CN110059871A - Photovoltaic power generation power prediction method - Google Patents
Photovoltaic power generation power prediction method Download PDFInfo
- Publication number
- CN110059871A CN110059871A CN201910272790.1A CN201910272790A CN110059871A CN 110059871 A CN110059871 A CN 110059871A CN 201910272790 A CN201910272790 A CN 201910272790A CN 110059871 A CN110059871 A CN 110059871A
- Authority
- CN
- China
- Prior art keywords
- attribute
- value
- photovoltaic
- data
- environment
- 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.)
- Granted
Links
Classifications
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to a kind of photovoltaic power generation power prediction methods, its optimal degree of membership that each environment attribute is acquired in the way of iterative calculation, the case where being able to reflect actual degree of membership, overcome subjectivity existing for existing artificial selection subordinating degree function it is larger caused by the weaker technical problem of photovoltaic power generation power prediction method applicability.And method provided by the invention carries out attribute reduction to the environment attribute for influencing photovoltaic generation power, finding influences the maximum ring environment attribute set of photovoltaic generation power, input as support vector machines, predetermined speed and precision that model can be improved are of great significance for improving grid stability and improving photovoltaic plant operation management efficiency.
Description
Technical field
The present invention relates to field of power systems, more particularly, to a kind of photovoltaic power generation power prediction method.
Background technique
Due to being influenced by intensity of solar radiation, photovoltaic module temperature, weather and some enchancement factors, photovoltaic generating system
Operational process be a nonequilibrium random process, the randomness of generated energy and output power is strong, fluctuation is big, not easily-controllable
System, this shows especially prominent in change in weather.As more and more MW class photovoltaic generating systems access operation of power networks
Problems are brought to the stabilization and management and running of power grid.Therefore, it is necessary to be carried out to the power of photovoltaic generating system accurate pre-
It surveys, and then takes the smooth photovoltaic generation power fluctuation of corresponding technical measures, improve the safety and stability of electric system.
Existing photovoltaic power generation power prediction method can be divided into direct forecast methods and indirect prediction method.Indirect predictions method
Solar radiation is predicted first, output power value is then obtained according to photovoltaic generating system generation model.Direct method is benefit
The output power or hair of photovoltaic system or array are directly predicted with the historical data and data of weather forecast of built photovoltaic power station power generation amount
Electricity.Support vector machines is one of prediction model, it is built upon structural risk minimization and VC dimension concept base
A kind of small sample Statistical Learning Theory on plinth, it avoids the network structure selection of the methods of artificial neural network, overfitting
The problems such as with deficient study and local minimum.But support vector machines is applied in photovoltaic power generation power prediction, if by various shadows
The factor of sound is included in the input variable of input layer, and it is excessive to will cause input variable, is aggravated network training burden, not only can not
To improve precision of prediction, the performance of neural network forecast can be also reduced.And for reduction input variable, it can use fuzzy coarse central
Attribute reduction is carried out, but is artificially to select subordinating degree function mostly, there are larger when fuzzy coarse central calculates degree of membership
Subjectivity, so the applicability of such method is weaker.
Summary of the invention
The present invention is to solve the prior art artificially to select photovoltaic power generation power prediction method caused by subordinating degree function suitable
With the weaker technological deficiency of property, a kind of photovoltaic power generation power prediction method is provided, is acquired in the way of iterative calculation each
The optimal degree of membership of a environment attribute, overcomes existing artificial selection degree of membership at the case where being able to reflect actual degree of membership
The weaker technical problem of photovoltaic power generation power prediction method applicability caused by subjectivity existing for function is larger.
To realize the above goal of the invention, the technical solution adopted is that:
Photovoltaic power generation power prediction method, comprising the following steps:
S1. acquisition is mounted on the power output data and environmental attribute data that the monitoring system of photovoltaic plant is recorded, structure
Build initial attribute decision table；
S2. it is determined according to the initial attribute decision table of building using the fuzzy of fuzzy C-clustering constructing environment attribute
Plan table:
S21. constructing environment attribute value matrix A
Wherein alIt (n) is the value of n-th of sample data of l class environment attribute；N is the sample data of various environment attributes
Number；
S22. determine each environment attribute in the cluster centre initialization value of fuzzy C-clustering:
Wherein,For the radius of neighbourhood, c indicates the classification number of l class environment attribute
Mesh；N is the sample data number within the scope of the radius of neighbourhood；
S23. according to formula (1), j-th of data corresponding to formulae results are obtained, it is poly- using its attribute value as first
Then the initialization value at class center removes this attribute value, repeat step S22, S23 until finding c cluster centre
Initialization value；
S24. cluster centre matrix V=[V is constructed according to the result of step S231V2...Vl], wherein VlIt indicates first to gather
The initialization value at class center, Vl=[vl1vl2...vlc], vlcIndicate the first of the cluster centre of l class environment attribute c class classification
Beginning value；
S25. the objective function that fuzzy C-clustering is continued to optimize by way of iterative calculation acquires each ring
The optimal degree of membership of border attribute；
S26. the iterative calculation that step S25 is carried out to all environment attributes, obtains fuzzy decision table；
S3. according to the fuzzy decision table of building, the environment attribute in fuzzy decision table is belonged to using fuzzy coarse central
Property reduction；
S4. the corresponding environmental attribute data of environment attribute after reduction is normalized；
S5. support vector machines is trained using the environmental attribute data after normalization as input, then acquisition prison
The real time environment attribute data of control system record is input in support vector machines, the photovoltaic plant hair of support vector machines output prediction
Electrical power.
Preferably, specific step is as follows by the step S25:
1) the number of iterations t is initialized, classify number c and weight ω；
2) subordinated-degree matrix U, the matrix element μ in matrix U are initializedijIndicate that i-th of object belongs to the journey of jth generic attribute
Degree, μijFor random number 0 or 1；
3) in the t times iterative calculation, subordinated-degree matrix is updated according to following equation:
In formula, i=1,2 ..., n, j=1,2 ..., c, CljIn the cluster for indicating the classification of l class environment attribute jth class
The heart；
In the t times iterative calculation, cluster centre value matrix is updated according to following equation:
In formula, cljIndicate that the cluster centre value of the jth generic attribute of l class environment attribute, the calculation formula of coefficient B are as follows:
If 4)Or reaching the number of iterations, then iteration terminates, the optimal degree of membership of output environment attribute；It is no
Then return step 3) carry out next iteration.
Preferably, in the step S1, with the power output data and environment attribute number of each hour record of monitoring system
According to as a data sample, prediction time and 10 hours before power output data and environmental attribute data building are obtained just
Beginning attribute decision table.
Preferably, the step S4 is normalized that detailed process is as follows:
Wherein, xmaxAnd xminThe maximum value and minimum value in same type of environmental attribute data are respectively indicated, x indicates ring
The actual value of border attribute data, y indicate the normalized value of environmental attribute data.
Preferably, after the photovoltaic power station power generation power that the step S5 is predicted, to the photovoltaic power station power generation function of prediction
Rate carries out anti-normalization processing, obtains actual predicted value.
Preferably, the detailed process of the anti-normalization processing is as follows:
D=dmax-f.(dmax-dmin)；
dmaxAnd dminThe maximum value and minimum value of the photovoltaic generation power of prediction are respectively indicated, d indicates the photovoltaic hair of prediction
The actual value of electrical power, f indicate the normalized value of the photovoltaic generation power of prediction.
Compared with prior art, the beneficial effects of the present invention are:
Method provided by the invention acquires the optimal degree of membership of each environment attribute in the way of iterative calculation, can be anti-
The case where reflecting actual degree of membership, overcome subjectivity existing for existing artificial selection subordinating degree function it is larger caused by light
Lie prostrate the weaker technical problem of generated power forecasting method applicability.And method provided by the invention is to influence photovoltaic generation power
Environment attribute carries out attribute reduction, and finding influences the maximum ring environment attribute set of photovoltaic generation power, as support vector machines
Input, predetermined speed and precision of model can be improved, for improve grid stability and improve photovoltaic plant operation pipe
Reason efficiency is of great significance.
Detailed description of the invention
Fig. 1 is the flow diagram of method.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
Below in conjunction with drawings and examples, the present invention is further elaborated.
Embodiment 1
The process and method of step 1 description building initial attribute decision table in Fig. 1.Acquisition is mounted on the prison of photovoltaic plant
The historical power output data and relevant weather information that control system is recorded are obtained using the data of every 1h as a sample
The output power and environmental attribute data of prediction time and its 10h previous construct initial attribute decision using these data
Table, as shown in table 1, wherein t indicates the moment to be predicted, and P is photovoltaic generation power, Tave、Tmin、TmaxRespectively indicate mean temperature,
Minimum temperature and maximum temperature, H indicate relative humidity, and C indicates average cloud amount；The number of conditional attribute is u1~u59, decision
The number of attribute is u60。
Table 1
Step 2 in Fig. 1 describes the building of fuzzy decision table.According to output power data and different types of meteorological number
According to, utilize fuzzy C-means clustering method building attribute fuzzy decision table.
(1) constructing environment attribute value matrix A
Wherein, alIt (m) is the value of m-th of sample of l class environment attribute；N is sample number.
(2) the cluster centre initialization value of each environment attribute Fuzzy C-Means Clustering is determined with following equation:
In formula,For the radius of neighbourhood, c indicates the classification number of l class environment attribute
Mesh；N is the sample number within the scope of the radius of neighbourhood.
(3) according to (2) described formula, j-th of sample corresponding to formulae results is obtained, it is poly- using its attribute value as first
The initialization value v at class center, then removes this attribute value, jumps back to (2) until the initialization value for finding c cluster centre is
Only.
(4) cluster centre matrix V=[V is constructed according to (3) resulting results set1V2...V59], wherein VlIt indicates first
The initialization value of cluster centre, Vl=[vl1vl2...vlc], vlcIndicate the cluster centre of l class environment attribute c class classification
Initialization value；
(5) objective function that Fuzzy C-Means Clustering is continued to optimize with the mode of iterative calculation, acquires each environment with this
The optimal degree of membership of attribute value, the specific steps are as follows:
1) cluster centre initialization matrix V is obtained according to (4), initializes the number of iterations t, classify number c and weight ω；
2) subordinated-degree matrix U, matrix element μ are initializedijIndicate that i-th of object belongs to the degree of jth generic attribute, in matrix
Element be random number [0,1]；
3) in the t times iterative calculation, subordinated-degree matrix is updated according to following equation:
In formula, i=1,2 ..., n, j=1,2 ..., c, μijIndicate that i-th of object belongs to the degree of jth generic attribute；Clj
Indicate the cluster centre of l class environment attribute jth class classification；
In the t times iterative calculation, cluster centre value matrix is updated according to following equation:
Wherein, j=1,2 ..., c, cljIndicate the cluster centre value of the jth generic attribute of l class environmental factor, coefficient B
Calculation formula is as follows:
If 4)Or reaching the number of iterations, then iteration terminates, the optimal degree of membership of output environment attribute value；
Otherwise return step 3) carry out next iteration.
(6) iterative calculation that all environment attribute values are carried out with (5), obtains attribute fuzzy decision table
Step 3 description in Fig. 1 carries out the process and method of attribute reduction to environment attribute.If X is a son of domain U
Collection, P, Q are two equivalence relations on domain, respectively conditional attribute and decision attribute, if X is not the baseset by domain
It accurately forms, then X is referred to as rough set.And fuzzy coarse central is then that the precise set in classical rough set theory is substituted for mould
Paste set, while the exact relationship in classical rough set theory is substituted for fuzzy relation, then classical rough set theory can expand
Exhibition obtains fuzzy coarse central, the fuzzy upper approximation of generationWith fuzzy lower aprons μ X (Fi) it is respectively defined as:
In formula, FiIndicate the fuzzy equivalence relation class for belonging to U/P；μFi(x) indicate that object x belongs to FiDegree of membership；μX(x) expression pair
As x belongs to the degree of membership of arbitrary fuzzy set X on domain；And fuzzy coarse central is then expressed as two-value pair
Then fuzzy equivalence relation class F is calculated by following equationiFuzzy positive domain:
Object x is then calculated according to the following formula in domain in next step to the degree of membership for obscuring positive domain:
Last basis obscures the related meanings in positive domain, calculates the corresponding i.e. decision attribute of fuzzy dependency degree to conditional attribute
Dependency degree:
After calculating separately out dependency degree of the decision attribute to all conditions attribute, attribute is carried out about according to following rules
Letter:
1) the maximum attribute of dependency degree is found first；
2) by the maximum attribute of dependency degree and the one-to-one combination of remaining all properties, composite attribute is then calculated to decision
The dependency degree of attribute finds the maximum attribute set of dependency degree；
3) step 2) is repeated until the dependency degree of attribute set is not further added by, and gained combinations of attributes is a minimum
Reduction.
Step 4 description in Fig. 1 is using the environmental data after reduction to the process and method of supporting vector machine model training.
Environmental data is normalized first, in accordance with following formula:
In formula, xmaxAnd xminThe maximum value and minimum value in similar environmental attribute data are respectively indicated, x indicates environment attribute
The actual value of data, y indicate the normalized value of environmental attribute data.
Step 5 in Fig. 1 describes the process and method of photovoltaic power generation power prediction.The environmental data and photovoltaic of usage history
The normalized value of the historical data of power output is trained support vector machines as training data, obtains photovoltaic generation power
Prediction model.Then input parameter needed for value to be predicted is inputted in supporting vector machine model, exports moment photovoltaic to be predicted
The normalized value of generated output.
Step 6 in Fig. 1 describes process and method to photovoltaic power generation power prediction value renormalization.Utilize following equation
The predicted value of moment photovoltaic generation power to be predicted obtained to step 5 carries out anti-normalization processing, finally obtains photovoltaic hair
The actual prediction value of electrical power:
D=dmax-f.(dmax-dmin)；
dmaxAnd dminThe maximum value and minimum value of the photovoltaic generation power of prediction are respectively indicated, d indicates the photovoltaic hair of prediction
The actual value of electrical power, f indicate the normalized value of the photovoltaic generation power of prediction.
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (6)
1. photovoltaic power generation power prediction method, it is characterised in that: the following steps are included:
S1. acquisition is mounted on the power output data and environmental attribute data that the monitoring system of photovoltaic plant is recorded, and building is just
Beginning attribute decision table；
S2. the fuzzy decision of fuzzy C-clustering constructing environment attribute is utilized according to the initial attribute decision table of building
Table:
S21. constructing environment attribute value matrix A
Wherein alIt (n) is the value of n-th of sample data of l class environment attribute；N is the sample data number of various environment attributes；
S22. determine each environment attribute in the cluster centre initialization value of fuzzy C-clustering:
Wherein,For the radius of neighbourhood, c indicates the classification number of l class environment attribute；N is
Sample data number within the scope of the radius of neighbourhood；
S23. according to formula (1), j-th of data corresponding to formulae results are obtained, using its attribute value as in first cluster
Then the initialization value of the heart removes this attribute value, repeat step S22, S23 until finding the initial of c cluster centre
Change value；
S24. cluster centre matrix V=[V is constructed according to the result of step S231 V2...Vl], wherein VlIt indicates in first of cluster
The initialization value of the heart, Vl=[vl1 vl2...vlc], vlcIndicate the initialization of the cluster centre of l class environment attribute c class classification
Value；
S25. the objective function that fuzzy C-clustering is continued to optimize by way of iterative calculation acquires each environment category
The optimal degree of membership of property；
S26. the iterative calculation that step S25 is carried out to all environment attributes, obtains fuzzy decision table；
S3. according to the fuzzy decision table of building, attribute is carried out about to the environment attribute in fuzzy decision table using fuzzy coarse central
Letter；
S4. the corresponding environmental attribute data of environment attribute after reduction is normalized；
S5. support vector machines is trained using the environmental attribute data after normalization as input, then acquisition monitoring system
The real time environment attribute data of system record is input in support vector machines, the photovoltaic power station power generation function of support vector machines output prediction
Rate.
2. photovoltaic power generation power prediction method according to claim 1, it is characterised in that: the specific step of the step S25
It is rapid as follows:
1) the number of iterations t is initialized, classify number c and weight ω；
2) subordinated-degree matrix U, the matrix element μ in matrix U are initializedijIndicate that i-th of object belongs to the degree of jth generic attribute,
μijFor random number 0 or 1；
3) in the t times iterative calculation, subordinated-degree matrix is updated according to following equation:
In formula, i=1,2 ..., n, j=1,2 ..., c, CljIndicate the cluster centre of l class environment attribute jth class classification；
In the t times iterative calculation, cluster centre value matrix is updated according to following equation:
In formula, cljIndicate that the cluster centre value of the jth generic attribute of l class environment attribute, the calculation formula of coefficient B are as follows:
If 4)Or reaching the number of iterations, then iteration terminates, the optimal degree of membership of output environment attribute；Otherwise it returns
It returns step 3) and carries out next iteration.
3. photovoltaic power generation power prediction method according to claim 2, it is characterised in that: in the step S1, with monitoring
The power output data of each hour record of system and environmental attribute data as a data sample, obtain prediction time and it
First 10 hours power output data and environmental attribute data construct initial attribute decision table.
4. photovoltaic power generation power prediction method according to claim 2, it is characterised in that: the step S4 is normalized
Detailed process is as follows for processing:
Wherein, xmaxAnd xminThe maximum value and minimum value in same type of environmental attribute data are respectively indicated, x indicates environment category
Property data actual value, y indicate environmental attribute data normalized value.
5. photovoltaic power generation power prediction method according to any one of claims 1 to 4, it is characterised in that: the step S5
After the photovoltaic power station power generation power predicted, anti-normalization processing is carried out to the photovoltaic power station power generation power of prediction, obtains reality
The predicted value on border.
6. photovoltaic power generation power prediction method according to claim 5, it is characterised in that: the tool of the anti-normalization processing
Body process is as follows:
D=dmax-f·(dmax-dmin)；
dmaxAnd dminThe maximum value and minimum value of the photovoltaic generation power of prediction are respectively indicated, d indicates the photovoltaic power generation function of prediction
The actual value of rate, f indicate the normalized value of the photovoltaic generation power of prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272790.1A CN110059871B (en) | 2019-04-04 | 2019-04-04 | Photovoltaic power generation power prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910272790.1A CN110059871B (en) | 2019-04-04 | 2019-04-04 | Photovoltaic power generation power prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110059871A true CN110059871A (en) | 2019-07-26 |
| CN110059871B CN110059871B (en) | 2021-09-24 |
Family
ID=67318378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910272790.1A Expired - Fee Related CN110059871B (en) | 2019-04-04 | 2019-04-04 | Photovoltaic power generation power prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059871B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN117154724A (en) * | 2023-10-31 | 2023-12-01 | 山东中瑞电气有限公司 | Photovoltaic power generation power prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120230821A1 (en) * | 2011-03-10 | 2012-09-13 | Sinovel Wind Group Co., Ltd. | Wind power prediction method of single wind turbine generator |
| CN104239968A (en) * | 2014-09-02 | 2014-12-24 | 浙江大学 | Short-term load predicting method based on quick fuzzy rough set |
| CN106251001A (en) * | 2016-07-18 | 2016-12-21 | 南京工程学院 | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm |
| US20180046924A1 (en) * | 2015-08-31 | 2018-02-15 | Guangzhou Institute Of Energy Conversion, Chinese Academy Of Sciences | Whole-life-cycle power output classification prediction system for photovoltaic systems |
| CN108205717A (en) * | 2017-12-30 | 2018-06-26 | 国网江苏省电力公司无锡供电公司 | A kind of photovoltaic generation power Multiple Time Scales Forecasting Methodology |
| CN109086928A (en) * | 2018-07-27 | 2018-12-25 | 福州大学 | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model |
-
2019
- 2019-04-04 CN CN201910272790.1A patent/CN110059871B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120230821A1 (en) * | 2011-03-10 | 2012-09-13 | Sinovel Wind Group Co., Ltd. | Wind power prediction method of single wind turbine generator |
| CN104239968A (en) * | 2014-09-02 | 2014-12-24 | 浙江大学 | Short-term load predicting method based on quick fuzzy rough set |
| US20180046924A1 (en) * | 2015-08-31 | 2018-02-15 | Guangzhou Institute Of Energy Conversion, Chinese Academy Of Sciences | Whole-life-cycle power output classification prediction system for photovoltaic systems |
| CN106251001A (en) * | 2016-07-18 | 2016-12-21 | 南京工程学院 | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm |
| CN108205717A (en) * | 2017-12-30 | 2018-06-26 | 国网江苏省电力公司无锡供电公司 | A kind of photovoltaic generation power Multiple Time Scales Forecasting Methodology |
| CN109086928A (en) * | 2018-07-27 | 2018-12-25 | 福州大学 | Photovoltaic plant realtime power prediction technique based on SAGA-FCM-LSSVM model |
Non-Patent Citations (3)
| Title |
|---|
| LI SHAN 等: "Short-term Forecasting of PV Power Based on the Fuzzy Clustering Algorithm and Support Vector Machine in Smart Distribution Planning", 《PROCEEDINGS OF 2018 IEEE 3RD ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC 2018)》 * |
| LIU DING 等: "Research on Comprehensive Benefit Post Evaluation of Photovoltaic Poverty Alleviation Projects Based on FCM and SVM", 《2019 3RD INTERNATIONAL CONFERENCE ON ENVIRONMENTAL AND ENERGY ENGINEERING (IC3E 2019)》 * |
| 王欣,李胜刚,秦斌,刘俊杰: "基于模糊支持向量机的风电场功率预测", 《新型工业化》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705760A (en) * | 2019-09-19 | 2020-01-17 | 广东工业大学 | Photovoltaic power generation power prediction method based on deep belief network |
| CN117154724A (en) * | 2023-10-31 | 2023-12-01 | 山东中瑞电气有限公司 | Photovoltaic power generation power prediction method |
| CN117154724B (en) * | 2023-10-31 | 2024-02-23 | 山东中瑞电气有限公司 | Photovoltaic power generation power prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110059871B (en) | 2021-09-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhou et al. | Prediction of photovoltaic power output based on similar day analysis, genetic algorithm and extreme learning machine | |
| Liu et al. | Random forest solar power forecast based on classification optimization | |
| Afrasiabi et al. | Multi-agent microgrid energy management based on deep learning forecaster | |
| Semero et al. | A PSO-ANFIS based hybrid approach for short term PV power prediction in microgrids | |
| JP5888640B2 (en) | Photovoltaic power generation prediction apparatus, solar power generation prediction method, and solar power generation prediction program | |
| CN108205717A (en) | A kind of photovoltaic generation power Multiple Time Scales Forecasting Methodology | |
| Niu et al. | Uncertainty modeling for chaotic time series based on optimal multi-input multi-output architecture: Application to offshore wind speed | |
| CN109359786A (en) | A kind of power station area short-term load forecasting method | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| Dou et al. | Hybrid model for renewable energy and loads prediction based on data mining and variational mode decomposition | |
| CN103268366A (en) | Combined wind power prediction method suitable for distributed wind power plant | |
| CN109978284B (en) | Photovoltaic power generation power time-sharing prediction method based on hybrid neural network model | |
| CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
| Hu et al. | Short-term photovoltaic power prediction based on similar days and improved SOA-DBN model | |
| Gu et al. | Short-term wind power forecasting and uncertainty analysis based on FCM–WOA–ELM–GMM | |
| CN109858665A (en) | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO | |
| Luo et al. | Short-term photovoltaic generation forecasting based on similar day selection and extreme learning machine | |
| CN109242136A (en) | A kind of micro-capacitance sensor wind power Chaos-Genetic-BP neural network prediction technique | |
| CN110059871A (en) | Photovoltaic power generation power prediction method | |
| Wang et al. | Wind process pattern forecasting based ultra-short-term wind speed hybrid prediction | |
| Meng et al. | A new PV generation power prediction model based on GA-BP neural network with artificial classification of history day | |
| Shen et al. | Short-term load forecasting of power system based on similar day method and PSO-DBN | |
| Chen et al. | Graph neural network-based wind farm cluster speed prediction | |
| CN113270898A (en) | Distributed photovoltaic optimization configuration method based on two-stage planning | |
| CN110472770A (en) | A kind of photovoltaic power generation power prediction method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210924 |