CN104732296A - Modeling method for distributed photovoltaic output power short-term prediction model - Google Patents
Modeling method for distributed photovoltaic output power short-term prediction model Download PDFInfo
- Publication number
- CN104732296A CN104732296A CN201510147668.3A CN201510147668A CN104732296A CN 104732296 A CN104732296 A CN 104732296A CN 201510147668 A CN201510147668 A CN 201510147668A CN 104732296 A CN104732296 A CN 104732296A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic output
- data
- output power
- photovoltaic
- power short
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas 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
Abstract
The invention discloses a modeling method for a distributed photovoltaic output power short-term prediction model. The method comprises the steps of obtaining history photovoltaic output data from a power mechanism, obtaining meteorological factor data which correspond to the sampling moment of photovoltaic output from a meteorological monitoring point, and conducting normalization processing; by utilizing the Pearson correlation coefficient analysis method, obtaining the correlation coefficient between the photovoltaic output and illumination intensity, temperature and wind speed data by analyzing; analyzing the meteorological factor data with the correlation coefficient not less than 0.5 through the gray relational analysis grade method, and determining a similar day of the day to be predicted; regarding the photovoltaic output data of the similar day and the meteorological factor data with the correlation coefficient not less than 0.5 as input conditions of the model, and building an epsilon-SVR support vector regression prediction model; determining model parameters through two stages, and obtaining the complete distributed photovoltaic output power short-term prediction model. By means of the method, the problems that in the prior art, a traditional statistical method is adopted for predicting the short-term photovoltaic output, the applicability is low, and the prediction accuracy is low are solved.
Description
Technical field
The invention belongs to technical field of power systems, particularly relate to a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method.
Background technology
It is that the clean energy resource of representative obtains extensive concern that the energy and environmental problem are impelled with photovoltaic.Due to the self-characteristic of illumination and photovoltaic generation, photovoltaic generation is made to present undulatory property and intermittent feature.Many-sided impact can be produced on the safety of electrical network, economy and reliability service after photovoltaic large-scale grid connection, therefore must obtain the short-term forecasting numerical value that photovoltaic is exerted oneself, ACTIVE CONTROL be carried out to it, reaches Optimized Operation.
Adopt statistic law to short-term photovoltaic exert oneself predict time, depend on the history photometric data of photovoltaic plant position more.Classic method is associate feature closely between allowed for influencing factors and photovoltaic are exerted oneself, thus by training prediction.But after photovoltaic scale is grid-connected; installing meteorological measuring equipment in each photovoltaic mounting points can cause investment excessive; multiple photovoltaic devices can only be made to adopt same point measuring value; therefore photovoltaic is exerted oneself and certainly will to be weakened to some extent with meteorological gauge point image data coupling; the precision of traditional prediction method is not enough, and applicability reduces.
Summary of the invention
The technical problem to be solved in the present invention: provide a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method, adopts traditional statistical to exert oneself to short-term photovoltaic to predict to solve prior art, the problems such as applicability is low, and precision of prediction is low.
Technical solution of the present invention:
A kind of distributed photovoltaic output power Short-term Forecasting Model modeling method, it comprises the steps:
Step 1, to obtain photovoltaic history to exert oneself historical data from electric power mechanism, obtain photovoltaic from weather monitoring point and to exert oneself meteorologic factor data corresponding to sampling instant, it comprises intensity of illumination, temperature and air speed data, is normalized;
Step 2, utilize Pearson correlation coefficient analytic approach to analyze the data after normalized, obtain photovoltaic and exert oneself and intensity of illumination, related coefficient between temperature and air speed data;
Step 3, meteorologic factor data related coefficient being not less than 0.5 are analyzed by grey Relational Analysis Method, determine the similar day of day to be predicted;
Step 4, the photovoltaic of similar day gone out meteorologic factor data that force data and related coefficient be not less than 0.5 and build as the initial conditions of model
support vector regression forecast model;
Step 5, to be determined by two benches
support vector regression prediction model parameters, obtains complete distributed photovoltaic output power Short-term Forecasting Model.
Being determined by two benches described in step 5
support vector regression prediction model parameters refers to determines penalty coefficient C, insensitive parameter
with the numerical value of nuclear parameter p, it comprises the steps: a, uses global grid search procedure, is that 0.001--1 increases penalty coefficient C, insensitive parameter according to step-length
with the numerical value of nuclear parameter p, determine insensitive parameter
value, penalty coefficient C and nuclear parameter p variation range, the numerical value of the differential evolution algorithm determination penalty coefficient C and nuclear parameter p adjusted by parameter adaptive.
Beneficial effect of the present invention:
The distributed photovoltaic output power Short-term Forecasting Model that the present invention sets up, by grey Relational Analysis Method (Grey Analysis, GRA), have chosen and have the similar day training data of strong correlation as training sample with day to be predicted; Employing has good small sample generalization ability
forecast model, construct the forecast model based on similar day, improve the similarity between sample, improve precision of prediction, use this model, choosing of training sample can be reduced, expand the scope of application, and the method pair that the differential evolution algorithm (Self-adaptive Differential Evolution, SADE) adopting global grid search (Grid Search, GS) and parameter adaptive to adjust combines
carry out parameter adjustment, improve the accuracy of Selecting parameter, decrease the training time, stronger practical value is had in real work, form the GRA-GS/SADE-SVR short-term photovoltaic power generation output forecasting model for factor of influence weak coupling problem, solving prior art adopts traditional statistical to exert oneself to short-term photovoltaic and predict, the problems such as applicability is low, and precision of prediction is low.
accompanying drawing illustrates:
Fig. 1 embodiment of the present invention distributed photovoltaic continuous four days situation schematic diagram of exerting oneself;
Fig. 2 is with parameter in the embodiment of the present invention
the root-mean-square error schematic diagram of change;
Fig. 3 be in the embodiment of the present invention root-mean-square error with the situation of change schematic diagram of parameter C and p;
Fig. 4 is BP neural network prediction value in the embodiment of the present invention, employing model predication value of the present invention compares schematic diagram with actual value;
Fig. 5 is BP network neural predicted value in the embodiment of the present invention, adopts model predication value of the present invention to compare schematic diagram with the local of actual value;
Fig. 6 is BP network neural predicted value in the embodiment of the present invention, the absolute error curve synoptic diagram adopting model predication value of the present invention and actual value.
Embodiment
A kind of distributed photovoltaic output power Short-term Forecasting Model modeling method, it comprises the steps:
Step 1, to choose photovoltaic to exert oneself historical data from electric power mechanism, obtain photovoltaic from weather monitoring point and to exert oneself meteorologic factor data corresponding to sampling instant, it comprises intensity of illumination, temperature and air speed data, is normalized;
According to the maximal value of intensity, temperature and wind speed;
it is the value after normalized.
Step 2, utilize Pearson correlation coefficient analytic approach to analyze the data after normalized, obtain photovoltaic and exert oneself and intensity of illumination, related coefficient between temperature and air speed data; Described Pearson correlation coefficient analytic approach
Factor data is as the input factor of grey relational grade analysis.
Step 3, the meteorologic factor data such as intensity of illumination, temperature and the air speed data that related coefficient are not less than 0.5 are analyzed by grey Relational Analysis Method, determine the similar day of day to be predicted; Employing grey Relational Analysis Method described in step 3 is analyzed, and it comprises the steps:
4, choose 3 days similar day as this day to be predicted that the grey relational grade that calculates is maximum, the photovoltaic of similar day is gone out the meteorologic factor data composing training sample that force data and related coefficient are not less than 0.5, as mode input condition.
Step 4, the photovoltaic of similar day gone out intensity of illumination, temperature and the air speed data that force data and related coefficient be not less than 0.5 and build as the initial conditions of model
support vector regression forecast model;
Described structure
support vector regression forecast model, it comprises:
Step 1, determine support vector regression problem expression formula:
Introduce Lagrange multiplier and kernel function, according to duality theory, support vector regression problem can be expressed as form
The differential evolution algorithm of parameter adaptive adjustment is adopted in the scope that previous step is determined, to adjust parameter C and p, in the hope of optimum regularization coefficient C and nuclear parameter p subsequently.
The concrete steps of grid search are:
According to sudden change and the Crossover Strategy of differential evolution algorithm, in solution space, generate new offspring individual, and Fitness analysis is carried out to offspring individual;
Carry out greediness according to ideal adaptation degree to filial generation and parent population to select;
After iteration, will obtain optimum C and p, namely selected C and p makes Structural risk minization.
Below in conjunction with accompanying drawing citing, the invention will be further described:
Concrete steps are as follows:
Step 1: choose the influence factor that photovoltaic is exerted oneself:
Step 101: going out force data to the history in somewhere roof photovoltaic power station on March 31st, 1 day 1 February in 2013, is that step-length is sampled with 10min, obtain this area's distributed photovoltaic and to exert oneself situation, wherein certain situation of exerting oneself of four days as shown in Figure 1.
Step 102: be that step-length is sampled with 10min to the monitoring intensity of illumination on the March 31st, 1 day 1 February in 2013 of the weather monitoring device near this roof photovoltaic power station, temperature and wind speed historical data.
Step 103: force data is gone out to photovoltaic, influence factor data are normalized;
Step 104: use Pearson correlation coefficient analytic approach to measure the exert oneself correlation degree of historical data of meteorologic factor data and photovoltaic, obtaining the related coefficient that intensity of illumination and photovoltaic exert oneself is 0.55, the related coefficient that temperature and photovoltaic are exerted oneself is 0.64, the related coefficient that wind speed and photovoltaic are exerted oneself is 0.13, choose correlation degree relatively strong, namely related coefficient is greater than the temperature and light of 0.5 according to the input factor of data as grey Relational Analysis Method;
In the variation range of C and p obtained, produce initial population at random, individual amount gets 20, calculates the fitness of initial population individuality.
According to sudden change and the Crossover Strategy of differential evolution algorithm, in solution space, generate new offspring individual, and Fitness analysis is carried out to offspring individual; Carry out greediness according to ideal adaptation degree to filial generation and parent population to select; After the iteration of some, will obtain optimum C and p, namely selected C and p makes Structural risk minization.
Step 5: utilize selected parameter to use
the photovoltaic of model to prediction day is exerted oneself and is predicted.
Finally use conventional BP neural network prediction method to this number of cases according to predicting, the prediction of two kinds of methods is compared and is seen Fig. 4, Fig. 5 and Fig. 6, as can be seen from Figure 6: use the result of context of methods prediction than use the prediction of BP method closer to actual value.Table 1 describes this point with the error result of Fig. 6.
Fig. 5 is the partial schematic diagram predicted the outcome, the same with Fig. 4, and display context of methods predicts the outcome more accurate.From Fig. 6, the absolute error distribution curve of two kinds of methods can obviously be found out, SVR forecast model predicated error is less herein, closer to reality.
Model method of the present invention and BP neural network prediction are done multiple comparison test, and obtain average RMSE, Comparative result is in table 1:
As shown in Table 1, the average RMSE of 8 prediction days that conventional BP predicted method obtains is 6.789%, and the average RMSE that SVR model in this paper obtains is 5.551%, can meet prediction requirement, improving precision is 1.238%, illustrates and adopts the present invention to improve precision of prediction.
Claims (6)
1. a distributed photovoltaic output power Short-term Forecasting Model modeling method, it comprises the steps:
Step 1, obtain photovoltaic to exert oneself historical data from electric power mechanism, obtain photovoltaic from weather monitoring point and to exert oneself meteorologic factor data corresponding to sampling instant, it comprises intensity of illumination, temperature and air speed data, is normalized;
Step 2, utilize Pearson correlation coefficient analytic approach to analyze the data after normalized, obtain photovoltaic and exert oneself and intensity of illumination, related coefficient between temperature and air speed data;
Step 3, meteorologic factor data related coefficient being not less than 0.5 are analyzed by grey Relational Analysis Method, determine the similar day of day to be predicted;
Step 4, the photovoltaic of similar day gone out meteorologic factor data that force data and related coefficient be not less than 0.5 and build as the initial conditions of model
support vector regression forecast model;
Step 5, to be determined by two benches
support vector regression prediction model parameters, obtains complete distributed photovoltaic output power Short-term Forecasting Model.
2. a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method according to claim 1, is characterized in that:
The maximal value of intensity of illumination, temperature and wind speed;
it is the value after normalized.
3. a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method according to claim 1, is characterized in that: its formula of Pearson correlation coefficient analytic approach described in step 2 is:
The related coefficient that temperature and wind speed and photovoltaic are exerted oneself.
4. a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method according to claim 1, is characterized in that: the employing grey Relational Analysis Method described in step 3 is analyzed, and it comprises:
3 days similar day as this day to be predicted that the grey relational grade calculated in step 4, selecting step 3 is maximum, go out the meteorologic factor data composing training sample that force data and related coefficient are not less than 0.5, as mode input condition by the photovoltaic of similar day.
5. a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method according to claim 1, is characterized in that: the structure described in step 4
support vector regression forecast model, it comprises:
Step 1, determine support vector regression problem expression formula:
p is nuclear parameter.
6. a kind of distributed photovoltaic output power Short-term Forecasting Model modeling method according to claim 1, be is characterized in that: being determined by two benches described in step 5
support vector regression prediction model parameters refers to determines penalty coefficient C, insensitive parameter
with the numerical value of nuclear parameter p, it comprises the steps: a, uses global grid search procedure, is 0.001-1 increase penalty coefficient C, insensitive parameter according to step-length
with the numerical value of nuclear parameter p, determine insensitive parameter
value, penalty coefficient C and nuclear parameter p variation range, the numerical value of the differential evolution algorithm determination penalty coefficient C and nuclear parameter p adjusted by parameter adaptive.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510147668.3A CN104732296A (en) | 2015-04-01 | 2015-04-01 | Modeling method for distributed photovoltaic output power short-term prediction model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510147668.3A CN104732296A (en) | 2015-04-01 | 2015-04-01 | Modeling method for distributed photovoltaic output power short-term prediction model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104732296A true CN104732296A (en) | 2015-06-24 |
Family
ID=53456168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510147668.3A Pending CN104732296A (en) | 2015-04-01 | 2015-04-01 | Modeling method for distributed photovoltaic output power short-term prediction model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104732296A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104978611A (en) * | 2015-07-06 | 2015-10-14 | 东南大学 | Neural network photovoltaic power generation output prediction method based on grey correlation analysis |
CN105184399A (en) * | 2015-08-27 | 2015-12-23 | 许继集团有限公司 | Power prediction method for photovoltaic power plant |
CN105279582A (en) * | 2015-11-20 | 2016-01-27 | 中国水利水电第十四工程局有限公司 | An ultra-short-term wind electricity power prediction method based on dynamic correlation characteristics |
CN105426956A (en) * | 2015-11-06 | 2016-03-23 | 国家电网公司 | Ultra-short-period photovoltaic prediction method |
CN105512775A (en) * | 2016-02-01 | 2016-04-20 | 北京交通大学 | Method for power prediction of photovoltaic power generation system |
CN106197661A (en) * | 2016-07-15 | 2016-12-07 | 苏州科技大学 | Based on the online irradiance hard measurement meter supporting vector and measuring method thereof |
CN106570593A (en) * | 2016-11-10 | 2017-04-19 | 甘肃省电力公司风电技术中心 | Photovoltaic power station output data repairing method based on weather information |
CN108038569A (en) * | 2017-12-08 | 2018-05-15 | 北京汇通金财信息科技有限公司 | A kind of grid-connected power predicating method of distributed photovoltaic and system |
CN108053048A (en) * | 2017-11-06 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system |
CN109102102A (en) * | 2018-06-25 | 2018-12-28 | 南京邮电大学 | Based on the photovoltaic of multivariate phase space reconstruction and SVR power output short term prediction method |
CN111178821A (en) * | 2018-11-13 | 2020-05-19 | 台塑网科技股份有限公司 | Energy control and management system |
CN111260126A (en) * | 2020-01-13 | 2020-06-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
CN111950752A (en) * | 2019-05-14 | 2020-11-17 | 京东方科技集团股份有限公司 | Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof |
CN112686443A (en) * | 2020-12-30 | 2021-04-20 | 南京工程学院 | Photovoltaic power generation prediction method based on artificial intelligence |
CN114707769A (en) * | 2022-05-30 | 2022-07-05 | 广东电网有限责任公司佛山供电局 | Photovoltaic power generation output short-term prediction method and related device thereof |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
CN103617461A (en) * | 2013-12-10 | 2014-03-05 | 中国矿业大学 | Photovoltaic power station generated power predicting method |
-
2015
- 2015-04-01 CN CN201510147668.3A patent/CN104732296A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663513A (en) * | 2012-03-13 | 2012-09-12 | 华北电力大学 | Combination forecast modeling method of wind farm power by using gray correlation analysis |
CN103390202A (en) * | 2013-07-18 | 2013-11-13 | 华北电力大学 | Output power prediction method based on similarity data selection for photovoltaic plant |
CN103390199A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power generation capacity/power prediction device |
CN103390200A (en) * | 2013-07-18 | 2013-11-13 | 国家电网公司 | Photovoltaic power station electricity generation output power forecasting method based on similar days |
CN103617461A (en) * | 2013-12-10 | 2014-03-05 | 中国矿业大学 | Photovoltaic power station generated power predicting method |
Non-Patent Citations (3)
Title |
---|
张华彬 等: "基于最小二乘支持向量机的光伏出力超短期预测", 《现代电力》 * |
栗然 等: ""基于支持向量机回归的光伏发电出力预测"", 《中国电力》 * |
程泽 等: "光伏发电功率的智能预测算法", 《电力建设》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104978611A (en) * | 2015-07-06 | 2015-10-14 | 东南大学 | Neural network photovoltaic power generation output prediction method based on grey correlation analysis |
CN105184399B (en) * | 2015-08-27 | 2018-12-04 | 许继集团有限公司 | A kind of predicting power of photovoltaic plant method |
CN105184399A (en) * | 2015-08-27 | 2015-12-23 | 许继集团有限公司 | Power prediction method for photovoltaic power plant |
CN105426956A (en) * | 2015-11-06 | 2016-03-23 | 国家电网公司 | Ultra-short-period photovoltaic prediction method |
CN105426956B (en) * | 2015-11-06 | 2019-01-22 | 国家电网公司 | A kind of ultra-short term photovoltaic prediction technique |
CN105279582A (en) * | 2015-11-20 | 2016-01-27 | 中国水利水电第十四工程局有限公司 | An ultra-short-term wind electricity power prediction method based on dynamic correlation characteristics |
CN105279582B (en) * | 2015-11-20 | 2019-01-04 | 水电十四局大理聚能投资有限公司 | Super short-period wind power prediction technique based on dynamic correlation feature |
CN105512775A (en) * | 2016-02-01 | 2016-04-20 | 北京交通大学 | Method for power prediction of photovoltaic power generation system |
CN106197661A (en) * | 2016-07-15 | 2016-12-07 | 苏州科技大学 | Based on the online irradiance hard measurement meter supporting vector and measuring method thereof |
CN106570593A (en) * | 2016-11-10 | 2017-04-19 | 甘肃省电力公司风电技术中心 | Photovoltaic power station output data repairing method based on weather information |
CN108053048A (en) * | 2017-11-06 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of gradual photovoltaic plant ultra-short term power forecasting method of single step and system |
CN108038569A (en) * | 2017-12-08 | 2018-05-15 | 北京汇通金财信息科技有限公司 | A kind of grid-connected power predicating method of distributed photovoltaic and system |
CN109102102A (en) * | 2018-06-25 | 2018-12-28 | 南京邮电大学 | Based on the photovoltaic of multivariate phase space reconstruction and SVR power output short term prediction method |
CN111178821A (en) * | 2018-11-13 | 2020-05-19 | 台塑网科技股份有限公司 | Energy control and management system |
CN111950752A (en) * | 2019-05-14 | 2020-11-17 | 京东方科技集团股份有限公司 | Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof |
CN111260126A (en) * | 2020-01-13 | 2020-06-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
CN111260126B (en) * | 2020-01-13 | 2022-12-09 | 燕山大学 | Short-term photovoltaic power generation prediction method considering correlation degree of weather and meteorological factors |
CN112686443A (en) * | 2020-12-30 | 2021-04-20 | 南京工程学院 | Photovoltaic power generation prediction method based on artificial intelligence |
CN114707769A (en) * | 2022-05-30 | 2022-07-05 | 广东电网有限责任公司佛山供电局 | Photovoltaic power generation output short-term prediction method and related device thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104732296A (en) | Modeling method for distributed photovoltaic output power short-term prediction model | |
Ramsami et al. | A hybrid method for forecasting the energy output of photovoltaic systems | |
CN102930358B (en) | A kind of neural net prediction method of photovoltaic power station power generation power | |
CN102184337B (en) | Dynamic combination analysis method of new energy generating capacity influenced by meteorological information | |
CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
CN108388956A (en) | Consider the photovoltaic power prediction technique of attenuation | |
CN104933483A (en) | Wind power forecasting method dividing based on weather process | |
CN105389634A (en) | Combined short-term wind power prediction system and method | |
CN102496927A (en) | Wind power station power projection method based on error statistics modification | |
CN112285807B (en) | Meteorological information prediction method and device | |
CN104951834A (en) | LSSVM (least squares support vector machine) wind speed forecasting method based on integration of GA (genetic algorithm) and PSO (particle swarm optimization) | |
CN105488592A (en) | Method for predicting generated energy of photovoltaic power station | |
CN106934191B (en) | WRF mode wind speed correction method based on self-similarity | |
CN103065202A (en) | Wind power plant ultrashort term wind speed prediction method based on combination kernel function | |
CN105631550A (en) | Short-term wind power combined prediction method | |
CN104809532A (en) | Method for predicting generating capacity of photovoltaic system | |
CN110334870A (en) | Photovoltaic plant short term power prediction technique based on gating cycle unit networks | |
CN103984986B (en) | The self study arma modeling ultrashort-term wind power prediction method of real time correction | |
Chen et al. | Research on wind power prediction method based on convolutional neural network and genetic algorithm | |
CN103440428A (en) | Method for determining self-adaption dynamic weight of combined prediction model for wind electricity power | |
Cabezon et al. | Comparison of methods for power curve modelling | |
CN106815655B (en) | Photovoltaic output 2D interval prediction method based on fuzzy rule | |
Frogner et al. | Ensemble prediction with different spatial resolutions for the 2014 Sochi Winter Olympic Games: The effects of calibration and multimodel approaches | |
CN112307672A (en) | BP neural network short-term wind power prediction method based on cuckoo algorithm optimization | |
CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information |
Address after: 550002 Jiefang Road, Nanming, Guizhou, No. 32, Applicant after: ELECTRIC POWER RESEARCH INSTITUTE OF GUIZHOU POWER GRID CO., LTD. Address before: 550002 Jiefang Road, Guizhou, No. 251, Applicant before: Guizhou Power Test Institute |
|
COR | Change of bibliographic data | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150624 |