CN115249093A - Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium - Google Patents
Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115249093A CN115249093A CN202211066788.7A CN202211066788A CN115249093A CN 115249093 A CN115249093 A CN 115249093A CN 202211066788 A CN202211066788 A CN 202211066788A CN 115249093 A CN115249093 A CN 115249093A
- Authority
- CN
- China
- Prior art keywords
- date
- dest
- matrix
- time
- historical
- 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.)
- Withdrawn
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000011159 matrix material Substances 0.000 claims description 55
- 230000006870 function Effects 0.000 claims description 8
- 230000003442 weekly effect Effects 0.000 claims 1
- 238000011156 evaluation Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 230000009467 reduction Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention provides a method and a device for predicting photovoltaic power generation capacity, electronic equipment and a storage medium, wherein the prediction method comprises the following steps: the weather similarity factor, the date difference factor and the week difference factor between a plurality of historical dates and a target date are obtained, then, the similarity between the historical dates and the target date is calculated based on the three factors, a plurality of most similar historical dates are obtained, and the average value of the photovoltaic power generation amount of the plurality of historical dates is the predicted value of the photovoltaic power generation amount of the target date. In conclusion, the prediction method can accurately predict the power generation amount of the photovoltaic power station.
Description
Technical Field
The invention relates to the technical field of power dispatching, in particular to a method and a device for predicting photovoltaic power generation, electronic equipment and a storage medium.
Background
In the present day that traditional energy exploitation is increasingly seen and ecological environment is rapidly worsened, solar energy is taken as clean energy and abundant in reserves, and at present, photovoltaic power generation technology is increasingly mature, and photovoltaic power generation is considered as one of the most competitive energy technologies by international public. However, the photovoltaic power generation has obvious disadvantages, and is greatly influenced by factors such as weather and the like, and has strong intermittency and volatility, so that the photovoltaic power generation is unstable and discontinuous, and huge impact and challenge are caused to a power system after high-proportion photovoltaic is connected. If can accurately carry out the prediction of photovoltaic generated energy, not only can improve photovoltaic power plant operating efficiency, in some application scenarios, such as the garden of photovoltaic, energy storage and electric wire netting combined action, also have important meaning to realizing green electricity in garden.
Disclosure of Invention
The invention aims to provide a method and a device for predicting photovoltaic power generation, electronic equipment and a storage medium.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for predicting photovoltaic power generation, including the steps of:
obtaining N historical date data i Weather similarity factor ζ between target date dest and target date i Obtaining N historical date dates i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. Ang., N;
generating a matrix
Wherein,
j is a positive integer, j =1,2, ·, M +2; the indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor;
normalizing the matrix Y and date data i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y;
similarity F in descending order 1 、F 2 、...、F M And Num maximum similarities are selected, num historical dates corresponding to the Num similarities one by one are obtained, and the average value of the photovoltaic power generation amount corresponding to the Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest.
As a further improvement of one embodiment of the present invention, the step of "obtaining N historical date data i Weather similarity factor ζ between target date dest and target date i The method specifically comprises the following steps: obtaining historical date i At the Time point Time 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x i (1)、x i (2)、...、x i (M); obtaining a target datedest at Time Point Time 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x 0 (1)、x 0 (2)、...、x 0 (M); the weather type data are natural numbers, and different natural numbers corresponding to different weather types; each weather similarity factor ζ i Includes M Time points k Corresponding factor
Wherein k is a positive integer of 0<ρ<1，k＝1,2，...，M。
As a further improvement of one embodiment of the present invention, the step of "obtaining N historical date data i Date difference factor delta from target date dest i The method specifically comprises the following steps: each history date i Date difference factor from target date dest
Where mod is a remainder function, int is a rounding function, 1<β 1 ,β 2 ,β 3 <1，N 1 ,N 2 And N 3 Is a constant, Δ i For historical date i Days apart from the target date dest, when the historical date is date i When the date dest is the major day, P i =1, otherwise, P i ＝0。
As a further improvement of one embodiment of the present invention, the step of "obtaining N historical date data i Week difference factor gamma from target date dest i The method specifically comprises the following steps: each history date i Week difference factor gamma from target date dest i ＝1-|w i -w 0 Where the types of week are Monday, tuesday, wednesday, thursday, friday, saturday and Sunday, respectively, corresponding to a real number, w i For historical date i Real number, w, corresponding to the week type in which it is located 0 A real number corresponding to the week type on which the target date dest is located.
