CN113590685B - Electric energy substitution potential mining method based on user information big data - Google Patents
Electric energy substitution potential mining method based on user information big data Download PDFInfo
- Publication number
- CN113590685B CN113590685B CN202110854622.0A CN202110854622A CN113590685B CN 113590685 B CN113590685 B CN 113590685B CN 202110854622 A CN202110854622 A CN 202110854622A CN 113590685 B CN113590685 B CN 113590685B
- Authority
- CN
- China
- Prior art keywords
- enterprise
- users
- user
- energy
- equipment
- 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.)
- Active
Links
- 238000006467 substitution reaction Methods 0.000 title claims abstract description 36
- 238000005065 mining Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 34
- 238000011835 investigation Methods 0.000 claims abstract description 23
- 230000000694 effects Effects 0.000 claims abstract description 14
- 238000006243 chemical reaction Methods 0.000 claims abstract description 12
- 230000009466 transformation Effects 0.000 claims description 39
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 10
- 239000003245 coal Substances 0.000 claims description 7
- 239000012636 effector Substances 0.000 claims description 7
- BTCSSZJGUNDROE-UHFFFAOYSA-N gamma-aminobutyric acid Chemical compound NCCCC(O)=O BTCSSZJGUNDROE-UHFFFAOYSA-N 0.000 claims description 7
- 239000003345 natural gas Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 4
- 239000000295 fuel oil Substances 0.000 claims description 3
- 239000007789 gas Substances 0.000 claims description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An electric energy substitution potential mining method based on user information big data belongs to the technical field of electric energy utilization efficiency and comprehensive energy. The invention aims to provide an electric energy substitution potential mining method based on user information big data, which is used for measuring important indexes of electric energy substitution potential of enterprise users by using an energy utilization structure matrix of the enterprise users to replace daily load curves of the enterprise. The invention comprises the following steps: and inputting information of users in the area where electric energy is needed to replace potential mining, calculating an energy utilization structure matrix of each user according to the energy utilization equipment efficiency of different industries and the equipment conversion capacity of each user, obtaining the energy utilization structure similarity between the overflow effect factors and each matrix, comprehensively evaluating according to the overflow effect factors and the energy utilization structure similarity of the users, and comprehensively ranking the users of the non-replaced enterprises. The method improves the accuracy of big data prediction, reduces the workload of actual investigation, and realizes the mining of the electric energy substitution potential based on the big data of the user information.
Description
Technical Field
The invention belongs to the technical field of electricity utilization efficiency and comprehensive energy.
Background
One type of method in electric energy replacement potential mining is to acquire electricity consumption data of an enterprise to be replaced by electric power through a power grid enterprise in a region where an enterprise user is located, compare a daily load curve of the enterprise to be replaced by electric power with a typical energy consumption curve of different industries, and screen out an enterprise with high daily load curve similarity as an enterprise with large electric energy replacement potential. Therefore, the method can mine the electric energy substitution potential of enterprise users to a certain extent.
Such methods of potential mining for electrical energy are in fact one process for finding businesses that can be structurally similar. In the process, the traditional method starts from the daily load curve, but in the actual operation process, due to the influences of the enterprise work, the production schedule and the like, the daily load curve of enterprises of the same type can be changed greatly at intervals. The reasonable selection of daily load curves of enterprises becomes a difficult problem to solve.
Disclosure of Invention
The invention aims to provide an electric energy substitution potential mining method based on user information big data, which is used for measuring important indexes of electric energy substitution potential of enterprise users by using an energy utilization structure matrix of the enterprise users to replace daily load curves of the enterprise.
