CN117154724A - Photovoltaic power generation power prediction method - Google Patents
Photovoltaic power generation power prediction method Download PDFInfo
- Publication number
- CN117154724A CN117154724A CN202311422158.3A CN202311422158A CN117154724A CN 117154724 A CN117154724 A CN 117154724A CN 202311422158 A CN202311422158 A CN 202311422158A CN 117154724 A CN117154724 A CN 117154724A
- Authority
- CN
- China
- Prior art keywords
- sequence
- prediction
- optical power
- power
- power generation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000010248 power generation Methods 0.000 title claims abstract description 36
- 230000003287 optical effect Effects 0.000 claims abstract description 63
- 238000005070 sampling Methods 0.000 claims abstract description 30
- 238000009825 accumulation Methods 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000001172 regenerating effect Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 abstract description 3
- 230000004044 response Effects 0.000 abstract description 3
- 230000007613 environmental effect Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000012797 qualification Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Power Engineering (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of power generation power prediction, in particular to a photovoltaic power generation power prediction method, which comprises the following steps: step one: collecting power data of a photovoltaic power generation system; step two: generating an initial optical power sampling array based on power data of the photovoltaic power generation system; step three: generating an accumulation sequence based on the initial optical power sampling sequence; step four: generating a mean sequence based on the accumulated sequence; step five: generating a prediction 1-order model based on the mean value sequence; step six: generating a new optical power prediction model based on the fifth step; step seven: and D, carrying out photovoltaic power generation power prediction based on the new optical power prediction model generated in the step six, and realizing rapid prediction and real-time response of the optical power through a simple sequence logic calculation process, wherein the prediction precision is high.
Description
Technical Field
The application relates to the technical field of power generation power prediction, in particular to a photovoltaic power generation power prediction method.
Background
With the implementation of domestic series of new energy development policies, photovoltaic power generation has become one of the most popular renewable energy sources nowadays. However, although photovoltaic power generation has been successfully used in many fields, in actual production, the power of photovoltaic power generation varies greatly due to factors such as weather, foreign matter, shielding, and the like. This not only results in a decrease in output efficiency of photovoltaic power generation, but also brings great economic loss to photovoltaic power generation owners.
The following methods are generally adopted in the prior art to predict the photovoltaic power generation power:
1. prediction method based on physical model
The method mainly utilizes a known physical model to predict the power output of the photovoltaic panel by calculating the environmental conditions of the photovoltaic panel, the incident angle of sunlight and other factors. The method has high precision, but requires accurate environmental data, and the calculation process is relatively complex, and real-time calculation is difficult to realize, so that the application range is limited, for example, the method has the following publication number: CN116800172a discloses a photoelectric conversion method and an energy storage system.
2. Prediction method based on statistics
This approach uses historical data and statistical principles to predict the output of photovoltaic power. And analyzing the data by collecting the data such as the power information and the environmental factors in the corresponding time period to obtain a probability distribution function of power output, so as to predict the change trend of future power. This method requires a large amount of data, has a close relationship with factors such as environmental conditions, and is difficult to cope with sudden changes in a short period, for example, publication No.: CN110059871B discloses a photovoltaic power generation power prediction method.
3. Prediction method based on machine learning
This approach introduces machine learning techniques into the power prediction. The future power output is predicted by constructing a model using the training data. Compared with the former two methods, the method does not need a complete physical model and extremely strict environmental data, can well cope with sudden situations and has better applicability, but is limited by the cost of multiparty implementation and has poorer economy, for example, the publication number is: CN110414748A discloses a photovoltaic power prediction method.
Disclosure of Invention
The application aims to solve the technical problems that: the defect of the prior art is overcome, and a photovoltaic power generation power prediction method is provided.
