CN117195751B - Power combination prediction method and equipment for regional new energy - Google Patents
Power combination prediction method and equipment for regional new energy Download PDFInfo
- Publication number
- CN117195751B CN117195751B CN202311468645.3A CN202311468645A CN117195751B CN 117195751 B CN117195751 B CN 117195751B CN 202311468645 A CN202311468645 A CN 202311468645A CN 117195751 B CN117195751 B CN 117195751B
- Authority
- CN
- China
- Prior art keywords
- power
- prediction
- target area
- new energy
- prediction result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000005540 biological transmission Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004088 simulation Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 12
- 238000003860 storage Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a power combination prediction method and equipment for new regional energy, belonging to the technical field of power prediction, wherein the method comprises the following steps: obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area; determining the deviation condition and the correlation of the power prediction results corresponding to the prediction modes and the actual power data according to the power prediction results corresponding to the prediction modes; determining contribution degree duty ratios corresponding to all prediction modes according to deviation conditions and correlations corresponding to all prediction modes; and determining a target power prediction result of the target area according to the contribution duty ratio and the power prediction result corresponding to each prediction mode. In the scheme, various different prediction modes reflect different change trends of the new energy power, so that the accuracy of new energy power prediction can be improved, and errors can be reduced.
Description
Technical Field
The invention relates to the technical field of power prediction, in particular to a power combination prediction method and equipment for regional new energy.
Background
The new energy resource belongs to climate resources, is easily influenced by factors such as seasons, latitude, altitude, sea and land distribution, topography and cloud cover, the conventional numerical weather forecast technology cannot accurately grasp the change condition of the all-time wind and light resource in the whole domain, the power conversion model algorithm cannot adapt to new energy fluctuation in various scenes, the power grid starting mode arrangement and the power balance adjustment are difficult to support, and the power balance arrangement and the power grid safe and stable operation are influenced.
At present, different algorithms are adopted in a new energy power prediction system to obtain different power prediction data, the predicted power data obtained by the different algorithms have different fluctuation conditions, and the accuracy of each algorithm has larger difference in part of time. In order to eliminate the operation risk caused by errors, the full-scale thermal power generating unit is reserved before the safety of the system is ensured, so that on one hand, the operation cost of the system is increased, on the other hand, the new energy consumption space is occupied, and the new energy consumption is restricted to a certain extent.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a power combination prediction method and equipment for regional new energy.
The invention provides a power combination prediction method of a new regional energy source, which comprises the following steps:
Obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
determining contribution degree duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
and determining a target power prediction result of the target area according to the contribution degree duty ratio corresponding to each prediction mode and the power prediction result.
According to the power combination prediction method of the regional new energy provided by the invention, the power prediction results of the target region obtained based on a plurality of different prediction modes are obtained, and the method comprises the following steps:
acquiring power prediction data of each new energy station in the target area;
determining a power prediction result of the target area by using the following formula (1);
（1）
wherein,representing the power prediction result of the target area corresponding to the first prediction mode, Is->Power forecast data for each new energy station,qcapfor the total loader capacity within the target area,is->The installed capacity of the new energy stations.
According to the power combination prediction method of the regional new energy provided by the invention, the power prediction results of the target region obtained based on a plurality of different prediction modes are obtained, and the method comprises the following steps:
acquiring the actual transmission power data of each new energy station in the target area;
dividing the new energy stations in the target area into a plurality of groups by adopting a clustering algorithm according to the actual transmission power data of each new energy station;
selecting a new energy station with highest correlation with the real power data of the target area from each group as a target new energy station;
and determining a power prediction result of the target area according to the target new energy stations in each group in an upscaling mode.
According to the power combination prediction method of the regional new energy provided by the invention, the power prediction result of the target region is determined by utilizing an upscaling mode according to the target new energy stations in each group, and the method comprises the following steps:
determining a power prediction result of the target region using the following formula (2);
（2）
Wherein,representing the power prediction result of the target area corresponding to the second prediction mode,indicate->The>Power forecast data of the individual new energy stations,/->Indicate->The installed capacity of the new energy station, said +.>And the new energy stations are the target new energy stations.
According to the power combination prediction method of the regional new energy provided by the invention, the power prediction results of the target region obtained based on a plurality of different prediction modes are obtained, and the method comprises the following steps:
acquiring actual transmission power data and weather numerical simulation data of each new energy station in the target area;
and obtaining a power prediction result of the target area by utilizing the back propagation BP neural network model obtained by training according to the actual power data and the weather numerical simulation data.
According to the power combination prediction method of the regional new energy provided by the invention, the deviation condition of the power prediction result corresponding to each prediction mode and the actual power data is determined according to the power prediction result corresponding to each prediction mode, and the method comprises the following steps:
calculating absolute deviation of a predicted power result corresponding to each prediction mode and actual power data by using the following formula (3);
（3）
Wherein,indicates the first predictive mode corresponding to +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the second predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the third predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Indicates the first predictive mode corresponding to +.>Power prediction results of individual new energy stations，Representing the second predictive mode corresponding +.>Power prediction result of each new energy station, < >>Representing the third predictive mode corresponding +.>Power prediction result of each new energy station, < >>Indicate->Real power data of the new energy stations;
calculating the variance corresponding to each prediction mode according to the absolute deviation corresponding to each prediction mode to obtain the deviation condition corresponding to each prediction mode;
（4）
wherein,representing the variance of the power prediction result of the target area corresponding to the first prediction mode and the actual power data, +.>Representing the variance of the power prediction result of the target area corresponding to the second prediction mode and the actual power data, +. >Representing the variance of the power prediction result and the actual power data of the target area corresponding to the third prediction mode; n represents the target regionThe number of new energy stations in the system.
According to the power combination prediction method of the regional new energy provided by the invention, the correlation between the power prediction results corresponding to the prediction modes and the actual power data is determined according to the power prediction results corresponding to the prediction modes, and the method comprises the following steps:
determining the correlation between the power prediction result corresponding to each prediction mode and the actual power data by using the following formula (5);
（5）
wherein,representing the correlation corresponding to the first predictive mode, < >>Representing the correlation corresponding to the second predictive mode, < >>Representing the correlation corresponding to the third prediction mode;Representing covariance +_>Representing the variance;
determining a contribution degree duty ratio corresponding to each prediction mode according to the deviation condition and the correlation corresponding to each prediction mode, wherein the determination comprises the following steps:
calculating the contribution degree duty ratio of the predicted power result corresponding to each prediction mode by using the following formula (6);
（6）
wherein,representing the contribution degree ratio corresponding to the first prediction mode, +. >Representing the contribution ratio corresponding to the second prediction mode, +.>The contribution duty ratio corresponding to the third prediction mode is shown.
According to the power combination prediction method of the regional new energy provided by the invention, the target power prediction result of the target region is determined according to the contribution degree duty ratio and the power prediction result corresponding to each prediction mode, and the method comprises the following steps:
determining a comprehensive power prediction result of a target area corresponding to each adjustment coefficient according to the plurality of adjustment coefficients, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual transmission power data of the target area;
and determining a target adjustment coefficient according to the root mean square error accuracy, and determining a target power prediction result of the target area by using the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area.
According to the power combination prediction method of the regional new energy provided by the invention, the comprehensive power prediction result of the target region corresponding to each adjustment coefficient is determined according to the plurality of adjustment coefficients, the contribution degree duty ratio corresponding to each prediction mode and the power prediction result of the target region, and the method comprises the following steps:
Determining the comprehensive power prediction result according to a plurality of adjustment coefficients by using the following formula (7);
（7）
wherein X represents the adjustment coefficient,showing the comprehensive power prediction result;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual power data of the target area, wherein the method comprises the following steps:
calculating the root mean square error accuracy by using the following formula (8) for any one of the adjustment coefficients;
（8）
wherein,represents the root mean square error accuracy, m represents the number of data samples, +.>The value range of (2) is 1-m;the +.f in the array representing the integrated power prediction result>Individual integrated power prediction results,/->Indicate->Total loader capacity of target area corresponding to the individual data samples,/->The +.f in the array representing real transmit power data>Actual transmit power data;
determining a target adjustment coefficient according to the root mean square error accuracy, and determining a target power prediction result of the target area by using the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode, and the power prediction result of the target area, including:
Taking the adjustment coefficient corresponding to the maximum value in the root mean square accuracy corresponding to each adjustment coefficient as the target adjustment coefficient;
and obtaining the target power prediction result according to the target adjustment coefficient, the contribution degree duty ratio corresponding to each prediction mode and the power prediction result of the target area.
The invention also provides a power combination prediction device of the regional new energy, which comprises the following components:
the acquisition module is used for acquiring power prediction results of the target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
the processing module is used for determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
the processing module is further used for determining contribution duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
and the processing module is further used for determining a target power prediction result of the target area according to the contribution degree duty ratio corresponding to each prediction mode and the power prediction result.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the power combination prediction method of the new energy source in any one of the areas when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of power combination prediction for a regional new energy source as described in any of the above.
The invention also provides a computer program product comprising a computer program which when executed by a processor implements a method of predicting power combinations of a new energy source in an area as described in any one of the above.
The method and the equipment for predicting the power combination of the new regional energy source acquire the power prediction results of the target region based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area; determining the deviation condition and the correlation of the power prediction results corresponding to the prediction modes and the actual power data according to the power prediction results corresponding to the prediction modes; determining contribution degree duty ratios corresponding to all prediction modes according to deviation conditions and correlations corresponding to all prediction modes; and determining a target power prediction result of the target area according to the contribution duty ratio and the power prediction result corresponding to each prediction mode. In the scheme, different change trends of the new energy power are reflected by different prediction modes, and the power prediction is performed based on the power prediction results and the contribution duty ratio corresponding to the different prediction modes, so that the accuracy of the new energy power prediction can be improved, and the error is reduced.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a power combination prediction method of a new regional energy source provided by the invention;
FIG. 2 is a second flow chart of the power combination prediction method for regional new energy provided by the invention;
FIG. 3 is a schematic diagram of simulation results of a power combination prediction method of a regional new energy source provided by the invention;
FIG. 4 is a schematic structural diagram of a power combination prediction device for regional new energy provided by the invention;
fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
First, the nouns and application scenarios related to the embodiments of the present invention are described:
and (3) power prediction: the amount of power that can be output by a new energy station (e.g., a new energy station) for a future period of time is predicted to schedule a dispatch plan. The power prediction technology can help the power production scheduling mechanism to improve the utilization efficiency of new energy, reduce the rotation standby capacity of the system and improve the running economy of the power grid;
contribution degree: refers to the degree of contribution of a factor to the population and is typically used to measure the importance of a factor in the population.
