CN112116265A - Industry landscape index construction method driven by electric power data - Google Patents
Industry landscape index construction method driven by electric power data Download PDFInfo
- Publication number
- CN112116265A CN112116265A CN202011019707.9A CN202011019707A CN112116265A CN 112116265 A CN112116265 A CN 112116265A CN 202011019707 A CN202011019707 A CN 202011019707A CN 112116265 A CN112116265 A CN 112116265A
- Authority
- CN
- China
- Prior art keywords
- index
- industry
- daily
- enterprise
- data
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 16
- 230000005611 electricity Effects 0.000 claims abstract description 66
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000009792 diffusion process Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011144 upstream manufacturing 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
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an electric power data-driven industry business landscape index construction method, which comprises the following steps: 1) taking enterprises belonging to the same industry as an enterprise set V, and acquiring a daily electricity consumption set S comprising daily electricity consumption time sequence data of each enterprise in the enterprise set V; 2) carrying out data preprocessing on the daily electricity collection S and classifying through a clustering analysis method; 3) acquiring the influence weight of the influence factors on the daily electricity consumption of the enterprise under each classification by using a correlation analysis method; 4) acquiring a next-day power consumption predicted value by using a prediction model; 5) compared with the prior art, the method has the advantages of high frequency, fine granularity, strong prediction and the like.
Description
Technical Field
The invention relates to the field of big data of electric power information, in particular to an electric power data-driven industry landscape index construction method.
Background
The problems of excess enterprise capacity, single product structure, low technical level, low matching localization rate and the like restrict the sustainable development of the native shipbuilding industry, and the transformation and upgrading of the digital economy accelerated industry under the drive of big data are urgently needed.
In the field of economics, the power consumption objectively reflects the landscape situation and the trend of changes of industrial manufacturing industries such as shipbuilding industry and the like. By means of the large electric power data such as the electric power consumption of enterprises, business expansion data, the operation capacity, the contract capacity and the like, the scene fluctuation situation of the industries can be analyzed and predicted from the electric power view angle, and the participation of the industries such as governments, enterprises, banks and the like in the main body for customizing and adjusting the related policy planning is facilitated. At present, the domestic authoritative indexes such as the freight rate index of the Chinese export container, the freight rate index of the Chinese coastal (bulk cargo), the Chinese shipping scene index and the like take the power consumption as an important component of an index system. However, the conventional prospect indexes including the foregoing are difficult to exert the advantages of high frequency, multi-dimensional and mass power data, and mainly reflect the following aspects:
one is the low frequency. The frequency of the current scenery indexes is mostly monthly, quarterly and annual, and the collection frequency of the electricity consumption is daily, hourly and minute. In order to bring the electricity consumption into an index system, the existing landscape index aggregates the electricity consumption according to time units such as months, seasons, years and the like, and the daily change characteristic of electricity consumption data is lost.
Secondly, the particle size is coarse. The granularity of the existing prosperity index is mostly in the industry level and the industrial level, and the granularity of acquiring the power consumption is in the enterprise level and the building level. In order to bring the electricity consumption into an index system, the existing landscape index classifies and aggregates the electricity consumption according to industries, industries and the like, and the enterprise-level change characteristics of electricity consumption data are lost.
And thirdly, the prediction is weak. In the existing index system of the scenic index, the electricity consumption usually plays the role of a leading index. The landscape index is compiled based on real data of each index, so that the capability of predicting future changes of the landscape index is limited.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a high-frequency, fine-grained and strongly-predicted electric power data-driven industry prospect index construction method.
The purpose of the invention can be realized by the following technical scheme:
a power data driven industry prosperity index construction method comprises the following steps:
1) taking enterprises belonging to the same industry as an enterprise set V, and acquiring a daily electricity consumption set S comprising daily electricity consumption time sequence data of each enterprise in the enterprise set V;
2) carrying out data preprocessing on the daily electricity collection S and classifying through a clustering analysis method;
3) acquiring the influence weight of the influence factors on the daily electricity consumption of the enterprise under each classification by using a correlation analysis method;
4) acquiring a next-day power consumption predicted value by using a prediction model;
5) and respectively constructing an industry scene index system H, an industry scene comprehensive index CI and an industry scene diffusion index DI.