The application adopts the technical proposal for solving the technical problems that: the photovoltaic power generation power prediction method comprises the following steps:
step one: collecting power data of a photovoltaic power generation system;
step two: generating an initial optical power sampling array based on power data of the photovoltaic power generation system;
step three: generating an accumulation sequence based on the initial optical power sampling sequence;
step four: generating a mean sequence based on the accumulated sequence;
step five: generating a prediction 1-order model based on the mean value sequence;
step six: generating a new optical power prediction model based on the fifth step;
step seven: and D, carrying out photovoltaic power generation power prediction based on the new optical power prediction model generated in the step six.
In the second step, the generated initial optical power sampling sequence G0 is not less than 4 time units;
the initial optical power sampling sequence G0 is represented as follows:
G0={G0(1),G0(2),……,G0(i),……,G0(N)}；
wherein i is a sequence sampling point, i epsilon [1, N ], N is more than or equal to 4, N represents the total time of light power sampling, and the minimum unit is minutes.
In the third step, 1 accumulation sequence is generated by 1 accumulation sequence based on the initial optical power sampling sequence, and the calculation formula of the 1 accumulation sequence G1 is as follows:
G1={G1(1),G1(2),……,G1(k),……,G1(M)}={∑G0(1+k-1),∑G0(2+k-1),……,∑G0(i+k-1),……,∑G0(M+k-1)}；
wherein k is 1, M is 1 accumulation period, and M is less than or equal to N.
The optical power data average value sequence P1 in the fourth step is represented as follows:
P1={P1(2),P1(3),……,P1(j),……P1(L)}；
wherein P1 (j) = (ΣG0 (j+i+k) +ΣG0 (j+i+k-1))/2, j ε [1, L ], L is the average value sequence period, with minutes as the minimum unit, L is less than or equal to M.
The representation of the prediction 1-order model W1 in the fifth step is as follows:
W1(z+1)=D1*G0(1)/(D2*G0(1)+(D1-D2*G0(1))*exp(D1*z))；
wherein D1, D2 are model undetermined estimated parameter values, and z is a time point to be predicted.
The to-be-determined estimated parameter value of the fifth model is calculated according to the following formula:
D=(Q T Q) -1 Q T V；
wherein Q= [ -P1 (2), -P1 (3), … …, -P1 (L); (P1 (2)). Sup.2, (P1 (3)). Sup.2, … …, (P1 (L)). Sup.2)] T ，D=[D1,D2] T ，V=[G0(2),G0(3),……,G0(L)] T 。
The new optical power prediction model in the step sixIs represented as follows:
(z+1)=W1(z+1)-W1(z)。
the seventh step comprises the following substeps:
7-1: judging the new optical power prediction model generated in the step sixIf the qualification is qualified, the step 7-2 is carried out, otherwise, the step 7-3 is carried out;
7-2: based on the new optical power prediction model generated in step sixPerforming optical power prediction at the next moment;
7-3: and returning to the step two, regenerating an initial optical power sampling sequence based on the next period data, and regenerating the model.
The step 7-1 comprises the following substeps:
7-1-1: calculating a residual sequence E of the optical power prediction model;
7-1-2: calculating a relative error delta (i) of the point in time i;
7-1-3: calculating the average relative errorGiven the average relative error delta, if +.>And when < delta is established, judging that the model is qualified.
The calculation formula of the residual sequence E of the optical power prediction model is as follows:
E={E(1),E(2),……,E(i),……,E(n)}={[G0(1)-(1)],[G0(2)-/>(2)],……,[G0(N)-/>(N)]}；
the calculation formula of the i moment point relative error delta (i) is as follows:
Δ(i)=|E(i)/G0(i)|；
said average relative errorThe calculation formula is as follows:
=(Δ(1)+Δ(2)+……Δ(N))/N；
δ=0.5%。
compared with the prior art, the application has the following beneficial effects:
the application provides a photovoltaic power generation power prediction method, which only involves a small amount of optical power data and eliminates the influence of environmental data through a series of data processing, and can realize rapid prediction and real-time response of the optical power through a simple sequence logic calculation process, and has the technical advantages of low cost, strong economy and high data robustness while having high prediction precision.
