CN114792196A - Electric power comprehensive evaluation method and device - Google Patents
Electric power comprehensive evaluation method and device Download PDFInfo
- Publication number
- CN114792196A CN114792196A CN202210371107.1A CN202210371107A CN114792196A CN 114792196 A CN114792196 A CN 114792196A CN 202210371107 A CN202210371107 A CN 202210371107A CN 114792196 A CN114792196 A CN 114792196A
- Authority
- CN
- China
- Prior art keywords
- index
- power
- pool
- regression
- economic
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 63
- 230000001932 seasonal effect Effects 0.000 claims abstract description 32
- 238000010219 correlation analysis Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000010606 normalization Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 description 13
- 238000011161 development Methods 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 239000013589 supplement Substances 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- CDBYLPFSWZWCQE-UHFFFAOYSA-L Sodium Carbonate Chemical compound [Na+].[Na+].[O-]C([O-])=O CDBYLPFSWZWCQE-UHFFFAOYSA-L 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 229910001341 Crude steel Inorganic materials 0.000 description 1
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 description 1
- 239000005977 Ethylene Substances 0.000 description 1
- 229910000805 Pig iron Inorganic materials 0.000 description 1
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 235000012631 food intake Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 229910000029 sodium carbonate Inorganic materials 0.000 description 1
- 235000017550 sodium carbonate Nutrition 0.000 description 1
- 230000010473 stable expression Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for comprehensive evaluation of electric power. The method comprises the following steps: acquiring an electric power index and an economic index; inputting the power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing; performing regression on the GDP and the index data preprocessed in the index pool by using a LASSO regression method; according to the method, through variable selection and weighting of the preprocessed indexes and correlation analysis of the indexes and GDP, the variables with large correlation are reserved and given with high weight, and the variables with small correlation are abandoned, so that comprehensive power evaluation index data obtained by fully utilizing information contained in the GDP is accurate, and comprehensive power evaluation is realized.
Description
Technical Field
The application relates to the technical field of power evaluation, in particular to a power comprehensive evaluation method and device.
Background
The electric power comprehensive index is a comprehensive index which integrates electric power big data and contains a large amount of information of electric power industry and social economic development, and the electric power economic development can be comprehensively evaluated by utilizing the electric power comprehensive index. At present, three main types of researches on comprehensive indexes are provided, namely, one is to utilize a representative single index in the field of economics, such as full-element productivity, labor productivity and the like, to directly measure economic development; secondly, constructing a comprehensive index evaluation system to measure economic development; thirdly, constructing a prosperity index as a qualitative index to reflect the state or development trend of a specific survey group or a certain social and economic phenomenon.
In the prior art, a mode of constructing a comprehensive evaluation system is generally adopted for power comprehensive evaluation, but the existing evaluation mode has the problems of imperfect evaluation index pool, complexity of a final index system and incapability of fully utilizing information contained in GDP (graphics data processing), wherein the imperfect index means that due to the fact that measurement indexes are not accurately defined, the index pool has large difference, some indexes are not considered yet, some indexes do not meet the actual needs of a certain area, some indexes do not meet the requirements of time development, and especially the regional economic development quality evaluation research related to the application aspect of power big data is relatively lack; the redundancy of the final index system means that all indexes in the evaluation system are included in the synthesis of the final index, so that the weight of each index is further weakened and the change of the weight is increased, so that the redundancy of the final index system is realized; the fact that the information contained in the GDP is not fully utilized means that the GDP is defined as an index, but not a dependent variable containing the information, so that the weight of the obtained index GDP is generally small, and the GDP has large correlation with the existing index system. Due to the problems of incomplete evaluation index pool, complicated final index system and insufficient utilization of information contained in GDP, the obtained comprehensive power evaluation index data is inaccurate, and the actual evaluation significance cannot be generated.
Disclosure of Invention
The embodiment of the application provides a method and a device for comprehensive power evaluation, which are used for performing supervised learning and high-dimensional data analysis through the GDP same-proportion growth rate, and fully utilizing information contained in the GDP to calculate a comprehensive power evaluation index more accurately.
The embodiment of the application provides a method for comprehensively evaluating electric power in a first aspect, which comprises the following steps:
acquiring a power index and an economic index;
inputting the electric power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing;
performing regression on the GDP and the index data preprocessed in the index pool by using a Least absolute shrinkage and selection operator regression method;
and determining evaluation indexes corresponding to the power index and the economic index based on regression coefficients generated by the regression.
Optionally, the inputting the power index and the economic index into an index pool to adjust an index missing value includes:
supplementing data with a small amount of missing data in the index pool by a smooth interpolation method;
and interpolating the data with large missing amount in the index pool according to a data proportion analysis mode.
Optionally, the inputting the power index and the economic index into an index pool to adjust an index seasonal factor includes:
and removing seasonal factors from the index data in the index pool by adopting a geometric adjustment method and an X-12-ARIMA seasonal adjustment method.
Optionally, the inputting the power index and the economic index into an index pool for performing index and GDP correlation analysis includes:
and carrying out correlation analysis on the index geometric growth rate and the GDP geometric growth rate in the index pool.
Optionally, the inputting the power index and the economic index into an index pool to perform normalization processing on the indexes includes:
normalizing the growth rate in the index pool by the formula of
Wherein, max (x) i ) Representing a sequence x i A maximum value of }; min (x) i ) Representative sequence { x } i The minimum value of.
Optionally, the formula of LASSO regression is
Wherein
For the GDP comparable growth rate after the pretreatment,
is an index pool after the pretreatment,
beta is a regression coefficient vector omega for the index after pretreatment j And (4) penalty weight of each index.
Optionally, the determining the evaluation indexes corresponding to the power index and the economic index based on the regression coefficient generated by the regression includes:
determining weights for the power indicator and the economic indicator based on regression coefficients generated by the regression;
according to the weight, the power index and the economic index are assigned and calculated to obtain an evaluation index, and the calculation formula is
Where β is the corresponding parameter vector.
A second aspect of the embodiments of the present application provides an electric power comprehensive evaluation device, including:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring a power index and an economic index;
the execution unit is used for inputting the power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises the steps of adjusting an index missing value, adjusting seasonal factors contained in the index, performing correlation analysis on the index and performing normalization processing on the index;
the regression unit is used for performing regression on the GDP and the index data preprocessed in the index pool by an LASSO regression method;
and the determining unit is used for determining the evaluation indexes corresponding to the power index and the economic index based on the regression coefficient generated by the regression.
Optionally, the execution unit includes a missing value adjustment module, a seasonal factor adjustment module, an index and GDP correlation analysis module, and an index normalization processing module:
the missing value adjusting module is used for supplementing data with a small amount of missing in the index pool by a smooth interpolation method and interpolating data with a large missing amount in the index pool according to a data proportion analysis mode;
the seasonal factor adjustment module is used for removing seasonal factors from the index data in the index pool by adopting a same-ratio adjustment method and an X-12-ARIMA seasonal adjustment method;
the index and GDP correlation analysis module is used for carrying out correlation analysis on the index data same-ratio growth rate and the GDP same-ratio growth rate in the index pool;
and the index normalization processing module is used for normalizing the same-ratio growth rate in the index pool.
Optionally, the determining unit includes a determining module and a calculating module:
a determination module for determining the weight of the power indicator and the economic indicator based on a regression coefficient generated by the regression;
the calculation module is used for carrying out assignment calculation on the power index and the economic index according to the weight to obtain an evaluation index, and the calculation formula is
Where β is the corresponding parameter vector.
A third aspect of the embodiments of the present application provides an electric power comprehensive evaluation device, including:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the processor specifically performs the following operations:
acquiring a power index and an economic index;
inputting the electric power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing;
performing regression on the GDP and the index data preprocessed in the index pool by using a Least absolute shrinkage and selection operator regression method;
and determining evaluation indexes corresponding to the power index and the economic index based on regression coefficients generated by the regression.
Optionally, the processor is further configured to perform the operations of any of the alternatives of the first aspect.
A fourth aspect of the embodiments of the present application provides a computer-readable storage medium for a power comprehensive evaluation method, including:
the computer-readable storage medium has stored thereon a program that executes the aforementioned power comprehensive evaluation method on a computer.
According to the technical scheme, the embodiment of the application has the following advantages: in the application, after the system acquires the power index and the economic index, the power index and the economic index are input into the index pool to be preprocessed, such as missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis, index normalization processing and the like, then the GDP and the index data preprocessed in the index pool are regressed by an LASSO regression method, finally, the evaluation indexes corresponding to the power index and the economic index are determined based on the regression coefficient generated by the regression, the method utilizes the GDP same-ratio growth rate to carry out supervised learning and high-dimensional data analysis, the variable selection and weighting are performed on the index, the variable with larger analysis on the GDP correlation is reserved and weighted higher, and the variables with small correlation with the GDP are abandoned, so that the comprehensive evaluation index data of the electric power obtained by fully utilizing the information contained in the GDP is more accurate, and the comprehensive evaluation of the electric power is realized.
Drawings
Fig. 1 is a schematic flow chart of an embodiment of a comprehensive power evaluation method in an embodiment of the present application;
fig. 2 is a schematic flow chart of another embodiment of the comprehensive power evaluation method in the embodiment of the present application;
fig. 3 is a schematic structural diagram of an embodiment of the comprehensive power evaluation device in the embodiment of the present application;
fig. 4 is a schematic structural diagram of another embodiment of the comprehensive power evaluation device in the embodiment of the present application.
Detailed Description
The embodiment of the application provides a method and a device for comprehensive power evaluation, which are used for performing supervised learning and high-dimensional data analysis through the GDP same-proportion growth rate, and fully utilizing information contained in the GDP to calculate a comprehensive power evaluation index more accurately.
In this embodiment, the power comprehensive evaluation method may be implemented in a system, a server, or a terminal, and is not specifically limited.
Referring to fig. 1, an embodiment of the present application is described by using a system as an example, and an embodiment of a power comprehensive evaluation method in the embodiment of the present application includes:
101. the system acquires an electric power index and an economic index;
in the embodiment, the system takes the power consumption index and the economic development index as the elements of comprehensive evaluation, and the power index and the economic index are introduced to solve the problem of incomplete evaluation index pool, wherein the definition of each level of index is performed according to the specificity of each subject.
For example, the power index may include a power supply amount, a power purchase amount, a power sale amount, a line loss rate, a network loss rate, a hydropower generation amount, a thermal power generation amount, a oil power generation amount, a coal power generation amount, a gas power generation amount, a photovoltaic power generation amount, an installed capacity, a total profit amount of a power company, a net profit of the power company, an economic added value of the power company, a net asset profitability of the power company, a national value added value of the power company, a total asset reward rate of the power company, a business income of the power company, an asset liability rate of the power company, a unit power supply cost, a unit power purchase cost, a first industry power consumption, a second industry power consumption, a third industry power consumption, a city and countryside residential power consumption, a central city residential side comprehensive voltage qualification rate, a rural residential side customer satisfaction rate, a medium voltage line fault rate, Average power failure times of power failure users, coverage rate of the intelligent electric meter, power consumption of key industries in the area and the like;
the economic indicators can comprise crude oil processing yield, ten nonferrous metals yield, soda ash yield, chemical fertilizer yield, ethylene yield, cement yield, crude steel yield, alumina yield, pig iron yield, coke yield, raw coal yield, real estate industry added value, social consumer goods retail gross, freight volume, import and export total values, town resident family per capita consumption expenditure, town resident family per capita food consumption expenditure, town resident family per capita living consumption expenditure, town resident family per capita education and entertainment service consumption expenditure, consumer confidence index, town resident family per capita income, commodity room sale price, resident consumption price classification index, industrial producer purchase price index, industrial producer delivery price index, fixed asset investment completion amount, inventory total amount, railway manufacturing finished product monthly shipment volume, customs export monthly RMB and the like. In addition, the names of the indexes at each level are not limited.
102. The system inputs the electric power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing;
the system selects the electric power index and the economic index to be input into the index pool and then preprocesses the index data in the index pool, wherein the preprocessing comprises missing value adjustment, namely, the smooth interpolation supplement is adopted for data with a small amount of missing to carry out proportional analysis on a large amount of missing data; the seasonal factor adjustment is to remove the influence of the seasonal factor in the index model; the index and GDP correlation analysis is to analyze the correlation between the geometric proportion growth rate and the geometric proportion growth rate of GDP; the index normalization process is based on normalizing the proportional growth rate by the positive index and the negative index.
103. The system carries out regression on the GDP and the index data preprocessed in the index pool by an LASSO regression method;
the system constructs a model through an LASSO regression method, and then performs variable selection, wherein the variable selection is realized by adjusting parameters in the model, specifically, the larger the parameter is, the greater the punishment strength on a linear model with more variables is, so that a model with less variables is obtained. And the determination of the model is adjusted by a cross validation method, for example, a parameter lambda is given, lambda is substituted into the model for cross validation, the lambda value with the minimum cross validation error is selected, and then the model is re-fitted by using all data according to the obtained optimal lambda value.
The expression of the LASSO model in this embodiment is as follows:
wherein,
the vector after the same ratio is taken for the GDP,
for the preprocessed index matrix, ω j The method is characterized in that the weight of a punishment item is carried out on a certain index, and if the weight of the index is larger and the frequency of selecting the index pool is more, the punishment weight to be given is smaller. After solving the model, the parameter beta is estimated j Variables corresponding to zero can be directly excluded from the composition of the index pool in the final index.
104. And determining evaluation indexes corresponding to the power index and the economic index based on a regression coefficient system generated by regression.
With the d indexes selected in the above steps and the corresponding parameter vector being β, the final index of the i-th evaluation individual at time t can be calculated by the following formula:
the system uses the calculation mode to enable the calculation process to be fast, the obtained power comprehensive evaluation index structure has the characteristics of continuity, orderliness and low variance, the problem that the variable system is complicated in index construction so as to weaken the contribution of indexes to the indexes is solved by using supervised learning and high-dimensional data analysis, and the GDP information in the index system is effectively extracted, so that the power economic index is better utilized to carry out power comprehensive evaluation.
Referring to fig. 2, in the embodiment of the present application, a system is described by way of example, and another embodiment of the method for comprehensively evaluating the index of the electric power in the embodiment of the present application includes:
201. the system acquires an electric power index and an economic index;
step 201 in this embodiment is similar to step 101 in the previous embodiment, and is not described herein again.
202. The system inputs the power index and the economic index into an index pool to adjust the index missing value;
the system supplements the data with a small amount of missing data in the index pool through a smooth interpolation method, and the formula is as follows:
wherein x is i,t-1 And x i,t+1 The values of the ith index of the quarter or month t-1 and the quarter or month t +1,
i.e. the value requiring insertion, i.e. the value of t quarter or month of the i-th index is missing, inserted
Instead of this.
For data with large data loss, the numerical value is interpolated according to the ratio analysis of the existing data and the national data and the ratio obtained by multiplying the national data by the average, and the formula is as follows:
n is the number of the total seasons,
is the value of the ith index k quarter, x, which is known i,k National number, x, of the ith index k quarter i,t Is the national value of the ith index quartet,
i.e. the value that needs to be inserted.
203. The system inputs the power index and the economic index into an index pool to adjust seasonal factors;
the system firstly removes seasonal factors by using a homonymy adjustment method, and if the homonymy adjustment method still has obvious seasonal effect, the system adopts an X-12-ARIMA seasonal adjustment method for processing, wherein the formula of the homonymy adjustment method is as follows:
x i,t is the value of the ith index quarterly t, x i,t-12 Is the last year current value of the index. Subtracting the same-period value of last year from all index values, and dividing the obtained difference by the same-period value of last year x i,t-12 The same-proportion growth rate of the index can be obtained. The resulting rate of commensurately increasing removes seasonal effects as well as dimension. The invention firstly adjusts the seasonal factors by a method of calculating the geometric growth rate, is convenient for calculation and can effectively remove the seasonal effect.
The formula of the X-12-ARIMA seasonal adjustment method is as follows:
Y t ＝T t ×S t ×I t
T t represents the trend of the time series, S t Representing the seasonality of a time series, I t Representing irregular disturbance factors, the X-12-ARIMA seasonal adjustment method decomposes the trend and the seasonality of the time series by a moving average algorithm and divides the original sequence by the seasonal effect to obtain a new time series result without the seasonality.
204. The system inputs the electric power index and the economic index into an index pool to carry out correlation analysis of the indexes and GDP;
the system carries out correlation analysis on the percentage growth rate and the GDP percentage growth rate, and selects the index with larger correlation and stable expression on the time dimension into an index system; the index positively correlated with the GDP proportional growth rate is marked as a positive index, and the index is marked as a reverse index if the index is not positive.
205. The system inputs the power index and the economic index into an index pool to carry out index normalization processing;
the system normalizes all the same-ratio growth rates for the convenience of the following weighting steps.
The normalization formula is as follows:
wherein, max (x) i ) Representing a sequence x i A maximum value of }; min (x) i ) Representative sequence { x i The minimum value of.
206. The system carries out regression on the GDP and the index data preprocessed in the index pool by an LASSO regression method;
step 206 in this embodiment is similar to step 103 in the previous embodiment, and is not described herein again.
207. The system determines the weight of the power index and the economic index based on the regression coefficient generated by regression;
the system takes a regression coefficient generated by regression in an index pool by the LASSO regression method as the weight of an index system, weights the indexes, and can perform assignment calculation according to the weight point power index and the economic index.
208. And the system performs assignment calculation on the power index and the economic index according to the weight to obtain an evaluation index.
And the system assigns and calculates the power index and the economic index according to the set weight to finally obtain a more accurate evaluation index. The invention can play a role of supervising learning by using the information contained in GDP through the LASSO regression method, thereby better performing variable selection and empowerment on high-dimensional power big data. The problem that the index contribution is weakened due to the fact that a variable system is redundant and complicated in index construction can be effectively solved through supervised learning and high-dimensional data analysis, information of GDP in an index system is effectively extracted, and therefore comprehensive power evaluation by using the power economy index is better achieved.
Referring to fig. 3, an embodiment of the comprehensive power evaluation device in the embodiment of the present application includes:
an acquisition unit 301 configured to acquire an electric power index and an economic index;
the execution unit 302 is configured to input the power index and the economic index into the index pool to execute a preprocessing operation, where the preprocessing operation includes adjusting an index missing value, adjusting seasonal factors contained in the index, performing correlation analysis on the index, and performing normalization processing on the index;
a regression unit 303, configured to perform regression on the GDP and the index data preprocessed in the index pool by using a LASSO regression method;
and the determining unit 304 is used for determining evaluation indexes corresponding to the power index and the economic index based on the regression coefficient generated by regression.
In this embodiment, the execution unit 302 includes a missing value adjustment module, a season factor adjustment module, an index and GDP correlation analysis module, and an index normalization processing module.
The missing value adjusting module 3021 is configured to supplement data that is missing in a small amount in the index pool by using a smooth interpolation method, and interpolate data that is missing in the index pool in a large amount according to a data proportion analysis manner.
And the season factor adjusting module 3022 is configured to remove the season factors from the data in the index pool by using a geometric adjustment method and an X-12-ARIMA season adjustment method.
And (4) index and GDP correlation analysis 3023 for performing correlation analysis on the data same-proportion growth rate and the GDP same-proportion growth rate in the index pool.
And the index normalization processing module 3024 is configured to normalize the same-ratio growth rate in the index pool.
The determination unit 304 in this embodiment includes a determination module 3041 and a calculation module 3042.
A determining module 3041, configured to determine weights of the power index and the economic index based on regression coefficients generated by the regression;
the calculating module 3042 is configured to perform assignment calculation on the power index and the economic index according to the weight to obtain an evaluation index.
In this embodiment, after the obtaining unit 301 obtains the power index and the economic index, the execution unit 302 inputs the power index and the economic index into the index pool to perform a preprocessing operation, where the missing value adjusting module 3021 supplements data with a small amount of missing data in the index pool by a smooth interpolation method and interpolates data with a large amount of missing data in the index pool according to a data proportion analysis manner; the season factor adjusting module 3022 removes season factors from the data in the index pool by using a geometric adjustment method and an X-12-ARIMA season adjustment method; the season factor adjusting module 3022 removes season factors from the data in the index pool by using a geometric adjustment method and an X-12-ARIMA season adjustment method; the index normalization processing module 3024 normalizes the increase rate of the same ratio in the index pool, the regression unit 303 regresses the GDP and the index data preprocessed in the index pool by the LASSO regression method, the determination module in the determination unit 304 determines the weight according to the regression coefficient generated by the regression, and the calculation module 3042 performs assignment calculation on the power index and the economic index according to the weight to obtain a more accurate evaluation index.
Referring to fig. 4, another embodiment of the comprehensive electric power evaluation device in the embodiment of the present application includes:
a processor 401, a memory 402, an input determination unit 403, a bus 404;
the processor 401 is connected to the memory 402, the input determination unit 403, and the bus 404;
acquiring an electric power index and an economic index;
inputting the power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing;
performing regression on the GDP and the index data preprocessed in the index pool by an LASSO regression method;
and determining evaluation indexes corresponding to the power index and the economic index based on regression coefficients generated by regression.
Optionally, the functions of the processor 401 correspond to the steps in the embodiments shown in fig. 1 to fig. 2, and are not described herein again.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Claims (8)
1. A power comprehensive evaluation method is characterized by comprising the following steps:
acquiring a power index and an economic index;
inputting the electric power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises missing value adjustment, seasonal factor adjustment, index and GDP correlation analysis and index normalization processing;
performing regression on the GDP and the index data preprocessed in the index pool by a Least absolute shrinkage and selection operator regression method;
and determining evaluation indexes corresponding to the power index and the economic index based on regression coefficients generated by the regression.
2. The method of claim 1, wherein the inputting the power metric and the economic metric into a pool of metrics to adjust a metric deficiency value comprises:
supplementing data with a small amount of loss in the index pool by a smooth interpolation method;
and interpolating the data with large missing amount in the index pool according to a data proportion analysis mode.
3. The method of claim 1, wherein the inputting the power indicator and the economic indicator into a pool of indicators adjusts an indicator seasonal factor comprising:
and removing seasonal factors from the index data in the index pool by adopting a geometric adjustment method and an X-12-ARIMA seasonal adjustment method.
4. The method of claim 1, wherein inputting the power index and the economic index into a pool of indices for index-to-GDP correlation analysis comprises:
and carrying out correlation analysis on the index geometric growth rate and the GDP geometric growth rate in the index pool.
5. The method of claim 4, wherein the inputting the power metric and the economic metric into a pool of metrics to normalize the metrics comprises:
normalizing the same-ratio increase rate of the indexes in the index pool by the normalization formula
Wherein, max (x) i ) Representing a sequence x i -maximum value of }; min (x) i ) Representative sequence { x } i The minimum value of.
6. The method of claim 1, wherein the LASSO regression is formulated as
Wherein
For the GDP comparable growth rate after the pretreatment,
is an index pool after the pretreatment,
beta is a regression coefficient vector omega for the index after pretreatment j And (4) penalty weight of each index.
7. The method of claim 1, wherein determining the evaluation index corresponding to the power indicator and the economic indicator based on the regression coefficients generated by the regression comprises:
determining weights of the power index and the economic index based on regression coefficients generated by the regression;
according to the weight, the power index and the economic index are assigned and calculated to obtain an evaluation index, and the calculation formula is
Where β is the corresponding parameter vector.
8. An electric power comprehensive evaluation device, comprising:
the acquisition unit is used for acquiring a power index and an economic index;
the execution unit is used for inputting the power index and the economic index into an index pool to execute preprocessing operation, wherein the preprocessing operation comprises the steps of adjusting an index missing value, adjusting seasonal factors contained in the index, performing correlation analysis on the index and performing normalization processing on the index;
the regression unit is used for performing regression on the GDP and the index data preprocessed in the index pool by using a LASSO regression method;
and the determining unit is used for determining the evaluation indexes corresponding to the power index and the economic index based on the regression coefficient generated by the regression.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210371107.1A CN114792196A (en) | 2022-04-11 | 2022-04-11 | Electric power comprehensive evaluation method and device |
| PCT/CN2022/115190 WO2023197502A1 (en) | 2022-04-11 | 2022-08-26 | Comprehensive power evaluation method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210371107.1A CN114792196A (en) | 2022-04-11 | 2022-04-11 | Electric power comprehensive evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114792196A true CN114792196A (en) | 2022-07-26 |
Family
ID=82462007
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210371107.1A Pending CN114792196A (en) | 2022-04-11 | 2022-04-11 | Electric power comprehensive evaluation method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114792196A (en) |
| WO (1) | WO2023197502A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023197502A1 (en) * | 2022-04-11 | 2023-10-19 | 广西电网有限责任公司 | Comprehensive power evaluation method and apparatus |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778574A (en) * | 2014-02-26 | 2014-05-07 | 广西电网公司 | Method for evaluating development coordination of island microgrid |
| CN104881718B (en) * | 2015-06-02 | 2018-06-12 | 国家电网公司 | Region electric power consumer confidence index construction method based on multiple dimensioned economic leading indicators |
| CN105913366A (en) * | 2016-04-08 | 2016-08-31 | 国网安徽省电力公司经济技术研究院 | Industrial electric power big data-based regional industry business climate index building method |
| CN106570657A (en) * | 2016-11-14 | 2017-04-19 | 国家电网公司 | Power grid evaluation index weight determining method |
| JP7114956B2 (en) * | 2018-03-15 | 2022-08-09 | 東京電力ホールディングス株式会社 | Power demand calculation device and program |
| CN109118121A (en) * | 2018-09-13 | 2019-01-01 | 中国电力科学研究院有限公司 | Go out clear mode evaluation method based on the electricity market for improving PageRank |
| CN113313533A (en) * | 2021-06-21 | 2021-08-27 | 国网信通亿力科技有限责任公司 | Method for performing macroscopic economy prediction and monitoring by using electric power data |
| CN114792196A (en) * | 2022-04-11 | 2022-07-26 | 广西电网有限责任公司 | Electric power comprehensive evaluation method and device |
-
2022
- 2022-04-11 CN CN202210371107.1A patent/CN114792196A/en active Pending
- 2022-08-26 WO PCT/CN2022/115190 patent/WO2023197502A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023197502A1 (en) * | 2022-04-11 | 2023-10-19 | 广西电网有限责任公司 | Comprehensive power evaluation method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023197502A1 (en) | 2023-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shokri Kahi et al. | How to evaluate sustainability of supply chains? A dynamic network DEA approach | |
| Gonzalez et al. | Forecasting power prices using a hybrid fundamental-econometric model | |
| CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
| Boileau | Trade in capital goods and the volatility of net exports and the terms of trade | |
| Botrić | Determinants of intra-industry trade between Western Balkans and EU-15: Evidence from bilateral data | |
| CN108537379A (en) | Adaptive variable weight combination load forecasting method and device | |
| CN114792196A (en) | Electric power comprehensive evaluation method and device | |
| Shirov et al. | Input-output macroeconomic model as the core of complex forecasting calculations | |
| Foroni et al. | Are low frequency macroeconomic variables important for high frequency electricity prices? | |
| Meira et al. | A novel reconciliation approach for hierarchical electricity consumption forecasting based on resistant regression | |
| CN113506173A (en) | Credit risk assessment method and related equipment thereof | |
| CN112241804A (en) | Macroscopic economy leading index construction method and system for energy power data | |
| Chauvet et al. | Predicting recessions in Brazil | |
| Fu | Measuring the trend real interest rate in a data-rich environment | |
| Li et al. | Is entropy an indicator of port traffic predictability? The evidence from Chinese ports | |
| Doh et al. | Tracking US GDP in real time | |
| Shi et al. | A study of sales forecasting in multinational retail companies: a feature extraction-machine learning-classification based forecasting framework | |
| Joshi et al. | Inflation model for India in the context of open economy | |
| Firdaus et al. | Modelling the Price Forecast for Construction Steel: A Case Study in EPC Company | |
| Verikios et al. | Structural change in the Australian electricity industry during the 1990s and the effect on household income distribution: A macro–micro approach | |
| Xu | Accounting for Revealed Comparative Advantage: Economic Complexity Redux | |
| Verikios et al. | Microeconomic reform and income distribution: the case of Australian ports and rail freight | |
| Thuy | Evaluating the Relationship between Consumer Price Index with Gasoline and Hog Prices in Vietnam | |
| Zhang et al. | Vegetable Price Forecasting Based on ARIMA Model and Random Forest Prediction | |
| Bereznyatskiy et al. | Macroeconomic Relationships for Russian Economic Regions |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220726 |
|
| RJ01 | Rejection of invention patent application after publication |