CN110796292A - Photovoltaic power short-term prediction method considering haze influence - Google Patents
Photovoltaic power short-term prediction method considering haze influence Download PDFInfo
- Publication number
- CN110796292A CN110796292A CN201910971238.1A CN201910971238A CN110796292A CN 110796292 A CN110796292 A CN 110796292A CN 201910971238 A CN201910971238 A CN 201910971238A CN 110796292 A CN110796292 A CN 110796292A
- Authority
- CN
- China
- Prior art keywords
- data
- photovoltaic power
- photovoltaic
- prediction
- haze
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000010606 normalization Methods 0.000 claims description 12
- 238000010248 power generation Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims 1
- 238000010187 selection method Methods 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009897 systematic effect Effects 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
- G06N3/045—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
- G06N3/08—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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a photovoltaic power prediction method considering haze influence; selecting an Air Quality Index (AQI) as an index for measuring the haze weight, and listing the AQI and a weather condition into a historical data source for photovoltaic power prediction; on the basis of the complex nonlinear characteristics that the photovoltaic output power is influenced by a plurality of factors, a photovoltaic power prediction model considering the haze influence is established, and a BP neural network algorithm is utilized for solving; in order to ensure the accuracy of photovoltaic power prediction, a training sample selection method based on similarity time is provided. An example analysis verifies the necessity of accounting for haze in photovoltaic power prediction and the effectiveness of the method.
Description
Technical Field
The invention belongs to the technical field of power systems, relates to a photovoltaic power prediction method, and particularly relates to a photovoltaic power short-term prediction method considering haze influence.
Background
The power generation by using non-renewable energy sources such as coal, petroleum and the like faces double pressure of resource exhaustion and environmental pollution, and the search and development of new power generation energy sources become a worldwide problem. Solar energy is an inexhaustible energy source for human beings, and the solar energy which can be received by the earth every year is about 1.8 multiplied by 1018kWh is tens of thousands of times of energy consumption of all human beings every year, and solar power generation is an important mode for solar energy utilization. Under the influence of meteorological factors and the characteristics of a photovoltaic power generation system, the photovoltaic power has the characteristics of randomness, fluctuation and intermittence, and the grid connection of photovoltaic power generation can impact a large power grid. In recent years, long-time and large-range haze weather appears in China for many times, the weather is particularly severe in winter and spring, and the photovoltaic power generation is severely tested due to frequent attack of haze.
The accurate photovoltaic power prediction model can promote safe and stable operation of a power grid, improve the quality of electric energy, provide a scheduling basis for the power grid and take counter measures against power fluctuation in advance. At present, the academic circles have more researches on the photovoltaic power prediction problem, but the influence of haze factors on the photovoltaic power is hardly considered.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a photovoltaic power prediction method considering haze influence, and solves the problem that haze is not considered in photovoltaic power generation short-term power prediction in the prior art.
The technical scheme of the invention comprises the following steps:
step 1, selecting an Air Quality Index (AQI) as an index for measuring haze weight, and listing the AQI and a weather condition into a historical data source for photovoltaic power prediction;
step 3, quantifying fuzzy variables, and mapping the fuzzy weather conditions into specific numerical values in the (0,1) interval;
In the formula (1), X is data after normalization processing; x is data before normalization processing; x is the number ofminIs the minimum value of the variable;
xmaxis the maximum value of the variable;
step 7, analyzing and comparing the BP neural network prediction model based on the similar time and haze influence with the traditional BP neural network prediction model and the prediction results of the BP neural network prediction model based on the similar time without considering haze;
step 8, establishing a photovoltaic power prediction model; from solar irradiance (X)1) Photovoltaic panel temperature (X)2) Ambient temperature (X)3)、AQI(X4) And weather conditions(X5) The data can be used for obtaining a photovoltaic power (Y) value; and obtaining the relation between the predicted value of the photovoltaic output power and the actual photovoltaic power (Y) value under the model.
The invention has the following advantages and effects:
the method of the invention basically ensures that the solar irradiance, the photovoltaic panel temperature and the weather condition in the history are similar to those in the prediction, and effectively improves the prediction accuracy of the photovoltaic power.
Drawings
FIG. 1 is a flow diagram of short term photovoltaic power prediction in one embodiment;
FIG. 2 is a flow chart of a BP neural network in another embodiment;
FIG. 3 is a graph comparing photovoltaic output power in one embodiment;
FIG. 4 is a table comparing error performance in one embodiment.
Detailed Description
Examples
Referring to fig. 1, the method for short-term prediction of photovoltaic power considering haze influence in the embodiment includes the following steps.
S110: and quantifying the haze degree of haze weather by adopting AQI (air quality index), and mapping the fuzzy weather conditions (sunny, cloudy and the like) into specific numerical values in a (0,1) interval.
Preprocessing data, namely taking data of 1-6 months recorded by a photovoltaic power station, and acquiring data every 5min by an environment recorder, wherein the data comprises photovoltaic power (kW) and solar irradiance (W/m)2) Photovoltaic panel temperature (c), ambient temperature (c).
And abnormal data rejection, namely rejecting data with the photovoltaic power of 0 or close to 0 when the solar irradiance is obviously not 0 within a period of time.
S120: in order to avoid the problem that the prediction result has errors due to the dimensions and size ranges of different data, normalization processing is carried out on all the quantities (such as photovoltaic power, solar irradiance, photovoltaic panel temperature, ambient temperature, AQI and the like) by using a 'range method'; the method is shown as the formula (1).
In the formula (1), X is data after normalization processing; x is data before normalization processing; x is the number ofminIs the minimum value of the variable;
xmaxis the maximum value of the variable.
The influence of temperature on photovoltaic power is studied from two aspects, one is the surface temperature of the photovoltaic panel, and the other is the ambient temperature of the location of the photovoltaic power station. When the temperature of the photovoltaic panel is too high, the power generation performance is affected, namely, the photoelectric conversion efficiency of the photovoltaic panel is related to the temperature of the photovoltaic panel, and when the temperature is higher than the standard test temperature, the photoelectric conversion efficiency is reduced, and the photovoltaic output power is reduced. Through the SPSS software, the correlation analysis is respectively carried out on the temperature of the photovoltaic panel, the ambient temperature and the photovoltaic power, and the Pearson correlation coefficients of 0.485 and 0.379 can be obtained.
In order to further analyze the relationship between haze and photovoltaic power, the correlation between haze data and photovoltaic power data is analyzed by using SPSS software, and the Pearson correlation coefficient is-0.202, wherein a negative value indicates that the haze data and the photovoltaic power are negatively correlated, namely the more severe the haze is, the less the photovoltaic power is. The significance index Lsig is 0, and the value of the significance index Lsig is less than 0.05, which indicates that the significance index Lsig and the significance index Lsig are extremely significant and have strong statistical significance.
S130: weather indexes such as "sunny", "raining", "cloudy", and the like are determined based on the position, thickness, area, moving speed, and the like of the cloud layer. Under various weather conditions or indexes, the cloud layers have different degrees of shielding sunlight, and the amount of solar radiation received by the earth is also different, so that the photovoltaic output power is different finally. And analyzing the correlation between the photovoltaic output power and the weather condition data by using SPSS software to obtain a Pearson correlation coefficient of 0.324.
The method fully considers the time characteristic similarity, provides a training sample determining method based on similarity, namely constructs time meteorological characteristic vectors taking solar irradiance, photovoltaic panel temperature and weather conditions as similar factors, calculates similarity and sequences, and selects a plurality of similar time (the similarity is more than 0.6) data with high similarity as a training sample set of a subsequent BP neural network method prediction model.
S140: according to the correlation analysis of the photovoltaic power and the influence factors, solar irradiance, photovoltaic panel temperature and weather conditions which have more remarkable influence on the photovoltaic power are selected as meteorological factors influencing the photovoltaic power, and meteorological characteristic vectors are shown as a formula (1) in construction.
X＝[E Tmt](1)
Feature vector x of predicted and ith historical photovoltaic data0、xiAre respectively shown in formulas (2) and (3).
x0＝[x0(1),x0(2),x0(3)](2)
xi＝[xi(1),xi(2),xi(3)](3)
The specific steps when selecting similarities in the prediction are as follows:
(1) calculating the similarity F between the ith time and the prediction time from the historical data time by timei；
(2) Sorting according to the sequence of similarity from big to small, selecting similarity FiData > 0.6 as the similarity in prediction. And forming a training sample set of the prediction model by using the set of similar public meteorological data and actual power generation data of the photovoltaic power station.
From the foregoing analysis, it is known that the photovoltaic power is affected by various factors, and the factors are coupled to each other, so it is difficult to simulate the photovoltaic output power by establishing an accurate mathematical model. The BP neural network algorithm has good generalization and nonlinear mapping capability, and the characteristic of the BP neural network algorithm is very suitable for photovoltaic power prediction greatly influenced by external environment. The method is based on a BP neural network algorithm to carry out photovoltaic power prediction considering haze, solar irradiance, photovoltaic panel temperature, environment temperature and weather conditions. The unified and effective prediction precision evaluation index is beneficial to comparison among different research results. Let X be the measured value, X' be the predicted value, and N be the predicted sample data size.
① mean absolute percent error
The mean absolute percentage error analyzes the overall predictive power.
② mean absolute error
③ average error
The average error reflects the systematic deviation of the prediction system.
④ root mean square error
S131: and aiming at a certain prediction in the test set, forming a training sample set when the similarity of the time is selected in the training set according to the similarity time selection method. In order to verify the effectiveness of the BP neural network prediction model based on similar timekeeping and haze influence, the BP neural network prediction model is analyzed and compared with the prediction results of a traditional BP neural network prediction model (a similar time method is not adopted) and a BP neural network prediction model based on similar time (haze is not considered).
S132: from a set of solar irradiance (X)1) Photovoltaic panel temperature (X)2) Ambient temperature (X)3)、AQI(X4) And weather conditions (X)5) The data may yield a photovoltaic power (Y) value. The relation between the predicted value and the actual value of the photovoltaic output power under the model I is described.
From a set of solar irradiance (X)1) Photovoltaic panel temperature (X)2) Ambient temperature (X)3) And weather conditions (X)4) The data can be used to obtain a photovoltaic power (Y) value. Respectively constructing reference time weather characteristic vectors with solar irradiance, photovoltaic panel temperature and weather conditions as similar factors by using each group (30 groups in total) of test data, and removing abnormal data according to a similar time selection principleAnd selecting a plurality of similar points with high similarity (the similarity is more than 0.6) from the rest 565 groups of data to be used as sample data of the group to train the BP neural network. The relationship between the predicted value and the actual value of the photovoltaic output power under the model II is described.
From a set of solar irradiance (X)1) Photovoltaic panel temperature (X)2) Ambient temperature (X)3)、AQI(X4) And weather conditions (X)5) The data can be used to obtain a photovoltaic power (Y) value. The neural network was verified using the same test data as model i, model ii. When the similarity is realized, the selection process is the same as that of the model II. The relation between the predicted value and the actual value of the photovoltaic output power under the model III is described.
The highest photovoltaic output power prediction accuracy is the model III, the next is the model II, and the lowest photovoltaic output power prediction accuracy is the model I. As explained earlier, the effect of haze on photovoltaic power is significant and not negligible; in addition, the solar irradiance, the photovoltaic panel temperature and the weather condition of historical data are greatly different from those of prediction, and the influence of weather factors on the photovoltaic power cannot be reasonably considered in the traditional BP neural network prediction model. In the two BP neural network prediction models based on the similarity time theory, the main meteorological factors are processed more finely, the solar irradiance, the photovoltaic panel temperature and the weather condition in the historical time are basically ensured to be similar to those in the prediction time, and the prediction precision of the photovoltaic power is effectively improved.
Claims (4)
1. A photovoltaic power prediction method considering haze influence is characterized by comprising the following steps:
step 1, selecting an Air Quality Index (AQI) as an index for measuring haze weight, and listing the AQI and a weather condition into a historical data source for photovoltaic power prediction;
step 2, preprocessing data, taking data of 1-6 months recorded by the photovoltaic power station, and collecting data every 5min by an environment recorder, wherein the data comprises photovoltaic power (kW) and solar irradiance (W/m)2) Photovoltaic panel temperature (deg.C), ambient temperature (deg.C);
step 3, quantifying fuzzy variables, and mapping the fuzzy weather conditions into specific numerical values in the (0,1) interval;
step 4, abnormal data elimination, namely eliminating data with photovoltaic power of 0 or close to 0 when solar irradiance is obviously not 0 within a period of time;
step 5, normalization treatment: in order to avoid the problem that the prediction result has errors due to dimensions and size ranges of different data, normalization processing is carried out on each quantity by using a 'range difference method', and the method is as shown in formula (1):
in the formula (1), X is data after normalization processing; x is data before normalization processing; x is the number ofminIs the minimum value of the variable;
xmaxis the maximum value of the variable;
step 6, constructing a time meteorological feature vector taking solar irradiance, photovoltaic panel temperature and weather conditions as similar factors, calculating similarity and sequencing, and selecting a plurality of similar time data with high similarity as a training sample set of a subsequent BP neural network method prediction model;
step 7, analyzing and comparing the BP neural network prediction model based on the similar time and haze influence with the traditional BP neural network prediction model and the prediction results of the BP neural network prediction model based on the similar time without considering haze;
step 8, establishing a photovoltaic power prediction model; from solar irradiance (X)1) Photovoltaic panel temperature (X)2) Ambient temperature (X)3)、AQI(X4) And weather conditions (X)5) The data can be used for obtaining a photovoltaic power (Y) value; and obtaining the relation between the predicted value of the photovoltaic output power and the actual photovoltaic power (Y) value under the model.
2. The method according to claim 1, wherein in step 6, the temporal meteorological eigenvector is represented by formula (1):
X＝[E Tmt](1)
feature vector x of predicted and ith historical photovoltaic data0、xiRespectively expressed by formulas (2) and (3):
x0＝[x0(1),x0(2),x0(3)](2)
xi＝[xi(1),xi(2),xi(3)](3)。
3. the method according to claim 1, wherein in step 6, the steps of predicting the photovoltaic power based on the haze effect are as follows:
(1) calculating the similarity F between the ith time and the prediction time from the historical data time by timei；
(2) Sorting according to the sequence of similarity from big to small, selecting similarity FiAnd when the data of more than or equal to 0.6 is used as similarity in prediction, forming a training sample set of the prediction model by using the public meteorological data and the actual power generation data of the photovoltaic power station in the similarity.
4. The method as claimed in claim 1, wherein the normalization process in step 5 includes photovoltaic power, solar irradiance, photovoltaic panel temperature, ambient temperature, and AQI.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910971238.1A CN110796292A (en) | 2019-10-14 | 2019-10-14 | Photovoltaic power short-term prediction method considering haze influence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910971238.1A CN110796292A (en) | 2019-10-14 | 2019-10-14 | Photovoltaic power short-term prediction method considering haze influence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796292A true CN110796292A (en) | 2020-02-14 |
Family
ID=69439077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910971238.1A Pending CN110796292A (en) | 2019-10-14 | 2019-10-14 | Photovoltaic power short-term prediction method considering haze influence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796292A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932008A (en) * | 2020-08-06 | 2020-11-13 | 集美大学 | Ship photovoltaic output power prediction method applicable to different weather conditions |
| CN112364477A (en) * | 2020-09-29 | 2021-02-12 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学（保定） | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
| CN104200274A (en) * | 2014-03-27 | 2014-12-10 | 国家电网公司 | Power prediction method for photovoltaic devices |
| CN104463349A (en) * | 2014-11-11 | 2015-03-25 | 河海大学 | Photovoltaic generated power prediction method based on multi-period comprehensive similar days |
| CN105631558A (en) * | 2016-03-22 | 2016-06-01 | 国家电网公司 | BP neural network photovoltaic power generation system power prediction method based on similar day |
| CN108564192A (en) * | 2017-12-29 | 2018-09-21 | 河海大学 | A kind of short-term photovoltaic power prediction technique based on meteorological factor weight similar day |
| CN109165774A (en) * | 2018-08-07 | 2019-01-08 | 燕山大学 | A kind of short-term photovoltaic power prediction technique |
| CN109858673A (en) * | 2018-12-27 | 2019-06-07 | 南京工程学院 | A kind of photovoltaic generating system power forecasting method |
-
2019
- 2019-10-14 CN CN201910971238.1A patent/CN110796292A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103390116A (en) * | 2013-08-07 | 2013-11-13 | 华北电力大学（保定） | Method for predicting electricity generation power of photovoltaic power station in step-by-step way |
| CN104200274A (en) * | 2014-03-27 | 2014-12-10 | 国家电网公司 | Power prediction method for photovoltaic devices |
| CN104463349A (en) * | 2014-11-11 | 2015-03-25 | 河海大学 | Photovoltaic generated power prediction method based on multi-period comprehensive similar days |
| CN105631558A (en) * | 2016-03-22 | 2016-06-01 | 国家电网公司 | BP neural network photovoltaic power generation system power prediction method based on similar day |
| CN108564192A (en) * | 2017-12-29 | 2018-09-21 | 河海大学 | A kind of short-term photovoltaic power prediction technique based on meteorological factor weight similar day |
| CN109165774A (en) * | 2018-08-07 | 2019-01-08 | 燕山大学 | A kind of short-term photovoltaic power prediction technique |
| CN109858673A (en) * | 2018-12-27 | 2019-06-07 | 南京工程学院 | A kind of photovoltaic generating system power forecasting method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932008A (en) * | 2020-08-06 | 2020-11-13 | 集美大学 | Ship photovoltaic output power prediction method applicable to different weather conditions |
| CN111932008B (en) * | 2020-08-06 | 2022-08-30 | 集美大学 | Ship photovoltaic output power prediction method applicable to different weather conditions |
| CN112364477A (en) * | 2020-09-29 | 2021-02-12 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
| CN112364477B (en) * | 2020-09-29 | 2022-12-06 | 中国电器科学研究院股份有限公司 | Outdoor empirical prediction model library generation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Photovoltaic power forecasting with a hybrid deep learning approach | |
| CN106529814B (en) | Distributed photovoltaic ultra-short term prediction method based on Adaboost clustering and Markov chain | |
| CN112257941B (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
| CN110909919A (en) | Photovoltaic power prediction method of depth neural network model with attention mechanism fused | |
| CN108376262B (en) | Analytical model construction method for typical characteristics of wind power output | |
| CN110334870B (en) | Photovoltaic power station short-term power prediction method based on gated cyclic unit network | |
| CN105787594B (en) | Irradiation prediction technique based on multivariate time series and regression analysis | |
| CN110503153B (en) | Photovoltaic system fault diagnosis method based on differential evolution algorithm and support vector machine | |
| CN107403015B (en) | Short-term optical power prediction method based on time series similarity | |
| CN114004139A (en) | Photovoltaic power generation power prediction method | |
| CN110866633B (en) | Micro-grid ultra-short-term load prediction method based on SVR support vector regression | |
| CN112418346B (en) | Numerical weather forecast total radiation system error classification calculation method | |
| Zhang et al. | Wavelet-based neural network with genetic algorithm optimization for generation prediction of PV plants | |
| CN113837426A (en) | Weather-typing-based photovoltaic power prediction method | |
| CN111985678A (en) | Photovoltaic power short-term prediction method | |
| CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence | |
| CN115204444A (en) | Photovoltaic power prediction method based on improved cluster analysis and fusion integration algorithm | |
| CN116632823A (en) | Short-term photovoltaic power prediction method based on power conversion model and multi-layer perceptron | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN112132344A (en) | Short-term wind power prediction method based on similar day and FRS-SVM | |
| CN111461297B (en) | Solar irradiation quantity optimization prediction algorithm based on MPC and ELM neural network | |
| CN117060407A (en) | Wind power cluster power prediction method and system based on similar day division | |
| Tai et al. | Power prediction of photovoltaic power generation based on LSTM model with additive Attention mechanism | |
| CN116050592A (en) | Multi-dimensional photovoltaic power prediction method and system | |
| CN113437938B (en) | Photovoltaic array output power calculation method considering field characteristics due to regional differences |
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 |