Detailed Description
Embodiments of the application are further described below:
example 1
The photovoltaic power generation power prediction method comprises the following steps:
step one: collecting power data of a photovoltaic power generation system; according to the application, the photovoltaic solar panel is connected with the photovoltaic inverter, the photovoltaic inverter is connected with the prediction host, the acquisition of the power data of the photovoltaic solar panel is realized based on the photovoltaic inverter, and the acquired data are stored in the database of the prediction host.
Step two: the prediction host generates an initial optical power sampling sequence based on the power data stored in the database; specifically, the generated initial optical power sampling sequence G0 is not less than 4 time units;
the initial optical power sampling sequence G0 is represented as follows:
G0={G0(1),G0(2),……,G0(i),……,G0(N)}；
wherein i is a sequence sampling point, i epsilon [1, N ], N is more than or equal to 4, N represents the total time of light power sampling, and the minimum unit is minutes.
Step three: the prediction host generates an optical power data accumulation sequence based on the initial optical power sampling sequence; in this embodiment, 1 accumulation is performed, because the accumulation generation can enhance the regularity of the system, improve the randomness of the result, and have good noise immunity, the accumulation can be multiple accumulation, but only less than 2 times of accumulation can be used for prediction, wherein 2 times of accumulation is used for prediction and dynamic analysis in combination, and more times of accumulation is used for system dynamic analysis and cannot be used for prediction; for the optical power prediction, the general 1-time accumulation model is the most suitable accumulation mode which has the strongest real-time performance and is most in line with the system rule. The exponential law of the light power development change can be well shown by adopting 1 accumulation.
Based on this, the calculation formula of the 1-time accumulation sequence G1 of the optical power data is as follows:
G1={G1(1),G1(2),……,G1(k),……,G1(M)}={∑G0(1+k-1),∑G0(2+k-1),……,∑G0(i+k-1),……,∑G0(M+k-1)}；
wherein k is 1, M is 1 accumulation period, and M is less than or equal to N.
Step four: the prediction host generates an optical power data average value sequence P1 based on the optical power data 1-time accumulation sequence G1; the difference of the original data can be further eliminated by producing the optical power data average value sequence P1, so that the data is smoother and easier to model. The optical power data average value sequence P1 in the fourth step is represented as follows:
P1={P1(2),P1(3),……,P1(j),……P1(L)}；
wherein P1 (j) = (ΣG0 (j+i+k) +ΣG0 (j+i+k-1))/2, j ε [1, L ], L is the average value sequence period, with minutes as the minimum unit, L is less than or equal to M.
Step five: the prediction host generates an optical power prediction 1-order model W1 based on the optical power data average value sequence P1, and calculates a pending estimated parameter value in the optical power prediction 1-order model W1; the optical power prediction 1-order model in the fifth step is represented as follows:
W1(z+1)=D1*G0(1)/(D2*G0(1)+(D1-D2*G0(1))*exp(D1*z))；
wherein D1, D2 are model undetermined estimated parameter values, and z is a time point to be predicted.
The to-be-determined estimated parameter value of the fifth model is calculated according to the following formula:
D=(Q T Q) -1 Q T V；
wherein Q= [ -P1 (2), -P1 (3), … …, -P1 (L); (P1 (2)). Sup.2, (P1 (3)). Sup.2, … …, (P1 (L)). Sup.2)] T ，D=[D1,D2] T ，V=[G0(2),G0(3),……,G0(L)] T 。
Step six: generating a new optical power prediction model based on the fifth stepThe method comprises the steps of carrying out a first treatment on the surface of the The new optical power prediction model in said step six ∈>Is represented as follows:
(z+1)=W1(z+1)-W1(z)。
step seven: based on the new optical power prediction model generated in step sixAnd carrying out photovoltaic power generation power prediction.
If directly generating the optical power prediction modelThe noise data pollution of the original system data cannot be comprehensively removed, so the embodiment firstly generates the 1-order model W1, the 1-order model W1 can well inhibit the noise data pollution, and the regularity of the system is better reflected and reflected, so that the prediction model->The method is more in line with the system authenticity and has high prediction precision.
The seventh step comprises the following substeps:
7-1: judging the new optical power prediction model generated in the step sixIf the qualification is qualified, the step 7-2 is carried out, otherwise, the step 7-3 is carried out;
7-2: based on the new optical power prediction model generated in step sixPerforming optical power prediction at the next moment;
7-3: and returning to the step two, regenerating an initial optical power sampling sequence based on the next period data, and regenerating the model.
The step 7-1 comprises the following substeps:
7-1-1: calculating a residual sequence E of the optical power prediction model;
7-1-2: calculating a relative error delta (i) of the point in time i;
7-1-3: calculating the average relative errorGiven the average relative error delta, if +.>And when < delta is established, judging that the model is qualified.
The calculation formula of the residual sequence E of the optical power prediction model is as follows:
E={E(1),E(2),……,E(i),……,E(n)}={[G0(1)-(1)],[G0(2)-/>(2)],……,[G0(N)-/>(N)]}；
the calculation formula of the i moment point relative error delta (i) is as follows:
Δ(i)=|E(i)/G0(i)|；
said average relative errorThe calculation formula is as follows:
=(Δ(1)+Δ(2)+……Δ(N))/N；
δ=0.5%。
the embodiment can be used for modeling based on relatively fewer data samples, is simple in calculation, quick in system response and high in prediction accuracy.
Example 2
In the embodiment, the method of the application is further specifically verified by taking historical light power sampling data of a 12KW distributed photovoltaic power station of a new energy source in northwest China as an example, and the sampling period unit is 10 minutes for sampling once.
The historical sampling data of the power station optical power are shown in the following table:
the prediction analysis of the photovoltaic power generation power data in the table is performed according to the photovoltaic power generation power prediction method in embodiment 1, and specifically comprises the following steps:
generating an initial optical power sampling sequence G0:
G0=(4.93,5.33,5.87,6.35,6.63,7.15,7.37,7.39,7.81,8.35,9.39,10.59,10.94,10.44)；
generating a 1-time accumulation sequence G1: g1 = (4.93,0.4,0.54,0.48,0.28,0.52,0.22,0.02,0.42,0.54,1.04,1.2,0.35, -0.5);
generating an optical power data average value sequence P1:
P1=(5.13,5.6,6.11,6.49,6.89,7.26,7.38,7.6,8.08,8.87,9.99,10.765,10.69)；
generating a prediction 1-order model W1:
w1=d1×4.93/(d2×4.93+ (D1-d2×4.93) ×exp (D1×z)), D1, D2 are model undetermined estimated parameter values, and z is a time point to be predicted.
According to formula d= (Q T Q) -1 Q T V, solving the undetermined estimated parameter values D1, D2 to obtain d1= -0.128, d2= -0.0089;
generating new photovoltaic power prediction modelsThe following are provided:
(z+1) =0.6312/(0.04409+0.8395*exp(-0.128z))-=0.6312/(0.04409+0.8395*exp(-0.128(z-1)))；
and (3) performing qualification verification of the optical power prediction model:
given an average relative error δ=0.5%, based on a photovoltaic power prediction modelThe obtained photovoltaic power prediction data sequence is as follows: (4.93,5.3517,5.7872,6.2335,6.6873,7.1448,7.4025,7.3866,7.8234,8.3397,9.3822,10.5685,10.9562,10.4237)；
The model eligibility verification calculation is as follows:
average relative error is calculated using the data in the table= 0.425823624% < δ=0.5%, the model is qualified, and the optical power prediction at the next time can be performed based on the model.
Claims (10)
1. The photovoltaic power generation power prediction method is characterized by comprising the following steps of:
step one: collecting power data of a photovoltaic power generation system;
step two: generating an initial optical power sampling sequence based on power data of the photovoltaic power generation system;
step three: generating an accumulation sequence based on the initial optical power sampling sequence;
step four: generating a mean sequence based on the accumulated sequence;
step five: generating a prediction 1-order model based on the mean value sequence;
step six: generating a new prediction model based on the fifth step;
step seven: and D, forecasting the photovoltaic power generation power based on the new forecasting model generated in the step six.
2. The method according to claim 1, wherein in the second step, the generated initial optical power sampling sequence G0 is not less than 4 time units;
the initial optical power sampling sequence G0 is represented as follows:
G0={G0(1),G0(2),……,G0(i),……,G0(N)}；
wherein i is a sequence sampling point, i epsilon [1, N ], N is more than or equal to 4, N represents the total time of light power sampling, and the minimum unit is minutes.
3. The method according to claim 2, wherein in the third step, 1 accumulation sequence is performed based on the initial optical power sampling sequence to generate 1 accumulation sequence G1, and the calculation formula of the 1 accumulation sequence G1 is as follows:
G1={G1(1),G1(2),……,G1(k),……,G1(M)}={∑G0(1+k-1),∑G0(2+k-1),……,∑G0(i+k-1),……,∑G0(M+k-1)}；
wherein k is 1, M is 1 accumulation period, and M is less than or equal to N.
4. A method for predicting photovoltaic power generation according to claim 3, wherein the mean value sequence P1 in the fourth step is represented as follows:
P1={P1(2),P1(3),……,P1(j),……P1(L)}；
wherein P1 (j) = (ΣG0 (j+i+k) +ΣG0 (j+i+k-1))/2, j ε [1, L ], L is the average value sequence period, with minutes as the minimum unit, L is less than or equal to M.
5. The method according to claim 4, wherein the prediction 1-order model W1 in the fifth step is represented as follows:
W1(z+1)=D1*G0(1)/(D2*G0(1)+(D1-D2*G0(1))*exp(D1*z))；
wherein D1, D2 are model undetermined estimated parameter values, and z is a time point to be predicted.
6. The method according to claim 5, wherein the model-to-be-determined estimated parameter value in the fifth step is calculated according to the following formula:
D=(Q T Q) -1 Q T V；
wherein Q= [ -P1 (2), -P1 (3), … …, -P1 (L); (P1 (2)). Sup.2, (P1 (3)). Sup.2, … …, (P1 (L)). Sup.2)] T ，D=[D1,D2] T ，V=[G0(2),G0(3),……,G0(L)] T 。
7. The photovoltaic power generation power prediction method according to claim 6, characterized in thatThe method comprises the following steps ofIs represented as follows:
(z+1)=W1(z+1)-W1(z)。
8. the photovoltaic power generation power prediction method according to claim 7, characterized in that the step seven includes the sub-steps of:
7-1: judging the new optical power prediction model generated in the step sixIf the test result is qualified, the step 7-2 is carried out, otherwise, the step 7-3 is carried out;
7-2: based on the new optical power prediction model generated in step sixPerforming optical power prediction at the next moment;
7-3: and returning to the step two, regenerating an initial optical power sampling sequence based on the next period data, and regenerating the model.
9. The method for predicting the photovoltaic power generation power according to claim 8, wherein the step 7-1 includes the sub-steps of:
7-1-1: calculating a residual sequence E of the optical power prediction model;
7-1-2: calculating a relative error delta (i) of the point in time i;
7-1-3: calculating the average relative errorGiven the average relative error delta, if +.>When < delta is established, it is determined thatAnd (5) qualified model.
10. The photovoltaic power generation power prediction method according to claim 9, wherein the calculation formula of the residual sequence E of the optical power prediction model is as follows:
E={E(1),E(2),……,E(i),……,E(n)}={[G0(1)- (1)],[G0(2)- /> (2)],……,[G0(N)- /> (N)]}；
the calculation formula of the i moment point relative error delta (i) is as follows:
Δ(i)=|E(i)/G0(i)|；
said average relative errorThe calculation formula is as follows:
=(Δ(1)+Δ(2)+……Δ(N))/N；
δ=0.5%。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311422158.3A CN117154724B (en) | 2023-10-31 | 2023-10-31 | Photovoltaic power generation power prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311422158.3A CN117154724B (en) | 2023-10-31 | 2023-10-31 | Photovoltaic power generation power prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117154724A true CN117154724A (en) | 2023-12-01 |
| CN117154724B CN117154724B (en) | 2024-02-23 |
Family
ID=88901122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311422158.3A Active CN117154724B (en) | 2023-10-31 | 2023-10-31 | Photovoltaic power generation power prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117154724B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103996073A (en) * | 2014-05-06 | 2014-08-20 | 国家电网公司 | Photometric-network real-time-correction self-learning ARMA model photovoltaic power prediction method |
| CN106503828A (en) * | 2016-09-22 | 2017-03-15 | 上海电力学院 | A kind of photovoltaic power output ultra-short term Methods of Chaotic Forecasting |
| WO2018082132A1 (en) * | 2016-11-04 | 2018-05-11 | 江南大学 | Short-period prediction method for output power of energy system |
| CN109670652A (en) * | 2018-12-29 | 2019-04-23 | 石家庄科林电气股份有限公司 | A kind of failure prediction method of photovoltaic module |
| CN110059871A (en) * | 2019-04-04 | 2019-07-26 | 广东工业大学 | Photovoltaic power generation power prediction method |
| CN110059878A (en) * | 2019-04-15 | 2019-07-26 | 中国计量大学 | Based on CNN LSTM photovoltaic power generation power prediction model and its construction method |
| CN110414748A (en) * | 2019-08-12 | 2019-11-05 | 合肥阳光新能源科技有限公司 | Photovoltaic power prediction technique |
| CN112183221A (en) * | 2020-09-04 | 2021-01-05 | 北京科技大学 | Semantic-based dynamic object self-adaptive trajectory prediction method |
| CN112949918A (en) * | 2021-02-25 | 2021-06-11 | 山东大学 | DGM-RNN-based day-ahead photovoltaic power prediction method and system |
| CN114492964A (en) * | 2022-01-13 | 2022-05-13 | 河海大学 | Photovoltaic power ultra-short term probability prediction method based on wavelet decomposition and optimized deep confidence network |
| KR102413415B1 (en) * | 2021-11-29 | 2022-06-27 | 홍석훈 | Method of interpolation of missing values in a time series model for solar power generation data |
| CN115809732A (en) * | 2022-11-30 | 2023-03-17 | 南京邮电大学 | Distributed photovoltaic power generation power prediction method and system |
| CN116191412A (en) * | 2023-02-16 | 2023-05-30 | 山东中瑞电气有限公司 | Power load prediction method |
| CN116800172A (en) * | 2023-08-23 | 2023-09-22 | 中通服建设有限公司 | Photoelectric conversion method and energy storage system |
-
2023
- 2023-10-31 CN CN202311422158.3A patent/CN117154724B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103996073A (en) * | 2014-05-06 | 2014-08-20 | 国家电网公司 | Photometric-network real-time-correction self-learning ARMA model photovoltaic power prediction method |
| CN106503828A (en) * | 2016-09-22 | 2017-03-15 | 上海电力学院 | A kind of photovoltaic power output ultra-short term Methods of Chaotic Forecasting |
| WO2018082132A1 (en) * | 2016-11-04 | 2018-05-11 | 江南大学 | Short-period prediction method for output power of energy system |
| CN109670652A (en) * | 2018-12-29 | 2019-04-23 | 石家庄科林电气股份有限公司 | A kind of failure prediction method of photovoltaic module |
| CN110059871A (en) * | 2019-04-04 | 2019-07-26 | 广东工业大学 | Photovoltaic power generation power prediction method |
| CN110059878A (en) * | 2019-04-15 | 2019-07-26 | 中国计量大学 | Based on CNN LSTM photovoltaic power generation power prediction model and its construction method |
| CN110414748A (en) * | 2019-08-12 | 2019-11-05 | 合肥阳光新能源科技有限公司 | Photovoltaic power prediction technique |
| CN112183221A (en) * | 2020-09-04 | 2021-01-05 | 北京科技大学 | Semantic-based dynamic object self-adaptive trajectory prediction method |
| CN112949918A (en) * | 2021-02-25 | 2021-06-11 | 山东大学 | DGM-RNN-based day-ahead photovoltaic power prediction method and system |
| KR102413415B1 (en) * | 2021-11-29 | 2022-06-27 | 홍석훈 | Method of interpolation of missing values in a time series model for solar power generation data |
| CN114492964A (en) * | 2022-01-13 | 2022-05-13 | 河海大学 | Photovoltaic power ultra-short term probability prediction method based on wavelet decomposition and optimized deep confidence network |
| CN115809732A (en) * | 2022-11-30 | 2023-03-17 | 南京邮电大学 | Distributed photovoltaic power generation power prediction method and system |
| CN116191412A (en) * | 2023-02-16 | 2023-05-30 | 山东中瑞电气有限公司 | Power load prediction method |
| CN116800172A (en) * | 2023-08-23 | 2023-09-22 | 中通服建设有限公司 | Photoelectric conversion method and energy storage system |
Non-Patent Citations (2)
| Title |
|---|
| 李燕斌;张久菊;肖俊明;: "基于指数平滑法的灰色预测模型", 中原工学院学报, vol. 26, no. 04 * |
| 杨锡运 等 基于相似日的GREY-MARKOV与BP_ADABOOST的短期光伏功率预测, 电源技术, vol. 47, no. 6, 30 June 2023 (2023-06-30) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117154724B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214575B (en) | Ultrashort-term wind power prediction method based on small-wavelength short-term memory network | |
| CN111860982B (en) | VMD-FCM-GRU-based wind power plant short-term wind power prediction method | |
| Bommidi et al. | Hybrid wind speed forecasting using ICEEMDAN and transformer model with novel loss function | |
| CN110909919A (en) | Photovoltaic power prediction method of depth neural network model with attention mechanism fused | |
| CN109272156B (en) | Ultra-short-term wind power probability prediction method | |
| CN110880789A (en) | Economic dispatching method for wind power and photovoltaic combined power generation system | |
| CN104573876A (en) | Wind power plant short-period wind speed prediction method based on time sequence long memory model | |
| CN111242377A (en) | Short-term wind speed prediction method integrating deep learning and data denoising | |
| CN105426989A (en) | EEMD and combined kernel RVM-based photovoltaic power short-term prediction method | |
| CN114266416A (en) | Photovoltaic power generation power short-term prediction method and device based on similar days and storage medium | |
| CN111600300A (en) | Robust optimization scheduling method considering wind power multivariate correlation ellipsoid set | |
| CN113159102A (en) | Multi-time-scale photovoltaic power prediction method and system | |
| CN115689055A (en) | Short-term solar irradiance prediction method and device | |
| CN117114160A (en) | Short-term photovoltaic power prediction method | |
| CN114091317A (en) | Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction | |
| CN116632820A (en) | Wind power prediction method based on sequence extension VMD and wind speed fluctuation characteristics | |
| CN113095534A (en) | Wind power prediction method combining ARIMA and improved Elman neural network | |
| CN110796292A (en) | Photovoltaic power short-term prediction method considering haze influence | |
| CN117060407B (en) | Wind power cluster power prediction method and system based on similar day division | |
| CN118095891A (en) | Active power distribution network payload prediction method and system considering source load meteorological characteristic decoupling | |
| CN113361782A (en) | Photovoltaic power generation power short-term rolling prediction method based on improved MKPLS | |
| CN117154724B (en) | Photovoltaic power generation power prediction method | |
| CN110555566B (en) | B-spline quantile regression-based photoelectric probability density prediction method | |
| CN117239735A (en) | Wind power prediction method based on space-time convolution | |
| CN116663727A (en) | Photovoltaic power prediction method and system |
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 |