The invention comprises the following steps:
step 1: inputting information of users in areas needing electric energy to replace potential mining, wherein the information comprises main energy utilization equipment, energy utilization forms of the equipment and equipment replacement willingness of the users;
step 2: establishing a sample library of a modified enterprise according to industries, and calculating coal-electricity coefficients k of different industries according to energy utilization equipment efficiency of different industries m Coefficient of gas-electric power k t Coefficient of oil-electricity k q ；
Step 21: dividing according to different enterprise user industries, and selecting typical energy utilization equipment in the industries as reference equipment;
step 22: setting the general coal efficiency eta of equipment 11 Natural gas efficiency eta 21 Diesel efficiency eta 31 Setting the corresponding coal efficiency eta of corresponding substituted electric equipment after electric energy substitution 12 Natural gas efficiency eta 22 Diesel efficiency eta 32 ；
Step 23: calculating various conversion coefficients according to the various fossil energy consumption efficiencies obtained in the step 22 and the corresponding substituted electric equipment efficiency after substitution, wherein:
step 3: calculating the energy usage structure matrix L of each user according to the equipment conversion capacity of the user i ；
Step 31: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，S mi ，S ti ，S qi ；
Step 32: calculating the energy utilization structure matrix L of the enterprise user i Wherein:
step 4: computing an overflow effector I based on per-user device conversion capacity and client willingness to device replacement fi ；
Step 41: selecting replacement willingness h of various equipment of enterprise user to be calculated i ，h i Taking 1 as the positive value, and taking 0 as the negative value;
step 42: the estimated annual average consumption energy of each equipment of enterprise users to be calculated is selected, and the coal-fired equipment is selected for calculation S mi Gas plant meter S ti Fuel oil equipment meter S qi ；
Step 43: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，h i ，S mi ，S ti ，S qi ；
Step 44: calculating the user overflow effect factor I of the enterprise fi Wherein:
∑I fi ＝1 (4)；
step 5: for the energy utilization structure matrix L in the step 4 i Calculating the energy utilization structural similarity D between the matrixes by using the Euclidean distance;
step 51: selecting the enterprise energy structure matrix L calculated in the step 4 i Energy utilization structure matrix integrated with successfully transformed users in sample library
Step 52: computing energy usage structure matrix L for selected enterprises i Energy utilization structure matrix integrated with successfully transformed users
Is a Euclidean distance d of (1), wherein:
step 53: calculating the structural similarity D of the energy according to the euclidean distance D calculated in step 52, wherein:
the execution sequence of the step 4 and the step 5 is executed randomly or simultaneously;
step 6: according to user overflow effect factor I fi Comprehensively evaluating the structural similarity D of the user and comprehensively ranking the users of the non-replaced enterprises;
step 61: enterprise user overflow effector I calculated according to step 34 fi Calculating a reformable index E of the enterprise user with the structural similarity D with the enterprise user i Wherein:
E i ＝I fi ·D (7)
step 62: from the enterprise user's reformable index E calculated in step 61 i According to reformable index E for all enterprise users to be reformulated i Ranking from big to small;
step 7: performing on-site investigation and verification on enterprise users with top comprehensive ranking, performing electric energy replacement transformation according to the ranking order, and calculating the comprehensive transformation success rate;
step 71: all enterprise users to be retrofitted obtained according to step 62 are based on the reformable index E i Ranking from large to small and taking 20% before each verification investigation when the number N of users of all enterprises to be modified is less than or equal to 100; when N is more than or equal to 101, 20 is taken for each verification investigation;
step 72: according to the actual investigation result, calculating the success rate lambda of the comprehensive transformation of the electric energy substitution
Step 8: comparing whether the comprehensive transformation success rate meets the transformation expectation rate or not by comparing the preset comprehensive success rate;
step 81: comparing the expected lambda according to the electric energy substitution comprehensive transformation success rate lambda calculated in the step 72 E The method comprises the steps of carrying out a first treatment on the surface of the If lambda < lambda E At this time, the criteria obtained by the modified enterprises in the sample library are considered to be not universal, and the samples in the sample library need to be adjustedSelecting an electric energy replacement failure enterprise according to the actual investigation result, selecting the energy utilization structure similarity of a failure sample, calculating the energy utilization structure similarity D between the failure sample and the failure sample in a sample library, selecting and screening out samples with the similarity D more than or equal to 0.75, and if the number n of the samples in the sample pool is less than or equal to 20 after the samples are screened out, reducing the number of the screened out samples to enable the sample pool to keep the minimum number of the samples to be 20; if lambda is greater than or equal to lambda E Then the criteria obtained by the modified enterprises in the sample library are considered to have universality; adding a successful sample according to the investigation result;
step 9: judging whether the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate in the circulation process, stopping the circulation if the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate, considering that successful samples in the sample library are no longer referenced, and ending the judgment;
step 91: performing a loop screening according to step 73 when a loop occurs twice λ < λ E Then the successful cases in the sample pool are considered to be no longer referential, at which point the algorithm is aborted in advance.
The invention starts from the equipment information of the user, and the electric energy substitution potential of the industrial user is measured through the equipment data, so that the influence of various uncertainty factors caused by selecting a daily load curve is avoided. The potential for power replacement for enterprise users can be better exploited. And (3) potential mining of electric energy substitution of energy utilization equipment of each user under the condition of possessing big data of the user. And correcting the big data prediction error by big data prediction and user electric energy substitution potential scoring and matching with actual user investigation. The accuracy of big data prediction is improved, the workload of actual investigation is reduced, and the electric energy substitution potential mining based on the user information big data is realized.
Drawings
FIG. 1 is a process flow diagram of the present invention.
Detailed Description
In the process of mining the potential of electric energy substitution for enterprise users, under the condition of higher requirements on the capacity and accuracy of potential mining, a good electric energy substitution potential mining algorithm must simultaneously consider the mining accuracy of potential users, the mining of the potential of users and the emphasis of user substitution. The daily load curve of the enterprise is replaced by the energy utilization structure matrix of the enterprise user, so that the daily load curve becomes an important index for measuring the electric energy replacement potential of the enterprise user. From the equipment information of the user, the electric energy substitution potential of the industrial user is measured through the equipment data, and the influence of various uncertainty factors caused by the selection of a daily load curve is avoided. The mining accuracy of potential users is improved, the mining of the potential amount of the users is predicted, and the emphasis of user substitution is realized. Thus solving some problems existing in the potential excavation of electric energy replacement.
The invention comprises the following steps:
step 1: and inputting information of users in the area where electric energy is needed to replace potential mining, wherein the information comprises main energy utilization equipment, energy utilization form of the equipment and willingness to replace the equipment of the users.
Step 2: establishing a sample library of a modified enterprise according to industries, and calculating coal-electricity coefficients k of different industries according to energy utilization equipment efficiency of different industries m Coefficient of gas-electric power k t Coefficient of oil-electricity k q 。
Step 3: calculating the energy usage structure matrix L of each user according to the equipment conversion capacity of the user i 。
Step 4: computing an overflow effector I based on per-user device conversion capacity and client willingness to device replacement fi 。
Step 5: for the energy utilization structure matrix L in the step 4 i The euclidean distance is used to calculate the structural similarity D of energy between the matrices.
Step 6: according to user overflow effect factor I fi And comprehensively evaluating the structural similarity D and comprehensively ranking the users of the non-replaced enterprises.
Step 7: and (5) on-site investigation and verification of enterprise users with top comprehensive ranking, carrying out electric energy replacement transformation according to the ranking order, and calculating the comprehensive transformation success rate.
Step 8: and comparing whether the comprehensive transformation success rate meets the transformation expectation rate or not by comparing the preset comprehensive success rate.
Step 9: judging whether the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate in the circulation process, stopping circulation if the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate, considering that successful samples in the sample library are no longer referenced, and ending the judgment.
The present invention is described in detail below:
step 1: and inputting information of users in the area needing electric energy to replace potential mining, wherein the information comprises main energy utilization equipment of the users, energy utilization forms of the equipment and willingness of equipment replacement to form an operable Excel table.
Step 2: establishing a sample library of a modified enterprise according to industries, and calculating coal-electricity coefficients k of different industries according to energy utilization equipment efficiency of different industries m Coefficient of gas-electric power k t Coefficient of oil-electricity k q The specific steps of (a) are as follows:
step 21: dividing according to different enterprise user industries, and selecting typical energy utilization equipment in the industries as reference equipment.
Step 22: setting the general coal efficiency eta of equipment 11 Natural gas efficiency eta 21 Diesel efficiency eta 31 Setting the corresponding coal efficiency eta of corresponding substituted electric equipment after electric energy substitution 12 Natural gas efficiency eta 22 Diesel efficiency eta 32 。
Step 23: calculating various conversion coefficients according to the various fossil energy consumption efficiencies obtained in the step 22 and the corresponding substituted electric equipment efficiency after substitution, wherein:
step 3: calculating the energy usage structure matrix L of each user according to the equipment conversion capacity of the user i The specific steps of (a) are as follows: step 31: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，S mi ，S ti ，S qi 。
Step 32: calculating the energy utilization structure matrix L of the enterprise user i Wherein:
step 4: computing an overflow effector I based on per-user device conversion capacity and client willingness to device replacement fi The specific steps of (a) are as follows:
step 41: selecting replacement willingness h of various equipment of enterprise user to be calculated i ，h i Taking a value of 1, and if not, 0.
Step 42: the estimated annual average consumption energy of each equipment of enterprise users to be calculated is selected, and the coal-fired equipment is selected for calculation S mi Gas plant meter S ti Fuel oil equipment meter S qi 。
Step 43: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，h i ，S mi ，S ti ，S qi 。
Step 44: calculating the user overflow effect factor I of the enterprise fi Wherein:
∑I fi ＝1 (4)
step 5: for the energy utilization structure matrix L in the step 4 i The specific steps of calculating the energy-utilization structural similarity D between the matrixes by using the Euclidean distance are as follows:
step 51: selecting the enterprise energy structure matrix L calculated in the step 4 i Energy utilization structure matrix integrated with successfully transformed users in sample library
Step 52: computing energy usage structure matrix L for selected enterprises i Energy utilization structure matrix integrated with successfully transformed users
Is a Euclidean distance d of (1), wherein:
step 53: calculating the structural similarity D of the energy according to the euclidean distance D calculated in step 52, wherein:
the execution sequence of the step 4 and the step 5 is arbitrary or simultaneous.
Step 6: according to user overflow effect factor I fi The specific steps of comprehensively evaluating the structural similarity D and comprehensively ranking the users of the non-replaced enterprises are as follows:
step 61: enterprise user overflow effector I calculated according to step 34 fi Calculating a reformable index E of the enterprise user with the structural similarity D with the enterprise user i Wherein:
E i ＝I fi ·D (7)
step 62: from the enterprise user's reformable index E calculated in step 61 i According to reformable index E for all enterprise users to be reformulated i Ranking from big to small.
Step 7: the method comprises the specific steps of performing on-site investigation and verification on enterprise users with top comprehensive ranking, performing electric energy replacement transformation according to ranking order, and calculating comprehensive transformation success rate:
step 71: all enterprise users to be retrofitted obtained according to step 62 are based on the reformable index E i Ranking from large to small and the number of users N of all enterprises to be remodeled, when N is less than or equal to 100, taking the first 20% of each verification investigation. When N is more than or equal to 101, 20 are taken for each verification investigation.
Step 72: according to the actual investigation result, calculating the success rate lambda of the comprehensive transformation of the electric energy substitution
Step 8: the specific steps of comparing whether the comprehensive transformation success rate meets the transformation expected rate or not by comparing the preset comprehensive success rate are as follows:
step 81: comparing the expected lambda according to the electric energy substitution comprehensive transformation success rate lambda calculated in the step 72 E . If lambda < lambda E At this time, the criterion obtained by the modified enterprises in the sample library is considered to have no universality, the samples in the sample library need to be adjusted, the actual investigation result of the time is selected to select electric energy to replace the failed enterprises, the energy utilization structural similarity of the failed samples is selected, the energy utilization structural similarity D between the failed samples in the sample library and the failed samples is calculated, the samples with the similarity D being more than or equal to 0.75 are selected and screened out, if the number n of the samples in the sample pool is less than or equal to 20 after the samples are screened out, the number of the screened samples is reduced, and the sample pool keeps the minimum number of the samples 20. If lambda is greater than or equal to lambda E The criteria obtained by the modified enterprise in the sample library are considered generic at this time. And adding a successful sample according to the investigation result.
Step 9: judging whether the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate in the circulation process, stopping the circulation if the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate, and considering that successful samples in a sample library are no longer referenced, wherein the specific steps of ending the judgment are as follows: step 91: performing a loop screening according to step 73 when a loop occurs twice λ < λ E Then the successful cases in the sample pool are considered to be no longer referential, at which point the algorithm is aborted in advance.
Simulation test:
the data of all enterprises are collected and arranged through the data of 8 enterprises to be replaced by electric energy in an industry in a certain area, the energy utilization equipment and equipment replacement willingness of 4 enterprises in the industry which successfully performs electric energy replacement in the area, and the results are shown in the tables 1 and 2.
Meter 1 8 household electric energy to replace enterprise data
Meter 23 has completed replacing enterprise data with electrical energy
And (3) sorting the completed electric energy of the table 2 to replace enterprise data to obtain a sample library of the modified enterprise, wherein the library comprises energy devices with enterprise numbers of 9, 10 and 11 and device replacement willingness information.
Parameter calculation and comparison standard
And replacing enterprise data with the obtained electric energy to be obtained according to the table 1 and a sample library of the modified enterprise.
According to the general transformation of the industry of the region, selecting industry energy to replace typical electric appliances of the same type, and calculating the power consumption increment before and after replacing the electric energy of a certain device according to an equal energy criterion. Gauge k m Is the coal electric coefficient, k t Is the gas-electric coefficient, k q Is the oil-electricity coefficient. The overflow effect factors of all the to-be-electric energy substitution enterprises in the table 1 are calculated as shown in the table 3.
TABLE 3 Overflow Effect factors for all to-be-electric energy replacement enterprises
Wherein:
M＝(S m11 +S m12 +S m23 +S m31 +S m32 +S m44 +S m51 +S m53 +S m63 +S m71 )·k m +(S q11 +S q21 +S q31 +S q41 +S q51 +S q61 +S q71 )·k q +S t32 ·k t
then calculate the energy utilization structure matrix of each enterprise to be replaced by electric energy as shown in Table 4
Table 4 energy usage structure matrix for enterprises to be replaced with electric energy
Then calculating the energy structure matrix for the marker post in the sample library of the transformed enterprise
Wherein, the liquid crystal display device comprises a liquid crystal display device,
the similarity of the energy utilization structure matrix of each enterprise and the sample library marker post is calculated respectively, and the result is shown in Table 5
And multiplying the overflow benefit factors of all enterprises by the similarity of the energy utilization structure matrix, and sequencing the overflow benefit factors from large to small according to the obtained result which is the user remodelling degree E. The result is that the higher is the enterprise user who prefers to perform the replacement of the electrical energy, and the overflow effect factor represents the electrical energy replacement potential of the enterprise.
Sample library update replacement
According to the calculated user reformability E of each enterprise, investigating the enterprise with the priority enterprise number 3,1,5 in the field, obtaining that the enterprise users with the numbers 3 and 5 accept the replacement, when the enterprise user with the number 1 does not accept the replacement, newly adding the enterprise data with the numbers 3 and 5 into a sample library of the reformed enterprise, and calculating the comprehensive success reform rate lambda, wherein
Meets the minimum requirements. And reorder all remaining unmodified enterprises based on the new sample libraries of modified enterprises. And judging that other enterprises are not suitable for performing electric energy replacing activities until all enterprises are screened or algorithms appear.
Analysis of results
The invention can find out the priority enterprise with large comprehensive replacement potential from the enterprise users to be replaced by the electric energy, thereby greatly helping to find valuable electric energy replacement modification users in the electric energy replacement activities.
Conclusion(s)
The daily load curve of the enterprise is replaced by the energy utilization structure matrix of the enterprise user, so that the daily load curve becomes an important index for measuring the electric energy replacement potential of the enterprise user. From the equipment information of the user, the electric energy substitution potential of the industrial user is measured through the equipment data, and the influence of various uncertainty factors caused by the selection of a daily load curve is avoided. The mining accuracy of potential users is improved, the mining of the potential amount of the users is predicted, and the emphasis of user substitution is realized. Thus solving some problems existing in the potential excavation of electric energy replacement. The validity of the method is verified by carrying out visit investigation on actual enterprise users in the actual area. The accuracy of screening the electric energy substitution users is remarkably improved, and great convenience is provided for the whole electric energy substitution work.
Claims (1)
1. The electric energy substitution potential mining method based on the user information big data is characterized by comprising the following steps of:
step 1: inputting information of users in areas needing electric energy to replace potential mining, wherein the information comprises main energy utilization equipment, energy utilization forms of the equipment and equipment replacement willingness of the users;
step 2: establishing a sample library of a modified enterprise according to industries, and calculating coal-electricity coefficients k of different industries according to energy utilization equipment efficiency of different industries m Coefficient of gas-electric power k t Coefficient of oil-electricity k q ；
Step 21: dividing according to different enterprise user industries, and selecting typical energy utilization equipment in the industries as reference equipment;
step 22: setting the general coal efficiency eta of equipment 11 Natural gas efficiency eta 21 Diesel efficiency eta 31 Setting the corresponding coal efficiency eta of corresponding substituted electric equipment after electric energy substitution 12 Natural gas efficiency eta 22 Diesel efficiency eta 32 ；
Step 23: calculating various conversion coefficients according to the various fossil energy consumption efficiencies obtained in the step 22 and the corresponding substituted electric equipment efficiency after substitution, wherein:
step 3: calculating the energy usage structure matrix L of each user according to the equipment conversion capacity of the user i ；
Step 31: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，S mi ，S ti ，S qi ；
Step 32: calculating the energy utilization structure matrix L of the enterprise user i Wherein:
step 4: computing an overflow effector I based on per-user device conversion capacity and client willingness to device replacement fi ；
Step 41: selecting replacement willingness h of various equipment of enterprise user to be calculated i ，h i Taking 1 as the positive value, and taking 0 as the negative value;
step 42: the estimated annual average consumption energy of each equipment of enterprise users to be calculated is selected, and the coal-fired equipment is selected for calculation S mi Gas plant meter S ti Fuel oil equipment meter S qi ；
Step 43: selecting the coefficients of enterprise users to be calculated to comprise k m ，k t ，k q ，h i ，S mi ，S ti ，S qi ；
Step 44: calculating the user overflow effect factor I of the enterprise fi Wherein:
∑I fi ＝1 (4)；
step 5: for the energy utilization structure matrix L in the step 4 i Calculating the energy utilization structural similarity D between the matrixes by using the Euclidean distance;
step 51: selecting the enterprise energy structure matrix L calculated in the step 4 i Energy utilization structure matrix integrated with successfully transformed users in sample library
Step 52: computing energy usage structure matrix L for selected enterprises i Energy utilization structure matrix integrated with successfully transformed users
Is a Euclidean distance d ofIn (a):
step 53: calculating the structural similarity D of the energy according to the euclidean distance D calculated in step 52, wherein:
the execution sequence of the step 4 and the step 5 is executed randomly or simultaneously;
step 6: according to user overflow effect factor I fi Comprehensively evaluating the structural similarity D of the user and comprehensively ranking the users of the non-replaced enterprises;
step 61: enterprise user overflow effector I calculated according to step 34 fi Calculating a reformable index E of the enterprise user with the structural similarity D with the enterprise user i Wherein:
E i ＝I fi ·D (7)
step 62: from the enterprise user's reformable index E calculated in step 61 i According to reformable index E for all enterprise users to be reformulated i Ranking from big to small;
step 7: performing on-site investigation and verification on enterprise users with top comprehensive ranking, performing electric energy replacement transformation according to the ranking order, and calculating the comprehensive transformation success rate;
step 71: all enterprise users to be retrofitted obtained according to step 62 are based on the reformable index E i Ranking from large to small and taking 20% before each verification investigation when the number N of users of all enterprises to be modified is less than or equal to 100; when N is more than or equal to 101, 20 is taken for each verification investigation;
step 72: according to the actual investigation result, calculating the success rate lambda of the comprehensive transformation of the electric energy substitution
Step 8: comparing whether the comprehensive transformation success rate meets the transformation expectation rate or not by comparing the preset comprehensive success rate;
step 81: comparing the expected lambda according to the electric energy substitution comprehensive transformation success rate lambda calculated in the step 72 E The method comprises the steps of carrying out a first treatment on the surface of the If lambda < lambda E At the moment, the criterion obtained by the modified enterprises in the sample library is considered to have no universality, the samples in the sample library are required to be adjusted, the actual investigation result of the time is selected to select electric energy to replace a failed enterprise, the energy utilization structural similarity of the failed samples is selected, the energy utilization structural similarity D between the failed samples in the sample library and the failed samples is calculated, the samples with the similarity D being more than or equal to 0.75 are selected and screened out, if the number n of the samples in the sample pool is less than or equal to 20 after the samples are screened out, the number of the screened out samples is reduced, and the sample pool keeps the minimum number of the samples to 20; if lambda is greater than or equal to lambda E Then the criteria obtained by the modified enterprises in the sample library are considered to have universality;
adding a successful sample according to the investigation result;
step 9: judging whether the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate in the circulation process, stopping the circulation if the continuous two-time comprehensive successful transformation rate is lower than the transformation expected rate, considering that successful samples in the sample library are no longer referenced, and ending the judgment;
step 91: performing a loop screening according to step 73 when a loop occurs twice λ < λ E Then the successful cases in the sample pool are considered to be no longer referential, at which point the algorithm is aborted in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854622.0A CN113590685B (en) | 2021-07-28 | 2021-07-28 | Electric energy substitution potential mining method based on user information big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110854622.0A CN113590685B (en) | 2021-07-28 | 2021-07-28 | Electric energy substitution potential mining method based on user information big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113590685A CN113590685A (en) | 2021-11-02 |
| CN113590685B true CN113590685B (en) | 2023-04-28 |
Family
ID=78250847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110854622.0A Active CN113590685B (en) | 2021-07-28 | 2021-07-28 | Electric energy substitution potential mining method based on user information big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113590685B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022646A (en) * | 2016-06-08 | 2016-10-12 | 国网上海市电力公司 | Electric power user information data analysis system and analysis method |
| CN108764584A (en) * | 2018-06-05 | 2018-11-06 | 国网浙江省电力有限公司 | A kind of enterprise electrical energy replacement potential evaluation method |
| CN109461025A (en) * | 2018-10-23 | 2019-03-12 | 国网湖南省电力公司节能管理分公司 | A kind of electric energy substitution potential customers' prediction technique based on machine learning |
| CN110135745A (en) * | 2019-05-21 | 2019-08-16 | 昆明理工大学 | A kind of regional electric energy substitution comprehensive potential evaluation method based on combining weights |
-
2021
- 2021-07-28 CN CN202110854622.0A patent/CN113590685B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022646A (en) * | 2016-06-08 | 2016-10-12 | 国网上海市电力公司 | Electric power user information data analysis system and analysis method |
| CN108764584A (en) * | 2018-06-05 | 2018-11-06 | 国网浙江省电力有限公司 | A kind of enterprise electrical energy replacement potential evaluation method |
| CN109461025A (en) * | 2018-10-23 | 2019-03-12 | 国网湖南省电力公司节能管理分公司 | A kind of electric energy substitution potential customers' prediction technique based on machine learning |
| CN110135745A (en) * | 2019-05-21 | 2019-08-16 | 昆明理工大学 | A kind of regional electric energy substitution comprehensive potential evaluation method based on combining weights |
Non-Patent Citations (1)
| Title |
|---|
| 涂莹 ; 刘强 ; 王庆娟 ; 陈烨洪 ; .基于协同过滤算法的电能替代潜力用户挖掘模型研究.电力信息与通信技术.2017,(12),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113590685A (en) | 2021-11-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Benson et al. | On improvement rates for renewable energy technologies: Solar PV, wind turbines, capacitors, and batteries | |
| Zhi et al. | Research on the Pearson correlation coefficient evaluation method of analog signal in the process of unit peak load regulation | |
| CN109448788B (en) | On-line analysis platform architecture of microbiology of genomics and bioinformatics | |
| CN107832927B (en) | 10kV line variable relation evaluation method based on grey correlation analysis method | |
| CN112749849A (en) | Integrated learning online prediction method for key parameters of continuous catalytic reforming process | |
| Adewuyi et al. | Environmental pollution, energy import, and economic growth: evidence of sustainable growth in South Africa and Nigeria | |
| Lenz et al. | Total-factor energy efficiency in EU: Do environmental impacts matter? | |
| CN115907173A (en) | Carbon peak value prediction method, system and device based on STIRPAT model | |
| CN113590685B (en) | Electric energy substitution potential mining method based on user information big data | |
| CN111737249A (en) | Abnormal data detection method and device based on Lasso algorithm | |
| CN111549193A (en) | Furnace changing method, furnace changing device and control equipment for multiple blast furnace hot blast stoves | |
| Wu et al. | Forecasting natural gas production and consumption using grey model with latent information function: The cases of China and USA | |
| Su et al. | Temporal validation of life cycle greenhouse gas emissions of energy systems in China | |
| CN116305702A (en) | Method and system for analyzing data fluctuation shale gas well yield experience decreasing curve | |
| CN105787599A (en) | Methyl alcohol future price prediction method | |
| Meilinger | Application of Stochastic Optimization Techniques to the Unit Commitment Problem--A Review | |
| Shu et al. | A Novel EGM (1, 1) Model Based On Kernel And Degree Of Greyness And Its Application On Smog Prediction. | |
| Penkuhn | Further development and application of advanced exergy-based methods | |
| Khalid et al. | Estimation of substitution possibilities between hydroelectricity and classical factor inputs for Pakistan’s economy | |
| Staňková et al. | LEVEL OF TECHNICAL EFFICIENCY OF THE CONSTRUCTION SECTOR IN EU COUNTRIES. | |
| CN116629622A (en) | Prediction method for coal enterprise yield | |
| Li et al. | An Optimized Multivariate Grey Bernoulli Model for Forecasting Fossil Energy Consumption in China. | |
| Zhang et al. | Economic impact analysis of the science and technology investment's contribution to the regional GDPs in the northern central cities of Anhui province, China | |
| TSODIKOV | CHAPTER EIGHTEEN ANALYSIS OF AN INFEASIBLE SOLUTION TO THE REFINERY PLANNING PROBLEM | |
| Li et al. | Application of improved gm (1, n) models in annual electricity demand forecasting |
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 |