Further, the data preprocessing specifically includes:
21) removing outliers of each daily electric quantity time sequence data in the daily electric quantity set S by adopting a quartile method;
22) filling missing points of each daily electricity quantity time sequence data in the daily electricity quantity set S by adopting a moving average method;
23) classifying the daily electricity consumption set S by using a daily electricity consumption curve by adopting a K-Shape curve clustering analysis method;
24) and correcting abnormal points of the enterprise daily electricity consumption time sequence data in each category.
Further, the step 23) specifically includes:
231) constructing a power consumption matrix U corresponding to each category, wherein the ith row vector in the power consumption matrix U is the ith power consumption time sequence data in the corresponding category;
232) obtaining a clustering number k, and initializing a clustering center C of each categorykWherein the center C is clusteredkIs zero vector;
233) calculating power consumptionEach vector in the quantity matrix U goes to each cluster center CkClassifying each vector into a category with the minimum shape similarity distance;
234) updating the clustering center C of each category according to the clustering resultkSo as to cluster the center CkThe sum of the similarity distances with the shapes of all vectors in the category is shortest;
235) steps 233) and 234) are repeated until a preset maximum number of iterations is reached or the clustering result is no longer changed.
Further, the step 24) corrects only the abnormal point in the missing point of the daily electricity consumption time series data filled in the step 22), which specifically includes:
241) acquiring a power consumption matrix U corresponding to any category G in the daily power set S;
242) traversing each row of the electricity consumption matrix U, and searching the row with the least missing points and outliers as a standard row;
243) traversing the electricity consumption matrix U from left to right, and calculating the cosine similarity of the standard row and other rows;
244) if the cosine similarity between a certain line and the standard line is lower than the set threshold, modifying the partial point values in the line to ensure that the cosine similarity between the line and the standard line is higher than the set threshold, and finishing the correction of the abnormal point.
Furthermore, the daily electricity consumption curve is a curve of the daily electricity consumption time sequence data of each enterprise in a two-dimensional coordinate system of date-electricity consumption.
Further, the influence factors comprise meteorological information and holiday information, the meteorological information comprises temperature, humidity, wind speed and rainfall, the holiday information comprises statutory holiday and weekend time sequence data, and the influence weight of the influence factors on the daily electric quantity of the enterprise is obtained through calculation of a Pearson correlation coefficient.
Further, the prediction model adopts a Seq2Seq prediction model, and the input of the prediction model comprises daily power consumption time series data, holiday time series data and meteorological information.
Furthermore, each enterprise in the enterprise set V is an index in an industry and landscape architecture H, a current value of each index of the industry and landscape architecture H is a ratio of a next-day electricity consumption predicted value and a current-day actual electricity consumption of the corresponding enterprise, and a weight of each index is an operation capacity or a contract capacity of the corresponding enterprise.
Furthermore, the current value of the industry and landscape comprehensive index CI is a normalized value of the sum of products of the current values and the corresponding weights of all the indexes in the industry and landscape index system H, and the calculation formula is as follows:
wherein p isiIs the weight value q of the ith index in the industrial prosperity index system HiThe current time value of the ith index in the industry prosperity index system H.
Furthermore, the current value of the industry and landscape spread index DI is a normalized value of the sum of comparison results of the current value and the previous value of all indexes in the industry and landscape index system H, and the calculation formula is as follows:
wherein x isiIs the upper value, q, of the ith index in the industrial prosperity index system HiIs the current value of the ith index in the industry scene index system H, I (x)i,qi) Is a piecewise continuous binary function that maps the comparison of the last and current values of the ith index to [0,1]An interval.
Compared with the prior art, the invention has the following advantages:
1) high frequency: the daily comprehensive index CI and the daily diffusion index DI constructed by the method are used for updating and predicting the daily frequency by utilizing the collection frequency of the power consumption, can obtain the daily variation characteristics of the industrial landscape index, and are beneficial to industry subjects such as governments, enterprises and financial institutions to develop daily decision analysis work;
2) fine granularity: the industry scene gas index system H constructed by the invention is an enterprise-level index system, wherein each index corresponds to each enterprise one by one, and the industry scene gas condition is described from a microscopic level, so that the analysis of the scene gas covariant condition among industry subdivision categories is facilitated by combining the upstream and downstream relations in the industry;
3) strong prediction: the next-day power consumption prediction model constructed by the method comprehensively utilizes a cluster analysis technology, a data cleaning technology, a time sequence prediction technology and the like to effectively preprocess input data, and has high prediction accuracy, so that the daily comprehensive index CI and the daily diffusion index DI constructed on the basis of the model can reflect the short-term future changes of industrial scenery more truly.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
As shown in fig. 1, the invention provides an electric power data-driven industry business interest index construction method, which first establishes three sets, namely an enterprise set V, a daily electricity quantity set S and a power consumption time sequence curve set C, wherein the enterprise set V ═ V1, V2.., Vm } is a set of enterprises belonging to a certain industry, the daily electricity quantity set S ═ { S1, S2.., Sm } is daily electricity quantity time sequence data of each enterprise in the enterprise set V, and the power consumption time sequence curve set C ═ C1, C2., Cm } is a corresponding curve of each daily electricity quantity time sequence data in a "date-power consumption" two-dimensional coordinate system in the daily electricity quantity set S. The construction method of the invention sequentially executes the following steps:
s1: and eliminating outliers of each daily electric quantity time sequence data in the daily electric quantity set S by adopting a quartile method.
The method specifically comprises the following steps: for any time sequence data S in the daily electricity quantity set SiAnd calculating a first quartile P, a median Q and a third quartile R of the quartile. Let IQR become R-P, and convert the time-series data SiThe value is [ P-1.5 iQR, R +1.5 iQR]The points outside are set as missing points.
S2: and filling missing points of each daily electricity quantity time sequence data in the daily electricity quantity set S by adopting a moving average method.
The method specifically comprises the following steps: for any time sequence data S in the daily electricity quantity set SiProgression from left to right through ordinal data SiAnd calculating a moving average of the window w if Si[j]If it is a missing value, S isi[j]Assigned a value of window Si[j-w,j-w+1,...,j-1]Average number of medium elements.
S3: and classifying the daily electricity consumption set S by adopting a K-Shape curve clustering analysis method, so that corresponding curves of the daily electricity consumption time series data belonging to the same classification in the electricity quantity time series curve set C have similar morphological characteristics.
The method specifically comprises the following steps:
s301: constructing a power consumption matrix U corresponding to each category, wherein the ith row vector in the power consumption matrix U is the ith power consumption time sequence data in the corresponding category;
s302: appointing the number k of clusters, initializing the cluster center C of each classkWherein the center C is clusteredkIs a zero vector;
s303: calculating each vector in the power consumption matrix U to each clustering center CkThe vectors are classified into the class with the minimum shape similarity distance, wherein two vectors S in the electricity consumption matrix UiAnd SjThe calculation formula of the shape similarity distance between the two is as follows:
wherein S isiAnd SjRespectively two vectors in the power consumption matrix U, wherein ED, MD and DSD are respectively the Euclidean distance, Manhattan distance and the absolute value of the element sum of the difference vectors of the two vectors;
s304: updating the clustering center C of each category according to the clustering resultkSo as to cluster the center CkThe sum of the similarity distances with the shapes of all vectors in the category is shortest;
s305: and repeating the steps S303-S304 until the preset maximum iteration number is reached or the clustering result is not changed.
S4: and (4) correcting abnormal points of the enterprise daily electricity consumption time sequence data in the classification by adopting a cosine similarity method aiming at each category in the daily electricity consumption set S, wherein the modifiable points are the missing points filled in the step S2.
The method specifically comprises the following steps:
s401: acquiring a power consumption matrix U corresponding to any category G in the daily power set S;
s402: and traversing each row of the electricity consumption matrix U, and searching the row with the least missing points and outliers before cleaning to serve as a standard row.
S403: traversing the power consumption matrix U from left to right, calculating the cosine similarity between the standard line and other lines, and if the cosine similarity between a certain line and the standard line is lower than a threshold, modifying the point values in the line to make the cosine similarity between the line and the standard line higher than a preset threshold, wherein the modified point must be the missing point filled in the step S2.
S5: and aiming at each category of the daily electricity consumption set S, calculating the influence weight of the influence factors on the daily electricity consumption of each enterprise under the category by adopting a correlation analysis method.
The influence factors comprise meteorological information and holiday information, the meteorological information comprises temperature, humidity, wind speed and rainfall, the holiday information comprises time sequence data of legal holidays and weekends, the influence weight of the influence factors on the daily electric quantity of the enterprise is obtained by calculation of a Pearson correlation coefficient, and the calculation formula is as follows:
wherein X and
is daily power time sequence data and its mean value, Y and
is the time series data and the average value of a certain influence factor.
S6: aiming at each daily electricity consumption time sequence data of the daily electricity consumption set S, a Seq2Seq prediction model is adopted to calculate the predicted value of the next daily electricity consumption, the input of the prediction model comprises the daily electricity consumption time sequence data, the time sequence data of factors such as weather, holidays and the like and the influence weight, and the method specifically comprises the following steps: (1) electricity consumption time sequence data; (2) 1 and 0 respectively represent whether a certain day is a holiday of the festival, such as a spring festival, a weekend and the like; (3) the time series data of meteorological factors such as temperature, humidity, wind speed and rainfall are used as the correlation coefficients calculated in step S5 to initialize the influence weight of each factor of the prediction model on the electric quantity.
S7: and constructing an industry scene gas index system H, wherein each enterprise in the enterprise set V is an index in the industry scene gas index system H, the current value of each index is the ratio of the next-day predicted power consumption of the corresponding enterprise to the current-day actual power consumption, and the right of each index is the operation capacity or contract capacity of the corresponding enterprise.
S8: and constructing an industry and landscape comprehensive index CI, wherein the current-stage value of the industry and landscape comprehensive index CI is a normalized value of the sum of products of the current-stage values and corresponding weights of all indexes in the H, and the calculation formula is as follows:
wherein p isiIs the weight value q of the ith index in the industrial prosperity index system HiFor the current time value of the ith index in an industry scene index system H。
S9: and constructing an industry landscape spread index DI, wherein the current value of the industry landscape spread index DI is a normalized value of the sum of comparison results of the current value and the last value of all indexes in the H, and the calculation formula is as follows:
wherein x isiIs the upper value, q, of the ith index in the industrial prosperity index system HiSegmenting a continuous binary function I (x) for the current value of the ith index in the industrial prospectus index system Hi,qi) Mapping the comparison result of the last period value and the current period value of the ith index to [0, 1%]An interval.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and those skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A construction method of an industry prospect index driven by electric power data is characterized by comprising the following steps:
1) taking enterprises belonging to the same industry as an enterprise set V, and acquiring a daily electricity consumption set S comprising daily electricity consumption time sequence data of each enterprise in the enterprise set V;
2) carrying out data preprocessing on the daily electricity collection S and classifying through a clustering analysis method;
3) acquiring the influence weight of the influence factors on the daily electricity consumption of the enterprise under each classification by using a correlation analysis method;
4) acquiring a next-day power consumption predicted value by using a prediction model;
5) and respectively constructing an industry scene index system H, an industry scene comprehensive index CI and an industry scene diffusion index DI.
2. The electric power data driven industry scene index construction method according to claim 1, wherein the data preprocessing specifically comprises:
21) removing outliers of each daily electric quantity time sequence data in the daily electric quantity set S by adopting a quartile method;
22) filling missing points of each daily electricity quantity time sequence data in the daily electricity quantity set S by adopting a moving average method;
23) classifying the daily electricity quantity set S by using a daily electricity quantity curve by adopting a K-Shape curve clustering analysis method;
24) and correcting abnormal points of the enterprise daily electricity consumption time sequence data in each category.
3. The electric power data driven industry scene index construction method according to claim 2, wherein the step 23) specifically comprises:
231) constructing a power consumption matrix U corresponding to each category, wherein the ith row vector in the power consumption matrix U is the ith power consumption time sequence data in the corresponding category;
232) obtaining a clustering number k, and initializing a clustering center C of each categorykWherein the center C is clusteredkIs a zero vector;
233) calculating each vector in the power consumption matrix U to each clustering center CkThe shape similarity distance of (1), and classifying the each vector into the category with the minimum shape similarity distance;
234) updating the clustering center C of each category according to the clustering resultkSo as to cluster the center CkThe sum of the similarity distances to the shapes of all vectors in the category is shortest;
235) steps 233) and 234) are repeated until a preset maximum number of iterations is reached or no further change in clustering results occurs.
4. The electric power data-driven industry prospect index construction method as claimed in claim 2, wherein said step 24) only corrects abnormal points in the missing points of the daily electricity quantity time series data filled in the step 22), which specifically includes:
241) acquiring a power consumption matrix U corresponding to any category G in the daily power set S;
242) traversing each row of the electricity consumption matrix U, and searching the row with the least missing points and outliers as a standard row;
243) traversing the electricity consumption matrix U from left to right, and calculating the cosine similarity of the standard row and other rows;
244) if the cosine similarity between a certain row and the standard row is lower than the set threshold, modifying partial point values in the row to ensure that the cosine similarity between the row and the standard row is higher than the set threshold, and finishing the correction of the abnormal point.
5. The electric power data-driven industry landscape index construction method as claimed in claim 2, wherein the daily power curve is a curve of daily power time sequence data of each enterprise in a two-dimensional coordinate system of date-power consumption.
6. The method as claimed in claim 1, wherein the influencing factors include weather information and holiday information, the weather information includes temperature, humidity, wind speed and rainfall, the holiday information includes legal holiday and weekend time series data, and the influence weight of the influencing factors on the daily electricity consumption of the enterprise is calculated through a Pearson correlation coefficient.
7. The electric power data driven industry scene index construction method as claimed in claim 6, wherein the prediction model is a Seq2Seq prediction model, and the input of the prediction model comprises daily power consumption time series data, holiday time series data and meteorological information.
8. The electric power data-driven industry scene index construction method according to claim 6, wherein each enterprise in the enterprise set V is an index in an industry scene index system H, the current value of each index of the industry scene index system H is the ratio of the next-day electricity consumption predicted value and the current-day actual electricity consumption of the corresponding enterprise, and the weight value of each index is the operation capacity or contract capacity of the corresponding enterprise.
9. The electric power data-driven industry landscape index construction method according to claim 8, wherein the current value of the industry landscape comprehensive index CI is a normalized value of the sum of products of the current values and corresponding weights of all indexes in an industry landscape index system H, and the calculation formula is as follows:
wherein p isiIs the weight value q of the ith index in the industrial prosperity index system HiThe current time value of the ith index in the industry prosperity index system H.
10. The method as claimed in claim 8, wherein the current value of the industry landscape spread index DI is a normalized value of a sum of comparison results of the current value and the previous value of all indexes in the industry landscape index system H, and the calculation formula is as follows:
wherein x isiIs the upper value, q, of the ith index in the industrial prosperity index system HiFor the tradeCurrent value of ith index, I (x) in scenic gas index system Hi,qi) Is a piecewise continuous binary function that maps the comparison of the last and current values of the ith index to [0,1]An interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011019707.9A CN112116265A (en) | 2020-09-25 | 2020-09-25 | Industry landscape index construction method driven by electric power data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011019707.9A CN112116265A (en) | 2020-09-25 | 2020-09-25 | Industry landscape index construction method driven by electric power data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116265A true CN112116265A (en) | 2020-12-22 |
Family
ID=73800761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011019707.9A Pending CN112116265A (en) | 2020-09-25 | 2020-09-25 | Industry landscape index construction method driven by electric power data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116265A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348281A (en) * | 2020-11-23 | 2021-02-09 | 国网北京市电力公司 | Power data processing method and device |
| CN113240228A (en) * | 2021-03-23 | 2021-08-10 | 苏州易助能源管理有限公司 | Power demand analysis device and method for various industries in local area |
| CN113298175A (en) * | 2021-06-10 | 2021-08-24 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of old people living alone based on multiple scenes and multivariate data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007042060A (en) * | 2005-07-06 | 2007-02-15 | Koji Kasahara | Business forecast calendar and business forecast program |
| CN104657788A (en) * | 2015-02-04 | 2015-05-27 | 国家电网公司 | Method for predicting key industrial electricity consumption based on industrial condition index |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105844351A (en) * | 2016-03-22 | 2016-08-10 | 广西电网有限责任公司电力科学研究院 | Prosperity index prediction method for electric power consumption market |
| 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 |
| CN106056477A (en) * | 2016-06-06 | 2016-10-26 | 国网江苏省电力公司 | Industry capacity utilization rate calculating method based on electricity consumption big data |
| CN106557835A (en) * | 2016-10-24 | 2017-04-05 | 南方电网科学研究院有限责任公司 | Power consumption prediction method and system based on scenic gas index |
| 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 |
| CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | Deep learning-based power consumption prediction method, device and equipment |
| CN110084398A (en) * | 2019-03-15 | 2019-08-02 | 国网上海市电力公司 | A kind of Industrial Cycle self-adapting detecting method based on enterprise's electric power big data |
-
2020
- 2020-09-25 CN CN202011019707.9A patent/CN112116265A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007042060A (en) * | 2005-07-06 | 2007-02-15 | Koji Kasahara | Business forecast calendar and business forecast program |
| CN104657788A (en) * | 2015-02-04 | 2015-05-27 | 国家电网公司 | Method for predicting key industrial electricity consumption based on industrial condition index |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN105844351A (en) * | 2016-03-22 | 2016-08-10 | 广西电网有限责任公司电力科学研究院 | Prosperity index prediction method for electric power consumption market |
| 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 |
| CN106056477A (en) * | 2016-06-06 | 2016-10-26 | 国网江苏省电力公司 | Industry capacity utilization rate calculating method based on electricity consumption big data |
| CN106557835A (en) * | 2016-10-24 | 2017-04-05 | 南方电网科学研究院有限责任公司 | Power consumption prediction method and system based on scenic gas index |
| 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 |
| CN109685290A (en) * | 2019-02-11 | 2019-04-26 | 南方电网科学研究院有限责任公司 | Deep learning-based power consumption prediction method, device and equipment |
| CN110084398A (en) * | 2019-03-15 | 2019-08-02 | 国网上海市电力公司 | A kind of Industrial Cycle self-adapting detecting method based on enterprise's electric power big data |
Non-Patent Citations (2)
| Title |
|---|
| 吴海民;: "BP人工神经网络在我国工业企业景气指数预测中的应用", 兰州商学院学报, no. 02 * |
| 李斌;: "用电大数据的应用研究", 电力需求侧管理, no. 04 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348281A (en) * | 2020-11-23 | 2021-02-09 | 国网北京市电力公司 | Power data processing method and device |
| CN113240228A (en) * | 2021-03-23 | 2021-08-10 | 苏州易助能源管理有限公司 | Power demand analysis device and method for various industries in local area |
| CN113298175A (en) * | 2021-06-10 | 2021-08-24 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of old people living alone based on multiple scenes and multivariate data |
| CN113298175B (en) * | 2021-06-10 | 2023-09-12 | 国网江苏省电力有限公司营销服务中心 | Method and system for monitoring power consumption of solitary old people based on multiple scenes and multiple data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Almalaq et al. | A review of deep learning methods applied on load forecasting | |
| CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
| CN112116265A (en) | Industry landscape index construction method driven by electric power data | |
| CN106448151B (en) | Short-term traffic flow prediction method | |
| CN109902953B (en) | Power consumer classification method based on self-adaptive particle swarm clustering | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN108805213B (en) | Power load curve double-layer spectral clustering method considering wavelet entropy dimensionality reduction | |
| CN110991311A (en) | Target detection method based on dense connection deep network | |
| CN109146063B (en) | Multi-segment short-term load prediction method based on important point segmentation | |
| CN110188919A (en) | A kind of load forecasting method based on shot and long term memory network | |
| Biard et al. | Automated detection of weather fronts using a deep learning neural network | |
| CN113361785A (en) | Power distribution network short-term load prediction method and device, terminal and storage medium | |
| CN114912720A (en) | Memory network-based power load prediction method, device, terminal and storage medium | |
| CN115393631A (en) | Hyperspectral image classification method based on Bayesian layer graph convolution neural network | |
| CN113191419B (en) | Sag homologous event detection and type identification method based on track key point matching and region division | |
| CN115660182A (en) | Photovoltaic output prediction method based on maximum expected sample weighted neural network model | |
| CN116454870A (en) | Regional distributed photovoltaic short-term power prediction method | |
| CN117235587A (en) | Meteorological target classification method based on lightGBM | |
| CN114862363A (en) | Evaluation analysis method based on substation project cost data analysis | |
| CN115829418B (en) | Method and system for constructing load characteristic portraits of power consumers suitable for load management | |
| CN108830603A (en) | transaction identification method and device | |
| CN117094754A (en) | Macroscopic and microscopic combined medium-long term electric quantity prediction method | |
| CN116862043A (en) | Load prediction method and system based on multilayer feedforward network | |
| CN110766274A (en) | Industry prosperity index determination method and device | |
| CN114254828B (en) | Power load prediction method based on mixed convolution feature extractor and GRU |
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 |