As a further improvement of one embodiment of the invention, monday corresponds to 0.1, tuesday to thursday corresponds to 0.2, friday corresponds to 0.3, saturday corresponds to 0.7, and sunday corresponds to 1.
As a further improvement of an embodiment of the present invention, the "normalizing the matrix Y" specifically includes: generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
As a further improvement of an embodiment of the present invention, the "normalizing the matrix Y" specifically includes: generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
The embodiment of the invention also provides a photovoltaic power generation capacity prediction device, which comprises the following modules: an information acquisition module for acquiring N historical date data i Weather similarity factor ζ with target date dest i Obtaining N historical date dates i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. N; a matrix generation module for generating a matrix
Wherein,
j is a positive integer, j =1,2. The indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor; a matrix processing module for normalizing the matrix Y and date data i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y; a prediction module for similarity F in descending order 1 、F 2 、...、F M And Num maximum similarities are selected, num historical dates corresponding to the Num similarities one by one are obtained, and the average value of the photovoltaic power generation amount corresponding to the Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest.
An embodiment of the present invention further provides an electronic device, including: a memory for storing executable instructions; and the processor is used for realizing the photovoltaic power generation capacity prediction method when executing the executable instructions stored in the memory.
The embodiment of the invention also provides a storage medium, which stores executable instructions and is used for causing a processor to execute so as to realize the photovoltaic power generation capacity prediction method.
Compared with the prior art, the invention has the technical effects that: the embodiment of the invention provides a method and a device for predicting photovoltaic power generation, electronic equipment and a storage medium, wherein the method for predicting the photovoltaic power generation comprises the following steps: the weather similarity factor, the date difference factor and the week difference factor between a plurality of historical dates and a target date are obtained, then, the similarity between the historical dates and the target date is calculated based on the three factors, a plurality of most similar historical dates are obtained, and the average value of the photovoltaic power generation amount of the plurality of historical dates is the predicted value of the photovoltaic power generation amount of the target date. In conclusion, the prediction method can accurately predict the power generation amount of the photovoltaic power station.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting photovoltaic power generation amount according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail below with reference to embodiments shown in the drawings. These embodiments are not intended to limit the present invention, and structural, methodological, or functional changes made by those skilled in the art according to these embodiments are included in the scope of the present invention.
Terms such as "upper," "above," "lower," "below," and the like, used herein to denote relative spatial positions, are used for ease of description to describe one element or feature's relationship to another element or feature as illustrated in the figures. The spatially relative positional terms may be intended to encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "below" or "beneath" other elements or features would then be oriented "above" the other elements or features. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be otherwise oriented (rotated 90 degrees or at other orientations) and the spatially relative descriptors used herein interpreted accordingly.
The embodiment of the invention provides a method for predicting photovoltaic power generation, as shown in fig. 1, which comprises the following steps:
step 101: obtaining NHistorical date i Weather similarity factor ζ with target date dest i Obtaining N historical date data i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. N;
step 102: generating a matrix
Wherein,
j is a positive integer, j =1,2, ·, M +2; the indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor;
step 103: normalizing the matrix Y and date data i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y;
step 104: similarity F in order of big to little 1 、F 2 、...、F M Num maximum similarities are selected, and Num histories corresponding to the Num similarities in a one-to-one mode are obtainedAnd the average value of the photovoltaic power generation amount corresponding to the Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest. Here, the similarity F can be expressed 1 、F 2 、...、F M The Num similarities are selected by performing permutation in order from large to small and then acquiring the first Num.
Here, r ij The correlation coefficient between the indexes in the ith row and the j-th row of the matrix Y is expressed by using the correlation coefficient, and the stronger the correlation with other indexes, the smaller the conflict between the index and other indexes, the more the same information is reflected, the more repeated the evaluation contents can be embodied, the strength of the evaluation of the index is weakened to a certain extent, and the weight assigned to the index should be reduced. Here, C j The larger the j-th evaluation index is, the more the j-th evaluation index plays a role in the whole evaluation index system, and more weight should be assigned to the j-th evaluation index. And multiplying the weather type similarity coefficient, the date difference similarity coefficient and the week type similarity coefficient to obtain a total similarity coefficient. The larger the total similarity coefficient is, the closer the characteristics of the selected similar day and the predicted day are.
The prediction method in the embodiment has the advantages of various weather types and reasonable weight distribution, can consider the condition that the weather is constantly changed every day, selects weather type data of a plurality of time points in one day, combines other similar day factors, selects similar days according to a similar day selection algorithm, and adopts the average value of the generated energy of the similar days as the generated energy of the prediction day, so that the generated energy of the photovoltaic power station can be accurately predicted.
In this embodiment, the step of "obtaining N historical date data i Weather similarity factor ζ with target date dest i The method specifically comprises the following steps:
obtaining historical date i At Time point Time 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x i (1)、x i (2)、...、x i (M); acquiring the Time of the target date dest at the Time point 1 、Time 2 、...、Time M One-to-one correspondence of daysGas type data x 0 (1)、x 0 (2)、...、x 0 (M); the weather type data are natural numbers, and different natural numbers corresponding to different weather types;
each weather similarity factor ζ i Includes M Time points k Corresponding factor
Wherein k is a positive integer of 0<ρ<1，k＝1,2，...，M。
Here, ρ is a resolution coefficient, 0< ρ <1, and it is understood that the smaller ρ is, the larger the difference between the correlation coefficients is, and the stronger the discrimination capability is. Optionally, ρ =0.5.
Here, time 1 、Time 2 、...、Time M Respectively corresponding M Time points in one day, optionally, time point 1 Earlier than Time 2 Time of day 2 Earlier than Time 3 . M-1 Earlier than Time m . Optionally, time 2 And Time 1 Time interval between = Time 3 And Time 2 Time interval between =. = Time M-1 And Time M Time interval therebetween, e.g., M =6,time 1 、Time 2 、...、Time 6 Respectively 5 points, 8 points, 11 points, 14 points, 17 points and 20 points. The weather type may be cloudy, sunny, rainy, etc., which specifies different natural numbers for different weather type data.
To obtain N historical date dates i At Time point of Time with target date dest 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x 0 (1)、x 0 (2)、...、x 0 (M) which may be obtained using a crawler from a chinese air net (e.g., a crawler written in python language) that stores weather types at hourly intervals.
In this embodiment, the step of "obtaining N historical date data i Date difference factor delta from target date dest i The method specifically comprises the following steps:
each history date i Date difference factor from target date dest
Where mod is a remainder function, int is a rounding function, 1<β 1 ,β 2 ,β 3 <1，N 1 ,N 2 And N 3 Is a constant, Δ i For historical date i Days apart from the target date dest, when the historical date is date i When the date dest is the major day, P i =1, otherwise, P i ＝0。
Here, generally, the history date i The closer the date difference with the target date dest, the higher the similarity, and the principle of 'big and small distance' is adopted, and the periodicity of load change and the periodic change rule of holiday and holiday are considered at the same time.
Here, (1) mod is a remainder function, i.e., mod (Δ) i ,N 1 )＝Δ i mod N 1 (ii) a (2) int is a rounding function, which is either top rounding or bottom rounding; (3) Beta is a 1 ,β 2 And beta 3 Can be understood as the attenuation coefficient, and the value of the attenuation coefficient can be more than or equal to 0.9 and less than or equal to beta 1 ,β 2 ,β 3 ≤0.98，β 1 For indicating historical date i Similar reduction ratio, β, of every day of the day apart from the target date dest 2 For indicating historical date i Similar reduction ratio, β, per week increase in days apart from the target date dest 3 For indicating historical date i A similar reduction rate of every year of days apart from the target date dest; (3) N is a radical of 1 And N 2 May be taken to be 7 days of the week, considering that the spacing between false days of some major festivals is less than 365 days, N 3 A value of 350; (4) Delta i For historical date i Days from the target date dest, e.g. historical date i In relation to the target date dest of today and yesterday, then Δ i =1, and the likeSimilarly, the days Δ apart corresponding to other situations can be obtained i (ii) a (5) Here, national day, the day of the year, the spring festival, etc. can be understood as a significant festival, in which people often leave a holiday, a leisure, etc., so that the photovoltaic power plant may be shut down, or be treated by regulating the power generation amount, etc., and therefore, if the historical date is date i The similarity between the two dates is high when the target date dest is a big date.
In this embodiment, the step of "obtaining N historical date data i Week difference factor gamma from target date dest i The method specifically comprises the following steps:
each history date i Week difference factor gamma from target date dest i ＝1-|w i -w 0 Where the types of week are Monday, tuesday, wednesday, thursday, friday, saturday and Sunday, respectively, corresponding to a real number, w i For historical date i Real number, w, corresponding to the week type in which it is located 0 A real number corresponding to the week type on which the target date dest is located. Alternatively, week corresponds to 0.1, tuesday to thursday corresponds to 0.2, friday corresponds to 0.3, saturday corresponds to 0.7, and sunday corresponds to 1.
In this embodiment, the "normalizing the matrix Y" specifically includes:
generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
In this embodiment, the "normalizing the matrix Y" specifically includes:
generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
The embodiment of the invention provides a photovoltaic power generation capacity prediction device, which comprises the following modules:
an information acquisition module for acquiring N historical date data i Weather similarity factor ζ with target date dest i Obtaining N historical date data i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. N;
a matrix generation module for generating a matrix
Wherein,
j is a positive integer, j =1,2. The indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor;
a matrix processing module for normalizing the matrix Y and date data i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y;
a prediction module for similarity F in descending order 1 、F 2 、...、F M And Num maximum similarities are selected, num historical dates corresponding to the Num similarities one by one are obtained, and the average value of the photovoltaic power generation amount corresponding to the Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest.
An embodiment of the present invention provides an electronic device, including: a memory for storing executable instructions; and the processor is used for realizing the photovoltaic power generation capacity prediction method in the first embodiment when the processor executes the executable instructions stored in the memory.
The third embodiment of the invention provides a storage medium, which stores executable instructions and is used for causing a processor to execute the method for predicting the photovoltaic power generation amount in the first embodiment.
It should be understood that although the specification describes embodiments, not every embodiment includes only a single embodiment, and such description is for clarity purposes only, and it will be appreciated by those skilled in the art that the specification as a whole may be appropriately combined to form other embodiments as will be apparent to those skilled in the art.
The above-listed detailed description is only a specific description of a possible embodiment of the present invention, and they are not intended to limit the scope of the present invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for predicting photovoltaic power generation capacity is characterized by comprising the following steps:
obtaining N historical date data i Weather similarity factor ζ with target date dest i Obtaining N historical dates date i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. N;
generating a matrix
Wherein,
j is a positive integer, j =1,2. The indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor;
normalizing the matrix Y and date history i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y;
similarity F in order of big to little 1 、F 2 、...、F M The Num largest similarities are selected from among them,acquiring Num historical dates corresponding to Num similarities one by one, wherein the average value of the photovoltaic power generation amount corresponding to Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest.
2. Prediction method according to claim 1, characterised in that said "obtaining N historical date data i Weather similarity factor ζ with target date dest i The method specifically comprises the following steps:
obtaining historical date i At Time point Time 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x i (1)、x i (2)、...、x i (M); acquiring the Time of the target date dest at the Time point 1 、Time 2 、...、Time M One-to-one correspondence of weather type data x 0 (1)、x 0 (2)、...、x 0 (M); the weather type data are natural numbers, and different natural numbers corresponding to different weather types;
each weather similarity factor ζ i Includes M Time points k Corresponding factor
Wherein k is a positive integer of 0<ρ<1，k＝1,2，...，M。
3. Prediction method according to claim 1, characterised in that said "obtaining N historical date data i Date difference factor delta from target date dest i The method specifically comprises the following steps:
each history date i Date difference factor from target date dest
Where mod is a remainder function, int is a rounding function, 1<β 1 ,β 2 ,β 3 <1，N 1 ,N 2 And N 3 Is a constant, Δ i For historical date i Days apart from the target date dest, when the historical date is date i When the date dest is the major day, P i =1, otherwise, P i ＝0。
4. Prediction method according to claim 1, characterised in that said "obtaining N historical date data i Week difference factor gamma from target date dest i The method specifically comprises the following steps:
each history date i Week difference factor gamma from target date dest i ＝1-|w i -w 0 Where the types of week are Monday, tuesday, wednesday, thursday, friday, saturday and Sunday, respectively, corresponding to a real number, w i For historical date i Real number, w, corresponding to the week type in which it is located 0 A real number corresponding to the week type on which the target date dest is located.
5. The prediction method according to claim 4, wherein:
weekly corresponds to 0.1, tuesday to Thursday corresponds to 0.2, friday corresponds to 0.3, saturday corresponds to 0.7, and Sunday corresponds to 1.
6. The prediction method according to claim 1, wherein the "normalizing the matrix Y" specifically includes:
generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
7. The prediction method according to claim 1, wherein the "normalizing the matrix Y" specifically includes:
generating a matrix
Wherein,
thereafter, for each Y in the matrix Y i,j ＝y′ i,j 。
8. The photovoltaic power generation capacity prediction device is characterized by comprising the following modules:
an information acquisition module for acquiring N historical date data i Weather similarity factor ζ with target date dest i Obtaining N historical date data i Date difference factor delta from target date dest i Obtaining N historical date data i Week difference factor gamma from target date dest i The weather similarity factor ζ i Includes M Time points 1 、Time 2 、...、Time M Corresponding factor ζ i (1)、ζ i (2)、...、ζ i (M), wherein N, M and i are positive integers, and i =1,2,. N;
a matrix generation module for generating a matrix
Wherein,
j is a positive integer, j =1,2. The indexes of the 1 st row, the 2 nd row, the 1 、Time 2 、...、Time M The index of the M +1 th row of the matrix Y is a date difference factor, and the index of the M +1 th row of the matrix Y is a week difference factor;
a matrix processing module for normalizing the matrix Y and date data i Similarity to target date dest
C j ＝S j ×R j ，
r ij Is the correlation coefficient between the index of the ith row and the index of the jth row of the matrix Y;
a prediction module for similarity F in descending order 1 、F 2 、...、F M The Num maximum similarities are selected, num historical dates corresponding to the Num similarities one by one are obtained, and the average value of the photovoltaic power generation amount corresponding to the Num historical dates one by one is the predicted value of the photovoltaic power generation amount of the target date dest.
9. An electronic device, comprising:
a memory for storing executable instructions;
a processor for implementing the method of predicting photovoltaic power generation as claimed in any one of claims 1 to 7 when executing executable instructions stored in the memory.
10. A storage medium storing executable instructions for causing a processor to perform the method of predicting photovoltaic power generation according to any one of claims 1 to 7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211066788.7A CN115249093A (en) | 2022-09-01 | 2022-09-01 | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211066788.7A CN115249093A (en) | 2022-09-01 | 2022-09-01 | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115249093A true CN115249093A (en) | 2022-10-28 |
Family
ID=83699788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211066788.7A Withdrawn CN115249093A (en) | 2022-09-01 | 2022-09-01 | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115249093A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118095784A (en) * | 2024-04-17 | 2024-05-28 | 杭州城投建设有限公司 | Project management method, system and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636003A (en) * | 2018-11-14 | 2019-04-16 | 北京电力经济技术研究院有限公司 | A kind of power-system short-term load forecasting method of high precision of prediction |
| CN109978262A (en) * | 2019-03-27 | 2019-07-05 | 新奥数能科技有限公司 | The selection method and device of similar day for photovoltaic power prediction |
| CN113222270A (en) * | 2021-05-25 | 2021-08-06 | 苏州沃联新能源有限公司 | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium |
-
2022
- 2022-09-01 CN CN202211066788.7A patent/CN115249093A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636003A (en) * | 2018-11-14 | 2019-04-16 | 北京电力经济技术研究院有限公司 | A kind of power-system short-term load forecasting method of high precision of prediction |
| CN109978262A (en) * | 2019-03-27 | 2019-07-05 | 新奥数能科技有限公司 | The selection method and device of similar day for photovoltaic power prediction |
| CN113222270A (en) * | 2021-05-25 | 2021-08-06 | 苏州沃联新能源有限公司 | Power consumption load prediction method, power consumption load prediction device, electronic device, and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 卢舟鑫;王冰;荣军峰;: "基于多时段综合相似日的光伏发电功率预测", 电源技术, no. 01 * |
| 陈国栋;罗素芹;刘文斌;朱翔鸥;: "基于改进相似日的光伏系统日发电量预测", 照明工程学报, no. 03 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118095784A (en) * | 2024-04-17 | 2024-05-28 | 杭州城投建设有限公司 | Project management method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qing et al. | Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM | |
| Hao et al. | A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting | |
| CN102930358B (en) | A kind of neural net prediction method of photovoltaic power station power generation power | |
| Zhou et al. | Deep learning-based rolling horizon unit commitment under hybrid uncertainties | |
| CN112070311A (en) | Day-ahead light power prediction method based on similar day clustering and meteorological factor weighting | |
| CN116128150B (en) | Photovoltaic intelligent output prediction method based on two-stage optimization | |
| CN115249093A (en) | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium | |
| CN111242355A (en) | Photovoltaic probability prediction method and system based on Bayesian neural network | |
| CN111355250A (en) | Power grid side energy storage optimization method and system | |
| Li et al. | Sizing ramping reserve using probabilistic solar forecasts: A data-driven method | |
| CN112862215B (en) | Micro-grid energy demand prediction method, system and equipment | |
| CN117650532A (en) | New energy access power grid management method | |
| CN108846529A (en) | A kind of generated energy forecasting system | |
| Vyas et al. | Forecasting solar power generation on the basis of predictive and corrective maintenance activities | |
| Kim et al. | Solar radiation forecasting using boosting decision tree and recurrent neural networks | |
| Liu et al. | Optimizing size of Lithium-ion battery combined with PV generation | |
| CN112101608A (en) | Offshore wind farm site selection method and device | |
| CN114897220A (en) | Micro-grid short-term load prediction method based on GRU neural network | |
| Dahal et al. | Improved load and generation forecasting for extended day-ahead estimates in the Nordic grid | |
| CN114897229A (en) | Ultra-short-term prediction method for irradiance of photovoltaic power station based on AP clustering and Markov chain | |
| Ye et al. | A comparative study of ensemble support vector regression methods for short-term load forecasting | |
| Trivedi et al. | Peak demand management and schedule optimisation for energy storage through the machine learning approaches | |
| Matsuo et al. | Short-term load forecasting using artificial neural network | |
| CN109149644B (en) | Light-storage integrated online strategy matching and collaborative optimization method based on big data analysis | |
| Chen et al. | Short-term wind power forecasting based on spatial correlation and artificial neural network |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221028 |
|
| WW01 | Invention patent application withdrawn after publication |