The following describes the technical solution of the embodiment of the present invention in detail with reference to fig. 1 to 5. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a flow chart of a power combination prediction method of a regional new energy source provided by the invention. As shown in fig. 1, the method provided in this embodiment includes:
step 101, obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
Specifically, power prediction results of a target area, which are obtained based on a plurality of different prediction modes, are obtained, wherein the power prediction results are total power prediction results of all new energy stations in the target area;
the different prediction modes refer to, for example, calculating power prediction results of the target area by using different power prediction algorithms.
Step 102, determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlation of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
specifically, historical actual power data of a target area are obtained, and deviation situations and correlations of power prediction results corresponding to all prediction modes and the actual power data are further determined;
the deviation condition is, for example, absolute deviation, relative deviation, etc. calculated.
Step 103, determining contribution degree duty ratios corresponding to all prediction modes according to deviation conditions and correlations corresponding to all prediction modes;
specifically, for each prediction mode, the contribution degree duty ratio corresponding to the prediction mode is determined according to the deviation condition and the correlation corresponding to the prediction mode.
And 104, determining a target power prediction result of the target area according to the contribution duty ratio and the power prediction result corresponding to each prediction mode.
Specifically, the target power prediction result of the target area is determined according to the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area corresponding to each prediction mode, for example, the target power prediction result is obtained by adopting a weighting processing mode.
The method of the embodiment obtains power prediction results of the target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area; determining the deviation condition and the correlation of the power prediction results corresponding to the prediction modes and the actual power data according to the power prediction results corresponding to the prediction modes; determining contribution degree duty ratios corresponding to all prediction modes according to deviation conditions and correlations corresponding to all prediction modes; and determining a target power prediction result of the target area according to the contribution duty ratio and the power prediction result corresponding to each prediction mode. In the scheme, different change trends of the new energy power are reflected by different prediction modes, and the power prediction is performed based on the power prediction results and the contribution duty ratio corresponding to the different prediction modes, so that the accuracy of the new energy power prediction can be improved, and the error is reduced.
Alternatively, for the first prediction mode, step 101 may be implemented as follows:
acquiring power prediction data of each new energy station in the target area;
determining a power prediction result of the target area by using the following formula (1);
（1）
wherein,representing the power prediction result of the target area corresponding to the first prediction mode,is->Power forecast data for each new energy station,qcapfor the total loader capacity within the target area,is->The installed capacity of the new energy stations.
Specifically, the first prediction mode is to obtain a predicted power result of the target area through a station predicted power accumulation mode.
Acquiring power prediction data of each new energy station in target areaFinally obtaining the power prediction result of the target area by means of the installed ratio calculation>。
The installed capacity refers to the installed quantity.
Optionally, the new energy station is a wind farm station.
In the embodiment, the power prediction result of the target area is determined by a prediction power accumulation mode, so that the implementation complexity is low, and the accuracy and the efficiency are high.
Alternatively, for the second prediction mode, step 101 may be implemented as follows:
Acquiring the actual transmission power data of each new energy station in the target area;
dividing the new energy stations in the target area into a plurality of groups by adopting a clustering algorithm according to the actual transmission power data of each new energy station;
selecting a new energy station with highest correlation with the real power data of the target area from each group as a target new energy station;
and determining a power prediction result of the target area according to the target new energy stations in each group in an upscaling mode.
Specifically, the second prediction mode is to obtain the power prediction result of the target area by using an upscaling mode through the power prediction result of the typical station.
Acquiring the actual power data RPower of each new energy station in the target area i The stations are divided into a plurality of groups by a clustering algorithm (such as a k-means clustering algorithm), the station with the highest correlation with the real power data of the target area is selected as a typical template station (namely a target new energy station) in each group, and then the station is increasedThe power result of the scale mode calculation target area can be expressed as。
Optionally, determining a power prediction result of the target region using the following formula (2);
（2）
Wherein,representing the power prediction result of the target area corresponding to the second prediction mode,indicate->The>Power forecast data of the individual new energy stations,/->Indicate->The installed capacity of the new energy stations.
In the embodiment, the power prediction result of the target area is determined through the clustering algorithm and the upscaling mode, so that the implementation complexity is low, and the accuracy and the efficiency are high.
Alternatively, for the third prediction mode, step 101 may be implemented as follows:
acquiring actual transmission power data and weather numerical simulation data of each new energy station in the target area;
and obtaining a power prediction result of the target area by utilizing the back propagation BP neural network model obtained by training according to the actual power data and the weather numerical simulation data.
