CN112669169B - Short-term photovoltaic power prediction device and method - Google Patents
Short-term photovoltaic power prediction device and method Download PDFInfo
- Publication number
- CN112669169B CN112669169B CN202011479990.3A CN202011479990A CN112669169B CN 112669169 B CN112669169 B CN 112669169B CN 202011479990 A CN202011479990 A CN 202011479990A CN 112669169 B CN112669169 B CN 112669169B
- Authority
- CN
- China
- Prior art keywords
- data
- module
- real
- neural network
- value
- 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 43
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 238000012806 monitoring device Methods 0.000 claims abstract description 13
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 230000000739 chaotic effect Effects 0.000 claims description 31
- 238000013528 artificial neural network Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 12
- 230000035772 mutation Effects 0.000 claims description 9
- 238000005286 illumination Methods 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- QENJZWZWAWWESF-UHFFFAOYSA-N tri-methylbenzoic acid Natural products CC1=CC(C)=C(C(O)=O)C=C1C QENJZWZWAWWESF-UHFFFAOYSA-N 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 241000288673 Chiroptera Species 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 description 16
- 230000008859 change Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model provides a short-term photovoltaic power prediction device and method, belongs to electric power system technical field, real-time meteorological data collection device, historical database module, power prediction module, data transmission module, man-machine interface, power station monitoring devices, real-time meteorological data receiving device is connected with historical database module and power prediction module, power station monitoring devices is connected with data transmission module through man-machine interface; the real-time meteorological data collecting device is used for comparing and combining acquired real-time meteorological data with meteorological data received from an meteorological platform, and the like.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to a short-term photovoltaic power prediction device and method.
Background
Along with the continuous development of society and economy, energy sources are reflected in living aspects, the demands of people on the energy sources are continuously increased, and the social development is restricted by the energy source problem. Fossil energy, such as coal, however, generates a large amount of pollutants during use, and polluted air causes a greenhouse effect and global warming. Compared with renewable energy sources, the renewable energy sources have the advantages of energy consumption, particulate matter emission and zero generated polluted gas. The large-scale development and utilization of the photovoltaic power generation system are actively encouraged in China, so that the photovoltaic power generation industry is rapidly developed in recent years.
After 2009, the proportion of the photovoltaic power station with the installed capacity at the megawatt level is larger and larger, and the characteristics of the photovoltaic power station have larger fluctuation by combining weather reasons and new energy power generation characteristics, so that the safety and the stability of the power system are affected to a certain extent. On the one hand, particularly in recent years, the phenomenon that a grid-connected photovoltaic power station is separated from a power system for a plurality of times causes huge energy loss, and threatens the safety of the power system; on the other hand, uncertainty of output power of the photovoltaic power station brings great difficulty to grid connection of the power system. In order to ensure safe and reliable operation of the power system, accurate prediction of the output power of the photovoltaic power station is important.
At present, a prediction model is built through the multiple linear regression method, the Artificial Neural Network (ANN) method, the Support Vector Machine (SVM) method, the gray theory method and the like, so that the output power of a photovoltaic power generation system can be predicted, the photovoltaic power generation power prediction can improve the utilization efficiency of solar photovoltaic power generation resources, but the prediction methods are only based on predictions obtained on the basis of the same period and the same day type of history, the same period of history refers to the same historical time period such as one month, the same day type refers to the same weather condition such as sunny day, the prediction methods have the defects that the prediction day is only due to a certain day type such as sunny day, the weather change and the power generation power of the photovoltaic power station of the same history period and the same day type are considered to have similarity, but the real-time change information of each element of the weather change of the prediction day is not processed sufficiently, the local searching capability is not strong, and the prediction accuracy is not accurate enough.
Disclosure of Invention
Based on the technical problems, the invention provides a MTMBA-BP-based short-term photovoltaic power prediction device and a method, the method has stronger local searching capability, a good global optimizing effect can be obtained, and a prediction result is more accurate than that of a common method.
The invention adopts the following technical scheme:
The system comprises a short-term photovoltaic power prediction device, a real-time meteorological data collection device, a historical database module, a power prediction module, a data transmission module, a man-machine interface and a power station monitoring device, wherein the real-time meteorological data receiving device is connected with the historical database module and the power prediction module, the power station monitoring device is connected with the data transmission module through the man-machine interface, and meanwhile the data transmission module, the power prediction module and the historical database module are monitored in real time and managed; the real-time meteorological data collecting device is used for comparing and combining acquired real-time meteorological data with meteorological data received from an meteorological platform, and carrying out dimension reduction screening processing on the received high-dimension meteorological data to obtain predicted meteorological data; the data contained in the historical database module comprises real-time and historical power, temperature and illumination intensity of the photovoltaic power station, the resolution of each data is 60 minutes, the data can receive the power data of the photovoltaic power station transmitted by the power station monitoring device and the real-time meteorological data transmitted by the real-time meteorological collecting device, and the historical data and the real-time data are utilized to carry out comparison analysis on errors; the power prediction module comprises a weight threshold processing module and a neural network module, wherein the weight threshold processing module is used for bating the weight threshold of the data by using a population position and a speed formula, updating the data individual to obtain a new position solution, correspondingly forming the new solution into a neural network structure by the neural network module, and updating the weight threshold again by using a neural network method to obtain the new solution.
Further, the power station monitoring device monitors the power prediction module in real time, sends real-time meteorological data and prediction data of the photovoltaic power station to the historical database module, monitors and manages the transmitted data in real time through the man-machine interface, wherein the monitored data comprises temperature, illumination intensity and real-time power of the photovoltaic power station, and the monitored data resolution is 60 minutes.
The prediction method of the short-term photovoltaic power prediction device comprises the following steps that a weight threshold processing module adopts a TMBA method based on chaotic disturbance improvement:
(1) Initializing the method, namely randomly generating n bat individuals in a search range to form an initial population, giving initial values to the position, speed, frequency, pulse frequency and pulse intensity of each bat, wherein parameters beststep represent the continuous unchanged times of the optimal individuals, and the initial population is set to 0;
(2) Evaluating the population, calculating the adaptive value of each bat in the population, and finding out the current global optimal value;
(3) Updating population, introducing speed weight in iterative process And the chaotic map updates the frequency f i, the speed v i and the spatial position x i of the individual respectively;
fi＝fmin+(fmax-fmin)CMi (1)
Wherein CM i is the generic name of chaotic mapping, CM i E [0,1] is chaotic number, and X * is the current local optimal solution in the group;
(4) Generating a random number rand, and obtaining a local new solution of the optimal bat individual by the formula (5) through a random walk rule if the rand is more than r;
(5) Evaluating each individual in the current population, if a certain individual is better than global optimum, updating to global optimum bat, juxtaposing beststep to 0, otherwise, adding 1 to beststep for updating;
(6) Judging whether the variation condition beststep reaches the maximum value maxstep or whether the variation of the global optimum values of two successive iterations is small (< eta), if so, executing (7), otherwise, executing (8);
(7) Performing a mutation operation ①, wherein the mutation operation is to perform Gaussian mutation on the optimal bat individuals in the current population and perform t distribution mutation on other bats; ② Evaluating the adaptability of the new population, if a certain bat adaptation value is better than global optimum, replacing beststep to be 0, otherwise, adding 1 to beststep for updating;
(8) Judging a termination condition: whether the iteration number reaches a maximum value Maxgen or whether the optimal solution reaches the preset precision, if not, adding 1 to beststep for updating, and turning to (3) continuously executing the next generation bat optimization process, otherwise turning to (9) for executing;
(9) The method is terminated, and an optimal solution is output;
The neural network module is a BP neural network learning module, and comprises the following steps:
(1) Initializing, namely firstly setting a weight value and a threshold value in a module as an arbitrary value, and updating;
(2) Randomly learning an input vector (X k,Yk) into the neural network;
(3) The data is transmitted to an input layer, an implicit layer and an output layer, and the number of the output nodes is the vector number obtained by the predicted model;
(4) The following formulas are combined to obtain hidden layer corresponding data
(5) The following formulas are combined to obtain corresponding data of output points
(6) According to the related data output by the output layer, the corresponding calculation is carried out by using the formula (8), so that the corresponding numerical value of each node and the correction error can be obtained
(7) Calculating the error of the corresponding hidden layer node value according to the formula (9),
(8) Introducing chaotic mapping to enhance randomness to accelerate the searching step to adjust the link weight V between the hidden layer and the output layer and the threshold gamma of the output layer,
Wherein:
CM i, which is the generic name for chaotic mapping, CM i ε [0,1],
(9) The weights and thresholds are further modified according to the chaotic map,
(10) Selecting an input vector, and repeatedly returning to the step (3) until all data are trained completely;
(11) Checking all calculated errors to see if the criteria are met; if yes, directly turning to the step (13);
(12) Adjusting the training times of the neural network model according to the requirement, and if the training times are smaller than or equal to the set value after adjustment, directly transferring to the step (2);
(13) And (5) finishing the learning of the neural network model.
Further, the data transmission module transmits measurement data, alarm events and file data to the monitoring system, and various data are modeled according to the DL/T860 standard.
The invention has the advantages and effects that:
The invention relates to a short-term photovoltaic power prediction device based on a self-adaptive t-distribution bat method improved by chaotic disturbance and a back propagation method (MTMBA-BP) improved by chaotic mapping. The power prediction module combines a TMBA method based on chaotic disturbance improvement with a BP neural network learning method based on chaotic mapping improvement. And after the weight threshold value of the data is bated by utilizing the improved population position and speed formula, updating the data individual to obtain a new position solution, correspondingly forming the new position solution into a neural network structure, and updating the weight threshold value again by utilizing a neural network method to obtain a new solution. The whole device has stronger local searching capability, the searching step is executed at a faster speed, a good global optimizing effect can be obtained, and the prediction result is more accurate than that of a common method.
Drawings
FIG. 1 is a schematic diagram of a short-term photovoltaic power prediction apparatus based on MTMBA-BP method;
FIG. 2 is a flow chart of a chaotic disturbance improved TMBA method;
FIG. 3 is a flowchart of a MTMBA-BP neural network learning method;
FIG. 4 is a verification comparison of the predicted power generation of the improved TMBA-BP based on chaotic disturbance;
Fig. 5 is a comparison of BP predicted power generation verification.
Detailed Description
1-3, The system comprises a real-time meteorological data collecting and receiving device, a historical database module, a power prediction module, a data transmission module, a man-machine interface and a power station monitoring device. The meteorological data receiving device is connected with the historical power generation server and the power prediction module; the power station monitoring module is connected with the data transmission module through a man-machine interface, and simultaneously monitors and manages the data transmission module, the power prediction module and the historical power generation server in real time.
The real-time weather collecting device performs comparison and combination processing on the collected real-time weather data and the weather data received from the weather table, and performs dimension reduction screening processing on the received high-dimension weather data to obtain finer and accurate predicted weather data.
The historical database module comprises real-time and historical power, temperature and illumination intensity of the photovoltaic power station, the resolution ratio of each data is 60 minutes, the data can also receive the photovoltaic power station power data transmitted by the power station monitoring device and the real-time meteorological data transmitted by the real-time meteorological collecting device, and the historical data and the real-time data are utilized to compare so as to be convenient for analyzing errors.
The power prediction module comprises a weight threshold processing module and a neural network module. And the weight threshold processing module is used for carrying out batylation on the weight threshold of the data by using an improved population position and speed formula method, and then updating the data individual to obtain a new position solution. The new solution is correspondingly a neural network structure through a neural network module, and the weight threshold value is updated again by using a neural network method to obtain the new solution.
As shown in fig. 2, the weight threshold processing module adopts a chaotic disturbance improved TMBA method, and includes the following steps:
(1) The method is initialized. N bat individuals are randomly generated in the search range to form an initial population. Initial values are given to the position, speed, frequency, pulse frequency, and pulse intensity of each bat. Parameter beststep represents the number of times that the optimal individual is continuously unchanged, and is initially set to 0;
(2) The population is assessed. Calculating the adaptive value of each bat in the population, and finding out the current global optimal value;
(3) Updating the population. In the iterative process, a velocity weight is introduced And the chaotic map updates the frequency f i, the speed v i and the spatial position x i of the individual respectively;
fi＝fmin+(fmax-fmin)CMi (1)
Wherein CM i is the generic name of chaotic mapping, CM i ε [0,1] is chaotic number, and X * is the current local optimal solution (position) in the population. In the experimental process, a corresponding frequency change interval can be set according to the needs of the problem.
(4) A random number rand is generated. If rand > r, obtaining a local new solution of the optimal bat individual by the formula (5) through a random walk rule;
(5) Evaluating each individual in the current population, updating to global optimal bat if a certain individual is better than global optimal, juxtaposing beststep to 0, otherwise adding 1 to beststep for updating;
(6) And judging variation conditions. beststep reaches a maximum maxstep, or if the change in global optimum is small (< η) for two successive iterations, if so, then execution (7) is performed, otherwise execution (8) is performed;
(7) And (5) performing mutation operation. ① Performing Gaussian variation on the optimal bat individuals in the current population, and performing t distribution variation on other bats; ② Evaluating the adaptability of the new population, if a certain bat adaptation value is better than global optimum, replacing beststep to be 0, otherwise, adding 1 to beststep for updating;
(8) Judging a termination condition: whether the iteration number reaches a maximum value Maxgen or whether the optimal solution reaches the preset precision, if not, adding 1 to beststep for updating, and turning to (3) continuously executing the next generation bat optimization process, otherwise turning to (9) for executing;
(9) And (5) terminating the method and outputting the optimal solution.
The BP neural network learning method adopts a chaotic mapping improved BP method, and comprises the following steps:
(1) Initializing. Firstly, the weight and the threshold value in the module are set to be an arbitrary value, and updating is carried out.
(2) The input vector (X k,Yk) is randomly learned into the neural network.
(3) And the data is transmitted to the input layer, the hidden layer and the output layer, and the number of the output nodes is the vector number obtained by the predicted model.
(4) The following formulas are combined to obtain hidden layer corresponding data
(5) The following formulas are combined to obtain corresponding data of output points
(6) According to the related data output by the output layer, the corresponding calculation is carried out by using the formula (8), so that the corresponding numerical value of each node and the correction error can be obtained
(7) And calculating the error of the corresponding hidden layer node value according to the formula (9).
(8) In order to obtain a globally optimal weight and a threshold value, a chaotic mapping enhanced randomness acceleration searching step is introduced to adjust a continuous weight V between an implicit layer and an output layer and a threshold value gamma of the output layer.
Wherein:
CM i -is a generic term for chaotic mapping, CM i ε [0,1].
(9) And further correcting the weight and the threshold according to the chaotic map.
(10) And (3) selecting an input vector, and repeatedly returning to the step (3) until all data are trained completely.
(11) Checking all calculated errors to see if the criteria are met; if so, go directly to step (13).
(12) And (3) adjusting the training times of the neural network model according to the requirement, and if the training times are smaller than or equal to the set value after adjustment, directly turning to the step (2).
(13) And (5) finishing the learning of the neural network model.
The data transmission module transmits measurement data, alarm event and file data to the monitoring system, and various data are modeled according to the DL/T860 standard.
The power station monitoring device monitors the power prediction module in real time, sends real-time meteorological data and prediction data of the photovoltaic power station to the historical database module, monitors and manages the transmitted data in real time through the man-machine interface, and is convenient for finding fault data in time. The monitored data comprises temperature, illumination intensity, real-time power of the photovoltaic power station and the like, and the resolution of the monitored data is 60 minutes.
Example 1
The method provided by the invention is compared with the traditional BP network model by utilizing the electric quantity data of a certain photovoltaic station 2019 and 6 months acquired by the electric energy acquisition system to carry out verification analysis. The daily sampling frequency is 5min, one point, and 8:00-16:00 time data values are selected every day after data processing, as shown in table 1.
The result of simulation prediction and simulation of the solar photovoltaic power generation amount of the year 2019, 10 months and 21 is shown in fig. 4-5 by using a trained chaotic disturbance improvement TMBA-BP model and a trained BP model respectively, and the result shows that the absolute error of the predicted power generation amount and the expected power generation amount based on the chaotic disturbance improvement TMBA-BP model is within 20%, and the absolute error of the predicted power generation amount and the expected power generation amount exceeds 20% in a plurality of time periods. The improved TMBA-BP neural network based on the chaotic disturbance has higher prediction precision.
Claims (3)
1. A short term photovoltaic power prediction device, characterized by: the system comprises a real-time meteorological data collection device, a historical database module, a power prediction module, a data transmission module, a man-machine interface and a power station monitoring device, wherein the real-time meteorological data collection device is connected with the historical database module and the power prediction module, and the power station monitoring device is connected with the data transmission module through the man-machine interface and simultaneously monitors and manages the data transmission module, the power prediction module and the historical database module in real time; the real-time meteorological data collecting device is used for comparing and combining acquired real-time meteorological data with meteorological data received from an meteorological platform, and carrying out dimension reduction screening processing on the received high-dimension meteorological data to obtain predicted meteorological data; the data contained in the historical database module comprises real-time and historical power, temperature and illumination intensity of the photovoltaic power station, the resolution of each data is 60 minutes, the data can receive the power data of the photovoltaic power station transmitted by the power station monitoring device and the real-time meteorological data transmitted by the real-time meteorological collecting device, and the historical data and the real-time data are utilized to carry out comparison analysis on errors; the power prediction module comprises a weight threshold processing module and a neural network module, wherein the weight threshold processing module is used for bating the weight threshold of the data by using a population position and a speed formula, updating the data individual to obtain a new position solution, correspondingly forming the new solution into a neural network structure by the neural network module, and updating the weight threshold again by using a neural network method to obtain the new solution;
The weight threshold processing module adopts a TMBA method based on chaotic disturbance improvement, and comprises the following steps:
(1) Initializing the method, namely randomly generating n bat individuals in a search range to form an initial population, giving initial values to the position, speed, frequency, pulse frequency and pulse intensity of each bat, wherein parameters beststep represent the continuous unchanged times of the optimal individuals, and the initial population is set to 0;
(2) Evaluating the population, calculating the adaptive value of each bat in the population, and finding out the current global optimal value;
(3) Updating population, introducing speed weight in iterative process And the chaotic map updates the frequency f i, the speed v i and the spatial position x i of the individual respectively;
fi＝fmin+(fmax-fmin)CMi (1)
Wherein CM i is the generic name of chaotic mapping, CM i E [0,1] is chaotic number, and X * is the current local optimal solution in the group;
(4) Generating a random number rand, and obtaining a local new solution of the optimal bat individual by the formula (5) through a random walk rule if the rand is more than r;
(5) Evaluating each individual in the current population, if a certain individual is better than global optimum, updating to global optimum bat, juxtaposing beststep to 0, otherwise, adding 1 to beststep for updating;
(6) Judging whether the variation condition beststep reaches the maximum value maxstep or whether the variation of the global optimum value is small or not for two successive iterations, < eta, if so, executing (7), otherwise, executing (8);
(7) Performing a mutation operation ①, wherein the mutation operation is to perform Gaussian mutation on the optimal bat individuals in the current population and perform t distribution mutation on other bats; ② Evaluating the adaptability of the new population, if a certain bat adaptation value is better than global optimum, replacing beststep to be 0, otherwise, adding 1 to beststep for updating;
(8) Judging a termination condition: whether the iteration number reaches a maximum value Maxgen or whether the optimal solution reaches the preset precision, if not, adding 1 to beststep for updating, and turning to (3) continuously executing the next generation bat optimization process, otherwise turning to (9) for executing;
(9) The method is terminated, and an optimal solution is output;
The neural network module is a BP neural network learning module, and comprises the following steps:
(1) Initializing, namely firstly setting a weight value and a threshold value in a module as an arbitrary value, and updating;
(2) Randomly learning an input vector (X k,Yk) into the neural network;
(3) The data is transmitted to an input layer, an implicit layer and an output layer, and the number of the output nodes is the vector number obtained by the predicted model;
(4) The following formulas are combined to obtain hidden layer corresponding data
(5) The following formulas are combined to obtain corresponding data of output points
(6) According to the related data output by the output layer, the corresponding calculation is carried out by using the formula (8), so that the corresponding numerical value of each node and the correction error can be obtained
(7) Calculating the error of the corresponding hidden layer node value according to the formula (9),
(8) Introducing chaotic mapping to enhance randomness to accelerate the searching step to adjust the link weight V between the hidden layer and the output layer and the threshold gamma of the output layer,
Wherein:
CM i, which is the generic name for chaotic mapping, CM i ε [0,1],
(9) The weights and thresholds are further modified according to the chaotic map,
(10) Selecting an input vector, and repeatedly returning to the step (3) until all data are trained completely;
(11) Checking all calculated errors to see if the criteria are met; if yes, directly turning to the step (13);
(12) Adjusting the training times of the neural network model according to the requirement, and if the training times are smaller than or equal to the set value after adjustment, directly transferring to the step (2);
(13) And (5) finishing the learning of the neural network model.
2. A short term photovoltaic power prediction apparatus according to claim 1, characterized in that: the power station monitoring device monitors the power prediction module in real time, sends real-time meteorological data and prediction data of the photovoltaic power station to the historical database module, monitors and manages the transmitted data in real time through the man-machine interface, wherein the monitored data comprises temperature, illumination intensity and real-time power of the photovoltaic power station, and the monitored data resolution is 60 minutes.
3. A method of predicting short term photovoltaic power of claim 1, wherein: the data transmission module transmits measurement data, alarm events and file data to the monitoring system, and various data are modeled according to the DL/T860 standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011479990.3A CN112669169B (en) | 2020-12-15 | 2020-12-15 | Short-term photovoltaic power prediction device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011479990.3A CN112669169B (en) | 2020-12-15 | 2020-12-15 | Short-term photovoltaic power prediction device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112669169A CN112669169A (en) | 2021-04-16 |
| CN112669169B true CN112669169B (en) | 2024-04-30 |
Family
ID=75404902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011479990.3A Active CN112669169B (en) | 2020-12-15 | 2020-12-15 | Short-term photovoltaic power prediction device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112669169B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
| CN108765951A (en) * | 2018-06-11 | 2018-11-06 | 广东工业大学 | Method for identifying traffic status of express way based on bat algorithm support vector machines |
| CN109344990A (en) * | 2018-08-02 | 2019-02-15 | 中国电力科学研究院有限公司 | A kind of short-term load forecasting method and system based on DFS and SVM feature selecting |
| CN109426889A (en) * | 2017-09-01 | 2019-03-05 | 南京理工大学 | Short-term load forecasting method based on KPCA in conjunction with improvement neural network |
| CN110852902A (en) * | 2019-11-14 | 2020-02-28 | 合肥工业大学 | Photovoltaic power generation power prediction method based on BAS-BP |
| WO2020063690A1 (en) * | 2018-09-25 | 2020-04-02 | 新智数字科技有限公司 | Electrical power system prediction method and apparatus |
| CN111260116A (en) * | 2020-01-10 | 2020-06-09 | 河南理工大学 | Time-interval refined short-term load prediction method based on BOA-SVR and fuzzy clustering |
| CN112052913A (en) * | 2020-09-27 | 2020-12-08 | 国网江苏省电力有限公司南京供电分公司 | Distributed photovoltaic power station power data virtual acquisition method |
-
2020
- 2020-12-15 CN CN202011479990.3A patent/CN112669169B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018072351A1 (en) * | 2016-10-20 | 2018-04-26 | 北京工业大学 | Method for optimizing support vector machine on basis of particle swarm optimization algorithm |
| CN109426889A (en) * | 2017-09-01 | 2019-03-05 | 南京理工大学 | Short-term load forecasting method based on KPCA in conjunction with improvement neural network |
| CN108765951A (en) * | 2018-06-11 | 2018-11-06 | 广东工业大学 | Method for identifying traffic status of express way based on bat algorithm support vector machines |
| CN109344990A (en) * | 2018-08-02 | 2019-02-15 | 中国电力科学研究院有限公司 | A kind of short-term load forecasting method and system based on DFS and SVM feature selecting |
| WO2020063690A1 (en) * | 2018-09-25 | 2020-04-02 | 新智数字科技有限公司 | Electrical power system prediction method and apparatus |
| CN110852902A (en) * | 2019-11-14 | 2020-02-28 | 合肥工业大学 | Photovoltaic power generation power prediction method based on BAS-BP |
| CN111260116A (en) * | 2020-01-10 | 2020-06-09 | 河南理工大学 | Time-interval refined short-term load prediction method based on BOA-SVR and fuzzy clustering |
| CN112052913A (en) * | 2020-09-27 | 2020-12-08 | 国网江苏省电力有限公司南京供电分公司 | Distributed photovoltaic power station power data virtual acquisition method |
Non-Patent Citations (3)
| Title |
|---|
| 基于主成分分析和遗传优化BP 神经网络的光伏输出功率短期预测;许童羽，马艺铭, 曹英丽, 唐瑞，陈俊杰;电力***保护与控制;第44卷(第22期);1-6 * |
| 基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测;吴云，雷建文，鲍丽山，李春哲;电力***自动化;第42卷(第20期);1-8 * |
| 蝙蝠算法研究及应用综述;许德刚，赵萍;计算机工程与应用;第55卷(第15期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112669169A (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111626506B (en) | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof | |
| Song et al. | Hourly heat load prediction model based on temporal convolutional neural network | |
| CN102663513B (en) | Utilize the wind power combined prediction modeling method of grey relational grade analysis | |
| CN110729764B (en) | Optimal scheduling method for photovoltaic power generation system | |
| CN110334870B (en) | Photovoltaic power station short-term power prediction method based on gated cyclic unit network | |
| Lu et al. | A hybrid approach for day-ahead forecast of PV power generation | |
| CN111027775A (en) | Step hydropower station generating capacity prediction method based on long-term and short-term memory network | |
| CN110766200A (en) | Method for predicting generating power of wind turbine generator based on K-means mean clustering | |
| Yadav et al. | Short-term PV power forecasting using empirical mode decomposition in integration with back-propagation neural network | |
| CN109242136A (en) | A kind of micro-capacitance sensor wind power Chaos-Genetic-BP neural network prediction technique | |
| Luo et al. | Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine | |
| CN106611243A (en) | Residual correction method for wind speed prediction based on GARCH (Generalized ARCH) model | |
| CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
| Sunny et al. | Design and simulation of maximum power point tracking of photovoltaic system using ANN | |
| Wang et al. | Ultra-short-term wind power forecasting based on deep belief network | |
| Wang et al. | Hybrid deep learning model for short-term wind speed forecasting based on time series decomposition and gated recurrent unit | |
| CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
| CN112669169B (en) | Short-term photovoltaic power prediction device and method | |
| Wu et al. | Combined IXGBoost-KELM short-term photovoltaic power prediction model based on multidimensional similar day clustering and dual decomposition | |
| CN116485139A (en) | Short-term photovoltaic power generation amount prediction method based on multi-feature fusion | |
| CN113095534A (en) | Wind power prediction method combining ARIMA and improved Elman neural network | |
| Zhen et al. | Multi-level wavelet decomposition based day-ahead solar irradiance forecasting | |
| CN116128211A (en) | Wind-light-water combined short-term optimization scheduling method based on wind-light uncertainty prediction scene | |
| CN113962357A (en) | GWO-WNN-based distributed photovoltaic power data virtual acquisition method | |
| CN114626622A (en) | Photovoltaic power prediction method, system, device and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211228 Address after: 123000 No. 53 Jiefang Avenue, Haizhou District, Liaoning, Fuxin Applicant after: STATE GRID FUXIN ELECTRIC POWER SUPPLY Co. Applicant after: STATE GRID CORPORATION OF CHINA Address before: 123200 No.53 Jiefang street, Haizhou District, Fuxin City, Liaoning Province Applicant before: STATE GRID FUXIN ELECTRIC POWER SUPPLY Co. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |