CN116432874A - Distributed photovoltaic power prediction method based on characteristic power - Google Patents
Distributed photovoltaic power prediction method based on characteristic power Download PDFInfo
- Publication number
- CN116432874A CN116432874A CN202310700554.1A CN202310700554A CN116432874A CN 116432874 A CN116432874 A CN 116432874A CN 202310700554 A CN202310700554 A CN 202310700554A CN 116432874 A CN116432874 A CN 116432874A
- Authority
- CN
- China
- Prior art keywords
- power
- data
- characteristic
- photovoltaic power
- distributed photovoltaic
- 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 33
- 238000010248 power generation Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims abstract description 4
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the field of photovoltaic power generation power prediction, and discloses a distributed photovoltaic power prediction method based on characteristic power, which comprises the following steps: collecting historical power generation data, power station capacity, meteorological data and time data of each distributed power station in a set area; carrying out normalization processing on the collected historical data of each photovoltaic power station, and then clustering according to the days; processing the clustered power data to obtain the characteristic power of each photovoltaic power station; training a CNN neural network prediction model; s5: and updating the characteristic power of the power station according to a certain frequency, inputting the characteristic power, weather forecast data and time data into a prediction model, and predicting the photovoltaic power. Comprehensively, the invention realizes that the power generation power of each photovoltaic power station is accurately predicted under the condition that part of distributed photovoltaic power stations have no historical power data, thereby ensuring the safe operation of the power grid to a certain extent.
Description
Technical Field
The invention relates to the field of photovoltaic power generation power prediction, in particular to a distributed photovoltaic power prediction method based on characteristic power.
Background
Photovoltaic power generation is a technology that converts solar energy into electrical energy. Centralized photovoltaic is a relatively mature power generation mode at present, generally has perfect power and weather monitoring devices, can store a large amount of historical data, and can establish a special prediction model for a centralized photovoltaic power station to predict photovoltaic power. The distributed photovoltaic starting is relatively late, and has the following characteristics: firstly, the investment cost of a single power station is low, a meteorological monitoring device is not generally provided, and the inclination angle, the phase angle, the cleanliness degree and the like of different photovoltaic power stations are different; secondly, the installation time of the distributed photovoltaic is uneven, and part of the photovoltaic has no historical power data. Thus, distributed photovoltaics are difficult to achieve one-station-one prediction like centralized photovoltaics.
With the increasing number of distributed power stations, the randomness and fluctuation of the output of the distributed power stations cause pressure on the safe operation of a power grid, so that the accurate prediction of the generated power of the distributed photovoltaic power stations in a certain area is more and more important. At present, a method for accurately predicting the power generated by each photovoltaic power station under the condition that part of distributed photovoltaic power stations have no historical power data is still lacking in the industry.
Disclosure of Invention
Aiming at the defects and drawbacks existing in the prior art, the invention provides a distributed photovoltaic power prediction method based on characteristic power, which uses the characteristic power to represent the characteristics of a photovoltaic power station in a fuzzy manner and establishes a unified prediction model for the photovoltaic in a set area; for a distributed photovoltaic power station without historical data, the characteristic power can be obtained through several days of power, and a unified prediction model is used for more accurate prediction.
The object of the invention can be achieved by the following technical scheme.
A distributed photovoltaic power prediction method based on characteristic power comprises the following steps.
S1: collecting historical power generation power data and power station capacity of each distributed photovoltaic power station in a set area; meteorological data and time data of a set area are collected.
S2: carrying out normalization processing on each historical power generation power data based on the capacity of each power station acquired by the S1, and clustering according to days;
s3: and processing the clustered data to obtain the characteristic power of each distributed photovoltaic power station.
S4: and taking meteorological data, time data and characteristic power as input, taking normalized historical power generation power data as output, and training by using a CNN neural network to obtain a photovoltaic power unified prediction model of a set area.
S5: and updating the characteristic power of the distributed photovoltaic power station according to a certain frequency, inputting the updated characteristic power, meteorological data and time data into the photovoltaic power unified prediction model obtained in the step S4, and outputting a photovoltaic power prediction result.
Preferably, in the step S1, the set area is a county or a district; the meteorological data comprise ambient temperature, relative humidity, wind speed and air pressure; the time data comprises month, day, time and minute.
Preferably, the clustering method in S2 is k-means clustering.
And intercepting part of data from the normalized daily historical power generation data, and extracting the sum, the discrete difference and the third derivative average value of the power curve from the intercepted data as clustering features.
Preferably, the clustering in S3 is k-means clustering.
And processing the class data with highest sum of power in the k class data by using an exponential weighted average method to obtain the characteristic power of each distributed photovoltaic power station at different time.
in the method, in the process of the invention,is the characteristic power after smoothing at time point i, < >>Is the historical actual power at time point i, α is the memory decay factor, +.>Is the characteristic power smoothed at the time point i-1.
Preferably, in S4, the meteorological data, the time data, and the characteristic power of the same day are taken as one input sample, and different characteristics are taken as different channels of the input.
Preferably, the method for updating the characteristic power in S5 is as follows: and (3) classifying the daily power generation power curve by using the clustering center obtained in the step (S2), and then executing the step (S3) to obtain updated characteristic power.
The beneficial technical effects of the invention are as follows: the method comprises the steps of clustering and processing historical power data of photovoltaic power stations to obtain continuously-changed characteristic power of each power station, taking the continuously-changed characteristic power, meteorological data and time data as input, and training a unified prediction model of a distributed photovoltaic power station in a set area; for a distributed photovoltaic power station without historical data, the characteristic power can be obtained through several days of power, and a unified prediction model is used for more accurate prediction. Comprehensively, the invention realizes that the power generation power of each photovoltaic power station is accurately predicted under the condition that part of distributed photovoltaic power stations have no historical power data, thereby ensuring the safe operation of the power grid to a certain extent.
Drawings
Fig. 1 is a general flow chart of the present invention.
FIG. 2 is a schematic diagram of the clustering result of the power curve according to the present invention.
Figure 3 shows the characteristic power of the multi-station calculated on a certain day according to the invention.
FIG. 4 shows the prediction results of the generated power of the multiple power stations according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Examples: as shown in fig. 1, a distributed photovoltaic power prediction method based on characteristic power includes the following steps.
S1: historical power generation data and power station capacity of each distributed photovoltaic power station in a set area are collected, and meteorological data and time data of the set area are collected.
The set area is an area with the weather condition close to that of the county or the district, and the acquired weather data comprise the ambient temperature, the relative humidity, the wind speed and the air pressure; the time data comprises month, day, time and minute. In this embodiment, the plant history generated power data used is from several distributed photovoltaic plants in the urban and sunny region of the Qingdao city.
S2: after normalization processing is carried out on each historical power generation power data based on the capacity of each power station acquired by the S1, the normalized daily historical power generation power data is divided by using a k-means clustering method, and k-class power data are obtained.
When k-means clustering is carried out, part of power data is intercepted in normalized daily historical power generation power data, and features such as the sum of power, discrete difference, power curve third-order derivative average value and the like are extracted and clustered to be used as clustering features. In this embodiment, the data from 6:00 to 18:00 are intercepted as input data, and the clustering result is shown in fig. 2, and it can be seen that the power curve of the photovoltaic power station is classified into 4 types according to this embodiment, wherein the second type of curve has relatively high power and stable variation, and accords with the generating power curve in sunny days.
S3: and (3) using the power data after clustering, which is the highest sum of the power in the 4 types of data, as the power generated on sunny days, and processing the power data by using an exponential weighted average method to obtain the characteristic power of the photovoltaic power station at different times.
Firstly, averaging normalized power of each distributed power station in the area in a sunny day for a period of time to obtain average power, wherein the average power is used as initial characteristic power of each distributed power station; and updating the characteristic power of each power station by using an exponential weighted average method according to the generated power of each power station under sunny days so as to achieve the purpose of representing the power generation characteristics of each power station. The formula of the exponential weighted average method is:。
in the method, in the process of the invention,is the characteristic power after smoothing at time point i, < >>Is the historical actual power at time point i, α is the memory decay factor, +.>Is the characteristic power smoothed at the time point i-1. In the embodiment, alpha is 0.2 so as to ensure that the characteristic power changes correspondingly with seasons, dust coverage conditions and aging conditions of the photovoltaic panel on the premise that the characteristic power of the power station is basically stable.
The characteristic power is updated and calculated for the power stations 13, 25, 29 of the area, and the calculated characteristic power is shown in fig. 3 on a certain day, wherein the characteristic power of the power stations 13, 25 is similar, and the characteristic power of the power station 29 is higher than that of the power stations 13, 25.
S4: and taking meteorological data, time data and characteristic power as input, taking normalized historical power generation power data as output, and training by using a CNN neural network to obtain a photovoltaic power unified prediction model.
S5: and updating the characteristic power of the distributed photovoltaic power station according to a certain frequency, inputting the updated characteristic power, meteorological data and time data into the photovoltaic power unified prediction model obtained in the step S4, and outputting a photovoltaic power prediction result.
As a result of the prediction, as shown in fig. 4, the power generated by the distributed photovoltaic power stations 13, 25, 29 on a certain day is predicted together. It can be seen that the power generated by the power stations 13, 25 is almost uniform over the day, whereas the power generated by the power station 29 is significantly higher than 13, 25, since the characteristic power characterizing the power generation characteristics of each power station is used, even if the same predictive model is used, the predicted powers of the power stations 13, 25 are similar on the basis of the predicted results, whereas the predicted power of the power station 29 is higher than 13, 25.
The above embodiments are illustrative of the specific embodiments of the present invention, and not restrictive, and various changes and modifications may be made by those skilled in the relevant art without departing from the spirit and scope of the invention, so that all such equivalent embodiments are intended to be within the scope of the invention.
Claims (6)
1. The distributed photovoltaic power prediction method based on the characteristic power is characterized by comprising the following steps of:
s1: collecting historical power generation power data and power station capacity of each distributed photovoltaic power station in a set area; collecting meteorological data and time data of a set area;
s2: carrying out normalization processing on each historical power generation power data based on the capacity of each power station acquired by the S1, and clustering according to days;
s3: processing the clustered data to obtain the characteristic power of each distributed photovoltaic power station;
s4: taking meteorological data, time data and characteristic power as input, taking normalized historical power generation power data as output, and training by using a CNN neural network to obtain a photovoltaic power unified prediction model of a set area;
s5: and updating the characteristic power of the distributed photovoltaic power station according to a certain frequency, inputting the updated characteristic power, meteorological data and time data into the photovoltaic power unified prediction model obtained in the step S4, and outputting a photovoltaic power prediction result.
2. The method for predicting the distributed photovoltaic power based on the characteristic power according to claim 1, wherein in S1, the set area is a county or a district; the meteorological data comprise ambient temperature, relative humidity, wind speed and air pressure; the time data comprises month, day, time and minute.
3. The method for predicting the distributed photovoltaic power based on the characteristic power according to claim 1, wherein the clustering method in S2 is k-means clustering;
and intercepting part of data from the normalized daily historical power generation data, and extracting the sum, the discrete difference and the third derivative average value of the power curve from the intercepted data as clustering features.
4. The method for predicting the distributed photovoltaic power based on the characteristic power according to claim 1, wherein the clustering in the S3 is k-means clustering;
processing class data with highest sum of power in the k class data by using an exponential weighted average method to obtain characteristic power of each distributed photovoltaic power station at different time;
the formula of the exponential weighted average method is as follows:
5. The method according to claim 1, wherein in S4, weather data, time data, and characteristic power of the same day are taken as one input sample, and different characteristics are taken as different channels of the input.
6. The method for predicting the distributed photovoltaic power based on the characteristic power according to claim 1, wherein the method for updating the characteristic power in S5 is as follows: and (3) classifying the daily power generation power curve by using the clustering center obtained in the step (S2), and then executing the step (S3) to obtain updated characteristic power.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310700554.1A CN116432874A (en) | 2023-06-14 | 2023-06-14 | Distributed photovoltaic power prediction method based on characteristic power |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310700554.1A CN116432874A (en) | 2023-06-14 | 2023-06-14 | Distributed photovoltaic power prediction method based on characteristic power |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116432874A true CN116432874A (en) | 2023-07-14 |
Family
ID=87080136
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310700554.1A Pending CN116432874A (en) | 2023-06-14 | 2023-06-14 | Distributed photovoltaic power prediction method based on characteristic power |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116432874A (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017155421A1 (en) * | 2016-03-07 | 2017-09-14 | Centro De Investigação Em Energia Ren - State Grid, S.A | Method and system for forecasting the power output of a group of photovoltaic power plants and managing the integration of said power output into a power grid |
CN107730044A (en) * | 2017-10-20 | 2018-02-23 | 燕山大学 | A kind of hybrid forecasting method of renewable energy power generation and load |
CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
CN113627674A (en) * | 2021-08-12 | 2021-11-09 | 中国华能集团清洁能源技术研究院有限公司 | Distributed photovoltaic power station output prediction method and device and storage medium |
CN113919232A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | Photovoltaic power station power prediction method and system based on recurrent neural network |
CN114186723A (en) * | 2021-11-26 | 2022-03-15 | 内蒙古工业大学 | Distributed photovoltaic power grid virtual prediction system based on space-time correlation |
CN114862023A (en) * | 2022-05-11 | 2022-08-05 | 济南大学 | Distributed photovoltaic power prediction method and system based on four-dimensional point-by-point meteorological forecast |
CN115423145A (en) * | 2022-07-26 | 2022-12-02 | 泛太能源环境(浙江)有限公司 | Photovoltaic power prediction method based on Kmeans-VMD-WT-LSTM method |
CN115759467A (en) * | 2022-12-03 | 2023-03-07 | 国网福建省电力有限公司 | Time-division integrated learning photovoltaic prediction method for error correction |
CN115829105A (en) * | 2022-11-24 | 2023-03-21 | 三峡大学 | Photovoltaic power prediction method based on historical data feature search |
CN115907195A (en) * | 2022-12-08 | 2023-04-04 | 国电和风风电开发有限公司 | Photovoltaic power generation power prediction method, system, electronic device and medium |
CN115936062A (en) * | 2023-01-10 | 2023-04-07 | 国网内蒙古东部电力有限公司通辽供电公司 | Photovoltaic power day-ahead interval prediction method based on scene generation and deep learning |
CN115983477A (en) * | 2023-01-04 | 2023-04-18 | 湖南大唐先一科技有限公司 | Load prediction method based on K-means clustering and convolutional neural network model |
CN116011608A (en) * | 2022-09-16 | 2023-04-25 | 浙江大学 | Photovoltaic power ultra-short-term prediction method and device, electronic equipment and storage medium |
CN116050636A (en) * | 2023-02-01 | 2023-05-02 | 阳光电源(上海)有限公司 | Output prediction method, device, equipment and medium of photovoltaic power station |
CN116227637A (en) * | 2023-02-27 | 2023-06-06 | 国网福建省电力有限公司 | Active power distribution network oriented refined load prediction method and system |
-
2023
- 2023-06-14 CN CN202310700554.1A patent/CN116432874A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017155421A1 (en) * | 2016-03-07 | 2017-09-14 | Centro De Investigação Em Energia Ren - State Grid, S.A | Method and system for forecasting the power output of a group of photovoltaic power plants and managing the integration of said power output into a power grid |
CN107730044A (en) * | 2017-10-20 | 2018-02-23 | 燕山大学 | A kind of hybrid forecasting method of renewable energy power generation and load |
CN109002915A (en) * | 2018-07-13 | 2018-12-14 | 福州大学 | Photovoltaic plant short term power prediction technique based on Kmeans-GRA-Elman model |
CN113627674A (en) * | 2021-08-12 | 2021-11-09 | 中国华能集团清洁能源技术研究院有限公司 | Distributed photovoltaic power station output prediction method and device and storage medium |
CN113919232A (en) * | 2021-10-25 | 2022-01-11 | 北京航天创智科技有限公司 | Photovoltaic power station power prediction method and system based on recurrent neural network |
CN114186723A (en) * | 2021-11-26 | 2022-03-15 | 内蒙古工业大学 | Distributed photovoltaic power grid virtual prediction system based on space-time correlation |
CN114862023A (en) * | 2022-05-11 | 2022-08-05 | 济南大学 | Distributed photovoltaic power prediction method and system based on four-dimensional point-by-point meteorological forecast |
CN115423145A (en) * | 2022-07-26 | 2022-12-02 | 泛太能源环境(浙江)有限公司 | Photovoltaic power prediction method based on Kmeans-VMD-WT-LSTM method |
CN116011608A (en) * | 2022-09-16 | 2023-04-25 | 浙江大学 | Photovoltaic power ultra-short-term prediction method and device, electronic equipment and storage medium |
CN115829105A (en) * | 2022-11-24 | 2023-03-21 | 三峡大学 | Photovoltaic power prediction method based on historical data feature search |
CN115759467A (en) * | 2022-12-03 | 2023-03-07 | 国网福建省电力有限公司 | Time-division integrated learning photovoltaic prediction method for error correction |
CN115907195A (en) * | 2022-12-08 | 2023-04-04 | 国电和风风电开发有限公司 | Photovoltaic power generation power prediction method, system, electronic device and medium |
CN115983477A (en) * | 2023-01-04 | 2023-04-18 | 湖南大唐先一科技有限公司 | Load prediction method based on K-means clustering and convolutional neural network model |
CN115936062A (en) * | 2023-01-10 | 2023-04-07 | 国网内蒙古东部电力有限公司通辽供电公司 | Photovoltaic power day-ahead interval prediction method based on scene generation and deep learning |
CN116050636A (en) * | 2023-02-01 | 2023-05-02 | 阳光电源(上海)有限公司 | Output prediction method, device, equipment and medium of photovoltaic power station |
CN116227637A (en) * | 2023-02-27 | 2023-06-06 | 国网福建省电力有限公司 | Active power distribution network oriented refined load prediction method and system |
Non-Patent Citations (2)
Title |
---|
严华江;章坚民;胡瑛俊;张力行;焦田利;闻安;: "考虑空间相关性的分布式光伏发电出力预测及误差评价指标研究", 浙江电力, no. 03, pages 54 - 60 * |
程泽 等: "基于数据挖掘的光伏阵列发电预测方法研究", 《太阳能学报》, vol. 38, no. 3, pages 728 - 731 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Han et al. | A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm | |
CN112257941B (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 | |
CN109086928A (en) | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model | |
CN115425680B (en) | Power prediction model construction and prediction method of multi-energy combined power generation system | |
WO2023201552A1 (en) | County-wide photovoltaic prediction method based on cluster division and data enhancement | |
CN105069521A (en) | Photovoltaic power plant output power prediction method based on weighted FCM clustering algorithm | |
CN112070311A (en) | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting | |
CN111898812B (en) | Distributed photovoltaic data virtual acquisition method | |
CN114792156A (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
CN111401603A (en) | Multi-type energy demand prediction method | |
Qijun et al. | Photovoltaic power prediction based on principal component analysis and Support Vector Machine | |
CN115759467A (en) | Time-division integrated learning photovoltaic prediction method for error correction | |
CN111541273B (en) | Method for calculating and analyzing consumption capacity of new energy in region | |
CN112215392A (en) | Method for predicting power generation capacity of wind power medium and long term region based on equipment state and environmental factors | |
CN105207255B (en) | A kind of power system peak regulation computational methods suitable for wind power output | |
CN116432874A (en) | Distributed photovoltaic power prediction method based on characteristic power | |
CN108876060B (en) | Big data based prediction method for wind power output probability of sample collection | |
CN111242371A (en) | Photovoltaic power generation short-term prediction correction method based on non-iterative multi-model | |
CN116484998A (en) | Distributed photovoltaic power station power prediction method and system based on meteorological similar day | |
CN112949938B (en) | Wind power climbing event direct forecasting method for improving training sample class imbalance | |
CN112668764B (en) | Offshore wind farm energy storage system optimization configuration method based on cloud model and FCM algorithm | |
CN113780643A (en) | Photovoltaic power station short-term output prediction method based on case reasoning | |
CN109274124A (en) | Wind-powered electricity generation on-site elimination energy force prediction method based on scene Markov method | |
Cheng et al. | Establishing The Photovoltaic Output Model With PIC-LS-SVM Based on Curve Characteristic Index Dimensionality Reduction |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230714 |