CN116011665A - New energy power generation industry subsidy prediction method based on multiple linear regression model - Google Patents
New energy power generation industry subsidy prediction method based on multiple linear regression model Download PDFInfo
- Publication number
- CN116011665A CN116011665A CN202310059540.6A CN202310059540A CN116011665A CN 116011665 A CN116011665 A CN 116011665A CN 202310059540 A CN202310059540 A CN 202310059540A CN 116011665 A CN116011665 A CN 116011665A
- Authority
- CN
- China
- Prior art keywords
- linear regression
- multiple linear
- power generation
- payment
- patch
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012417 linear regression Methods 0.000 title claims abstract description 63
- 238000010248 power generation Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000001419 dependent effect Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 19
- 239000002028 Biomass Substances 0.000 claims description 7
- 230000027311 M phase Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a patch prediction method for new energy power generation industry based on a multiple linear regression model, which comprises the following steps: acquiring the influence factors of patch payment in real-time power transaction; inputting the influence factors of patch payment in real-time power transaction into a trained multiple linear regression prediction model, and calculating to obtain predicted payment amount; the training method of the multiple linear regression prediction model comprises the following steps: establishing a multiple linear regression prediction equation of the independent variable and the dependent variable with respect to the coefficient to be determined; substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set; converting the simultaneous equation set into an equation set of undetermined coefficients, and solving and calculating to obtain specific values of the undetermined coefficients; substituting into a multiple linear regression prediction equation. The patch prediction method for the new energy power generation industry based on the multiple linear regression model provided by the invention can be used for effectively predicting patches for the new energy power generation industry.
Description
Technical Field
The invention relates to a patch prediction method for new energy power generation industry based on a multiple linear regression model, and belongs to the technical field of new energy.
Background
In recent years, the development and utilization of renewable energy sources are continuously increased in China, the energy source structure transformation policy is raised to the national strategy, and the renewable energy sources enter a high-speed growth stage. Since 2017, the renewable energy consumption in China increases by 36.0% of the world renewable energy consumption. Wherein, solar power generation increases by 76% in the same ratio, biomass power generation increases by 25% in the same ratio, and wind power generation increases by 21% in the same ratio. Although renewable energy sources in China are rapid and rapid at present, renewable energy source power generation still exists in the current situations of immature technology and relatively high production cost, cannot compete with a coal-fired power generator set, and electricity price subsidy support is still needed for renewable energy source development. The existing fixed subsidy policy leads to the problems of large electric price subsidy scale, large government financial subsidy fund pressure, shortfall of renewable energy power generation subsidy, decline of subsidy efficiency and the like, so that research on renewable energy power generation project subsidy measurement is beneficial to relevant departments to know electric price subsidy financial pressure, corresponding policy adjustment is made for the subsidy amount which is possibly generated, and meanwhile, the method plays a positive promotion role in renewable energy consumption. In the prior art, related research on subsidy prediction of power generation projects is still under exploration, and a method for providing more reliable basis for enterprise measurement and prediction of subsidy payment amount is needed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a new energy power generation industry patch prediction method based on a multiple linear regression model, which can effectively predict the new energy power generation industry patch.
And a more reliable basis is provided for the enterprise to calculate and predict the obtained subsidy payment amount.
In order to solve the technical problems, the invention adopts the following technical scheme:
a new energy power generation industry subsidy prediction method based on a multiple linear regression model comprises the following steps:
acquiring the influence factors of patch payment in real-time power transaction;
inputting the influence factors of patch payment in real-time power transaction into a trained multiple linear regression prediction model, and calculating to obtain predicted payment amount;
the training method of the multiple linear regression prediction model comprises the following steps:
taking the influence factors of patch payment in the electric power transaction as independent variables and the amount of payment to be paid as dependent variable, and establishing a multiple linear regression prediction equation of the independent variables and the dependent variables relative to the coefficient to be determined;
substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set;
converting the simultaneous equations into equations of undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of undetermined coefficients;
substituting the specific value of the undetermined coefficient into a multiple linear regression prediction equation.
The multiple linear regression prediction equation is:
Y＝ b 0 + b 1 x 1 + b 2 x 2 + b 3 x 3 + ··· + b n x n (1)
wherein Y is a dependent variable, x j As an independent variable, b 0 ，b 1 ，b 2 ...，b n For the undetermined coefficients, j=1, 2,3.
The actual data y of the m-phase dependent variable is denoted as y 1 ，y 2 ，...，y m And the actual data for the m-phase argument are expressed as:
substituting the actual data of the formula (2) into the formula (1) to obtain the following simultaneous equations:
converting equation (3) into a matrix form:
Y ＝ XB (4)
in the above formula, Y is an independent variable actual data matrix, X is an independent variable actual data matrix, B is a coefficient matrix to be determined, and the following formulas are adopted:
coefficient b of undetermining 0 ,b 1 ,b 2 ,...,b n The equation set of (2) is:
the above formula (8) can be expressed in matrix form as:
X T Y＝X T XB (9)
multiplying both sides of equation (9) by (X) T X) -1 The following matrix expression can be obtained:
B＝ (X T X) -1 X T Y (10)。
the influence factors of the subsidy payment in the electric power transaction comprise the installed capacity of domestic wind power generation, solar power generation and biomass power generation projects, the online electric quantity, the subsidy year and the paid amount, and the paid amount comprises the wind power generation paying amount, the solar power generation paying amount and the biomass power generation project paying amount.
New energy power generation industry subsidy prediction device based on multiple linear regression model includes:
the influence factor acquisition module is used for acquiring the influence factors of patch payment in real-time power transaction;
the training method of the multiple linear regression prediction model comprises the following steps:
the training method of the multiple linear regression prediction model comprises the following steps:
taking the influence factors of patch payment in the electric power transaction as independent variables and the amount of payment to be paid as dependent variable, and establishing a multiple linear regression prediction equation of the independent variables and the dependent variables relative to the coefficient to be determined;
substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set;
converting the simultaneous equations into equations of undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of undetermined coefficients;
substituting the specific value of the undetermined coefficient into a multiple linear regression prediction equation.
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a new energy power generation industry subsidy prediction method based on a multiple linear regression model as described above.
The invention has the beneficial effects that: the invention provides a patch prediction method for new energy power generation industry based on a multiple linear regression model, which establishes a multiple linear regression prediction equation through the influence factors of patch payment and the amount of payment in historical power transaction, can effectively predict the patch of the new energy power generation industry, and provides a more reliable basis for enterprise measurement and prediction to obtain the amount of payment of patch payment.
Detailed Description
The present invention is further described below, and the following examples are only for more clearly illustrating the technical solution of the present invention, but are not to be construed as limiting the scope of the present invention.
The invention discloses a patch prediction method for new energy power generation industry based on a multiple linear regression model, which comprises the following steps:
acquiring the influence factors of patch payment in real-time power transaction;
and inputting the influence factors of patch payment in real-time power transaction into a trained multiple linear regression prediction model, and calculating to obtain the predicted payment amount.
Aiming at the subsidy amount distribution prediction of new energy power generation enterprises, it is clear that the change of factors such as installed capacity, online electric quantity, subsidy age, amount paid and the like can cause the change of measuring and calculating results, so when a renewable energy industry subsidy prediction model based on a multiple linear regression algorithm is determined, the input quantity is mainly the factors, and meanwhile, the following assumption is made: the patch distribution in the past years is developed according to a multiple linear following rule, and the distribution rule is changed again due to new external factors. In this embodiment, the impact factors of the subsidy payment in the electric power transaction are four impact factors in total including the wind power generation payment amount, the solar power generation payment amount and the biomass power generation payment amount, which are all three values to be predicted.
The installed capacity unit is MW, the network electric quantity unit is GWh, the patch year unit is year, and the paid and the payable amount unit is 10 6 The units of the element, correlation coefficient, are correspondingly transformed, e.g. b 0 In units of 10 6 Element, x 1 B when indicating the installed capacity 1 In units of 10 6 meta/MW.
In the invention, the training method of the multiple linear regression prediction model comprises the following steps:
and firstly, establishing a multiple linear regression prediction equation of the independent variable and the dependent variable with respect to the coefficient to be determined by taking the influence factor of patch payment in the electric power transaction as the independent variable and the amount of payment to be paid as the dependent variable. The multiple linear regression prediction equation is:
Y＝ b 0 + b 1 x 1 + b 2 x 2 + b 3 x 3 + ··· + b n x n (1)
wherein Y is a dependent variable, i.e. the amount to be paid, x j Is an independent variable, namely, an influence factor of patch payment in power transaction. b 0 ，b 1 ，b 2 ...，b n For the undetermined coefficients, j=1, 2,3. In this embodiment, n is 4. The key point of the prediction is to determine the coefficient of the multiple linear regression equation. It can be seen that in the multiple linear regression equation, once the undetermined coefficients are determined, the equation is alsoIt is determined.
And secondly, substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set.
The actual data y of the m-phase dependent variable is denoted as y 1 ，y 2 ，...，y m And the actual data for the m-phase argument are expressed as:
substituting the actual data of the formula (2) into the formula (1) to obtain the following simultaneous equations:
converting equation (3) into a matrix form:
Y ＝ XB (4)
in the above formula, Y is an independent variable actual data matrix, X is an independent variable actual data matrix, B is a coefficient matrix to be determined, and the following formulas are adopted:
and thirdly, converting the simultaneous equations into equations of the undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of the undetermined coefficients. Coefficient b of undetermining 0 ,b 1 ,b 2 ,...,b n The equation set of (2) is:
the above formula (8) can be expressed in matrix form as:
X T Y＝X T XB (9)
multiplying both sides of equation (9) by (X) T X) -1 The following matrix expression can be obtained:
B＝ (X T X) -1 X T Y (10)。
step four, the matrix result obtained in the formula (10) is the undetermined coefficient b 0 ,b 1 ,b 2 ,...,b n After the undetermined coefficient is determined, substituting the specific value of the undetermined coefficient into the multiple linear regression prediction equation of the formula (1).
According to the invention, 4000 project basic data in 2017 are input as variables to obtain the coefficient to be determined of each power generation type, specifically shown in table 1, and then the project of grid connection in 2019 is used to verify the accuracy of the model, so that the result accuracy of wind power generation, photovoltaic power generation and biomass project results is higher, the model can preliminarily realize the subsidy distribution measurement and calculation of renewable energy power generation projects, theoretical analysis shows that a multiple linear regression algorithm in power transaction can play a great potential in the application of subsidy prediction models, and a more reliable basis is provided for enterprise measurement and calculation prediction to obtain subsidy payment amounts.
Table 1 pending coefficient values for various types of power generation projects
The coefficient to be determined of the prediction model is not always unchanged, and when the deviation between the predicted value and the actual value is great, the selected sample is required to be learned again, so that the coefficient to be determined is updated in time, and the accuracy of the prediction model is improved.
The invention also discloses a new energy power generation industry subsidy prediction device based on the multiple linear regression model, which comprises:
the influence factor acquisition module is used for acquiring the influence factors of patch payment in real-time power transaction;
the training method of the multiple linear regression prediction model comprises the following steps:
the training method of the multiple linear regression prediction model comprises the following steps:
taking the influence factors of patch payment in the electric power transaction as independent variables and the amount of payment to be paid as dependent variable, and establishing a multiple linear regression prediction equation of the independent variables and the dependent variables relative to the coefficient to be determined;
substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set;
converting the simultaneous equations into equations of undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of undetermined coefficients;
substituting the specific value of the undetermined coefficient into a multiple linear regression prediction equation.
The invention also discloses a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the patch prediction method of the new energy power generation industry based on the multiple linear regression model.
The foregoing is only a preferred embodiment of the invention, it being noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the present invention, and such modifications and adaptations are intended to be comprehended within the scope of the invention.
Claims (7)
1. A new energy power generation industry subsidy prediction method based on a multiple linear regression model is characterized by comprising the following steps of: the method comprises the following steps:
acquiring the influence factors of patch payment in real-time power transaction;
inputting the influence factors of patch payment in real-time power transaction into a trained multiple linear regression prediction model, and calculating to obtain predicted payment amount;
the training method of the multiple linear regression prediction model comprises the following steps:
taking the influence factors of patch payment in the electric power transaction as independent variables and the amount of payment to be paid as dependent variable, and establishing a multiple linear regression prediction equation of the independent variables and the dependent variables relative to the coefficient to be determined;
substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set;
converting the simultaneous equations into equations of undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of undetermined coefficients;
substituting the specific value of the undetermined coefficient into a multiple linear regression prediction equation.
2. The new energy power generation industry subsidy prediction method based on a multiple linear regression model of claim 1 is characterized by comprising the following steps: the multiple linear regression prediction equation is:
Y＝b 0 +b 1 x 1 +b 2 x 2 +b 3 x 3 +···+b n x n (1)
wherein Y is a dependent variable, x j As an independent variable, b 0 ，b 1 ，b 2 ...，b n For the undetermined coefficients, j=1, 2,3.
3. The new energy power generation industry subsidy prediction method based on the multiple linear regression model is characterized by comprising the following steps of: the actual data y of the m-phase dependent variable is denoted as y 1 ，y 2 ，...，y m And the actual data for the m-phase argument are expressed as:
substituting the actual data of the formula (2) into the formula (1) to obtain the following simultaneous equations:
converting equation (3) into a matrix form:
Y＝XB (4)
in the above formula, Y is an independent variable actual data matrix, X is an independent variable actual data matrix, B is a coefficient matrix to be determined, and the following formulas are adopted:
4. the new energy power generation industry subsidy prediction method based on a multiple linear regression model according to claim 3, wherein the new energy power generation industry subsidy prediction method is characterized by comprising the following steps of: the set of equations for the undetermined coefficients b0, b1, b2,..bn is:
the above formula (8) can be expressed in matrix form as:
X T Y＝X T XB (9)
multiplying both sides of equation (9) by (X) T X) -1 The following matrix expression can be obtained:
B＝(X T X) -1 X T Y (10)。
5. the new energy power generation industry subsidy prediction method based on a multiple linear regression model of claim 1 is characterized by comprising the following steps: the influence factors of the subsidy payment in the electric power transaction comprise the installed capacity of domestic wind power generation, solar power generation and biomass power generation projects, the online electric quantity, the subsidy year and the paid amount, and the paid amount comprises the wind power generation paying amount, the solar power generation paying amount and the biomass power generation project paying amount.
6. New energy power generation industry subsidy prediction device based on multiple linear regression model, characterized by comprising:
the influence factor acquisition module is used for acquiring the influence factors of patch payment in real-time power transaction;
the training method of the multiple linear regression prediction model comprises the following steps:
the training method of the multiple linear regression prediction model comprises the following steps:
taking the influence factors of patch payment in the electric power transaction as independent variables and the amount of payment to be paid as dependent variable, and establishing a multiple linear regression prediction equation of the independent variables and the dependent variables relative to the coefficient to be determined;
substituting the influence factors of patch payment and the actual data of the payment amount in the plurality of groups of power transactions into a multiple linear regression prediction equation to establish a simultaneous equation set;
converting the simultaneous equations into equations of undetermined coefficients by adopting a least squares method, and solving and calculating to obtain specific values of undetermined coefficients;
substituting the specific value of the undetermined coefficient into a multiple linear regression prediction equation.
7. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the new energy power generation industry patch prediction method based on a multiple linear regression model as claimed in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310059540.6A CN116011665A (en) | 2023-01-18 | 2023-01-18 | New energy power generation industry subsidy prediction method based on multiple linear regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310059540.6A CN116011665A (en) | 2023-01-18 | 2023-01-18 | New energy power generation industry subsidy prediction method based on multiple linear regression model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116011665A true CN116011665A (en) | 2023-04-25 |
Family
ID=86031806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310059540.6A Pending CN116011665A (en) | 2023-01-18 | 2023-01-18 | New energy power generation industry subsidy prediction method based on multiple linear regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011665A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057486A (en) * | 2023-10-11 | 2023-11-14 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
-
2023
- 2023-01-18 CN CN202310059540.6A patent/CN116011665A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117057486A (en) * | 2023-10-11 | 2023-11-14 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
| CN117057486B (en) * | 2023-10-11 | 2023-12-22 | 云南电投绿能科技有限公司 | Operation and maintenance cost prediction method, device and equipment for power system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Drivers of CO2 emissions from power generation in China based on modified structural decomposition analysis | |
| Tan et al. | Optimization and evaluation of a dispatch model for an integrated wind-photovoltaic-thermal power system based on dynamic carbon emissions trading | |
| CN106099993B (en) | A kind of power source planning method for adapting to new energy and accessing on a large scale | |
| Hong et al. | The importance of flexible power plant operation for Jiangsu's wind integration | |
| Li et al. | Analysis of wind power generation operation management risk in China | |
| CN102930343A (en) | Energy optimization method for distributed power generation and energy supply system | |
| CN108960541A (en) | Distributed photovoltaic system effectiveness appraisal procedure and device based on the analysis of cloud data | |
| CN107204615A (en) | A kind of method and system for realizing power prediction | |
| CN102479347A (en) | Method and system for forecasting short-term wind speed of wind farm based on data driving | |
| CN116011665A (en) | New energy power generation industry subsidy prediction method based on multiple linear regression model | |
| CN112072643A (en) | Light-storage system online scheduling method based on depth certainty gradient strategy | |
| CN115954903A (en) | Method and system for controlling charging and discharging of distributed energy storage equipment | |
| CN116187509A (en) | Method and device for measuring and calculating production cost of power system | |
| Zhang et al. | Cost analysis of onshore wind power in China based on learning curve | |
| CN115965385A (en) | Distributed green electricity green certificate issuing method, device, equipment and readable storage medium | |
| CN115879976A (en) | Carbon neutralization simulation method and terminal | |
| CN108376345A (en) | A kind of distributed natural gas power generation pricing method based on cost learning curve | |
| Barley et al. | Feasibility of hybrid retrofits to off-grid diesel power plants in the Philippines | |
| CN112785166A (en) | Block chain-based power distribution network distributed generation unit output evaluation method and device | |
| Wang et al. | On the use of techno‐economic evaluation on typical integrated energy technologies matching different companies | |
| Zhao et al. | Analysis of economic benefit of wind power based on system dynamics | |
| CN108537421A (en) | Suitable for the isolated micro-capacitance sensor life cycle management economic evaluation method containing new energy | |
| Saravanaraj et al. | Empirical modelling of consumer price index of electricity and percentage inflation for Dhofar governorate in Sultanate of Oman | |
| Du et al. | Integrating cost information in energy efficiency measurement: An empirical study on thermal power companies | |
| CN116362793A (en) | Leveling electric energy cost measuring and calculating method and device considering carbon price |
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 |