Specifically, the third prediction mode is to obtain a power prediction result of the target area by using a Back Propagation (BP) neural network model obtained by training.
The following is a training process of the BP neural network model:
establishing an initial BP neural network model;
acquiring historical sample data of each new energy station in the target area, including: real transmit power data and weather numerical simulation data.
And carrying out normalization and standardization processing on the actual power data and the weather numerical simulation data in the historical sample data, and training the BP neural network model by using the processed data, thereby obtaining the trained BP neural network model.
The power prediction result of the target area is obtained by utilizing the BP neural network model obtained by training and can be expressed as。
In the embodiment, the power prediction result of the target area is determined through the trained BP neural network model, so that the accuracy and the efficiency are high.
Optionally, in step 102, the deviation situation between the predicted power result corresponding to each prediction mode and the actual power data is determined, which may be the following manner:
calculating absolute deviation of a predicted power result corresponding to each prediction mode and actual power data by using the following formula (3);
（3）
wherein,indicates the first predictive mode corresponding to +.>New energy sourceAbsolute deviation of the power prediction result of the station from the actual power data, < >>Representing the second predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the third predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +. >Representing the first prediction modejPower prediction result of each new energy station, < >>Representing the second predictive mode corresponding +.>Power prediction result of each new energy station, < >>Representing the third predictive mode corresponding +.>Power prediction result of each new energy station, < >>Indicate->Real power data of the new energy stations;
calculating the variance corresponding to each prediction mode according to the absolute deviation corresponding to each prediction mode to obtain the deviation condition corresponding to each prediction mode;
（4）
wherein,representing the variance of the power prediction result of the target area corresponding to the first prediction mode and the actual power data, +.>Representing the variance of the power prediction result of the target area corresponding to the second prediction mode and the actual power data, +.>Representing the variance of the power prediction result and the actual power data of the target area corresponding to the third prediction mode; n represents the number of new energy stations within the target area.
Specifically, calculating absolute deviation of a power prediction result corresponding to each prediction mode and actual power data by using a formula (3);
further, calculating the deviation condition corresponding to each prediction mode by using a formula (4);
In the above embodiment, the absolute deviation and the variance are used to obtain the deviation condition corresponding to each prediction mode, so that the deviation condition of the predicted power result and the actual power data can be more accurately represented, and the power prediction result of the target area is finally determined with higher accuracy.
Optionally, in step 102, the correlation between the predicted power result corresponding to each of the prediction modes and the actual power data is determined, which may be the following manner:
determining the correlation between the power prediction result corresponding to each prediction mode and the actual power data by using the following formula (5);
（5）
wherein,representing the correlation corresponding to the first predictive mode, < >>Representing the correlation corresponding to the second predictive mode, < >>Representing the correlation corresponding to the third prediction mode;Representing covariance +_>Representing the variance;
step 102 may be performed in the following manner:
calculating the contribution degree duty ratio of the predicted power result corresponding to each prediction mode by using the following formula (6);
（6）
wherein,representing the contribution degree ratio corresponding to the first prediction mode, +.>Representing the contribution ratio corresponding to the second prediction mode, +.>The contribution duty ratio corresponding to the third prediction mode is shown.
In the embodiment, the determination of the initial weight of each prediction mode is realized by calculating the contribution degree duty ratio corresponding to each prediction mode, the realization complexity is low, and then the target power prediction result is determined by combining according to each prediction mode, so that the power prediction result is more accurate.
Alternatively, as shown in fig. 2, step 104 may be specifically implemented by:
step 1041, determining a comprehensive power prediction result of the target area corresponding to each adjustment coefficient according to the plurality of adjustment coefficients, the contribution duty ratio corresponding to each prediction mode, and the power prediction result of the target area;
step 1042, determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual power data of the target area;
step 1043, determining a target adjustment coefficient according to the root mean square error accuracy, and determining a target power prediction result of the target area by using the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode, and the power prediction result of the target area.
Specifically, the target adjustment coefficients may be calculated by a multivariate repetitive weighting method, for example, the initial value of the adjustment coefficient is set to x=0.5, the step size is set to 0.05, and the number of times is set to 20, so as to repeatedly and circularly determine the comprehensive power prediction result of the target area corresponding to each adjustment coefficient, determine the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual power data of the target area, and finally calculate the target adjustment coefficient according to a plurality of root mean square error accuracy.
Optionally, determining the comprehensive power prediction result according to a plurality of adjustment coefficients by using the following formula (7);
（7）
wherein X represents the adjustment coefficient,representing the comprehensive power prediction result;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual power data of the target area, wherein the method comprises the following steps:
calculating the root mean square error accuracy by using the following formula (8) for any one of the adjustment coefficients;
（8）
wherein,represents the root mean square error accuracy, m represents the number of data samples, +.>The value range of (2) is 1-m;the +.f in the array representing the integrated power prediction result>Individual integrated power prediction results,/->Indicate->Total loader capacity of target area corresponding to the individual data samples,/->The +.f in the array representing real transmit power data>Actual transmit power data;
the number of the data samples is the number of a plurality of different adjustment coefficients, and the comprehensive power prediction results corresponding to the plurality of adjustment coefficients and the actual power data are respectively combined to obtain an array.
Determining a target adjustment coefficient according to the root mean square error accuracy, and determining a target power prediction result of the target area by using the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode, and the power prediction result of the target area, including:
Taking the adjustment coefficient corresponding to the maximum value in the root mean square accuracy corresponding to each adjustment coefficient as the target adjustment coefficient;
and obtaining the target power prediction result according to the target adjustment coefficient, the contribution degree duty ratio corresponding to each prediction mode and the power prediction result of the target area.
Specifically, calculating the root mean square error accuracy of qpower and Rpower once by using the formula (8) once for each X value in each cycle;
for example, a set of root mean square error accuracy arrays are obtained after 20 cycle traversals。
Finding root mean square accuracy rate arrayMaximum value of +.>Corresponding adjustment coefficient->Obtaining a final power prediction combination formula (9) as target adjustment;
（9）
calculating a target power prediction result of the target region using equation (9),and representing the target power prediction result of the target area. />
In the above embodiment, the integrated power prediction result corresponding to the adjustment coefficient is determined multiple times, and the root mean square error accuracy is determined, so that the target adjustment coefficient is determined, that is, the power prediction result of the target area can be determined more accurately according to the target adjustment coefficient.
Fig. 3 shows simulation results corresponding to several prediction modes, in which the power prediction result 1 is a power prediction result obtained by using the first prediction mode, the power prediction result 2 is a power prediction result obtained by using the second prediction mode, and the power prediction result 3 is a power prediction result obtained by using the third prediction mode.
In summary, the method of the embodiment of the invention has the following advantages: the accuracy of new energy power prediction can be improved, and errors are reduced. The multi-prediction power combined prediction solves the limitation of a single model prediction method, avoids uncertainty and error existing in single model prediction, and accordingly predicts new energy power better.
The power combination prediction device for the regional new energy provided by the invention is described below, and the power combination prediction device for the regional new energy described below and the power combination prediction method for the regional new energy described above can be correspondingly referred to each other.
Fig. 4 is a schematic structural diagram of a power combination prediction device for regional new energy provided by the invention. As shown in fig. 4, the power combination prediction apparatus for regional new energy provided in this embodiment includes:
an obtaining module 410, configured to obtain power prediction results of the target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
the processing module 420 is configured to determine, according to the power prediction results corresponding to the prediction modes, a deviation condition of the power prediction results corresponding to the prediction modes and real power data, and a correlation between the power prediction results and the real power data;
The processing module 420 is further configured to determine a contribution duty ratio corresponding to each prediction mode according to the deviation condition and the correlation corresponding to each prediction mode;
the processing module 420 is further configured to determine a target power prediction result of the target area according to the contribution duty ratio and the power prediction result corresponding to each prediction mode.
Optionally, the obtaining module 410 is specifically configured to:
acquiring power prediction data of each new energy station in the target area;
determining a power prediction result of the target area by using the following formula (1);
（1）
wherein,representing the power prediction result of the target area corresponding to the first prediction mode,is->Power forecast data for each new energy station,qcapfor the total loader capacity within the target area,is->The installed capacity of the new energy stations.
Optionally, the obtaining module 410 is specifically configured to:
acquiring the actual transmission power data of each new energy station in the target area;
dividing the new energy stations in the target area into a plurality of groups by adopting a clustering algorithm according to the actual transmission power data of each new energy station;
selecting a new energy station with highest correlation with the real power data of the target area from each group as a target new energy station;
And determining a power prediction result of the target area according to the target new energy stations in each group in an upscaling mode.
Optionally, the obtaining module 410 is specifically configured to:
determining a power prediction result of the target region using the following formula (2);
（2）
wherein,representing the power prediction result of the target area corresponding to the second prediction mode,indicate->The>Power forecast data of the individual new energy stations,/->Indicate->The installed capacity of the new energy stations.
Optionally, the obtaining module 410 is specifically configured to:
acquiring actual transmission power data and weather numerical simulation data of each new energy station in the target area;
and obtaining a power prediction result of the target area by utilizing the back propagation BP neural network model obtained by training according to the actual power data and the weather numerical simulation data.
Optionally, the processing module 420 is specifically configured to:
calculating absolute deviation of a predicted power result corresponding to each prediction mode and actual power data by using the following formula (3);
（3）
wherein,indicates the first predictive mode corresponding to +.>Absolute deviation of power prediction result of each new energy station from real power data, +. >Representing the second predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the third predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Indicates the first predictive mode corresponding to +.>Power prediction result of each new energy station, < >>Representing the second predictive mode corresponding +.>Power prediction result of each new energy station, < >>Representing the third predictive mode corresponding +.>Power prediction result of each new energy station, < >>Indicate->Real power data of the new energy stations;
calculating the variance corresponding to each prediction mode according to the absolute deviation corresponding to each prediction mode to obtain the deviation condition corresponding to each prediction mode;
（4）
wherein,representing the variance of the power prediction result of the target area corresponding to the first prediction mode and the actual power data, +.>Representing the variance of the power prediction result of the target area corresponding to the second prediction mode and the actual power data, +.>Representing the variance of the power prediction result and the actual power data of the target area corresponding to the third prediction mode; n represents the number of new energy stations within the target area.
Optionally, the processing module 420 is specifically configured to:
determining the correlation between the power prediction result corresponding to each prediction mode and the actual power data by using the following formula (5);
（5）
wherein,representing the correlation corresponding to the first predictive mode, < >>Representing the correlation corresponding to the second predictive mode, < >>Representing the correlation corresponding to the third prediction mode;Representing covariance +_>Representing the variance;
calculating the contribution degree duty ratio of the predicted power result corresponding to each prediction mode by using the following formula (6);
（6）
wherein,representing the contribution degree ratio corresponding to the first prediction mode, +.>Representing the contribution ratio corresponding to the second prediction mode, +.>The contribution duty ratio corresponding to the third prediction mode is shown.
Optionally, the processing module 420 is specifically configured to:
determining a comprehensive power prediction result of a target area corresponding to each adjustment coefficient according to the plurality of adjustment coefficients, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual transmission power data of the target area;
And determining a target adjustment coefficient according to the root mean square error accuracy, and determining a target power prediction result of the target area by using the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area.
Optionally, the processing module 420 is specifically configured to:
determining the comprehensive power prediction result according to a plurality of adjustment coefficients by using the following formula (7);
（7）
wherein X represents the adjustment coefficient,representing the comprehensive power prediction result;
calculating the root mean square error accuracy by using the following formula (8) for any one of the adjustment coefficients;
（8）
wherein,represents the root mean square error accuracy, m represents the number of data samples, +.>The value range of (2) is 1-m;the +.f in the array representing the integrated power prediction result>Individual integrated power prediction results,/->Indicate->Total loader capacity of target area corresponding to the individual data samples,/->The +.f in the array representing real transmit power data>Actual transmit power data;
taking the adjustment coefficient corresponding to the maximum value in the root mean square accuracy corresponding to each adjustment coefficient as the target adjustment coefficient;
and obtaining the target power prediction result according to the target adjustment coefficient, the contribution degree duty ratio corresponding to each prediction mode and the power prediction result of the target area.
The device of the embodiment of the present invention is configured to perform the method of any of the foregoing method embodiments, and its implementation principle and technical effects are similar, and are not described in detail herein.
Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a power combination prediction method for a regional new energy source, the method comprising: obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
determining contribution degree duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
And determining a target power prediction result of the target area according to the contribution degree duty ratio corresponding to each prediction mode and the power prediction result.
Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the method for predicting the power combination of the regional new energy source provided by the above methods, the method comprising: obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
Determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
determining contribution degree duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
and determining a target power prediction result of the target area according to the contribution degree duty ratio corresponding to each prediction mode and the power prediction result.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform a method of predicting a power combination of a regional new energy source provided by the above methods, the method comprising: obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
Determining contribution degree duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
and determining a target power prediction result of the target area according to the contribution degree duty ratio corresponding to each prediction mode and the power prediction result.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. The power combination prediction method of the regional new energy source is characterized by comprising the following steps of:
obtaining power prediction results of a target area based on a plurality of different prediction modes; the power prediction result is the power prediction result of all new energy stations in the target area;
determining deviation conditions of the power prediction results corresponding to the prediction modes and the actual power data and correlations of the power prediction results and the actual power data according to the power prediction results corresponding to the prediction modes;
determining contribution degree duty ratios corresponding to the prediction modes according to deviation conditions and correlations corresponding to the prediction modes;
Determining a comprehensive power prediction result of a target area corresponding to each adjustment coefficient according to the plurality of adjustment coefficients, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual transmission power data of the target area;
taking the adjustment coefficient corresponding to the maximum value in the root mean square accuracy corresponding to each adjustment coefficient as a target adjustment coefficient;
obtaining a target power prediction result according to the target adjustment coefficient, the contribution duty ratio corresponding to each prediction mode and the power prediction result of the target area;
the obtaining the power prediction result of the target area based on a plurality of different prediction modes comprises the following steps:
when the prediction mode is a first prediction mode, acquiring power prediction data of each new energy station in the target area;
determining a power prediction result of the target area by using the following formula (1);
（1）
wherein,representing the power prediction result of the target area corresponding to the first prediction mode,/for the target area >Is->Power forecast data of the individual new energy stations,/->For the total loader capacity in the target area,/->Is the firstThe installed capacity of each new energy station;
when the prediction mode is a second prediction mode, acquiring actual transmission power data of each new energy station in the target area;
dividing the new energy stations in the target area into a plurality of groups by adopting a clustering algorithm according to the actual transmission power data of each new energy station;
selecting a new energy station with highest correlation with the real power data of the target area from each group as a target new energy station;
determining a power prediction result of the target area according to the target new energy stations in each group in an upscaling mode;
when the prediction mode is a third prediction mode, acquiring actual transmission power data and weather numerical simulation data of each new energy station in the target area;
according to the actual power data and the weather numerical simulation data, a back propagation BP neural network model obtained through training is utilized to obtain a power prediction result of the target area;
obtaining a target power prediction result according to the target adjustment coefficient, the contribution degree duty ratio corresponding to each prediction mode and the power prediction result of the target area, wherein the target power prediction result comprises the following steps:
Determining the comprehensive power prediction result according to the target adjustment coefficient by using the following formula (9);
（9）
wherein,representing the target adjustment factor,/->Representing the comprehensive power prediction result;Representing the power prediction result of the target area corresponding to the first prediction mode,/for the target area>Representing the power prediction result of the target area corresponding to the second prediction mode,/for the target area>Representing a power prediction result of the target area corresponding to the third prediction mode;Representing the contribution degree ratio corresponding to the first prediction mode, +.>Representing the contribution ratio corresponding to the second prediction mode, +.>The contribution duty ratio corresponding to the third prediction mode is shown.
2. The method for predicting power combination of regional new energy according to claim 1, wherein determining the power prediction result of the target region according to the target new energy station in each group by using an upscaling manner comprises:
determining a power prediction result of the target region using the following formula (2);
（2）
wherein,representing the power prediction result of the target area corresponding to the second prediction mode,/for the target area>Indicate->The>Power forecast data of the individual new energy stations,/- >Indicate->The installed capacity of the new energy station, said +.>And the new energy stations are the target new energy stations.
3. The method for predicting power combination of new regional energy according to any one of claims 1-2, wherein determining, according to the power prediction results corresponding to the prediction modes, a deviation between the power prediction results corresponding to the prediction modes and actual power data includes:
calculating absolute deviation of a predicted power result corresponding to each prediction mode and actual power data by using the following formula (3);
（3）
wherein,indicates the first predictive mode corresponding to +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the second predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Representing the third predictive mode corresponding +.>Absolute deviation of power prediction result of each new energy station from real power data, +.>Indicates the first predictive mode corresponding to +.>Power prediction result of each new energy station, < >>Representing the second predictive mode corresponding +.>Power prediction result of each new energy station, < > >Representing the third predictive mode corresponding +.>New onesThe power prediction results of the energy stations,indicate->Real power data of the new energy stations;
calculating the variance corresponding to each prediction mode according to the absolute deviation corresponding to each prediction mode to obtain the deviation condition corresponding to each prediction mode;
（4）
wherein,representing the variance of the power prediction result of the target area corresponding to the first prediction mode and the actual power data, +.>Representing the variance of the power prediction result of the target area corresponding to the second prediction mode and the actual power data, +.>Representing the variance of the power prediction result and the actual power data of the target area corresponding to the third prediction mode; n represents the number of new energy stations within the target area.
4. The method for predicting power combination of new regional energy according to claim 3, wherein determining the correlation between the power prediction result corresponding to each prediction mode and real power data according to the power prediction result corresponding to each prediction mode comprises:
determining the correlation between the power prediction result corresponding to each prediction mode and the actual power data by using the following formula (5);
（5）
Wherein,representing the correlation corresponding to the first predictive mode, < >>Representing the correlation corresponding to the second predictive mode,representing the correlation corresponding to the third prediction mode;Representing covariance +_>Representing the variance;
determining a contribution degree duty ratio corresponding to each prediction mode according to the deviation condition and the correlation corresponding to each prediction mode, wherein the determination comprises the following steps:
calculating the contribution degree duty ratio of the predicted power result corresponding to each prediction mode by using the following formula (6);
（6）
wherein,representing the contribution degree ratio corresponding to the first prediction mode, +.>Representing the contribution ratio corresponding to the second prediction mode, +.>The contribution duty ratio corresponding to the third prediction mode is shown.
5. The method for predicting power combination of new regional energy according to claim 1, wherein determining the comprehensive power prediction result of the target region corresponding to each adjustment coefficient according to the plurality of adjustment coefficients, the contribution duty ratio corresponding to each prediction mode, and the power prediction result of the target region, comprises:
determining the comprehensive power prediction result according to a plurality of adjustment coefficients by using the following formula (7);
（7）
wherein X represents the adjustment coefficient, Representing the comprehensive power prediction result;Representing the power prediction result of the target area corresponding to the first prediction mode,/for the target area>Representing the power prediction result of the target area corresponding to the second prediction mode,/for the target area>Representing a power prediction result of the target area corresponding to the third prediction mode;Representing the contribution degree ratio corresponding to the first prediction mode, +.>Representing the second kindContribution degree duty ratio corresponding to prediction mode, +.>Representing the contribution degree duty ratio corresponding to the third prediction mode;
determining the root mean square error accuracy according to the comprehensive power prediction result of the target area corresponding to each adjustment coefficient and the actual power data of the target area, wherein the method comprises the following steps:
calculating the root mean square error accuracy by using the following formula (8) for any one of the adjustment coefficients;
（8）
wherein,represents the root mean square error accuracy, m represents the number of data samples,kthe value range of (2) is 1-m;The first in the array representing the integrated power prediction resultkIndividual integrated power prediction results,/->Represent the firstkTotal loader capacity of target area corresponding to the individual data samples,/->The first in the array representing real transmit power datakAnd the actual transmit power data.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the power combining prediction method of the regional new energy source of any of claims 1 to 5 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468645.3A CN117195751B (en) | 2023-11-07 | 2023-11-07 | Power combination prediction method and equipment for regional new energy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311468645.3A CN117195751B (en) | 2023-11-07 | 2023-11-07 | Power combination prediction method and equipment for regional new energy |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117195751A CN117195751A (en) | 2023-12-08 |
| CN117195751B true CN117195751B (en) | 2024-03-15 |
Family
ID=88987346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311468645.3A Active CN117195751B (en) | 2023-11-07 | 2023-11-07 | Power combination prediction method and equipment for regional new energy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117195751B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819374A (en) * | 2022-05-10 | 2022-07-29 | 南京南瑞水利水电科技有限公司 | Regional new energy ultra-short term power prediction method and system |
| CN115310648A (en) * | 2022-02-16 | 2022-11-08 | 国网河南省电力公司 | Medium-and-long-term wind power combination prediction method based on multi-meteorological variable model identification |
| CN115374995A (en) * | 2022-06-22 | 2022-11-22 | 国网浙江省电力有限公司丽水供电公司 | Distributed photovoltaic and small wind power station power prediction method |
| CN116316617A (en) * | 2023-05-26 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Multi-station intelligent fusion new energy generation power region prediction method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626506B (en) * | 2020-05-27 | 2022-08-26 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
-
2023
- 2023-11-07 CN CN202311468645.3A patent/CN117195751B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115310648A (en) * | 2022-02-16 | 2022-11-08 | 国网河南省电力公司 | Medium-and-long-term wind power combination prediction method based on multi-meteorological variable model identification |
| CN114819374A (en) * | 2022-05-10 | 2022-07-29 | 南京南瑞水利水电科技有限公司 | Regional new energy ultra-short term power prediction method and system |
| CN115374995A (en) * | 2022-06-22 | 2022-11-22 | 国网浙江省电力有限公司丽水供电公司 | Distributed photovoltaic and small wind power station power prediction method |
| CN116316617A (en) * | 2023-05-26 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Multi-station intelligent fusion new energy generation power region prediction method and system |
Non-Patent Citations (2)
| Title |
|---|
| 宁波地区基于统计升尺度的新能源区域功率预测算法;王威;王波;张俊;陆春良;贺旭;;中国电力(05);100-111 * |
| 王威 ; 王波 ; 张俊 ; 陆春良 ; 贺旭 ; .宁波地区基于统计升尺度的新能源区域功率预测算法.中国电力.2019,(05),100-111. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117195751A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107204615B (en) | Method and system for realizing power prediction | |
| CN108717579B (en) | Short-term wind power interval prediction method | |
| CN105868853A (en) | Method for predicting short-term wind power combination probability | |
| CN113592144B (en) | Medium-long term runoff probability forecasting method and system | |
| CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
| JP2017135964A (en) | Operation of photovoltaic power generation system | |
| CN111612244B (en) | QRA-LSTM-based method for predicting nonparametric probability of photovoltaic power before day | |
| CN114417623A (en) | GRAPES-REPS area set forecasting method and system | |
| CN116581755B (en) | Power prediction method, device, equipment and storage medium | |
| CN117744916A (en) | Method and device for predicting energy storage capacity, computer equipment and readable storage medium | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN113984198B (en) | Shortwave radiation prediction method and system based on convolutional neural network | |
| Ruan et al. | Accurately forecasting solar radiation distribution at both spatial and temporal dimensions simultaneously with fully-convolutional deep neural network model | |
| CN117713238B (en) | Random optimization operation strategy combining photovoltaic power generation and energy storage micro-grid | |
| CN108233357A (en) | Wind-powered electricity generation based on nonparametric probabilistic forecasting and risk expectation dissolves optimization method a few days ago | |
| CN117195751B (en) | Power combination prediction method and equipment for regional new energy | |
| CN117371581A (en) | New energy generated power prediction method, device and storage medium | |
| CN104269886A (en) | Method used for calculating and distributing capacity benefit margins of wind power grid-connected system | |
| CN112070320A (en) | Ultra-short-term wind power prediction method and system based on dynamic harmonic regression | |
| CN108876041B (en) | Polar sea ice area prediction method and device based on causal influence network algorithm | |
| CN117220286B (en) | Risk assessment method, device and medium for water-wind-solar multi-energy complementary system | |
| CN115186940B (en) | Comprehensive energy scheduling method, device and equipment | |
| CN109038663B (en) | Risk assessment method for wind power prediction error | |
| KR102642404B1 (en) | Method for prediction power generation using meta-learning, device and system using the same | |
| CN118313496A (en) | Distributed photovoltaic cluster power prediction method based on depth similarity clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |