CN117578425A - Regional power prediction correction method under extreme weather condition - Google Patents
Regional power prediction correction method under extreme weather condition Download PDFInfo
- Publication number
- CN117578425A CN117578425A CN202311561590.0A CN202311561590A CN117578425A CN 117578425 A CN117578425 A CN 117578425A CN 202311561590 A CN202311561590 A CN 202311561590A CN 117578425 A CN117578425 A CN 117578425A
- Authority
- CN
- China
- Prior art keywords
- weather
- data
- power
- prediction
- extreme weather
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012937 correction Methods 0.000 title claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 20
- 238000012216 screening Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000007637 random forest analysis Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 12
- 238000010248 power generation Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000006870 function Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- 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
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of power prediction, and discloses a regional power prediction correction method under extreme weather conditions, which comprises the following steps: s1, obtaining and screening actual measurement data: collecting power actual measurement data, weather data and power prediction data of a power station, and screening the collected data; s2, preprocessing actual measurement data: performing time matching on the collected power station power actual measurement data, weather data and power prediction data to generate a new DataFrame; s3, extreme weather division: and carrying out condition judgment on the collected weather data content according to the weather type, thereby obtaining extreme weather type data. The invention has the advantages of accuracy, flexibility, instantaneity and the like; the accuracy of new energy power prediction can be improved by classifying the extreme weather and correcting the prediction result by using the RF model; the method has important significance for reliable operation of the power system, improvement of energy utilization efficiency and reasonable operation of the power market.
Description
Technical Field
The invention relates to the technical field of power prediction, in particular to a regional power prediction correction method under extreme weather conditions.
Background
Instability and unpredictability of new energy power generation pose a great challenge to power prediction, especially when extreme weather conditions such as strong winds and storms are faced, the efficiency of wind power generation and photovoltaic power generation can be affected to different extents, and thus the accuracy of power prediction is reduced. At present, the existing power prediction method has the problem of inaccurate prediction under extreme weather conditions;
the current power prediction technology has the following problems in extreme weather conditions:
the current short-term power prediction model lacks of effectively dividing and verifying the accuracy of the extreme weather type, and the existing short-term power prediction model has the problem of insufficient effectively dividing and verifying the accuracy of the extreme weather type under extreme weather conditions. Different extreme weather types have different effects on the efficiency of new energy power generation such as wind power generation, photovoltaic power generation and the like, but the existing model cannot fully consider the effect differences, and also lacks effective division and accuracy verification;
the current prediction model has poor generalization capability under extreme weather conditions, so that a prediction result is easy to have larger deviation, the reason is that extreme weather is rare and unpredictable, and the model cannot fully consider and capture the changes under the special conditions, so that a regional power prediction correction method under the extreme weather conditions is provided.
Disclosure of Invention
The invention provides a regional power prediction correction method under extreme weather conditions, which aims to solve the technical problem that the existing power prediction method has inaccurate prediction under extreme weather conditions.
The invention is realized by adopting the following technical scheme: a regional power prediction correction method under extreme weather conditions comprises the following steps:
s1 actual measurement data acquisition and screening
Collecting power actual measurement data, weather data and power prediction data of a power station, and screening the collected data;
s2 actual measurement data preprocessing
Performing time matching on the collected power station power actual measurement data, weather data and power prediction data to generate a new DataFrame;
s3 extreme weather division
The acquired weather data content is subjected to condition judgment according to weather types, so that extreme weather type data are obtained;
s4 extreme weather accuracy impact analysis
Performing accuracy comparison according to the divided extreme weather type data, and selecting a mean square error and a decision coefficient as accuracy evaluation indexes;
s5 prediction accuracy result optimization
And summarizing influence factors according to the comparison accuracy, optimizing the result of weather types with influenced prediction accuracy according to the summarizing result, and respectively modeling based on the divided weather types with different poles so as to eliminate prediction errors under each extreme weather type.
As a further improvement of the above solution, the content of the measured weather data in step S1 includes: the temperature, wind speed, wind power level and weather phenomenon content, and the power prediction data are the power generation amount content in the power station plan.
As a further improvement of the above-mentioned scheme, the extreme weather type in the step S3 includes windy weather, snowy weather, low-temperature weather, extreme rainfall weather, and haze cloud weather.
As a further improvement of the above solution, the root mean square error formula in step S4 is:
in the formula (1), n represents the number of samples, y i The true value is represented by a value that is true,representing the predicted value;
determining coefficient (R) 2 ) The calculation formula is as follows:
in the formula (2), y i Representing the actual value of the i-th sample,representing the predicted value of the ith sample, +.>Represents the average of all samples, and n represents the number of samples.
As a further improvement of the above solution, the modeling stage in the step S5 uses a random forest model for modeling, where the random forest model modeling step is as follows:
first for a given classifier h 1 (x),h 2 (x),…,h K (x) Randomly selecting a training set according to a distribution of random vectors X, Y and d, wherein a margin function is defined as:
in formula (3), I (X) represents an index function, which is mainly measured by the degree to which the average score of the right class at X, Y exceeds the average score of any other class. The larger the mg (x, y) value, the greater the confidence in its classification, wherein the generalization error is:
PE * =P X,Y (mg(X,Y)<0) (4)
in the formula (4), the subscript X, Y represents a probability in the X, Y space. In random forests, h k (X)=h(X,Θ k ) For a large number of trees, it follows the law of "powerful numbers" and tree structure, i.e. as the number of trees increases, all sequences Θ 1 ,…PE * All tend to converge given by (5):
the random forest model is used for modeling and prediction in the following way:
firstly, establishing a sample library under various extreme weather types, wherein x is initial predicted power uploaded by provincial regulations, y is actual measured power, and dividing a data set according to the ratio of a training set to a test set=8:2, wherein the training set is used for model training, and the test set is used for model testing;
realizing RF based on a ski-learn library in python, obtaining a final optimization model under the extreme weather condition by using a regression class (random forest) and performing parameter adjustment (n_timer=100-200, random_state=42-82);
acquiring numerical weather forecast data uploaded by all new energy power stations, summarizing and averaging the data according to the local cities of the stations, and generating the numerical weather forecast data of each local city;
based on the numerical weather forecast data of each district market, the extreme weather dividing rules established according to the invention are divided to obtain the time of occurrence of extreme weather and what extreme weather happens specifically;
and carrying out model prediction on the original regional short-term power prediction data by utilizing various extreme weather prediction models and combining the last extreme weather type division and the occurrence time, and substituting the prediction result into the original short-term power prediction data according to the prediction time.
Compared with the prior art, the invention has the beneficial effects that:
1. the random forest algorithm (RF) adopted by the invention is realized based on a ski-learn library in python, and a regression class (RandomfortrEgRessor) is used and subjected to parameter adjustment (n_detectors=100-200 and random_state=42-82) to obtain a final optimization model under the extreme weather condition. Based on the optimization model obtained in the last step, extreme weather division is carried out on weather forecast data according to a rule in the table when the short-term power of the area is predicted, whether extreme weather occurs or not is judged, and initial prediction data under the condition of the extreme weather is optimized to obtain optimized short-term prediction power.
2. The method and the device provide an extreme weather dividing mode, and verify the prediction accuracy of various extreme weather according to the dividing mode; the prediction results under the extreme weather conditions are optimized by respectively modeling the prediction results under various extreme weather types through a random forest algorithm;
3. the regional power prediction correction method has the advantages of accuracy, flexibility, instantaneity and the like; the accuracy of new energy power prediction can be improved by classifying the extreme weather and correcting the prediction result by using the RF model; the method has important significance for reliable operation of the power system, improvement of energy utilization efficiency and reasonable operation of the power market.
Drawings
Fig. 1 is a schematic diagram of a prediction correction method provided by the invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and detailed description, wherein it is to be understood that, on the premise of no conflict, the following embodiments or technical features may be arbitrarily combined to form new embodiments.
Example 1:
referring to fig. 1, a regional power prediction correction method under extreme weather conditions in this embodiment includes the following steps:
s1 actual measurement data acquisition and screening
Collecting power actual measurement data, weather data and power prediction data of a power station, and screening the collected data;
s2 actual measurement data preprocessing
Performing time matching on the collected power station power actual measurement data, weather data and power prediction data to generate a new DataFrame;
s3 extreme weather division
The acquired weather data content is subjected to condition judgment according to weather types, so that extreme weather type data are obtained;
s4 extreme weather accuracy impact analysis
Performing accuracy comparison according to the divided extreme weather type data, and selecting a mean square error and a decision coefficient as accuracy evaluation indexes;
s5 prediction accuracy result optimization
Summarizing influence factors according to the comparison precision, optimizing the result of weather types with influenced prediction precision according to the summarizing result, and respectively modeling based on the divided weather types with different poles so as to eliminate prediction errors under each extreme weather type;
the content of the weather data actually measured in the step S1 includes: the temperature, wind speed, wind power level and weather phenomenon content, and the power prediction data are the power generation capacity content in the power station plan;
the extreme weather types in the step S3 comprise strong wind weather, snowing weather, low-temperature weather, extreme rainfall weather and haze cloud weather;
the root mean square error formula in the step S4 is:
in the formula (1), n represents the number of samples, y i The true value is represented by a value that is true,representing the predicted value;
determining coefficient (R) 2 ) The calculation formula is as follows:
in the formula (2), y i Representing the actual value of the i-th sample,representing the predicted value of the ith sample, +.>Represents the average value of all samples, n represents the number of samples;
in the modeling stage in the step S5, a random forest model is adopted for modeling, wherein the random forest model modeling step is as follows:
first for a given classifier h 1 (x),h 2 (x),…,h K (x) Randomly selecting a training set according to a distribution of random vectors X, Y and d, wherein a margin function is defined as:
in formula (3), I (X) represents an index function, which is mainly measured by the degree to which the average score of the right class at X, Y exceeds the average score of any other class. The larger the mg (x, y) value, the greater the confidence in its classification, wherein the generalization error is:
PE * =P X,Y (mg(X,Y)<0) (4)
in the formula (4), the subscript X, Y represents a probability in the X, Y space. In random forests, h k (X)=h(X,Θ k ) For a large number of trees, it follows the law of "powerful numbers" and tree structure, i.e. as the number of trees increases, all sequences Θ 1 ,…PE * All tend to converge given by (5):
the random forest model is used for modeling and prediction in the following way:
firstly, establishing a sample library under various extreme weather types, wherein x is initial predicted power uploaded by provincial regulations, y is actual measured power, and dividing a data set according to the ratio of a training set to a test set=8:2, wherein the training set is used for model training, and the test set is used for model testing;
realizing RF based on a ski-learn library in python, obtaining a final optimization model under the extreme weather condition by using a regression class (random forest) and performing parameter adjustment (n_timer=100-200, random_state=42-82);
acquiring numerical weather forecast data uploaded by all new energy power stations, summarizing and averaging the data according to the local cities of the stations, and generating the numerical weather forecast data of each local city;
based on the numerical weather forecast data of each district market, the extreme weather dividing rules established according to the invention are divided to obtain the time of occurrence of extreme weather and what extreme weather happens specifically;
and carrying out model prediction on the original regional short-term power prediction data by utilizing various extreme weather prediction models and combining the last extreme weather type division and the occurrence time, and substituting the prediction result into the original short-term power prediction data according to the prediction time.
Example 2:
a regional power prediction correction method under extreme weather conditions comprises the following steps:
s1 actual measurement data acquisition and screening
Collecting power actual measurement data, weather data and power prediction data of a power station, and screening the collected data;
the measured weather data content includes: the temperature, wind speed, wind power level and weather phenomenon content, and the power prediction data are the power generation capacity content in the power station plan;
s2 actual measurement data preprocessing
Performing time matching on the collected power station power actual measurement data, weather data and power prediction data to generate a new DataFrame;
s3 extreme weather division
The acquired weather data content is subjected to condition judgment according to weather types, so that extreme weather type data are obtained; extreme weather types include windy weather, snowy weather, low temperature weather, extreme precipitation weather, and haze cloudy weather;
wherein the various extreme weather division criteria are shown in table 1;
table 1 is extreme weather type and decision conditions:
s4 extreme weather accuracy impact analysis
Performing accuracy comparison according to the classified extreme weather type data, selecting a mean square error and a decision coefficient as accuracy evaluation indexes, and comparing the RMSE of the prediction result under certain extreme weather condition with that under normal weather conditionElevated and R 2 A decrease is considered to be affected by this extreme weather;
the root mean square error formula is:
in the formula (1), n represents the number of samples, y i The true value is represented by a value that is true,representing the predicted value;
determining coefficient (R) 2 ) The calculation formula is as follows:
in the formula (2), y i Representing the actual value of the i-th sample,representing the predicted value of the ith sample, +.>Represents the average value of all samples, n represents the number of samples;
s5 prediction accuracy result optimization
Summarizing influence factors according to the comparison precision, optimizing the result of weather types with influenced prediction precision according to the summarizing result, and respectively modeling based on the divided weather types with different poles so as to eliminate prediction errors under each extreme weather type;
taking low-temperature weather as an example, a machine learning model is established between the initial predicted value and the measured power value of the power under the extreme weather condition so as to eliminate the prediction error under the extreme weather condition.
Modeling is performed on model optimization by using a Random Forest model, wherein Random Forest (RF) is a machine learning model, and belongs to a form of integrated learning. It is a set of multiple decision trees, with the final predictions made by voting or averaging the predictions of each decision tree. For a given classifier h 1 (x),h 2 (x),…,h K (x) Randomly selecting a training set according to a distribution of random vectors X, Y and d, wherein a margin function is defined as:
in formula (3), I (X) represents an index function, which is mainly measured by the degree to which the average score of the right class at X, Y exceeds the average score of any other class. The larger the mg (x, y) value, the greater the confidence in its classification, wherein the generalization error is:
PE * =P X,Y (mg(X,Y)<0) (4)
in the formula (4), the subscript X, Y represents a probability in the X, Y space. In random forests, h k (X)=h(X,Θ k ) For a large number of trees, it follows the law of "powerful numbers" and tree structure, i.e. as the number of trees increases, all sequences Θ 1 ,…PE * All tend to converge given by (5):
when modeling prediction is carried out on the random forest model, the following mode is adopted:
firstly, establishing a sample library under various extreme weather types, wherein x is initial predicted power uploaded by provincial regulations, y is actual measured power, and dividing a data set according to the ratio of a training set to a test set=8:2, wherein the training set is used for model training, and the test set is used for model testing;
realizing RF based on a ski-learn library in python, obtaining a final optimization model under the extreme weather condition by using a regression class (random forest) and performing parameter adjustment (n_timer=100-200, random_state=42-82);
acquiring numerical weather forecast data uploaded by all new energy power stations, summarizing and averaging the data according to the local cities of the stations, and generating the numerical weather forecast data of each local city;
based on the numerical weather forecast data of each district market, the extreme weather dividing rules established according to the invention are divided to obtain the time of occurrence of extreme weather and what extreme weather happens specifically;
and carrying out model prediction on the original regional short-term power prediction data by utilizing various extreme weather prediction models and combining the last extreme weather type division and the occurrence time, and substituting the prediction result into the original short-term power prediction data according to the prediction time.
The random forest algorithm (RF) adopted in the application is implemented based on the ski-learn library in python, and a regression class (random forest) is used and subjected to parameter tuning (n_timer=100-200 and random_state=42-82) to obtain a final optimization model in the extreme weather condition. Based on the optimization model obtained in the last step, extreme weather division is carried out on weather forecast data according to a rule in the table when the short-term power of the area is predicted, whether extreme weather occurs or not is judged, and initial prediction data under the condition of the extreme weather is optimized to obtain optimized short-term prediction power.
The method and the device provide an extreme weather dividing mode, and verify the prediction accuracy of various extreme weather according to the dividing mode; the prediction results under the extreme weather conditions are optimized by respectively modeling the prediction results under various extreme weather types through a random forest algorithm;
the regional power prediction correction method has the advantages of accuracy, flexibility, instantaneity and the like; the accuracy of new energy power prediction can be improved by classifying the extreme weather and correcting the prediction result by using the RF model; the method has important significance for reliable operation of the power system, improvement of energy utilization efficiency and reasonable operation of the power market.
The above embodiments are only preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but any insubstantial changes and substitutions made by those skilled in the art on the basis of the present invention are intended to be within the scope of the present invention as claimed.
Claims (5)
1. The regional power prediction correction method under the extreme weather condition is characterized by comprising the following steps of:
s1 actual measurement data acquisition and screening
Collecting power actual measurement data, weather data and power prediction data of a power station, and screening the collected data;
s2 actual measurement data preprocessing
Performing time matching on the collected power station power actual measurement data, weather data and power prediction data to generate a new DataFrame;
s3 extreme weather division
The acquired weather data content is subjected to condition judgment according to weather types, so that extreme weather type data are obtained;
s4 extreme weather accuracy impact analysis
Performing accuracy comparison according to the divided extreme weather type data, and selecting a mean square error and a decision coefficient as accuracy evaluation indexes;
s5 prediction accuracy result optimization
And summarizing influence factors according to the comparison accuracy, optimizing the result of weather types with influenced prediction accuracy according to the summarizing result, and respectively modeling based on the divided weather types with different poles so as to eliminate prediction errors under each extreme weather type.
2. The method for regional power prediction correction in extreme weather conditions as claimed in claim 1, wherein said actually measured weather data content in step S1 comprises: the temperature, wind speed, wind power level and weather phenomenon content, and the power prediction data are the power generation amount content in the power station plan.
3. The method for predicting and correcting regional power in extreme weather according to claim 1, wherein the extreme weather type in step S3 includes windy weather, snowy weather, low temperature weather, extreme rainfall weather and haze cloud weather.
4. The method for regional power prediction correction under extreme weather conditions as claimed in claim 1, wherein the root mean square error formula in step S4 is:
in the formula (1), n represents the number of samples, y i The true value is represented by a value that is true,representing the predicted value;
determining coefficient (R) 2 ) The calculation formula is as follows:
in the formula (2), y i Representing the actual value of the i-th sample,representing the predicted value of the ith sample, +.>Represents the average of all samples, and n represents the number of samples.
5. The method for regional power prediction correction under extreme weather conditions as claimed in claim 1, wherein the modeling step in step S5 uses a random forest model for modeling, and the step of modeling the random forest model is as follows:
first for a given classifier h 1 (x),h 2 (x),…,h K (x) Is root and is assembledThe training set is randomly selected according to a distribution of random vectors X, Y and d, wherein the margin function is defined as:
in formula (3), I (X) represents an index function, which is mainly measured by the degree to which the average score of the right class at X, Y exceeds the average score of any other class. The larger the mg (x, y) value, the greater the confidence in its classification, wherein the generalization error is:
PE * =P X,Y (mg(X,Y)<0) (4)
in the formula (4), the subscript X, Y represents a probability in the X, Y space. In random forests, h k (X)=h(X,Θ k ) For a large number of trees, it follows the law of "powerful numbers" and tree structure, i.e. as the number of trees increases, all sequences Θ 1 ,…PE * All tend to converge given by (5):
the random forest model is used for modeling and prediction in the following way:
firstly, establishing a sample library under various extreme weather types, wherein x is initial predicted power uploaded by provincial regulations, y is actual measured power, and dividing a data set according to the ratio of a training set to a test set=8:2, wherein the training set is used for model training, and the test set is used for model testing;
realizing RF based on a ski-learn library in python, obtaining a final optimization model under the extreme weather condition by using a regression class (random forest) and performing parameter adjustment (n_timer=100-200, random_state=42-82);
acquiring numerical weather forecast data uploaded by all new energy power stations, summarizing and averaging the data according to the local cities of the stations, and generating the numerical weather forecast data of each local city;
based on the numerical weather forecast data of each district market, the extreme weather dividing rules established according to the invention are divided to obtain the time of occurrence of extreme weather and what extreme weather happens specifically;
and carrying out model prediction on the original regional short-term power prediction data by utilizing various extreme weather prediction models and combining the last extreme weather type division and the occurrence time, and substituting the prediction result into the original short-term power prediction data according to the prediction time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311561590.0A CN117578425A (en) | 2023-11-22 | 2023-11-22 | Regional power prediction correction method under extreme weather condition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311561590.0A CN117578425A (en) | 2023-11-22 | 2023-11-22 | Regional power prediction correction method under extreme weather condition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117578425A true CN117578425A (en) | 2024-02-20 |
Family
ID=89860282
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311561590.0A Pending CN117578425A (en) | 2023-11-22 | 2023-11-22 | Regional power prediction correction method under extreme weather condition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117578425A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117892638A (en) * | 2024-03-14 | 2024-04-16 | 河海大学 | Drought formation time prediction method and system using conditional probability function |
-
2023
- 2023-11-22 CN CN202311561590.0A patent/CN117578425A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117892638A (en) * | 2024-03-14 | 2024-04-16 | 河海大学 | Drought formation time prediction method and system using conditional probability function |
CN117892638B (en) * | 2024-03-14 | 2024-05-17 | 河海大学 | Drought formation time prediction method and system using conditional probability function |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
CN117578425A (en) | Regional power prediction correction method under extreme weather condition | |
WO2024051524A1 (en) | Joint prediction method and apparatus for hydraulic, wind and photovoltaic generation power | |
WO2023201552A1 (en) | County-wide photovoltaic prediction method based on cluster division and data enhancement | |
CN110766134A (en) | Photovoltaic power station short-term power prediction method based on cyclic neural network | |
CN114006369A (en) | Regional wind and light station power joint prediction method and device, electronic equipment and storage medium | |
CN113052386A (en) | Distributed photovoltaic daily generated energy prediction method and device based on random forest algorithm | |
CN110460038A (en) | It is a kind of to be related to more scene method for expansion planning of power transmission network of new-energy grid-connected | |
CN114240003A (en) | New energy output prediction method, system, storage medium and equipment | |
CN115936177A (en) | Photovoltaic output power prediction method and system based on neural network | |
CN114399081A (en) | Photovoltaic power generation power prediction method based on weather classification | |
CN117613883A (en) | Method and device for predicting generated power, computer equipment and storage medium | |
CN109599899B (en) | Setting method for new energy operation simulation boundary conditions | |
CN113689053B (en) | Strong convection weather overhead line power failure prediction method based on random forest | |
CN115169659A (en) | Ultra-short-term roof photovoltaic power prediction method and system based on multiple classifiers | |
CN112883577A (en) | Typical scene generation method for offshore wind farm output and storage medium | |
CN116663393A (en) | Random forest-based power distribution network continuous high-temperature fault risk level prediction method | |
CN115660132B (en) | Photovoltaic power generation power prediction method and system | |
Kratzenberg et al. | Identification and handling of critical irradiance forecast errors using a random forest scheme–A case study for southern Brazil | |
CN115733258A (en) | Control method of all-indoor intelligent substation system based on Internet of things technology | |
CN114330478B (en) | Wind speed classification correction method for wind speed forecast of power grid | |
CN111596384B (en) | Inclined plane radiation prediction method based on weather type effective identification | |
CN115238967A (en) | Photovoltaic power prediction method and device combining cloud picture and adjacent power station cluster | |
CN113780643A (en) | Photovoltaic power station short-term output prediction method based on case reasoning | |
CN114511127A (en) | Neural network-based regional photovoltaic output characteristic long-term prediction method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |