CN111898812B - Distributed photovoltaic data virtual acquisition method - Google Patents
Distributed photovoltaic data virtual acquisition method Download PDFInfo
- Publication number
- CN111898812B CN111898812B CN202010693864.1A CN202010693864A CN111898812B CN 111898812 B CN111898812 B CN 111898812B CN 202010693864 A CN202010693864 A CN 202010693864A CN 111898812 B CN111898812 B CN 111898812B
- Authority
- CN
- China
- Prior art keywords
- data
- irradiance
- photovoltaic
- historical
- day
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims abstract description 3
- 239000013598 vector Substances 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000013480 data collection Methods 0.000 claims 3
- 238000010586 diagram Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000011160 research 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Photovoltaic Devices (AREA)
Abstract
A distributed photovoltaic data virtual acquisition method is characterized in that historical operation and maintenance data of a distributed photovoltaic power station provided with a data acquisition device in a gray correlation theory analysis area are utilized to obtain a characteristic curve of irradiance and distributed photovoltaic output; and then, performing relevance calculation on the real-time regional daily irradiance information and historical irradiance data, selecting similar days according to the relevance, and establishing a BP neural network data virtual acquisition model to realize virtual acquisition of all distributed photovoltaic data in a regional range. The method utilizes the irradiance information closely related to the photovoltaic output power to virtually collect the photovoltaic output data, compared with the existing photovoltaic output prediction method, the method has the advantages that the required data volume is small, the dimensionality of data input is reduced, the algorithm is greatly simplified, the output data of the photovoltaic power station in one day can be collected systematically, the model is simple, the network model does not need to be trained in different time periods, and the purpose of minimizing the cost is achieved while the data precision is ensured.
Description
Technical Field
The invention belongs to the technical field of electric power, relates to distributed photovoltaic operation and maintenance data acquisition, and provides a distributed photovoltaic data virtual acquisition method based on gray correlation degree and BP neural network mixing.
Background
Photovoltaic power generation is the most rapidly developing renewable energy technology in recent years. By the end of 2019, 9 months, the installed capacity of photovoltaic power generation reaches 1.90 hundred million kilowatts, the distributed photovoltaic ratio reaches more than 30%, and the number of users exceeds hundreds of thousands. The mass distributed photovoltaic power station has the characteristics of complex and various application scenes, different meteorological conditions, different access point grid structures and the like, and has a lot of difficulties in the aspects of operation and maintenance information acquisition, decision model customization, result evaluation and the like. Particularly, the distributed photovoltaic operation and maintenance requires a large number of data points to be monitored, and the problems of high cost of data acquisition, transmission and storage can be caused only by increasing the number of sensors, increasing the acquisition frequency and the like. How to realize a low-cost and high-efficiency distributed photovoltaic operation and maintenance data acquisition scheme under the condition of fully considering the economy of the distributed photovoltaic operation and maintenance is worthy of deep research.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the operation and maintenance data amount of massive distributed photovoltaic is large, the cost of data acquisition, transmission and storage is too high, and a low-cost and high-efficiency distributed photovoltaic operation and maintenance data acquisition scheme needs to be realized.
The technical scheme of the invention is as follows: a distributed photovoltaic data virtual acquisition method is characterized in that virtual acquisition of photovoltaic data of a distributed photovoltaic power station in an area is achieved based on a gray correlation degree and BP neural network mixing method, a characteristic curve of irradiance and distributed photovoltaic output is obtained by means of operation and maintenance data of a photovoltaic power station D with a data acquisition device installed in the area, irradiance is used as a characteristic vector, similar days of irradiance are selected by means of a gray correlation theory, similar calendar history data of a set time period is selected as an original data training set to train the BP neural network, irradiance data of a day to be acquired in the area is used as input of the BP neural network, photovoltaic output data of the photovoltaic power station D to be acquired are obtained, photovoltaic power station data without the data acquisition device is obtained through deduction, and virtual acquisition of the distributed photovoltaic operation and maintenance data in the area is achieved.
Firstly, analyzing historical operation and maintenance data of a photovoltaic power station provided with a data acquisition device in a region by using a grey correlation theory, obtaining a characteristic curve of irradiance and distributed photovoltaic output, obtaining historical irradiance data, then carrying out correlation calculation on daily irradiance real-time information of the region and the historical irradiance data, and selecting a historical day with the correlation reaching more than 0.9 as a similar day; and establishing a BP neural network data virtual acquisition model based on historical data of similar days, and predicting the output of the photovoltaic to be acquired by using the trained BP neural network model to realize the virtual acquisition of the distributed photovoltaic data in the regional range.
The technical scheme of the invention aims to solve the problem of overhigh data acquisition cost caused by the fact that the data acquisition device is installed in a full-coverage mode in a distributed photovoltaic power station, and constructs a distributed photovoltaic data virtual acquisition method based on the gray correlation degree and BP neural network, the distributed photovoltaic power station which is installed with the data acquisition device in an area range is used for obtaining data, a main meteorological factor-irradiance which influences the photovoltaic output power is selected and used as a characteristic vector, and similar days are selected by using a gray correlation theory, and the accuracy of similar day selection is influenced because the overlarge deviation of the climatic factor is caused by overlong interval time, so that the characteristic that the influence of historical data on photovoltaic power generation is approximate to large and small is considered, and the data of about 90 days is selected as an original data training set. And then, taking historical data of similar days and irradiance data in a real-time regional range as the input of a BP neural network, and realizing virtual acquisition of distributed photovoltaic operation and maintenance data in the regional range. Compared with the traditional method for acquiring the photovoltaic data only by additionally installing a data acquisition device, the method greatly saves the cost of data acquisition on the premise of ensuring higher accuracy.
The photovoltaic output data is virtually collected by utilizing the irradiance information closely related to the photovoltaic output power, compared with the existing photovoltaic output prediction method, the photovoltaic output prediction method has the advantages that the required data volume is small, the dimension of data input is reduced, the complexity degree of an algorithm is greatly simplified, the output data of a photovoltaic power station in one day can be collected systematically, the model is simple, and a time-interval training model is not needed. And finally, the aim of minimizing the cost can be fulfilled while the data precision is ensured.
Drawings
Fig. 1 is a distributed photovoltaic data virtual acquisition model established according to the method of the present invention.
Fig. 2 shows the result of similar day selections for months 1, 2 and 3 according to the method of the invention.
Fig. 3 shows the result of similar day selections for months 6, 7 and 8 according to the method of the invention.
Fig. 4 shows the result of similar day selections for months 10, 11 and 12 according to the method of the invention.
FIG. 5 is a schematic diagram of the results of distributed photovoltaic data acquisition in the region of months 1, 2, and 3 according to the method of the present invention.
Fig. 6 is a schematic diagram of the result of collecting distributed photovoltaic data in the 6, 7 and 8 month regions according to the method of the present invention.
Fig. 7 is a schematic diagram of the result of collecting distributed photovoltaic data in the region of months 10, 11 and 12 according to the method of the present invention.
FIG. 8 is a schematic diagram of the present invention with virtual acquisition performed in scale.
Detailed Description
The technical scheme of the invention provides a distributed photovoltaic data virtual acquisition method based on the mixing of grey correlation degree and a BP neural network, so as to solve the problem of high cost caused by full coverage of a photovoltaic data acquisition device.
Referring now to the drawings, which illustrate exemplary embodiments of the present invention, first, irradiance data and output power data of historical days are known by means of distributed photovoltaic stations having data acquisition devices installed therein within a region, and irradiance, which is a main meteorological factor affecting photovoltaic output power, is selected and used as a feature vector to perform similar day selection by using a grey correlation theory. The method comprises the following steps:
considering that the influence of historical data on photovoltaic power generation has the characteristic of 'big end up and small end up', and selecting data which lasts for 90 days, namely three months as an original data training set.
And constructing a characteristic vector by adopting the average value of the irradiance of each historical day and the irradiance at each moment:
X＝[F 1 ,F 2 ,…,F n ,F av ] (1)
in the formula, F n Irradiance at the nth time, F av Is the average value of irradiance.
The degree of association is then calculated.
Firstly, carrying out normalization processing on irradiance data and photovoltaic power data as follows:
in the formula, x min 、x max The data are respectively original data, a minimum value in the original data and a maximum value in the original data, and x' is normalized data.
A gray correlation analysis of irradiance data is illustrated. The normalized irradiance characteristic vectors of the day to be collected and the historical day are respectively as follows:
x 0 ＝(x 0 (1),x 0 (2),…,x 0 (k)) (3)
x i ＝(x i (1),x i (2),…,x i (k)) (4)
in the formula, x 0 Is the feature vector of the day to be collected, x i K is the total number of normalized feature vectors, and is expressed as k = n +1, for the feature vector of the ith day in the history days.
Calculating the association degree of each historical day and the day to be acquired of the power station to be virtually acquired, wherein the calculation formula is as follows:
wherein ξ i (j) R is a resolution coefficient, and is generally 0.5.
For the correlation coefficient of each component in the comprehensive characteristic vector, the problem of the weight of each component can be effectively solved by defining the similarity in a continuous power mode, and the similarity between the historical daily irradiance data and the daily irradiance data to be collected is defined as follows:
the invention aims to select all samples with the relevance degree larger than 0.9 to form a similar day as a training sample for virtual acquisition.
Preferably, the historical data of similar days are preprocessed, and the time window of data acquisition is set as 6:00-19:00, converting the data acquisition time interval into 1 hour, and performing relevance analysis and BP neural network construction and training by using the preprocessed historical data.
Different periods are chosen to validate the practice of the invention depending on the climate. Selecting three different periods of 1 month, 2 months, 3 months, 6 months, 7 months, 8 months, 10 months, 11 months and 12 months for virtual acquisition of photovoltaic data, wherein the selection results of similar days are shown in tables 1-3.
Table 1, 2, 3 month similar daily irradiance data
Table 2, 6, 7, 8 month similar daily irradiance data
Table 3, 10, 11, 12 month similar daily irradiance data
The graphs corresponding to the above tables are shown in fig. 2, 3 and 4. The irradiance of the days to be collected in different months is similar to the irradiance characteristic curve of the similar day selected by the method, and the method has high correlation, so that the effectiveness of the similar day selection model established by the method is verified.
After the similar day is selected, the historical data of the similar day is used for training a BP neural network model, the data of the day to be collected is input into a neural network to be fitted to obtain the photovoltaic output power of the day, and the output result is shown in table 4.
TABLE 4 virtual Collection results
The graphs corresponding to table 4 are shown in fig. 5, 6, and 7.
Finally, the output prediction is carried out on the photovoltaic power station building model with the collecting devices in the same area through the process, and then other photovoltaic power stations without the collecting devices in the same area calculate the predicted photovoltaic output through the installed capacity proportion, so that the virtual collection of the photovoltaic output of all the photovoltaic power stations in the area is realized. Specifically, after the generated power of the daily unit capacity to be virtually collected is obtained, the generated power in the gridding area is calculated according to the proportion, and the formula is shown as follows.
In the formula: p k Data to be collected, P, for a photovoltaic power station k m Installed capacity, P, of photovoltaic plant k D Installed capacity, p, of photovoltaic plant D equipped with collecting means f The photovoltaic output data is obtained according to the data virtual collection of the photovoltaic power station D. As shown in fig. 8, the virtual collection of the photovoltaic output power of each power station is performed according to the installed capacity of each power station in proportion, where a, B, and C represent different photovoltaic power stations.
Claims (2)
1. A distributed photovoltaic data virtual acquisition method is characterized in that a gray correlation degree and BP neural network mixing method is used for achieving virtual acquisition of photovoltaic data of a distributed photovoltaic power station in an area, a characteristic curve of irradiance and distributed photovoltaic output is obtained by means of operation and maintenance data of a photovoltaic power station D with a data acquisition device installed in the area, irradiance is used as a characteristic vector, similar days of irradiance are selected by using a gray correlation theory, similar calendar history data in a set time period is selected as an original data training set to train the BP neural network, irradiance data of a day to be acquired in the area is used as input of the BP neural network, photovoltaic output data of the photovoltaic power station D to be acquired are obtained, photovoltaic power station data without the data acquisition device is obtained through deduction, and virtual acquisition of the distributed photovoltaic operation and maintenance data in the area is achieved;
firstly, analyzing historical operation and maintenance data of a photovoltaic power station provided with a data acquisition device in a region by using a grey correlation theory, obtaining a characteristic curve of irradiance and distributed photovoltaic output to obtain historical irradiance data, then carrying out correlation calculation on daily irradiance real-time information of the region and the historical irradiance data, and selecting a historical day with the correlation of more than 0.9 as a similar day; establishing a BP neural network data virtual acquisition model based on historical data of similar days, predicting the output of sunlight voltage to be acquired by using the trained BP neural network model, and realizing the virtual acquisition of distributed photovoltaic data in a regional range;
in grey correlation analysis, data of three consecutive months are selected as historical data, and an irradiance characteristic vector X is constructed by adopting the average value of irradiance in each historical day and irradiance at each moment, and is as follows:
X＝[F 1 ,F 2 ,…,F n ,F av ] (1)
in the formula, F n Irradiance at the nth time, F av Average value of irradiance;
firstly, carrying out normalization processing on irradiance data and photovoltaic power data as follows:
in the formula, x min 、x max Respectively, the original data, the minimum value in the original data and the maximum value in the original data, wherein x' is the normalized data;
the normalized irradiance characteristic vectors of the day to be collected and the historical day are respectively as follows:
x 0 ＝(x 0 (1),x 0 (2),…,x 0 (k)) (3)
x i ＝(x i (1),x i (2),…,x i (k)) (4)
in the formula, x 0 Is the feature vector of the day to be collected, x i K is the feature vector of the ith day in the historical days, and is the total number of the normalized feature vectors, and is represented as k = n +1;
calculating the association degree of each historical day and the day to be acquired of the power station to be virtually acquired, wherein the calculation formula is as follows:
wherein ξ i (j) Taking the correlation coefficient as the correlation coefficient, taking the resolution coefficient as r as 0.5;
for the correlation coefficient of each component in the comprehensive characteristic vector, the similarity is defined by adopting a continuous power mode, the problem of the weight of each component is solved, and the similarity of the historical daily irradiance data and the daily irradiance data to be collected is as follows:
the method comprises the steps of establishing a BP neural network model for a photovoltaic power station with a collection device in the same region to carry out output prediction, and then calculating and predicting photovoltaic output of other photovoltaic power stations without the collection device in the same region according to installed capacity proportion, so that virtual collection of the photovoltaic output of all photovoltaic power stations in the region is realized, photovoltaic output data of a day to be collected is generated power of unit capacity of the day to be virtually collected, and the generated power of the photovoltaic power stations in a gridding region is calculated according to proportion, and is shown as the following formula:
in the formula: p k For data to be collected, P, of a photovoltaic power station k m Installed capacity, P, of photovoltaic plant k D Installed capacity, p, for photovoltaic power station D equipped with a collection device f The photovoltaic output data is obtained according to the data virtual collection of the photovoltaic power station D.
2. The distributed virtual photovoltaic data collection method according to claim 1, wherein historical data of similar days are preprocessed, a time window is set for data collection, the data collection time interval is changed into 1 hour, and relevance analysis and construction and training of a BP neural network are performed by using the preprocessed historical data.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010693864.1A CN111898812B (en) | 2020-07-17 | 2020-07-17 | Distributed photovoltaic data virtual acquisition method |
| AU2021205108A AU2021205108A1 (en) | 2020-07-17 | 2021-07-16 | Virtual collection method for distributed photovoltaic data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010693864.1A CN111898812B (en) | 2020-07-17 | 2020-07-17 | Distributed photovoltaic data virtual acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111898812A CN111898812A (en) | 2020-11-06 |
| CN111898812B true CN111898812B (en) | 2022-10-04 |
Family
ID=73189401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010693864.1A Active CN111898812B (en) | 2020-07-17 | 2020-07-17 | Distributed photovoltaic data virtual acquisition method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111898812B (en) |
| AU (1) | AU2021205108A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113962357A (en) * | 2021-09-14 | 2022-01-21 | 天津大学 | GWO-WNN-based distributed photovoltaic power data virtual acquisition method |
| CN114552582B (en) * | 2022-04-27 | 2022-07-19 | 广东电网有限责任公司佛山供电局 | Real-time power generation load estimation method and system for photovoltaic power generation users |
| CN117973644B (en) * | 2024-04-02 | 2024-06-14 | 天津大学 | Distributed photovoltaic power virtual acquisition method considering optimization of reference power station |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218674A (en) * | 2013-04-07 | 2013-07-24 | 国家电网公司 | Method for predicating output power of photovoltaic power generation system based on BP (Back Propagation) neural network model |
| 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 |
| CN109685257A (en) * | 2018-12-13 | 2019-04-26 | 国网青海省电力公司 | A kind of photovoltaic power generation power prediction method based on Support vector regression |
| CN109858673A (en) * | 2018-12-27 | 2019-06-07 | 南京工程学院 | A kind of photovoltaic generating system power forecasting method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184404B (en) * | 2015-08-31 | 2018-12-18 | 中国科学院广州能源研究所 | Output power classification forecasting system suitable for photovoltaic system Life cycle |
-
2020
- 2020-07-17 CN CN202010693864.1A patent/CN111898812B/en active Active
-
2021
- 2021-07-16 AU AU2021205108A patent/AU2021205108A1/en not_active Abandoned
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218674A (en) * | 2013-04-07 | 2013-07-24 | 国家电网公司 | Method for predicating output power of photovoltaic power generation system based on BP (Back Propagation) neural network model |
| 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 |
| CN109685257A (en) * | 2018-12-13 | 2019-04-26 | 国网青海省电力公司 | A kind of photovoltaic power generation power prediction method based on Support vector regression |
| CN109858673A (en) * | 2018-12-27 | 2019-06-07 | 南京工程学院 | A kind of photovoltaic generating system power forecasting method |
Also Published As
| Publication number | Publication date |
|---|---|
| AU2021205108A1 (en) | 2022-02-03 |
| CN111898812A (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898812B (en) | Distributed photovoltaic data virtual acquisition method | |
| Li et al. | When weather matters: IoT-based electrical load forecasting for smart grid | |
| CN102663513B (en) | Utilize the wind power combined prediction modeling method of grey relational grade analysis | |
| CN110705743B (en) | New energy consumption electric quantity prediction method based on long-term and short-term memory neural network | |
| CN109546659B (en) | Power distribution network reactive power optimization method based on random matrix and intelligent scene matching | |
| CN110474339B (en) | Power grid reactive power control method based on deep power generation load prediction | |
| CN108388962B (en) | Wind power prediction system and method | |
| CN112257941A (en) | Photovoltaic power station short-term power prediction method based on improved Bi-LSTM | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| CN109376951B (en) | Photovoltaic probability prediction method | |
| CN111461921B (en) | Load modeling typical user database updating method based on machine learning | |
| CN115796393B (en) | Energy management optimization method, system and storage medium based on multi-energy interaction | |
| CN104463356A (en) | Photovoltaic power generation power prediction method based on multi-dimension information artificial neural network algorithm | |
| Dokur et al. | Hybrid model for short term wind speed forecasting using empirical mode decomposition and artificial neural network | |
| Li et al. | Photovoltaic array prediction on short-term output power method in centralized power generation system | |
| CN116151464A (en) | Photovoltaic power generation power prediction method, system and storable medium | |
| CN114997508A (en) | Greenhouse electricity utilization optimization method and system based on multi-energy complementation | |
| CN110852492A (en) | Photovoltaic power ultra-short-term prediction method for finding similarity based on Mahalanobis distance | |
| CN112561252B (en) | Reactive power combination evaluation method for power grid in new energy-containing region | |
| CN116187540B (en) | Wind power station ultra-short-term power prediction method based on space-time deviation correction | |
| CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
| CN112215392A (en) | Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors | |
| CN111242371A (en) | Photovoltaic power generation short-term prediction correction method based on non-iterative multi-model | |
| CN112949938B (en) | Wind power climbing event direct forecasting method for improving training sample class imbalance | |
| CN113850443A (en) | Short-term power load interval prediction method based on nonparametric Bootstrap error sampling |
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 |