CN112686491A - Enterprise power data analysis method based on power consumption behavior - Google Patents
Enterprise power data analysis method based on power consumption behavior Download PDFInfo
- Publication number
- CN112686491A CN112686491A CN202011186999.5A CN202011186999A CN112686491A CN 112686491 A CN112686491 A CN 112686491A CN 202011186999 A CN202011186999 A CN 202011186999A CN 112686491 A CN112686491 A CN 112686491A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- power
- power consumption
- analysis
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The invention discloses an enterprise electric power data analysis method based on electric power consumption behaviors, which overcomes the defects of the prior art and comprises the following steps: step 1, collecting basic information data, power consumption data, electric power archive data and industrial internet data of an enterprise, and performing data fusion on all the data; step 2, selecting characteristic quantities of the fusion data, and carrying out K-means + + clustering analysis on the characteristic quantities to complete energy utilization characteristic clustering analysis on enterprises; step 3, evaluating the energy consumption level of the enterprise by a Topsis evaluation method; step 4, performing table and image storage on the electric power data of the enterprise according to the energy consumption characteristics of the enterprise, the energy consumption level of the enterprise and the combination of the basic information data, the power consumption data, the electric power archive data and the industrial internet data of the enterprise; and 5, searching the power data of the enterprise by related personnel through the characteristic expression of the power data, and performing subsequent analysis and research through the search result.
Description
Technical Field
The invention relates to the technical field of power data analysis, in particular to an enterprise power data analysis method based on power consumption behaviors.
Background
With the development of economy, the analysis of power data of enterprises becomes very important, on one hand, government management departments need to master the current situation of macroscopic economy and the development trend of industry in time, integrate and analyze the upstream and downstream industrial chains, and scientifically make an industry development planning policy; under the emergency condition, the information of a production enterprise with the material production qualification needs to be timely and efficiently acquired, and the information statistics and production allocation efficiency are improved; on the other hand, enterprises need to improve the acute smell of wind direction in the insight industry, scientifically avoid investment risks and further release development kinetic energy; the upstream and downstream of a production chain and the market supply and demand conditions of the industry need to be known, and enterprise production scheduling and production expansion are optimized; the comprehensive energy consumption level in the industry needs to be known, the industrial optimization and upgrade are promoted, and the enterprise competitiveness is improved. However, while the existing enterprise power data services are managed internally, external value-added services are actively excavated, and government management departments or enterprises are supported to achieve the effect of comprehensive, accurate and comprehensive analysis through the power data.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides an enterprise power data analysis method based on power utilization behaviors.
The purpose of the invention is realized by the following technical scheme:
an enterprise power data analysis method based on power utilization behaviors comprises the following steps:
step 1, collecting basic information data, power consumption data, electric power archive data and industrial internet data of an enterprise, and performing data fusion on all the data;
step 2, selecting characteristic quantities of the fusion data, and carrying out K-means + + clustering analysis on the characteristic quantities to complete energy utilization characteristic clustering analysis on enterprises;
step 3, evaluating the energy consumption level of the enterprise by a Topsis evaluation method;
step 4, performing table and image storage on the electric power data of the enterprise according to the energy consumption characteristics of the enterprise, the energy consumption level of the enterprise and the combination of the basic information data, the electricity consumption data, the electric power archive data and the industrial internet data of the enterprise;
and 5, searching the power data of the enterprise by related personnel through the characteristic expression of the power data, and performing subsequent analysis and research through the search result.
In the scheme, firstly, basic information, power related information and productivity information of the industrial internet enterprise are collected in a multidimensional and omnibearing manner, and data fusion is carried out because the collected information is multidimensional; by grading the energy consumption characteristics of the enterprise and evaluating the energy consumption level of the enterprise, the electric power data of the enterprise can be deeply and visually known, and a powerful support is provided for the follow-up government management departments and the enterprise to research.
