro-grid ultra-short-term load prediction method based on SVR support vector regression | |
| CN111242355A (en) | Photovoltaic probability prediction method and system based on Bayesian neural network | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN112348287A (en) | Electric power system short-term load probability density prediction method based on LSTM quantile regression | |
| CN116629416A (en) | Photovoltaic power station power prediction method and device | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN115481772A (en) | Photovoltaic power generation capacity prediction method and device | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN116611702A (en) | Integrated learning photovoltaic power generation prediction method for building integrated energy management | |
| CN117952240A (en) | Photovoltaic power generation amount prediction method and device | |
| CN106960260B (en) | Wind power prediction system convenient for power dispatching | |
| CN115860190A (en) | Training of load detection model, method for detecting power load and related device | |
| CN115375014A (en) | Source-load combination probability prediction method, device and storage medium | |
| CN113033136B (en) | Simplified photovoltaic cell physical parameter extraction optimization method and system | |
| CN113505943A (en) | Method, system, equipment and medium for predicting short-term load of power grid | |
| CN110991743B (en) | Wind power short-term combination prediction method based on cluster analysis and neural network optimization | |
| CN112215383A (en) | Distributed photovoltaic power generation power prediction method and system | |
| CN116742622B (en) | Photovoltaic power generation-based power generation amount prediction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |