CN112633565A - Photovoltaic power aggregation interval prediction method - Google Patents
Photovoltaic power aggregation interval prediction method Download PDFInfo
- Publication number
- CN112633565A CN112633565A CN202011473590.1A CN202011473590A CN112633565A CN 112633565 A CN112633565 A CN 112633565A CN 202011473590 A CN202011473590 A CN 202011473590A CN 112633565 A CN112633565 A CN 112633565A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic power
- interval
- prediction
- optimization
- input
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000002776 aggregation Effects 0.000 title claims abstract description 21
- 238000004220 aggregation Methods 0.000 title claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012850 discrimination method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 238000010248 power generation Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 108090000672 Annexin A5 Proteins 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a photovoltaic power aggregation interval prediction method, which comprises the following steps: judging the non-stationary time period of the preprocessed historical photovoltaic power to obtain the photovoltaic power of the non-stationary time period; performing feature extraction on the photovoltaic power in the non-stationary time period to obtain an input variable; respectively carrying out point prediction and interval prediction on the photovoltaic power according to the input variables to obtain point prediction results and interval prediction results; respectively carrying out multi-objective optimization on the point prediction result and the interval prediction result to obtain a first optimization interval and a second optimization interval; and performing multi-objective optimization by taking the actual photovoltaic power of the first optimization interval, the actual photovoltaic power of the second optimization interval and the actual photovoltaic power of the prediction point as input, so as to obtain a photovoltaic power prediction interval. The effect is remarkable, the prediction precision is remarkably improved, and the dispatching system can more accurately evaluate the fluctuation condition of photovoltaic output.
Description
Technical Field
The invention belongs to the technical field of photovoltaic power prediction, and relates to a photovoltaic power set interval prediction method.
Background
The photovoltaic power prediction technology is a technology for predicting photovoltaic output power at a future moment according to conditions such as operating parameters and meteorological characteristics of a photovoltaic power station. In recent years, the most widely used method is an artificial intelligence method, and the relation between input variables implicit in historical data and a prediction result is mined through machine learning, so that the photovoltaic power is predicted. However, the photovoltaic power generation is greatly influenced by meteorological factors, when meteorological conditions are unstable in a prediction period, a photovoltaic output curve is unsmooth, the peak-valley difference is large, and the prediction accuracy of a traditional prediction model is poor.
Disclosure of Invention
The invention aims to provide a photovoltaic power set interval prediction method, which solves the problem of poor prediction accuracy in the prior art.
The technical scheme adopted by the invention is that the photovoltaic power aggregation interval prediction method comprises the following steps:
step 3, extracting characteristics of the photovoltaic power in the non-stationary time period to obtain an input variable;
step 4, respectively carrying out point prediction and interval prediction on the photovoltaic power according to the input variables to obtain point prediction results and interval prediction results;
and 6, performing multi-objective optimization by taking the first optimization interval, the second optimization interval and the actual photovoltaic power of the prediction point as input together to obtain a photovoltaic power prediction interval.
The invention is also characterized in that:
the specific process of the step 1 is as follows: and (3) performing abnormal data detection and elimination on the historical photovoltaic power by adopting a central limit theorem, and then filling the abnormal data by using a K neighbor full algorithm and an Euclidean distance method.
And 2, adopting a power ratio difference of radiation discrimination method to discriminate non-stationary time periods.
The step 3 specifically comprises the following steps:
respectively calculating the MIC value of each influence factor variable of the photovoltaic power in the non-stationary period, selecting the influence factor variable with a larger MIC value as an input variable, and calculating the MIC value in the following manner:
in the formula, x represents a characteristic factor, y represents photovoltaic output, a and B are divided into the number of cells in x and y directions respectively, and B is a variable.
The photovoltaic power point prediction method in the step 4 comprises the following steps:
firstly, training an LSTM model by taking an input variable as an input to obtain a first-layer base learner; then, training the first-layer basis learner by taking a prediction result output by the first-layer basis learner and an input variable as input together to obtain a Stack-LSTM model; and inputting the input variables into the Stack-LSTM model for prediction to obtain a point prediction result.
And step 4, inputting the input variable into a BAYES neural network for prediction to obtain an interval prediction result.
And step 6, jointly taking the first optimization interval, the second optimization interval and the actual photovoltaic power of the prediction point as input, and performing multi-objective optimization by adopting an NSGA-II optimization algorithm to obtain a photovoltaic power prediction interval.
The invention has the beneficial effects that:
according to the photovoltaic power aggregation interval prediction method, historical data are preprocessed, an MIC theory is adopted for feature selection, and irrelevant variables can be eliminated, so that the calculated amount is reduced, and the model training process is accelerated; the NSGA-II network model performs multi-objective optimization on the prediction result, so that the overall prediction precision is improved; the ensemble probability forecasting model disclosed by the invention has the advantages that the effect is excellent, the forecasting precision is obviously improved, and the dispatching system can more accurately evaluate the fluctuation condition of photovoltaic output.
Drawings
FIG. 1 is a flow chart of a photovoltaic power collection interval prediction method of the present invention;
FIG. 2 is a power station 1 point prediction result diagram adopting a Stack-LSTM model in the photovoltaic power aggregation interval prediction method of the invention;
FIG. 3 is a power station 2-point prediction result diagram adopting a Stack-LSTM model in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 4 is a power station 1 point prediction result diagram using an LSTM model in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 5 is a 2-point prediction result diagram of a power station using an LSTM model in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 6 is a diagram of a power station 1 point prediction result using an ANN model in a photovoltaic power aggregation interval prediction method of the present invention;
FIG. 7 is a 2-point prediction result diagram of a power station using an ANN model in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 8 is a diagram of a prediction result of a power station 1 interval in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 9 is a diagram of a prediction result of a section 2 of a power station in the photovoltaic power aggregation section prediction method of the present invention;
FIG. 10 is a flow chart of an NSGA-II optimization algorithm in the photovoltaic power aggregation interval prediction method of the present invention;
FIG. 11 is a comparison graph of prediction results before and after optimization of the power station 1 in the photovoltaic power aggregation interval prediction method of the present invention;
fig. 12 is a comparison graph of prediction results before and after optimization of the power station 2 in the photovoltaic power aggregation interval prediction method of the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
A photovoltaic power aggregation interval prediction method, as shown in fig. 1, includes the following steps:
and (3) performing abnormal data detection and elimination on the historical photovoltaic power by adopting a central limit theorem, and then filling the abnormal data by using a K neighbor full algorithm and an Euclidean distance method.
And 2, the photovoltaic output is greatly influenced by factors such as weather and irradiance, the periodicity is strong, and the common output curve types include a stable output type and a non-stable output type. Judging the non-stationary time period of the historical photovoltaic power processed in the step 1 by adopting a radiation power ratio difference judging method to obtain the photovoltaic power of the non-stationary time period;
step 2.1, setting a parameter radiation power ratio difference, and calculating a formula:
in the formula: st-1Irradiance of the t-1 th sample in the data sample; stIrradiance of the t sample in the data sample;
step 2.2, to X according to the following formulatDividing the value range:
step 2.3, for XtIs judged when X is taken astTake on the value of [0.7,1.3]In the above, the steady output time period is determined, and in addition, the non-steady output time period is determined.
Step 3, performing feature extraction on the photovoltaic power in the non-stationary time period by adopting an MIC (many integrated core) method to obtain an input variable; the MIC method specifically comprises the following steps: dividing the current two-dimensional space into a certain number of intervals in the x and y directions, and then checking the falling condition of the current scattered point in each square, namely calculating the joint probability;
the specific process is as follows: respectively calculating the MIC value of the influencing factor variable of the photovoltaic power in the non-stationary period, selecting the influencing factor variable with a larger MIC value as an input variable, selecting irradiance, humidity, temperature and wind speed as the input variables in the embodiment, wherein the MIC value is calculated in the following way:
in the formula, x represents a characteristic factor, y represents photovoltaic output, a and B divide the number of cells in x and y directions respectively, and B is a variable;
step 4, respectively carrying out point prediction and interval prediction on the photovoltaic power according to the input variables to obtain point prediction results and interval prediction results;
step 4.1, training the LSTM model by taking an input variable as an input to obtain a first-layer base learner; then, training the first layer basis learner by taking a prediction result output by the first layer basis learner and an input variable together as input to obtain a second layer basis learner, namely a Stack-LSTM model; inputting the input variables into a Stack-LSTM model for prediction to obtain a point prediction result;
specifically, step 4.1.1, data sets
Divided into n subsets I1,I2,......In；
Step 4.1.2, based on the n subsets, inputting the n subsets into an LSTM algorithm respectively to obtain a first prediction result w1,w2,......wn；
Step 4.1.3, adding the first prediction result as an additional feature into the original feature to form a new input feature x'1,x′2,......x′l＝(x1,x2,......xl,w1,w2,......wn) And inputting the data into the LSTM algorithm again to perform second prediction and obtain a result with higher precision.
And 4.2, inputting the input variable into a BAYES neural network for prediction to obtain an interval prediction result. Under the condition of complex weather, the short-time output of the photovoltaic power station is unstable, the prediction precision of the deterministic prediction method is obviously reduced, and compared with the deterministic prediction, the Bayes (BAYES) neural network is used for performing interval prediction to give all possible output value interval distribution of the photovoltaic equipment at the prediction moment.
and 6, performing multi-objective optimization by taking the first optimization interval, the second optimization interval and the actual photovoltaic power of the prediction point as input together to obtain a photovoltaic power prediction interval.
And performing multi-objective optimization by using the NSGA-II optimization algorithm. Firstly, randomly generating an initial population with the size of N, and obtaining a first generation progeny population through three basic operations of selection, crossing and variation of a genetic algorithm after non-dominated sorting; secondly, from the second generation, merging the parent population and the offspring population, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting proper individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population; finally, generating a new filial generation population through basic operation of a genetic algorithm; and so on until the condition of program end is satisfied, and the specific flow chart is shown in fig. 10.
Step 6.1, taking the actual photovoltaic power of the first optimization interval, the actual photovoltaic power of the second optimization interval and the actual photovoltaic power of the prediction point as input;
6.2, constructing a basic NSGA-II network model through input, and performing multi-objective optimization, wherein the optimization objectives are minimum interval width (PINAW) and maximum interval coverage (PICP);
and 6.3, verifying the NSGA-II network model.
Examples
According to the method, data provided by the official of the second photovoltaic prediction competition in the new state energy day are selected for prediction research, the output data of the power station 1 and the power station 2 in the whole year in 2017 are selected, the original data are complete data in the whole year in 2017, the data time step is 15 minutes, the data are sampled 24 hours every day, 32848 groups of data are shared by the power station 1, and 33060 groups of data are shared by the power station 2. Due to the periodicity and the intermittence of photovoltaic output, only data at the power generation time in the day are selected, data in the time period without power generation at night are removed, abnormal data, missing data and error data in the data are processed and repaired, finally, 16018 groups of effective data are reserved in the power station 1, and 16427 groups of effective data are reserved in the power station 2. The first 90% is the training set and the last 10% is the test set.
Through the optimization processing of the invention, the prediction precision is greatly improved, and in order to quantify the improvement degree of the uncertainty, specific data pairs such as table 1:
TABLE 1 Multi-Objective before and after optimization comparison table
From table 1, it can be seen that, through multi-objective optimization, under the same interval coverage rate, the interval width is reduced by 10% to 20% compared with the non-optimized prediction model, which means that the prediction accuracy is improved by at least 10%. Compared with the boundary estimation theoretical method, under the same interval coverage rate, after the multi-objective optimization is carried out on the deterministic prediction result and the interval prediction result by the prediction model method, as shown in fig. 11-12, the prediction precision is improved by more than 20%, and the prediction precision of the photovoltaic power prediction is obviously improved.
Two groups of data from different sources are selected to carry out verification on the Stack-LSTM model and the BAYES neural network respectively, and as is obvious from the graphs in FIGS. 2-7, the Stack-LSTM model has the highest curve fitting degree and the highest prediction precision compared with the LSTM model and the ANN model. As shown in fig. 8-9, compared with deterministic point prediction, in a non-stationary output period, the interval prediction can predict the possible output situation of the point as much as possible, which enables the scheduling system to adjust the scheduling policy in time, and ensures safe and stable operation of the power grid to the greatest extent.
Through the mode, the photovoltaic power aggregation interval prediction method disclosed by the invention has the advantages that historical data are preprocessed, the MIC theory is adopted for feature selection, and irrelevant variables can be eliminated, so that the calculated amount is reduced, and the model training process is accelerated; the NSGA-II network model performs multi-objective optimization on the prediction result, so that the overall prediction precision is improved; the ensemble probability forecasting model disclosed by the invention has the advantages that the effect is excellent, the forecasting precision is obviously improved, and the dispatching system can more accurately evaluate the fluctuation condition of photovoltaic output.
Claims (7)
1. A photovoltaic power collection interval prediction method is characterized by comprising the following steps:
step 1, performing data preprocessing on historical photovoltaic power;
step 2, judging the non-stationary time period of the historical photovoltaic power processed in the step 1 to obtain the photovoltaic power of the non-stationary time period;
step 3, extracting the characteristics of the photovoltaic power in the non-stationary time period to obtain an input variable;
step 4, respectively carrying out point prediction and interval prediction on the photovoltaic power according to the input variables to obtain point prediction results and interval prediction results;
step 5, respectively carrying out multi-objective optimization on the point prediction result and the interval prediction result to obtain a first optimization interval and a second optimization interval;
and 6, performing multi-objective optimization by taking the first optimization interval, the second optimization interval and the actual photovoltaic power of the prediction point as input together to obtain a photovoltaic power prediction interval.
2. The method for predicting the photovoltaic power aggregation interval according to claim 1, wherein the specific process in the step 1 is as follows: and (3) performing abnormal data detection and elimination on the historical photovoltaic power by adopting a central limit theorem, and then filling the abnormal data by using a K neighbor full algorithm and an Euclidean distance method.
3. The method for predicting the photovoltaic power collection interval according to claim 1, wherein a power-to-radiation ratio difference discrimination method is adopted in the step 2 to discriminate the non-stationary period.
4. The method for predicting the photovoltaic power aggregation interval according to claim 1, wherein the step 3 specifically includes the following steps:
respectively calculating the MIC value of each influence factor variable of the photovoltaic power in the non-stationary period, selecting the influence factor variable with a larger MIC value as an input variable, and calculating the MIC value in the following manner:
in the formula, x represents a characteristic factor, y represents photovoltaic output, a and B are divided into the number of cells in x and y directions respectively, and B is a variable.
5. The method according to claim 1, wherein the photovoltaic power point prediction method in step 4 is:
firstly, training an LSTM model by taking the input variable as input to obtain a first-layer base learner; then, training the first-layer basis learner by taking a prediction result output by the first-layer basis learner and an input variable as input together to obtain a Stack-LSTM model; and inputting the input variables into a Stack-LSTM model for prediction to obtain a point prediction result.
6. The photovoltaic power aggregation interval prediction method according to claim 1, wherein the input variable is input into a BAYES neural network in step 4 for prediction, so as to obtain an interval prediction result.
7. The method according to claim 1, wherein in step 6, the first optimization interval, the second optimization interval and the actual photovoltaic power of the predicted point are used as input together, and a NSGA-II optimization algorithm is used for multi-objective optimization to obtain the photovoltaic power prediction interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011473590.1A CN112633565B (en) | 2020-12-15 | 2020-12-15 | Photovoltaic power set interval prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011473590.1A CN112633565B (en) | 2020-12-15 | 2020-12-15 | Photovoltaic power set interval prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112633565A true CN112633565A (en) | 2021-04-09 |
| CN112633565B CN112633565B (en) | 2023-07-25 |
Family
ID=75312750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011473590.1A Active CN112633565B (en) | 2020-12-15 | 2020-12-15 | Photovoltaic power set interval prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633565B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780643A (en) * | 2021-08-31 | 2021-12-10 | 陕西燃气集团新能源发展股份有限公司 | Photovoltaic power station short-term output prediction method based on case reasoning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007003390A (en) * | 2005-06-24 | 2007-01-11 | National Institute Of Advanced Industrial & Technology | Photovoltaic power generation evaluation system |
| CN105826946A (en) * | 2016-05-09 | 2016-08-03 | 东北电力大学 | Power distribution network dynamic reactive power optimization method for large-scale photovoltaic access |
| JP2016224320A (en) * | 2015-06-02 | 2016-12-28 | 沖電気工業株式会社 | Information processor and information processing method |
| CN107453396A (en) * | 2017-08-02 | 2017-12-08 | 安徽理工大学 | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed |
| CN108921339A (en) * | 2018-06-22 | 2018-11-30 | 南京工程学院 | Genetic Support Vector Machine photovoltaic power interval prediction method based on quantile estimate |
| CN110059862A (en) * | 2019-03-25 | 2019-07-26 | 国网浙江省电力有限公司电力科学研究院 | A kind of photovoltaic interval prediction method and system based on from coding and extreme learning machine |
| CN111353653A (en) * | 2020-03-13 | 2020-06-30 | 大连理工大学 | Photovoltaic output short-term interval prediction method |
-
2020
- 2020-12-15 CN CN202011473590.1A patent/CN112633565B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007003390A (en) * | 2005-06-24 | 2007-01-11 | National Institute Of Advanced Industrial & Technology | Photovoltaic power generation evaluation system |
| JP2016224320A (en) * | 2015-06-02 | 2016-12-28 | 沖電気工業株式会社 | Information processor and information processing method |
| CN105826946A (en) * | 2016-05-09 | 2016-08-03 | 东北电力大学 | Power distribution network dynamic reactive power optimization method for large-scale photovoltaic access |
| CN107453396A (en) * | 2017-08-02 | 2017-12-08 | 安徽理工大学 | A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed |
| CN108921339A (en) * | 2018-06-22 | 2018-11-30 | 南京工程学院 | Genetic Support Vector Machine photovoltaic power interval prediction method based on quantile estimate |
| CN110059862A (en) * | 2019-03-25 | 2019-07-26 | 国网浙江省电力有限公司电力科学研究院 | A kind of photovoltaic interval prediction method and system based on from coding and extreme learning machine |
| CN111353653A (en) * | 2020-03-13 | 2020-06-30 | 大连理工大学 | Photovoltaic output short-term interval prediction method |
Non-Patent Citations (4)
| Title |
|---|
| PAVEL KROMER等: "Evolutionary prediction of photovoltaic power plant energy production", GECCO \'12: PROCEEDINGS OF THE 14TH ANNUAL CONFERENCE COMPANION ON GENETIC AND EVOLUTIONARY COMPUTATION * |
| 付宗见;梁明亮;王艳萍;: "基于遗传算法优化BP神经网络的光伏阵列短期功率预测", 电子器件 * |
| 路朋等: "基于模型预测控制的风电集群多时间尺度有功功率优化调度策略研究", 中国电机工程学报 * |
| 陈云龙;殷豪;孟安波;周亚武;: "基于模糊信息粒化的光伏出力区间预测", 电测与仪表 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113780643A (en) * | 2021-08-31 | 2021-12-10 | 陕西燃气集团新能源发展股份有限公司 | Photovoltaic power station short-term output prediction method based on case reasoning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112633565B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
| Yang et al. | Day-ahead forecasting of photovoltaic output power with similar cloud space fusion based on incomplete historical data mining | |
| CN110516840A (en) | Short term prediction method based on the wind light generation power output for improving random forest method | |
| CN105631558A (en) | BP neural network photovoltaic power generation system power prediction method based on similar day | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN107609774B (en) | Photovoltaic power prediction method for optimizing wavelet neural network based on thought evolution algorithm | |
| CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
| CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
| CN103473621A (en) | Wind power station short-term power prediction method | |
| Kolhe et al. | GA-ANN for short-term wind energy prediction | |
| CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN111626473A (en) | Two-stage photovoltaic power prediction method considering error correction | |
| CN114169445A (en) | Day-ahead photovoltaic power prediction method, device and system based on CAE and GAN hybrid network | |
| CN109242136A (en) | A kind of micro-capacitance sensor wind power Chaos-Genetic-BP neural network prediction technique | |
| CN109242200B (en) | Wind power interval prediction method of Bayesian network prediction model | |
| CN116629416A (en) | Photovoltaic power station power prediction method and device | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| CN112633565A (en) | Photovoltaic power aggregation interval prediction method | |
| CN110489893B (en) | Variable weight-based bus load prediction method and system | |
| CN112949938B (en) | Wind power climbing event direct forecasting method for improving training sample class imbalance | |
| CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
| CN115456286A (en) | Short-term photovoltaic power prediction method | |
| CN114676931A (en) | Electric quantity prediction system based on data relay technology |
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 |