CN109978258A - Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning - Google Patents
Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning Download PDFInfo
- Publication number
- CN109978258A CN109978258A CN201910229971.6A CN201910229971A CN109978258A CN 109978258 A CN109978258 A CN 109978258A CN 201910229971 A CN201910229971 A CN 201910229971A CN 109978258 A CN109978258 A CN 109978258A
- Authority
- CN
- China
- Prior art keywords
- data
- power generation
- photovoltaic power
- generation quantity
- machine learning
- 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 70
- 238000010248 power generation Methods 0.000 title claims abstract description 59
- 238000010801 machine learning Methods 0.000 title claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 238000002360 preparation method Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000011017 operating method Methods 0.000 claims abstract description 4
- 238000009434 installation Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 238000001556 precipitation Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning, the operating procedure of this method and system is as follows: step 1: data preparation；Step 2: data prediction；Step 3: multi-model training；Step 4: final mask is chosen based on minimum sandards difference；Step 5: generated energy prediction；Step 6: model evaluation.There is universality using such method provided by the invention, avoid an independent equipment and just need to establish a prediction model, simplify photovoltaic power generation quantity prediction process, improve forecasting efficiency；Photovoltaic apparatus self attributes are included in photovoltaic power generation quantity prediction process by this method, so that this method is effective to different regions, different types of photovoltaic power generation equipment；This method establishes the correlativity of photovoltaic power generation quantity and multi-data source using the method for machine learning；This method compares a variety of machine learning methods, finally selectes optimal machine learning method as ultimate method.
Description
Technical field
The present invention relates to photovoltaic power generation quantity electric powder predictions, specially the multi-data source photovoltaic power generation based on machine learning
Measure prediction technique and system.
Background technique
Many matters such as photovoltaic power generation quantity projected relationship is checked to electricity volume, grid-connected voltage is adjusted.At present about photovoltaic
Generated energy prediction method predominantly be directed to single photovoltaic power generation equipment (hereinafter referred to as equipment) progress, only take into account it is meteorological because
Influence of the son to photovoltaic power generation quantity does not consider influence of the equipment to photovoltaic power generation quantity itself, changes an equipment and is then based on this method
Prediction result may fail.And for Grid manager, a pervasive method for forecasting photovoltaic power generation quantity, and can
Method for forecasting photovoltaic power generation quantity suitable for arbitrary equipment is very necessary.
Summary of the invention
The purpose of the present invention is to provide multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning, with
Solve existing technological deficiency and inaccessiable technical requirements.
To achieve the above object, the invention provides the following technical scheme: the multi-data source photovoltaic power generation based on machine learning
The operating procedure of amount prediction technique and system, this method and system is as follows: step 1: data preparation；Step 2: data are located in advance
Reason；Step 3: multi-model training；Step 4: final mask is chosen based on minimum sandards difference；Step 5: generated energy prediction；Step
Six: model evaluation.
Preferably, the data preparation includes the collection to photovoltaic data and meteorological data, the photovoltaic data include but
It is not limited to daily generation, multiplying power, contract capacity, consumption mode, district number, installation site, the meteorological data includes but not
It is confined to height above sea level, day samming, the day highest temperature, total amount of cloud, low cloud cover, precipitation.
Preferably, the data prediction includes but is not limited to missing values removal or fills up, extreme value reparation, data standard
Change, data virtual variable design, the photovoltaic data do not have space-time gradient attributes, therefore the type shortage of data or appearance are unreasonable
Data are removed when the extreme value of situation；The meteorological data has space-time gradient attributes, by way of temporal-spatial interpolating to its into
Row is filled up, is repaired, if there is the pole of large area, the shortage of data of long-time (threshold value can manually be set) or the unreasonable situation of appearance
Data are removed when value.
Preferably, the multi-model training refers to that the photovoltaic for establishing prediction individual equipment using different machine learning methods is sent out
Power quantity predicting model, specific method include but is not limited to linear regression, LASSO recurrence, ridge regression, SVM recurrence, random forest
It returns, deep neural network.
Preferably, it is described based on minimum sandards difference choose final mask assessment different machines learning method as a result, described
Final mask is chosen using the difference between test set verifying model predication value and true value based on minimum sandards difference, chooses difference
The smallest model is as final mask.
Preferably, the generated energy prediction is using trained model, by the photovoltaic data after the data prediction
Multi-data source with meteorological data predicts that photovoltaic power generation quantity, the photovoltaic power generation quantity of individual equipment can directly lead to as mode input
Model prediction is crossed, the photovoltaic power generation quantity of somewhere armamentarium is to the cumulative summation of the premeasuring of the photovoltaic power generation quantity of each equipment
It can.
Preferably, the model evaluation is to compare assessment to the prediction result and legitimate reading of model.
Preferably, the data after the data prediction are divided into training set and test set, specific ratio can be but be not limited to
7:3 and 8:2 is trained the training set as the input of model.
Preferably, depending on the selection evaluation criterion based on minimum sandards difference selection final mask is by specific requirements, packet
Include but be not limited to minimum sandards are poor, assorted efficiency factor of receiving be evaluation criterion.
Preferably, for the gauge variable class data in the data preparation, such as daily generation, multiplying power, contract capacity, sea
It pulls out, day samming, the day highest temperature, total amount of cloud, low cloud cover, precipitation, data normalization is carried out to it, by the number of different gauge variables
It converts according to magnitude to same magnitude, specific standards method can be but be not limited to min-max standardization, z-score standard
Change；For the classified variable class data in the data preparation, mode, district number, installation site are such as dissolved, needing will be different
Classified variable is converted into dummy variable.
Compared with prior art, beneficial effects of the present invention are as follows:
There is universality using such method provided by the invention, avoid an independent equipment and just need to establish a prediction mould
Type simplifies photovoltaic power generation quantity prediction process, improves forecasting efficiency；Photovoltaic apparatus self attributes are included in photovoltaic hair by this method
In power quantity predicting process, so that this method is effective to different regions, different types of photovoltaic power generation equipment；This method uses
The method of machine learning establishes the correlativity of photovoltaic power generation quantity and multi-data source；This method compares a variety of machine learning methods,
Optimal machine learning method is finally selected as ultimate method.
Specific embodiment
Below in conjunction with the present invention, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that
Described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based on the implementation in the present invention
Example, every other embodiment obtained by those of ordinary skill in the art without making creative efforts belong to
The scope of protection of the invention.
The present invention provides a kind of technical solution: multi-data source method for forecasting photovoltaic power generation quantity based on machine learning and being
The operating procedure of system, this method and system is as follows: step 1: data preparation；Step 2: data prediction；Step 3: multi-model
Training；Step 4: final mask is chosen based on minimum sandards difference；Step 5: generated energy prediction；Step 6: model evaluation.
The data preparation includes the collection to photovoltaic data and meteorological data, and the photovoltaic data include but is not limited to day
Generated energy, multiplying power, contract capacity, consumption mode, district number, installation site, the meteorological data include but is not limited to sea
It pulls out, day samming, the day highest temperature, total amount of cloud, low cloud cover, precipitation.
The data prediction includes but is not limited to missing values removal or fills up, extreme value reparation, data normalization, data
Dummy variable, the photovoltaic data do not have space-time gradient attributes, therefore the type shortage of data or unreasonable situation occur
Data are removed when extreme value；The meteorological data has space-time gradient attributes, it is filled up by way of temporal-spatial interpolating,
It repairs, if will when there is the extreme value of large area, the shortage of data of long-time (threshold value can manually be set) or the unreasonable situation of appearance
Data removal.
The multi-model training refers to that the photovoltaic power generation quantity for establishing prediction individual equipment using different machine learning methods is pre-
Survey model, specific method include but is not limited to linear regression, LASSO recurrences, ridge regression, SVM return, random forest recurrence,
Deep neural network.
It is described based on minimum sandards difference choose final mask assessment different machines learning method as a result, it is described based on minimum
Standard deviation chooses final mask using the difference between test set verifying model predication value and true value, chooses the smallest mould of difference
Type is as final mask.
The generated energy prediction is using trained model, by the photovoltaic data and meteorology number after the data prediction
According to multi-data source as mode input, predict photovoltaic power generation quantity, the photovoltaic power generation quantity of individual equipment can be directly pre- by model
It surveys, the photovoltaic power generation quantity of somewhere armamentarium is to the cumulative summation of the premeasuring of the photovoltaic power generation quantity of each equipment.
The model evaluation is to compare assessment to the prediction result and legitimate reading of model.
Data after the data prediction are divided into training set and test set, specific ratio can be but be not limited to 7:3 and 8:
2, it is trained the training set as the input of model.
It is described the selection evaluation criterion of final mask is chosen by specific requirements based on minimum sandards difference depending on, including but not office
Be limited to minimum sandards are poor, assorted efficiency factor of receiving be evaluation criterion.
For the gauge variable class data in the data preparation, such as daily generation, multiplying power, contract capacity, height above sea level, average daily
Temperature, the day highest temperature, total amount of cloud, low cloud cover, precipitation, carry out data normalization to it, by the data magnitude of different gauge variables
To same magnitude, specific standards method can be but be not limited to min-max standardization, z-score standardization for conversion；For
Classified variable class data in the data preparation such as dissolve mode, district number, installation site, need to become different classifications
Amount is converted into dummy variable.
Embodiment 1
Multi-data source method for forecasting photovoltaic power generation quantity and system described in the present embodiment based on machine learning are in the present embodiment
The step of to photovoltaic power generation quantity prediction, is as follows:
Step 1: by the photovoltaic data in area, including but not limited to daily generation, multiplying power, contract capacity, consumption mode, area
County's number, installation site, include but is not limited to height above sea level, day samming, the day highest temperature, total amount of cloud, low cloud cover, drop with meteorological data
Water is collected.
Step 2: the missing values removal of photovoltaic data and meteorological data to collection is filled up, extreme value reparation, data standard
Change, data virtual variable design, photovoltaic data do not have space-time gradient attributes, therefore the type shortage of data or unreasonable situation occur
Extreme value when data are removed；The meteorological data has space-time gradient attributes, is filled out by way of temporal-spatial interpolating to it
It mends, repair, if there is the extreme value of large area, the shortage of data of long-time (threshold value can manually be set) or the unreasonable situation of appearance
Data are removed, the gauge variable class data in data preparation, such as daily generation, multiplying power, contract capacity, height above sea level, day samming, day
The highest temperature, total amount of cloud, low cloud cover, precipitation carry out data normalization to it, by the data magnitude of different gauge variables convert to
Same magnitude, specific standards method can be but be not limited to min-max standardization, z-score standardization；For the number
According to the classified variable class data in preparation, mode, district number, installation site are such as dissolved, is needed different classifications variables transformations
For dummy variable.
Step 3: the photovoltaic power generation quantity prediction model of prediction individual equipment, tool are established using different machine learning methods
Body method includes but is not limited to linear regression, LASSO recurrence, ridge regression, SVM is returned, random forest returns, depth nerve net
Data after data prediction are divided into training set and test set by network, and specific ratio can be but be not limited to 7:3 and 8:2, by institute
The input that training set is stated as model is trained.
Step 4: it is described based on minimum sandards difference choose final mask assessment different machines learning method as a result, described
Final mask is chosen using the difference between test set verifying model predication value and true value based on minimum sandards difference, chooses difference
The smallest model is described to choose the selection evaluation criterion of final mask by specific requirements based on minimum sandards difference as final mask
Depending on, including but not limited to minimum sandards are poor, assorted efficiency factor of receiving is evaluation criterion.
Step 5: generated energy prediction is to utilize trained model, and the photovoltaic data after the data prediction are gentle
The multi-data source of image data predicts that photovoltaic power generation quantity, the photovoltaic power generation quantity of individual equipment can directly pass through mould as mode input
Type prediction, the photovoltaic power generation quantity of somewhere armamentarium is to the cumulative summation of the premeasuring of the photovoltaic power generation quantity of each equipment.
Step 6: prediction result and legitimate reading to model compare assessment.
The present invention is based on the multi-data source method for forecasting photovoltaic power generation quantities and system of machine learning, are considering meteorological factor
Under the premise of, the self attributes of equipment are added, such as contract capacity, grid-connected voltage grade, installation site are also used as photovoltaic power generation quantity
The input variable of prediction；Using the method for machine learning, using meteorological factor and the multi-data source of the self attributes of equipment as defeated
Enter variable, using photovoltaic power generation quantity as output variable, establishes the multi-data source method for forecasting photovoltaic power generation quantity based on machine learning
And system；There is universality using such method provided by the invention, avoid an independent equipment and just need to establish one in advance
Model is surveyed, photovoltaic power generation quantity prediction process is simplified, improves forecasting efficiency；Photovoltaic apparatus self attributes are included in light by this method
It lies prostrate in generated energy prediction process, so that this method is effective to different regions, different types of photovoltaic power generation equipment；This method
The correlativity of photovoltaic power generation quantity and multi-data source is established using the method for machine learning；This method compares a variety of machine learning sides
Method finally selectes optimal machine learning method as ultimate method.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.In addition, it should be understood that although this specification is described in terms of embodiments, but it is not each
Embodiment only contains an independent technical solution, and this description of the specification is merely for the sake of clarity, this field
Technical staff should consider the specification as a whole, and the technical solutions in the various embodiments may also be suitably combined, form this
The other embodiments that field technical staff is understood that.
Claims (10)
1. multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning, it is characterised in that: this method and system
Operating procedure it is as follows: step 1: data preparation；Step 2: data prediction；Step 3: multi-model training；Step 4: base
Final mask is chosen in minimum sandards difference；Step 5: generated energy prediction；Step 6: model evaluation.
2. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: the data preparation includes the collection to photovoltaic data and meteorological data, and the photovoltaic data include but is not limited to day
Generated energy, multiplying power, contract capacity, consumption mode, district number, installation site, the meteorological data include but is not limited to sea
It pulls out, day samming, the day highest temperature, total amount of cloud, low cloud cover, precipitation.
3. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: the data prediction includes but is not limited to missing values removal or fills up, extreme value reparation, data normalization, data
Dummy variable, the photovoltaic data do not have space-time gradient attributes, therefore the type shortage of data or unreasonable situation occur
Data are removed when extreme value；The meteorological data has space-time gradient attributes, it is filled up by way of temporal-spatial interpolating,
It repairs, if will when there is the extreme value of large area, the shortage of data of long-time (threshold value can manually be set) or the unreasonable situation of appearance
Data removal.
4. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: the multi-model training refers to that the photovoltaic power generation quantity for establishing prediction individual equipment using different machine learning methods is predicted
Model, specific method includes but is not limited to linear regression, LASSO recurrence, ridge regression, SVM is returned, random forest returns, deep
Spend neural network.
5. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: it is described based on minimum sandards difference choose final mask assessment different machines learning method as a result, it is described based on minimum
Standard deviation chooses final mask using the difference between test set verifying model predication value and true value, chooses the smallest mould of difference
Type is as final mask.
6. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: the generated energy prediction is using trained model, by the photovoltaic data and meteorology number after the data prediction
According to multi-data source as mode input, predict photovoltaic power generation quantity, the photovoltaic power generation quantity of individual equipment can be directly pre- by model
It surveys, the photovoltaic power generation quantity of somewhere armamentarium is to the cumulative summation of the premeasuring of the photovoltaic power generation quantity of each equipment.
7. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 1 based on machine learning, special
Sign is: the model evaluation is to compare assessment to the prediction result and legitimate reading of model.
8. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 4 based on machine learning, special
Sign is: the data after the data prediction are divided into training set and test set, specific ratio can be but be not limited to 7:3 and
8:2 is trained the training set as the input of model.
9. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 5 based on machine learning, special
Sign is: it is described the selection evaluation criterion of final mask is chosen by specific requirements based on minimum sandards difference depending on, including but not office
Be limited to minimum sandards are poor, assorted efficiency factor of receiving be evaluation criterion.
10. the multi-data source method for forecasting photovoltaic power generation quantity and system according to claim 2 based on machine learning, special
Sign is: for the gauge variable class data in the data preparation, such as daily generation, multiplying power, contract capacity, height above sea level, average daily
Temperature, the day highest temperature, total amount of cloud, low cloud cover, precipitation, carry out data normalization to it, by the data magnitude of different gauge variables
To same magnitude, specific standards method can be but be not limited to min-max standardization, z-score standardization for conversion；For
Classified variable class data in the data preparation such as dissolve mode, district number, installation site, need to become different classifications
Amount is converted into dummy variable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229971.6A CN109978258A (en) | 2019-03-26 | 2019-03-26 | Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910229971.6A CN109978258A (en) | 2019-03-26 | 2019-03-26 | Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109978258A true CN109978258A (en) | 2019-07-05 |
Family
ID=67080492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910229971.6A Pending CN109978258A (en) | 2019-03-26 | 2019-03-26 | Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978258A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
| CN104915747A (en) * | 2015-02-03 | 2015-09-16 | 远景能源（江苏）有限公司 | Electricity generation performance evaluation method of generator set and equipment thereof |
| JP2017200360A (en) * | 2016-04-28 | 2017-11-02 | 清水建設株式会社 | Photovoltaic power generation amount prediction system, photovoltaic power generation amount prediction method, and program |
| CN107844836A (en) * | 2017-10-24 | 2018-03-27 | 信雅达系统工程股份有限公司 | A kind of system and learning method based on machine learning |
| CN109214552A (en) * | 2018-08-09 | 2019-01-15 | 上海安悦节能技术有限公司 | Intelligent O&M method based on the prediction of integrated study photovoltaic |
-
2019
- 2019-03-26 CN CN201910229971.6A patent/CN109978258A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104021427A (en) * | 2014-06-10 | 2014-09-03 | 上海电力学院 | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis |
| CN104915747A (en) * | 2015-02-03 | 2015-09-16 | 远景能源（江苏）有限公司 | Electricity generation performance evaluation method of generator set and equipment thereof |
| JP2017200360A (en) * | 2016-04-28 | 2017-11-02 | 清水建設株式会社 | Photovoltaic power generation amount prediction system, photovoltaic power generation amount prediction method, and program |
| CN107844836A (en) * | 2017-10-24 | 2018-03-27 | 信雅达系统工程股份有限公司 | A kind of system and learning method based on machine learning |
| CN109214552A (en) * | 2018-08-09 | 2019-01-15 | 上海安悦节能技术有限公司 | Intelligent O&M method based on the prediction of integrated study photovoltaic |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991700A (en) * | 2019-11-08 | 2020-04-10 | 北京博望华科科技有限公司 | Weather and electricity utilization correlation prediction method and device based on deep learning improvement |
| 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 |
|---|---|---|
| Ghorbani et al. | Optimizing a hybrid wind-PV-battery system using GA-PSO and MOPSO for reducing cost and increasing reliability | |
| Roberts et al. | Robust multi-objective optimization of a renewable based hybrid power system | |
| Bansal et al. | Economic analysis and power management of a small autonomous hybrid power system (SAHPS) using biogeography based optimization (BBO) algorithm | |
| Mei et al. | Game approaches for hybrid power system planning | |
| Amjady et al. | Short-term load forecast of microgrids by a new bilevel prediction strategy | |
| Billinton et al. | Maintaining supply reliability of small isolated power systems using renewable energy | |
| Xie et al. | Determination of the optimum capacity and type of wind turbine generators in a power system considering reliability and cost | |
| Ghaedi et al. | Incorporating Large Photovoltaic Farms in Power Generation System Adequacy Assessment | |
| CN112381269A (en) | Independent micro-grid capacity optimal configuration method considering load importance and electricity price excitation | |
| CN112347694A (en) | Sea island micro-grid power supply planning method containing ocean current-offshore wind power-tidal current power generation | |
| CN109978258A (en) | Multi-data source method for forecasting photovoltaic power generation quantity and system based on machine learning | |
| Mohseni et al. | Stochastic optimal sizing of micro-grids using the moth-flame optimization algorithm | |
| Lotfi et al. | Providing an optimal energy management strategy in distribution network considering distributed generators and energy storage units | |
| Mazaheri et al. | Data-driven joint tep-bess co-planning scheme to relieve transmission lines congestion: A min-max regret method | |
| Gill et al. | Quantifying fossil fuel savings from investment in renewables and energy storage | |
| Alanazi et al. | Day-ahead solar forecasting based on multi-level solar measurements | |
| Riahinia et al. | A neural network-based model for wind farm output in probabilistic studies of power systems | |
| CN116073406A (en) | Regional power grid source load unbalance degree assessment method | |
| CN116054129A (en) | Multi-electrolytic-tank combined operation power distribution method based on photovoltaic hydrogen production | |
| Safdarian et al. | Ramp rate effect on maximizing profit of a microgrid using gravitational search algorithm | |
| Gehbauer et al. | Synthetic caiso frequency regulation signal | |
| Bhusal et al. | Optimum locations of utility-scale shared energy storage systems | |
| Wang et al. | PSO-based hybrid generating system design incorporating reliability evaluation and generation/load forecasting | |
| Chen et al. | Effective load carrying capability evaluation for high penetration renewable energy integration | |
| CN113572168A (en) | Optimal scheduling method considering multiple uncertainty risks of wind, light and water energy |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190705 |