As a preferable scheme, in the step 5, the subsequent analysis and research includes industrial chain integration analysis, and the specific method includes:
step a, using power consumption data of upstream and downstream enterprises as discrete data, constructing a daily power consumption curve with an abscissa parameter as date and an ordinate parameter as power consumption, wherein the power consumption curve of the upstream enterprise is m and the power consumption curve of the downstream enterprise is n;
b, performing curve similarity analysis on the power consumption curve m and the power consumption curve n, and calculating the similarity;
and c, if the similarity index is larger than or equal to the set threshold, judging that the power utilization trends of the upstream and downstream enterprises are similar, the productivity is matched, and if the similarity index is smaller than the set threshold, judging that the power utilization trends of the upstream and downstream enterprises are not similar, and sending an abnormal alarm.
As a preferable scheme, in the step c, when the similarity index is smaller than the set threshold, it is determined that the power consumption trends of the upstream and downstream enterprises are not similar, the power consumption trends of the upstream and downstream enterprises are analyzed, if the upstream power consumption trend increases and the downstream power consumption trend declines, a suggestion that the upstream needs to reduce the capacity is given, and if the upstream power consumption trend decreases and the downstream power consumption trend increases, a suggestion that the upstream needs to increase the capacity is given.
As a preferable scheme, the step 1 further includes a step of data cleansing after data fusion, and the data cleansing includes the following sub-steps:
substep 1, calling a data cleaning model;
the substep 2, detecting the fusion data by the data cleaning model, and detecting error data in the fusion data;
and 3, generating a repair suggestion by the data cleaning model, and manually completing the repair of the error data by related personnel according to the repair suggestion or completing the repair of the error data by the data cleaning model according to the repair suggestion.
Preferably, the error data detected by the data cleansing model on the data set comprises one or more of the following: the repeated values, the alias values, the missing values and the abnormal values correspond to a data cleaning model for each error data.
During the process of data acquisition and fusion, data errors such as repeated values, aliases, missing values and abnormal values are inevitably generated. Data errors may affect the results of data visualization analysis, and thus, efficient data visualization analysis is necessarily not isolated from high quality and highly available data sets. The invention mainly carries out data cleaning facing to data visualization analysis, and the core is to clean partial data subsets which greatly affect data analysis results, reduce the cost of data cleaning and improve the efficiency of data cleaning and data preparation stages.
As a preferred scheme, the data cleaning model corresponding to the alias error data is a connection algorithm matching model, the connection algorithm matching model adopts a fuzzy matching algorithm to search synonyms possibly existing in any two alias data, and if the similarity is greater than a set threshold, the two alias data are the same entity concept, so that the data preparation layer corrects one data name as correct data and the other alias error data as correct data to complete alias error data cleaning.
As a preferable scheme, the step 2 specifically comprises: the feature quantities of the fused data comprise monthly power consumption, power consumption increasing trend, load variation, monthly electricity charge and packaging capacity, three analysis dimensions of the electricity change condition of the enterprise within a plurality of months are formed according to the monthly power consumption, the power consumption increasing trend and the load variation, K-means + + cluster analysis is carried out on the electricity change condition, and the energy consumption feature grading of the enterprise is completed.
As a preferable scheme, the step 3 specifically comprises the following substeps:
a substep a, extracting and calculating enterprise energy consumption indexes;
b, scoring the production capacity of the enterprise by a Topsis comprehensive evaluation algorithm;
and step c, visualizing the classification result by using a matplotlib module, and counting the number of the enterprises with different power utilization characteristics in the enterprise sections according to the enterprise score result.
The principle of the Topsis comprehensive evaluation method is to judge the distance between each sample and an ideal solution on the premise of defining the ideal solution, so as to judge the sequencing among a plurality of samples. The ideal solution generally comprises a positive ideal solution and a negative ideal solution, and the distance between the sample and the ideal solution is reflected by different expression modes of the designed distance.
As a preferable scheme, in the substep a, normalization processing is performed on the data extracted by the enterprise energy consumption index, and the normalization processing method is min-max normalization or z-score normalization.
The invention has the beneficial effects that: the enterprise power data analysis method based on the power utilization behaviors can effectively help government management departments or enterprises to judge power utilization trends and development situations of enterprises and industries through the power utilization behaviors by deep research and analysis of the power utilization data of the enterprises, and is convenient for making corresponding measures to improve productivity. The invention has strong practicability and is easy to realize.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of the industrial chain integration analysis of the present invention;
FIG. 3 is a data cleansing flow diagram of the present invention;
FIG. 4 is a flow chart of the Topsis evaluation method of the present invention;
FIG. 5 is a comparison graph of enterprise similarity curves.
Detailed Description
The invention is further described below with reference to the figures and examples.
Example (b): an enterprise power data analysis method based on power consumption behaviors is disclosed, and as shown in fig. 1, the method comprises the following steps:
step 1, collecting basic information data, power consumption data, electric power archive data and industrial internet data of an enterprise, and performing data fusion on all the data;
step 2, selecting characteristic quantities of the fusion data, and carrying out K-means + + clustering analysis on the characteristic quantities to complete energy utilization characteristic clustering analysis on enterprises;
step 3, evaluating the energy consumption level of the enterprise by a Topsis evaluation method;
step 4, performing table and image storage on the electric power data of the enterprise according to the energy consumption characteristics of the enterprise, the energy consumption level of the enterprise and the combination of the basic information data, the electricity consumption data, the electric power archive data and the industrial internet data of the enterprise;
and 5, searching the power data of the enterprise by related personnel through the characteristic expression of the power data, and performing subsequent analysis and research through the search result.
In the scheme, firstly, basic information, power related information and productivity information of the industrial internet enterprise are collected in a multidimensional and omnibearing manner, and data fusion is carried out because the collected information is multidimensional; by grading the energy consumption characteristics of the enterprise and evaluating the energy consumption level of the enterprise, the electric power data of the enterprise can be deeply and visually known, and a powerful support is provided for the follow-up government management departments and the enterprise to research.
In step 5, the subsequent analysis and research includes industrial chain integration analysis, and the specific method is shown in fig. 2:
step a, using power consumption data of upstream and downstream enterprises as discrete data, constructing a daily power consumption curve with an abscissa parameter as date and an ordinate parameter as power consumption, wherein the power consumption curve of the upstream enterprise is m and the power consumption curve of the downstream enterprise is n;
b, performing curve similarity analysis on the power consumption curve m and the power consumption curve n, and calculating the similarity;
and c, if the similarity index is larger than or equal to the set threshold, judging that the power utilization trends of the upstream and downstream enterprises are similar, the productivity is matched, and if the similarity index is smaller than the set threshold, judging that the power utilization trends of the upstream and downstream enterprises are not similar, and sending an abnormal alarm.
In the step c, when the similarity index is smaller than the set threshold value, the power utilization trends of the upstream enterprise and the downstream enterprise are judged to be not similar, the power utilization trends of the upstream enterprise and the downstream enterprise are analyzed, if the upstream power utilization trend rises and the downstream power utilization trend declines, a suggestion that the capacity needs to be reduced at the upstream is given, and if the upstream power utilization trend falls and the downstream power utilization trend rises, a suggestion that the capacity needs to be increased at the upstream is given.
In this embodiment, as shown in fig. 5, the similarity of the power consumption at the same time point of the upstream and downstream enterprises is analyzed, the similarity index is 89.9%, and is close to 1, which indicates that the power consumption trends of the upstream and downstream enterprises are similar and the capacities are matched.
In the step 1, a step of data cleansing is further included after data fusion, and as shown in fig. 3, the data cleansing includes the following sub-steps:
substep 1, calling a data cleaning model;
the substep 2, detecting the fusion data by the data cleaning model, and detecting error data in the fusion data;
and 3, generating a repair suggestion by the data cleaning model, and manually completing the repair of the error data by related personnel according to the repair suggestion or completing the repair of the error data by the data cleaning model according to the repair suggestion.
The error data detected by the data cleaning model on the data set comprises one or more of the following data: the repeated values, the alias values, the missing values and the abnormal values correspond to a data cleaning model for each error data.
During the process of data acquisition and fusion, data errors such as repeated values, aliases, missing values and abnormal values are inevitably generated. Data errors may affect the results of data visualization analysis, and thus, efficient data visualization analysis is necessarily not isolated from high quality and highly available data sets. The invention mainly carries out data cleaning facing to data visualization analysis, and the core is to clean partial data subsets which greatly affect data analysis results, reduce the cost of data cleaning and improve the efficiency of data cleaning and data preparation stages.
The data cleaning model corresponding to the alias error data is a connection algorithm matching model, the connection algorithm matching model adopts a fuzzy matching algorithm to search synonyms possibly existing in any two alias data, and if the similarity is greater than a set threshold, the two alias data are the same entity concept, so that the data preparation layer takes one data name as correct data, and the other alias error data is corrected into correct data to complete alias error data cleaning.
The step 2 specifically comprises the following steps: the feature quantities of the fused data comprise monthly power consumption, power consumption increasing trend, load variation, monthly electricity charge and packaging capacity, three analysis dimensions of the electricity change condition of the enterprise within 5 months are formed according to the monthly power consumption, the power consumption increasing trend and the load variation, K-means + + cluster analysis is carried out on the electricity change condition, and the energy consumption feature grading of the enterprise is completed. Three dimensional data of monthly electricity consumption, electricity consumption increase trend and electricity load variation of 5 months are selected as input, and the corresponding input data is an enterprise electricity utilization characteristic index value of 118-12 dimensions. By calculating the SSE error square sum curvature change when the enterprises are classified, the SSE error square sum curvature change is the largest when the electric enterprises are classified into 3 types, so that the three types of effects are optimal. Finally, visualizing the classification result by using a matplotlib module, judging attributes of different classes according to the visualization result, and formulating three classification labels of high power consumption, medium power consumption and low power consumption for each enterprise user; and dividing the power utilization characteristics of the enterprise into three grades according to the qualitative labels of the users.
As shown in fig. 4, the step 3 specifically includes the following sub-steps:
a substep a, extracting and calculating enterprise energy consumption indexes; acquiring enterprise capacity data and power utilization data based on an industrial interconnection platform and a power grid system, and judging an ideal solution: the indexes of the forward measurement comprise monthly electricity consumption, electricity consumption increase rate, accumulated yield, enterprise qualification quantity, limit capacity (a calculation formula is that the limit capacity is product yield/operation duration is 24 hours), and the like; the negative measure indexes comprise indexes such as unit energy consumption and accumulated energy consumption. And (4) clustering analysis result data by combining the power utilization characteristics of the enterprises, and taking the indexes as the input of the comprehensive evaluation and analysis of the energy consumption of the enterprises.
B, scoring the production capacity of the enterprise by a Topsis comprehensive evaluation algorithm; standardizing the index data, performing comprehensive evaluation by using a TOPSIS evaluation algorithm, performing 0-1 maximum and minimum standardization on the scores, and sequentially performing enterprise productivity sequencing from large to small.
And step c, visualizing the classification result by using a matplotlib module, and counting the number of the enterprises with different power utilization characteristics in the enterprise sections according to the enterprise score result.
In the substep a, normalization processing is carried out on the data extracted by the enterprise energy consumption index, and the normalization processing method is min-max standardization or z-score standardization.
The above-described embodiments are only preferred embodiments of the present invention, and are not intended to limit the present invention in any way, and other variations and modifications may be made without departing from the spirit of the invention as set forth in the claims.
Claims (9)
1. An enterprise electric power data analysis method based on electric power consumption behaviors is characterized by comprising the following steps:
step 1, collecting basic information data, power consumption data, electric power archive data and industrial internet data of an enterprise, and performing data fusion on all the data;
step 2, selecting characteristic quantities of the fusion data, and carrying out K-means + + clustering analysis on the characteristic quantities to complete energy utilization characteristic clustering analysis on enterprises;
step 3, evaluating the energy consumption level of the enterprise by a Topsis evaluation method;
step 4, performing table and image storage on the electric power data of the enterprise according to the energy consumption characteristics of the enterprise, the energy consumption level of the enterprise and the basic information data of the enterprise, the electricity consumption data, the electric power archive data and the industrial internet data;
and 5, searching the power data of the enterprise by related personnel through the characteristic expression of the power data, and performing subsequent analysis and research through the search result.
2. The method for analyzing the enterprise power data based on the power consumption behaviors as claimed in claim 1, wherein in the step 5, the follow-up analysis research comprises industrial chain integration analysis, and the specific method comprises the following steps:
step a, using power consumption data of upstream and downstream enterprises as discrete data, constructing a daily power consumption curve with an abscissa parameter as date and an ordinate parameter as power consumption, wherein the power consumption curve of the upstream enterprise is m and the power consumption curve of the downstream enterprise is n;
b, performing curve similarity analysis on the power consumption curve m and the power consumption curve n, and calculating the similarity;
step c, if the similarity index is larger than or equal to a set threshold value, judging that the power utilization trends of upstream and downstream enterprises are similar, and matching the productivity; and if the similarity index is smaller than the set threshold value, judging that the power utilization trends of upstream and downstream enterprises are not similar, and sending an abnormal alarm.
3. The method according to claim 2, wherein in the step c, when the similarity index is smaller than a set threshold, it is determined that the power consumption trends of the upstream and downstream enterprises are not similar, the power consumption trends of the upstream and downstream enterprises are analyzed, and if the upstream power consumption trend increases and the downstream power consumption trend decreases, a recommendation that the upstream needs to reduce the capacity is given; if the trend of the upstream power utilization is reduced and the trend of the downstream power utilization is increased, a suggestion that the capacity needs to be increased at the upstream is given.
4. The method for analyzing the enterprise power data based on the power utilization behaviors as claimed in claim 1, wherein the step 1 further comprises a step of data cleaning after data fusion, and the data cleaning comprises the following sub-steps:
substep 1, calling a data cleaning model;
the substep 2, detecting the fusion data by the data cleaning model, and detecting error data in the fusion data;
and 3, generating a repair suggestion by the data cleaning model, and manually completing the repair of the error data by related personnel according to the repair suggestion or completing the repair of the error data by the data cleaning model according to the repair suggestion.
5. The method as claimed in claim 4, wherein the error data detected by the data cleansing model on the data set includes one or more of the following: the repeated values, the alias values, the missing values and the abnormal values correspond to a data cleaning model for each error data.
6. The enterprise electric power data analysis method based on the electricity consumption behaviors as claimed in claim 5, wherein the data cleaning model corresponding to the alias error data is a connection algorithm matching model, the connection algorithm matching model adopts a fuzzy matching algorithm to search possible synonyms in any two alias data, and if the similarity is greater than a set threshold value, the two alias data are the same entity concept, so that the data preparation layer takes one data name as correct data, and the other alias error data is corrected into correct data, and the alias error data cleaning is completed.
7. The enterprise power data analysis method based on the power consumption behaviors as claimed in claim 1, wherein the step 2 is specifically as follows: the feature quantities of the fused data comprise monthly power consumption, power consumption increasing trend, load variation, monthly electricity charge and packaging capacity, three analysis dimensions of the electricity change condition of the enterprise within a plurality of months are formed according to the monthly power consumption, the power consumption increasing trend and the load variation, K-means + + cluster analysis is carried out on the electricity change condition, and the energy consumption feature grading of the enterprise is completed.
8. The method for analyzing the enterprise power data based on the power utilization behaviors as claimed in claim 1, wherein the step 3 specifically comprises the following substeps:
a substep a, extracting and calculating enterprise energy consumption indexes;
b, scoring the production capacity of the enterprise by a Topsis comprehensive evaluation algorithm;
and step c, visualizing the classification result by using a matplotlib module, and counting the number of the enterprises with different power utilization characteristics in the enterprise sections according to the enterprise score result.
9. The method as claimed in claim 8, wherein in the substep a, the data extracted from the energy consumption index of the enterprise is normalized by min-max normalization or z-score normalization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186999.5A CN112686491A (en) | 2020-10-30 | 2020-10-30 | Enterprise power data analysis method based on power consumption behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186999.5A CN112686491A (en) | 2020-10-30 | 2020-10-30 | Enterprise power data analysis method based on power consumption behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112686491A true CN112686491A (en) | 2021-04-20 |
Family
ID=75445728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011186999.5A Pending CN112686491A (en) | 2020-10-30 | 2020-10-30 | Enterprise power data analysis method based on power consumption behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686491A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313407A (en) * | 2021-06-16 | 2021-08-27 | 上海交通大学 | Enterprise power utilization behavior identification method and device |
| CN114495446A (en) * | 2022-01-04 | 2022-05-13 | 珠海格力电器股份有限公司 | Energy consumption monitoring alarm method and device, computing equipment and storage medium |
| CN117474375A (en) * | 2023-09-22 | 2024-01-30 | 国网江苏省电力有限公司泰州供电分公司 | Enterprise productivity utilization index research method based on power big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510006A (en) * | 2018-04-08 | 2018-09-07 | 重庆邮电大学 | A kind of analysis of business electrical amount and prediction technique based on data mining |
| CN110826886A (en) * | 2019-10-29 | 2020-02-21 | 南京华盾电力信息安全测评有限公司 | Electric power customer portrait construction method based on clustering algorithm and principal component analysis |
| CN111680851A (en) * | 2020-08-13 | 2020-09-18 | 国网浙江省电力有限公司营销服务中心 | Enterprise power utilization trend evaluation method based on K line graph |
-
2020
- 2020-10-30 CN CN202011186999.5A patent/CN112686491A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108510006A (en) * | 2018-04-08 | 2018-09-07 | 重庆邮电大学 | A kind of analysis of business electrical amount and prediction technique based on data mining |
| CN110826886A (en) * | 2019-10-29 | 2020-02-21 | 南京华盾电力信息安全测评有限公司 | Electric power customer portrait construction method based on clustering algorithm and principal component analysis |
| CN111680851A (en) * | 2020-08-13 | 2020-09-18 | 国网浙江省电力有限公司营销服务中心 | Enterprise power utilization trend evaluation method based on K line graph |
Non-Patent Citations (1)
| Title |
|---|
| 凌德祥等: "基于大数据的电力客户行为分析体系研究及实践", 《电力大数据》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113313407A (en) * | 2021-06-16 | 2021-08-27 | 上海交通大学 | Enterprise power utilization behavior identification method and device |
| CN114495446A (en) * | 2022-01-04 | 2022-05-13 | 珠海格力电器股份有限公司 | Energy consumption monitoring alarm method and device, computing equipment and storage medium |
| CN117474375A (en) * | 2023-09-22 | 2024-01-30 | 国网江苏省电力有限公司泰州供电分公司 | Enterprise productivity utilization index research method based on power big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112686491A (en) | Enterprise power data analysis method based on power consumption behavior | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN111724278A (en) | Fine classification method and system for power multi-load users | |
| CN110610121B (en) | Small-scale source load power abnormal data identification and restoration method based on curve clustering | |
| CN111062620B (en) | Intelligent electric power charging fairness analysis system and method based on hybrid charging data | |
| CN110991555A (en) | Method for monitoring abnormal electricity consumption of user in typical industry | |
| CN112101971B (en) | Sensitive client identification method, system and storage medium | |
| CN111626614A (en) | User classification method based on electric charge recovery | |
| CN111914942A (en) | Multi-table-combined one-use energy anomaly analysis method | |
| CN115794803B (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| CN113487448A (en) | Power credit labeling method and system based on power big data | |
| CN113742357A (en) | Method and system for automatically collecting and associating cross-platform design data | |
| CN115358481A (en) | Early warning and identification method, system and device for enterprise ex-situ migration | |
| CN115859099A (en) | Sample generation method and device, electronic equipment and storage medium | |
| CN111027841A (en) | Low-voltage transformer area line loss calculation method based on gradient lifting decision tree | |
| CN116485020B (en) | Supply chain risk identification early warning method, system and medium based on big data | |
| CN114841832B (en) | Power consumer portrait label establishing method based on secondary clustering of power loads | |
| CN114676931B (en) | Electric quantity prediction system based on data center technology | |
| CN111143431A (en) | Intelligent charge checking and anomaly identification system | |
| CN115908082A (en) | Enterprise pollution discharge monitoring method and device based on electricity utilization characteristic indexes | |
| CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
| CN110727910B (en) | Method and system for realizing copying and collecting risk prediction and business linkage | |
| CN115081514A (en) | Industrial equipment fault identification method under data imbalance condition | |
| CN112949700A (en) | Method and device for identifying execution strength of enterprise yield limit policy | |
| CN109753990B (en) | User electric energy substitution potential prediction method, system and storage medium |
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 |