CN115081795A - Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene - Google Patents

Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene Download PDF

Info

Publication number
CN115081795A
CN115081795A CN202210452617.1A CN202210452617A CN115081795A CN 115081795 A CN115081795 A CN 115081795A CN 202210452617 A CN202210452617 A CN 202210452617A CN 115081795 A CN115081795 A CN 115081795A
Authority
CN
China
Prior art keywords
energy consumption
enterprise
clustering
data
enterprise energy
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
Application number
CN202210452617.1A
Other languages
Chinese (zh)
Inventor
刘祥国
李峰
杜慧珺
许立
李文敬
淳于岳松
周佳
王安洋
孟卫东
张强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TaiAn Power Supply Co of State Grid Shandong Electric Power Co Ltd
Original Assignee
TaiAn Power Supply Co of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by TaiAn Power Supply Co of State Grid Shandong Electric Power Co Ltd filed Critical TaiAn Power Supply Co of State Grid Shandong Electric Power Co Ltd
Priority to CN202210452617.1A priority Critical patent/CN115081795A/en
Publication of CN115081795A publication Critical patent/CN115081795A/en
Pending legal-status Critical Current

Links

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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G06Q10/063114—Status monitoring or status determination for a person or group
    • 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
    • G06Q30/00—Commerce
    • G06Q30/018—Certifying business or products
    • 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 provides a method and a system for analyzing causes of enterprise energy consumption abnormity in a multidimensional scene, and relates to the technical field of enterprise energy consumption abnormity identification, wherein the method comprises the following steps: acquiring enterprise energy consumption data; preprocessing the enterprise energy consumption data; calculating the comprehensive energy consumption of carbon emission of enterprises; clustering the enterprise energy consumption curves to obtain standard energy consumption curves in different energy consumption modes; dividing energy scenes for enterprises; determining an optimal clustering number K based on the contour coefficient and the separation index; constructing an enterprise energy consumption standard interval based on a preset algorithm; determining an enterprise energy consumption abnormal characteristic parameter; establishing a typical scene library of enterprise energy consumption abnormity; and studying and judging the causes of abnormal energy consumption of enterprises. The invention provides establishment of the dynamic standard interval of enterprise energy consumption under a multidimensional scene in consideration of different modes and time scene division of enterprise energy consumption, improves the accuracy of studying and judging enterprise energy consumption abnormity, and realizes accurate positioning of enterprise energy consumption abnormity causes.

Description

Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene
Technical Field
The invention relates to the technical field of enterprise energy consumption abnormity identification, in particular to a method and a system for analyzing causes of enterprise energy consumption abnormity in a multidimensional scene.
Background
Along with the improvement of the importance of energy sources to the development of the current social economy, the problem of energy shortage gradually becomes the focus of national attention. The problem of enterprise energy consumption is the key influencing comprehensive energy consumption, so that enterprise energy consumption abnormity study and judgment and cause analysis become effective measures for energy conservation and emission reduction of the current enterprises. The existing high-energy-consumption enterprises have certain defects: firstly, the construction of an enterprise energy consumption dynamic standard interval under a multi-dimensional scene is not considered; secondly, the accuracy of the obtained dynamic standard interval is low due to the adoption of a general clustering algorithm; thirdly, the enterprise abnormal cause is not reasonably analyzed, and the problem of enterprise energy consumption abnormality is not fundamentally solved.
Disclosure of Invention
The enterprise energy consumption abnormal analysis method comprises the steps of considering enterprise energy consumption mode classification and time scene division, providing an enterprise energy consumption abnormal study judgment and cause analysis method under a multi-dimensional scene, establishing an enterprise energy consumption dynamic standard interval under the multi-dimensional scene, studying and judging enterprise energy consumption abnormity, and reasonably analyzing enterprise energy consumption abnormal causes; the accuracy of enterprise energy consumption abnormity study and judgment is improved.
The specific method comprises the following steps:
s1, acquiring enterprise energy consumption data;
s2, preprocessing the enterprise energy consumption data;
s3, calculating the comprehensive energy consumption of carbon emission of the enterprise;
s4, clustering the enterprise energy consumption curves to obtain standard enterprise energy consumption curves in different energy consumption modes;
s5, acquiring an enterprise energy utilization scene based on the standard enterprise energy consumption curve;
s6, determining an optimal clustering number K based on the contour coefficient and the separation index (PC);
s7, constructing enterprise energy consumption standard intervals of each scene under different energy consumption modes of an enterprise;
s8, determining abnormal characteristic parameters of enterprise energy consumption;
s9, establishing an enterprise energy consumption abnormal typical scene library;
and S10, studying and judging the causes of abnormal energy consumption of the enterprise.
It is further noted that the preprocessing the enterprise energy consumption data in step S2 includes: removing abnormal values of the enterprise energy consumption data and filling missing values, wherein the filling formula is as follows:
Figure 392685DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 492228DEST_PATH_IMAGE002
the data representing the energy consumption is presented,
Figure 98659DEST_PATH_IMAGE003
indicating the data sequence number.
Further, step S3 further includes:
s31, uniformly and equivalently converting the energy consumption data of different types into ton standard coal, and performing addition calculation;
standardizing the energy consumption data of each enterprise based on the GDP total value of the enterprise year, wherein the standardized processing formula is as follows:
Figure 574640DEST_PATH_IMAGE004
in the formula (I), the compound is shown in the specification,
Figure 723861DEST_PATH_IMAGE005
the daily energy consumption of the enterprise after standardized treatment is shown,
Figure 254026DEST_PATH_IMAGE006
representing the enterprise's original daily energy consumption data,
Figure 285435DEST_PATH_IMAGE007
the GDP is a specified standard enterprise year GDP total value, and G is an enterprise actual year GDP total value;
s32, constructing an enterprise carbon dioxide emission calculation formula:
Figure 565107DEST_PATH_IMAGE008
wherein CEE is the total carbon dioxide emission of enterprises,
Figure 834414DEST_PATH_IMAGE009
the total consumption of the natural gas of enterprises,
Figure 541339DEST_PATH_IMAGE010
is a carbon dioxide emission factor of natural gas of enterprises,
Figure 60045DEST_PATH_IMAGE011
b is the total consumption of the electric energy of the enterprise, b is the carbon dioxide emission factor of the power grid,
Figure 81091DEST_PATH_IMAGE012
c is the carbon dioxide emission factor of the coal of the enterprise.
Further, step S4 specifically includes:
s41, determining the optimal number of clusters;
s42, reducing the dimension of the enterprise energy consumption curve based on a segmented aggregation approximation algorithm (PAA);
s43, carrying out clustering analysis on the enterprise energy consumption curve by adopting a DBSCAN clustering algorithm to obtain different energy consumption modes of the enterprise;
and S44, drawing curve clusters in each energy consumption mode into box line graphs, and selecting data median connection lines as standard energy consumption curves for dividing subsequent energy consumption scenes.
It should be further noted that step S6 further includes the following steps:
s61, carrying out preliminary selection on the optimal clustering number by adopting a contour coefficient method, and selecting a value range of the optimal clustering number;
s62, defining cluster comprehensive evaluation index C
Figure 267222DEST_PATH_IMAGE013
Wherein PC represents a membership coefficient and SE represents a separation index;
Figure 348310DEST_PATH_IMAGE014
wherein k denotes a kth cluster class, n denotes an nth sample, m is a clustering dimension,
Figure 354312DEST_PATH_IMAGE015
representing the membership degree of the data point n belonging to the i class;
Figure 975786DEST_PATH_IMAGE016
wherein N represents the total number of data, k represents the kth cluster class, N represents the nth sample,
Figure 954107DEST_PATH_IMAGE015
the data point n belongs to the membership of class i,
Figure 274273DEST_PATH_IMAGE017
and
Figure 767571DEST_PATH_IMAGE018
a cluster class center representing cluster classes i and j,
Figure 130419DEST_PATH_IMAGE019
represents the nth sample number.
It should be further noted that step S7 further includes the following steps:
s71, clustering by adopting the optimal clustering number obtained in the step S6 through a K-means + + algorithm;
s72, counting the number of each cluster, and selecting the cluster with the largest number as a main cluster;
s73, processing the main cluster by adopting a 3 sigma rule, and selecting the maximum value and the minimum value of the processed main cluster to form an upper limit and a lower limit of an enterprise energy consumption standard interval;
and S74, repeating the steps S71-S73 until the energy consumption specification intervals of each scene of the enterprise under all the energy consumption modes are obtained.
It should be further noted that, in step S8, the energy consumption data exception is adopted as a basis for an enterprise fault, and the method includes the following steps:
s81, collecting enterprise operation parameters provided by an enterprise;
s82, carrying out normalization processing on the enterprise operation parameters and the energy consumption values;
and S83, defining the similarity between the enterprise energy consumption curve and each parameter curve.
It should be further noted that step S9 further includes the following steps:
s91, when detecting that the enterprise energy consumption is abnormal, recording an abnormal time period, and transmitting fault parameters corresponding to the abnormal time period to related enterprises;
s92, the enterprise receives the fault parameters, monitors and searches for specific faults in real time, and feeds back the fault types as labels to the enterprise energy consumption abnormity studying and judging system in a data communication mode;
and S93, carrying out initial clustering on the faults by the enterprise energy consumption abnormity studying and judging system, and determining the initial point clustering center and the number of initial clusters.
It should be further noted that step S10 specifically includes the following steps: s101, the number of initial clusters is k, and the initial cluster center
Figure 25563DEST_PATH_IMAGE020
;
Wherein the content of the first and second substances,
Figure 245192DEST_PATH_IMAGE021
n represents the number of the fault-related parameters;
s102, calculating the distance from the real-time data to each initial clustering center;
s103, updating the number of the clustering central points;
and S104, adaptively matching the sampling points to the cluster where each clustering center is located, and continuously updating the clustering centers.
And S105, matching the real-time abnormal energy consumption data to the cluster class where the cluster center closest to the real-time abnormal energy consumption data is located, acquiring an abnormal cause, and verifying the cause.
The invention also provides an enterprise energy consumption abnormity cause analysis system under the multidimensional scene, which comprises: the system comprises a data acquisition module, a preprocessing module, an energy consumption calculation module, a curve processing module, a scene division module, a clustering processing module, an energy consumption interval construction module, an abnormality determination module, a scene library establishment module and a study and judgment module;
the data acquisition module is used for acquiring enterprise energy consumption data;
the preprocessing module is used for preprocessing the enterprise energy consumption data;
the energy consumption calculation module is used for calculating the comprehensive energy consumption of carbon emission of the enterprise;
the curve processing module is used for clustering the enterprise energy consumption curves to obtain standard enterprise energy consumption curves in different energy consumption modes;
the scene division module is used for dividing the enterprise energy scene;
the clustering processing module is used for determining an optimal clustering number K based on the contour coefficient and the separation index;
the energy consumption interval construction module is used for constructing an enterprise energy consumption standard interval based on a K-means + + algorithm;
the abnormity determining module is used for determining an enterprise energy consumption abnormity characteristic parameter;
the scene library establishing module is used for establishing an enterprise energy consumption abnormal typical scene library;
the studying and judging module is used for studying and judging the abnormal cause of the energy consumption of the enterprise.
According to the technical scheme, the invention has the following advantages:
the enterprise energy consumption abnormity cause analysis method under the multidimensional scene comprises energy consumption standard formulation and scene analysis under different energy consumption modes, enterprise energy consumption time-sharing abnormity judgment under the multidimensional scene, enterprise energy consumption abnormity characteristic parameter determination, establishment of an enterprise energy consumption abnormity typical scene library and enterprise energy consumption abnormity cause study and judgment. The construction method of the complete enterprise energy consumption abnormity studying and judging system improves the accuracy of enterprise energy consumption abnormity studying and judging and cause analysis.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for analyzing causes of abnormal energy consumption of an enterprise in a multidimensional scenario.
FIG. 2 is a boxcar diagram of a Pattern 1 Enterprise energy consumption Standard Cluster class of the present invention.
FIG. 3 is a graph of contour coefficients for different cluster numbers according to the present invention.
FIG. 4 is a diagram showing the PC and SE and the overall evaluation index C for different numbers of clusters according to the present invention.
FIG. 5 is a graph of contour coefficients for different cluster numbers according to the present invention.
FIG. 6 is a flowchart of the K-means + + algorithm.
FIG. 7 is a diagram illustrating the division of the enterprise energy consumption specification interval according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
In the method and system for analyzing the cause of the enterprise energy consumption anomaly in the multidimensional scene under the mass data, the units and the algorithm steps of each example described in the disclosed embodiments can be realized by electronic hardware, computer software or a combination of the electronic hardware and the computer software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the method and the system for analyzing the causes of the enterprise energy consumption anomaly in the multidimensional scene, the block diagrams shown in the attached drawings are only functional entities and do not necessarily correspond to physically independent entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
As shown in fig. 1 to 7, the invention provides a method for analyzing an enterprise energy consumption abnormal cause in a multidimensional scene, which comprises the following steps:
s1, acquiring enterprise energy consumption data; the enterprise energy consumption data can be acquired through the data sensor and the data acquisition equipment, and the type of the enterprise energy consumption data can be specifically acquired and set according to actual needs. Of course, the enterprise energy consumption data includes, but is not limited to, electricity consumption, water consumption, gas consumption, carbon dioxide emission, and the like.
S2, the enterprise energy consumption data processing mainly comprises the steps of removing abnormal values of the enterprise energy consumption data and filling missing values, searching abnormal values in the energy consumption data based on the box type graph, and calculating average values of the data before and after the missing values by adopting an average filling method to fill, wherein the filling formula is as follows:
Figure 429048DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 392325DEST_PATH_IMAGE002
the data representing the energy consumption is presented,
Figure 141975DEST_PATH_IMAGE003
indicating the data sequence number.
S3, calculating the comprehensive energy consumption of carbon emission of the enterprise; comprehensive energy consumption calculation of carbon emission of enterprises can be considered. The method specifically comprises the following steps:
s31, uniformly and equivalently converting the energy consumption data of different types into ton standard coal, and performing addition calculation; aiming at the problem that the energy consumption of enterprises of different scales is difficult, the energy consumption data of each enterprise is subjected to standardized processing based on the annual GDP total value of the enterprise, and the standardized processing formula is as follows:
Figure 735768DEST_PATH_IMAGE022
in the formula (I), the compound is shown in the specification,
Figure 938079DEST_PATH_IMAGE005
the daily energy consumption of the enterprise after standardized treatment is shown,
Figure 970626DEST_PATH_IMAGE006
representing the enterprise's original daily energy consumption data,
Figure 778045DEST_PATH_IMAGE007
the GDP is a specified standard enterprise year GDP total value, and G is an enterprise actual year GDP total value;
s32, constructing a formula for calculating carbon dioxide emission of enterprises:
Figure 357054DEST_PATH_IMAGE008
wherein CEE is the total carbon dioxide emission of enterprises,
Figure 312241DEST_PATH_IMAGE009
the total consumption of the natural gas of enterprises,
Figure 555003DEST_PATH_IMAGE010
is a carbon dioxide emission factor of natural gas of enterprises,
Figure 279246DEST_PATH_IMAGE011
b is the total consumption of the electric energy of the enterprise, b is the carbon dioxide emission factor of the power grid,
Figure 277158DEST_PATH_IMAGE012
c is the carbon dioxide emission factor of the coal of the enterprise.
（a=5.62×10 4 t/m 3 , b=0.7707t/MWh=2.54t/tce）。
S4, clustering the enterprise energy consumption curve to obtain a standard enterprise energy consumption curve;
s41, determining the optimal number of clusters;
s42, reducing the dimension of the enterprise energy consumption curve based on a segmented aggregation approximation algorithm (PAA);
given length N enterprise energy consumption time series curve
Figure 657323DEST_PATH_IMAGE023
Converting it into a sequence of length n
Figure 500515DEST_PATH_IMAGE024
Wherein n is<And N is added. The voltage reduction ratio of the enterprise energy consumption curve is r = N/N, and
Figure 344843DEST_PATH_IMAGE025
satisfies the following conditions:
Figure 248077DEST_PATH_IMAGE026
s43, carrying out clustering analysis on the enterprise energy consumption curve by adopting a DBSCAN clustering algorithm to obtain different energy consumption modes of the enterprise;
and S44, drawing curve clusters in each energy consumption mode into box line graphs, and selecting data median connection lines as standard energy consumption curves for dividing subsequent energy consumption scenes.
The invention selects 96 working day energy consumption curves for research, and the number of each curve mode is shown in the following table:
watch 1
Mode 1 Mode 2 Mode 3
87 5 4
Selecting the energy consumption mode 1 with the most energy consumption curves for research, and obtaining the standard energy consumption curve of the enterprise type as shown in fig. 2;
s5, dividing the energy use scene of the enterprise;
referring to fig. 2, the energy-use scene in the enterprise mode 1 can be obtained by using the DBSCAN clustering algorithm, wherein a scene 1 is from 1 month to 8 months, and a scene 2 is from 9 months to 12 months.
S6, determining an optimal clustering number K based on the contour coefficient and the separation index;
s61, carrying out preliminary selection on the optimal clustering number by adopting a contour coefficient method (SC), and selecting the value range of the optimal clustering number;
Figure 115538DEST_PATH_IMAGE027
in the formula:
Figure 762420DEST_PATH_IMAGE028
the contour coefficient of the point i is represented,
Figure 461255DEST_PATH_IMAGE029
representing the average distance of point i from all points of the nearest cluster class,
Figure 541250DEST_PATH_IMAGE030
representing point i as well as all of the same cluster pointAn elemental distance average;
the contour coefficient method (SC) is adopted for preliminary selection, and the calculation result is shown in figure 3; the optimal clustering number cannot be determined by the contour coefficient index alone, so the final clustering number is further determined by adopting the comprehensive evaluation index C;
s62, defining cluster comprehensive evaluation index C
Figure 630428DEST_PATH_IMAGE013
Wherein PC represents a membership coefficient and SE represents a separation index;
Figure 81001DEST_PATH_IMAGE014
wherein k denotes a kth cluster class, n denotes an nth sample, m is a clustering dimension,
Figure 634342DEST_PATH_IMAGE015
representing the membership degree of the data point n belonging to the i class;
Figure 879379DEST_PATH_IMAGE016
wherein N represents the total number of data, k represents the kth cluster class, N represents the nth sample,
Figure 721433DEST_PATH_IMAGE015
the data point n belongs to the membership of class i,
Figure 710118DEST_PATH_IMAGE017
and
Figure 117965DEST_PATH_IMAGE018
a cluster class center representing cluster classes i and j,
Figure 799482DEST_PATH_IMAGE019
represents the nth sample number.
The nth number of samples.
The calculation result is shown in fig. 4, when k is 2, the comprehensive evaluation index of the clustering result is optimal and is obviously superior to the comprehensive evaluation index when k = 3; therefore, the optimal cluster number is determined to be 2.
S7, constructing enterprise energy consumption standard intervals of each scene under different energy consumption modes of the enterprise
S71, clustering by adopting the optimal clustering number obtained in the step S6 through a K-means + + algorithm, wherein the working flow of the K-means + + algorithm is shown in figure 5;
s72, counting the number of each cluster, and selecting the cluster with the largest number as a main cluster; after clustering analysis, the clustering division conditions of enterprise energy consumption are obtained and are shown in tables II and III; it can be seen that the number of data points of cluster 2 is 207 at most;
watch two
Clusters and the like 1 2
Clustering center (420.0,1209.5) (181.2，512.6)
Watch III
Clusters and the like 1 2
Number of data 40 207
S73, establishing the basis of the enterprise energy consumption specification interval, namely selecting the most representative data as the standard of the enterprise energy consumption, and if the upper limit and the lower limit of the cluster 2 are directly used as the upper limit and the lower limit of the enterprise energy consumption specification interval, the enterprise energy consumption abnormity is researched and judged to be invalid due to loose upper limit and lower limit. Therefore, the abnormal values of the energy consumption data main clusters obtained by clustering are removed, and the finally obtained enterprise energy consumption standard interval is shown in fig. 6, namely the upper and lower limits of the total enterprise energy consumption standard are [159.89tce,217.93tce ], and the upper and lower limits of the enterprise carbon emission standard are [454.38t,572.42t ]. And removing abnormal values in the main cluster based on the box line graph, and finally generating an enterprise energy consumption specification interval, as shown in fig. 7.
And S74, repeating the steps S71-S73 until the energy consumption specification intervals of each scene of the enterprise under all the energy consumption modes are obtained.
S8, determining abnormal characteristic parameters of enterprise energy consumption;
s81, acquiring enterprise operation parameters provided by related enterprises;
s82, normalizing the enterprise operation parameters and the energy consumption values;
s83, defining similarity between the enterprise energy consumption curve and each parameter curve:
s831, calculating the Spireman correlation coefficient between the energy consumption curve and each parameter curve;
the spearman correlation coefficient calculation formula is as follows:
Figure 863253DEST_PATH_IMAGE031
wherein d is i Representing the bit order difference value of the ith sample, and N represents the total number of samples;
the parameters which are consistent with the energy consumption change trend can be found out by applying the formula, but the calculation error of the parameters which are opposite to the energy consumption change trend is larger, so that the spearman calculation method is further improved to enable the selected relevant parameters to be more accurate;
Figure 1
wherein
Figure 917983DEST_PATH_IMAGE033
And
Figure 967804DEST_PATH_IMAGE034
the average ordering of the variables x, y,
Figure 50030DEST_PATH_IMAGE035
and
Figure 911675DEST_PATH_IMAGE036
is the order of the ith sample, N represents the total number of samples;
s832, carrying out correlation calculation on the enterprise energy consumption curve and each parameter curve of enterprise operation through the improved Spireman correlation coefficient formula, and selecting
Figure 2
The larger value parameter is used as a fault related parameter;
selecting 8 random operation parameters of an enterprise to compare the similarity of an enterprise energy consumption curve with each parameter curve, selecting energy consumption fault related parameters, and calculating results shown in a table IV;
watch four
Operating parameters X1 X2 X3 X4 X5 X6 X7 X8
p 0.941 0.528 0.421 0.227 0.854 0.269 0.538 0.754
Setting phasesA margin of similarity of
Figure 786276DEST_PATH_IMAGE039
X in the above table 1 ，X 5 And X 8 The similarity value meets the requirement, whether the energy consumption abnormal time period parameter has a corresponding extreme value is verified, and if the similarity value meets the requirement, the energy consumption abnormal time period parameter can be used as an energy consumption fault related parameter.
S9, establishing an enterprise energy consumption abnormal typical scene library;
s91, when the enterprise energy consumption abnormity studying and judging system detects that the enterprise energy consumption is abnormal, recording an abnormal time period, and transmitting fault phase parameters corresponding to the abnormal time period to related enterprises;
s92, the enterprise receives the relevant fault parameters, carries out real-time monitoring inside the enterprise to find specific faults, and feeds back the fault types as labels to the enterprise energy consumption abnormity studying and judging system;
s93, carrying out initial clustering on the faults to determine initial point clustering centers and initial clustering numbers;
and S10, judging the causes of the abnormal energy consumption of the enterprise.
S101, the number of initial clusters is k, and the initial cluster center
Figure 824639DEST_PATH_IMAGE040
;
Wherein the content of the first and second substances,
Figure 958817DEST_PATH_IMAGE041
n represents the number of the fault-related parameters;
s102, calculating the distance from the real-time data to each initial clustering center, wherein the following distance formula can be selected for calculation:
(1) the euclidean sum distance formula;
(2) a cosine distance formula;
the calculation amount is large due to the fact that the number of related parameters of the enterprise fault is large, and the calculation amount can be effectively reduced by adopting the formula (2) to calculate the data distance;
s103, updating the number of the clustering central points; because the typical scenes of the enterprise energy consumption faults have diversity, the initial typical scene can not completely cover all scenes, each sample point is verified to achieve the purpose of expanding the enterprise energy consumption abnormal library, and the judgment basis is as follows: if d is greater than dmax, adding a clustering center;
wherein d is the distance from the sample point to the center of the nearest cluster class, and dmax is the farthest distance from the cluster point to the cluster center point; similarity calculation is carried out on the newly added clustering centers, and whether the clustering centers are added or not is finally determined;
s104, adaptively matching sampling points to the cluster where each clustering center is located, and continuously updating the clustering centers;
and S105, matching the real-time abnormal energy consumption data to the cluster class where the cluster center closest to the real-time abnormal energy consumption data is located, acquiring an abnormal cause, and verifying the cause.
In summary, the invention provides an enterprise energy consumption abnormity cause analysis method under a multidimensional scene, which comprises energy consumption standard formulation and scene analysis under different energy consumption modes, enterprise energy consumption time-sharing abnormity judgment under the multidimensional scene, enterprise energy consumption abnormity characteristic parameter determination, establishment of an enterprise energy consumption abnormity typical scene library and enterprise energy consumption abnormity cause study and judgment. The construction method of the complete enterprise energy consumption abnormity studying and judging system improves the accuracy of enterprise energy consumption abnormity studying and judging and cause analysis.
Based on the method, the invention also provides an enterprise energy consumption abnormity studying and judging system, which comprises: the system comprises a data acquisition module, a preprocessing module, an energy consumption calculation module, a curve processing module, a scene division module, a clustering processing module, an energy consumption interval construction module, an abnormality determination module, a scene library establishment module and a study and judgment module;
the data acquisition module is used for acquiring enterprise energy consumption data; the preprocessing module is used for preprocessing the enterprise energy consumption data; the energy consumption calculation module is used for calculating the comprehensive energy consumption of carbon emission of the enterprise; the curve processing module is used for clustering the enterprise energy consumption curve to obtain a standard enterprise energy consumption curve; the scene division module is used for dividing energy scenes for enterprises; the clustering processing module is used for determining an optimal clustering number K based on the contour coefficient and the separation index; the energy consumption interval construction module is used for constructing an enterprise energy consumption standard interval based on a K-means + + algorithm; the abnormity determining module is used for determining an enterprise energy consumption abnormity characteristic parameter; the scene library establishing module is used for establishing an enterprise energy consumption abnormal typical scene library; the studying and judging module is used for studying and judging the abnormal cause of the energy consumption of the enterprise.
Based on the enterprise energy consumption standard interval construction and abnormal cause analysis system under the multidimensional scene, the enterprise energy consumption data can be preprocessed; calculating and standardizing comprehensive energy consumption considering carbon emission of enterprises; acquiring standard enterprise energy consumption curves in different energy consumption modes through enterprise energy consumption curve clustering; dividing energy scenes for enterprises; determining an optimal clustering number K based on the contour coefficient and the separation index; establishing an enterprise energy consumption standard interval of each scene under different energy consumption modes of an enterprise based on a K-means + + algorithm; determining an enterprise energy consumption abnormal characteristic parameter; establishing a typical scene library for enterprise energy consumption abnormity; studying and judging the causes of abnormal energy consumption of enterprises; the invention provides establishment of an enterprise energy consumption dynamic standard interval based on multi-energy coordination application in consideration of enterprise energy consumption classification and time scene division, and improves accuracy of enterprise energy consumption abnormity study and judgment.
The system for building the enterprise energy consumption specification interval and analyzing the abnormal cause in the multidimensional scene is the units and algorithm steps of each example described in connection with the embodiments disclosed herein, and can be implemented by electronic hardware, computer software, or a combination of the two. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Those skilled in the art will appreciate that aspects of the system and method for enterprise energy consumption specification interval construction and anomaly cause analysis in a multidimensional scenario may be implemented as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. The method for analyzing the cause of the abnormal energy consumption of the enterprise under the multidimensional scene is characterized by comprising the following steps:
s1, acquiring enterprise energy consumption data;
s2, preprocessing the enterprise energy consumption data;
s3, calculating the comprehensive energy consumption of carbon emission of the enterprise;
s4, clustering the enterprise energy consumption curves to obtain standard enterprise energy consumption curves in different energy consumption modes;
s5, acquiring an enterprise energy utilization scene based on the standard enterprise energy consumption curve;
s6, determining an optimal clustering number K based on the contour coefficient and the separation index;
s7, constructing enterprise energy consumption standard intervals of each scene under different energy consumption modes of an enterprise;
s8, determining abnormal characteristic parameters of enterprise energy consumption;
s9, establishing an enterprise energy consumption abnormal typical scene library;
s91, when detecting that the enterprise energy consumption is abnormal, recording an abnormal time period, and transmitting fault parameters corresponding to the abnormal time period to related enterprises;
s92, the enterprise receives the fault parameters, monitors and searches for specific faults in real time, and feeds back the fault types as labels to the enterprise energy consumption abnormity studying and judging system in a data communication mode;
s93, carrying out initial clustering on the faults by the enterprise energy consumption abnormity studying and judging system, and determining an initial point clustering center and the number of initial clusters;
s10, studying and judging the causes of abnormal energy consumption of enterprises;
s101, the number of initial clusters is k, and the initial cluster center
Figure 323326DEST_PATH_IMAGE001
;
Wherein the content of the first and second substances,
Figure 33619DEST_PATH_IMAGE002
n represents the number of the fault-related parameters;
s102, calculating the distance from the real-time data to each initial clustering center;
s103, updating the number of the clustering central points;
s104, adaptively matching sampling points to the cluster where each clustering center is located, and continuously updating the clustering centers;
and S105, matching the real-time abnormal energy consumption data to the cluster class where the cluster center closest to the real-time abnormal energy consumption data is located, acquiring an abnormal cause, and verifying the cause.
2. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
the preprocessing of the enterprise energy consumption data in step S2 includes: removing abnormal values of the enterprise energy consumption data and filling missing values, wherein the filling formula is as follows:
Figure 586960DEST_PATH_IMAGE003
in the formula (I), the compound is shown in the specification,
Figure 97576DEST_PATH_IMAGE004
the data representing the energy consumption is presented,
Figure 1947DEST_PATH_IMAGE005
indicating the data sequence number.
3. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
step S3 further includes:
s31, uniformly and equivalently converting the energy consumption data of different types into ton standard coal, and performing addition calculation;
standardizing the energy consumption data of each enterprise based on the GDP total value of the enterprise year, wherein the standardized processing formula is as follows:
Figure 990631DEST_PATH_IMAGE006
in the formula (I), the compound is shown in the specification,
Figure 132900DEST_PATH_IMAGE007
the daily energy consumption of the enterprise after standardized treatment is shown,
Figure 814417DEST_PATH_IMAGE008
representing the enterprise's original daily energy consumption data,
Figure 674925DEST_PATH_IMAGE009
the GDP is a specified standard enterprise year GDP total value, and G is an enterprise actual year GDP total value;
s32, constructing a formula for calculating carbon dioxide emission of enterprises:
Figure 201722DEST_PATH_IMAGE010
wherein CEE is the total carbon dioxide emission of enterprises,
Figure 198497DEST_PATH_IMAGE011
the total consumption of the natural gas of enterprises,
Figure 785336DEST_PATH_IMAGE012
is the carbon dioxide emission factor of natural gas of enterprisesThe combination of the sub-components,
Figure 139000DEST_PATH_IMAGE013
b is the total consumption of the electric energy of the enterprise, b is the carbon dioxide emission factor of the power grid,
Figure 203908DEST_PATH_IMAGE014
c is the carbon dioxide emission factor of the coal of the enterprise.
4. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
step S4 specifically includes:
s41, determining the optimal number of clusters;
s42, reducing the dimension of the enterprise energy consumption curve based on a piecewise aggregation approximation algorithm;
s43, carrying out clustering analysis on the enterprise energy consumption curve by adopting a DBSCAN clustering algorithm to obtain different energy consumption modes of the enterprise;
and S44, drawing curve clusters in each energy consumption mode into box line graphs, and selecting data median connection lines as standard energy consumption curves for dividing subsequent energy consumption scenes.
5. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
step S6 further includes the steps of:
s61, carrying out preliminary selection on the optimal clustering number by adopting a contour coefficient method, and selecting a value range of the optimal clustering number;
s62, defining cluster comprehensive evaluation index C
Figure 320768DEST_PATH_IMAGE015
Wherein PC represents a membership coefficient and SE represents a separation index;
Figure 78509DEST_PATH_IMAGE016
wherein k denotes a kth cluster class, n denotes an nth sample, m is a clustering dimension,
Figure 382451DEST_PATH_IMAGE017
representing the membership degree of the data point n belonging to the i class;
Figure 516629DEST_PATH_IMAGE018
wherein N represents the total number of data, k represents the kth cluster class, N represents the nth sample,
Figure 753576DEST_PATH_IMAGE017
the data point n belongs to the membership of class i,
Figure 151059DEST_PATH_IMAGE019
and
Figure 473456DEST_PATH_IMAGE020
a cluster class center representing cluster classes i and j,
Figure 145746DEST_PATH_IMAGE021
represents the nth sample number.
6. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
step S7 further includes the steps of:
s71, clustering by adopting the optimal clustering number obtained in the step 5 through a K-means + + algorithm;
s72, counting the number of each cluster, and selecting the cluster with the largest number as a main cluster;
s73, processing the main cluster by adopting a 3 sigma rule, and selecting the maximum value and the minimum value of the processed main cluster to form an upper limit and a lower limit of an enterprise energy consumption standard interval;
and S74, repeating the steps S71-S73 until the energy consumption specification intervals of each scene of the enterprise under all the energy consumption modes are obtained.
7. The method for analyzing enterprise energy consumption abnormality cause under multi-dimensional scene as claimed in claim 1,
in step S8, the energy consumption data exception is used as a basis for an enterprise fault, and the method includes the following steps:
s81, collecting enterprise operation parameters provided by an enterprise;
s82, carrying out normalization processing on the enterprise operation parameters and the energy consumption values;
and S83, defining the similarity between the enterprise energy consumption curve and each parameter curve.
8. An enterprise energy consumption abnormal cause analysis system under a multi-dimensional scene is characterized in that the system adopts the enterprise energy consumption abnormal cause analysis method under the multi-dimensional scene as claimed in any one of claims 1 to 7;
the system comprises: the system comprises a data acquisition module, a preprocessing module, an energy consumption calculation module, a curve processing module, a scene division module, a clustering processing module, an energy consumption interval construction module, an abnormality determination module, a scene library establishment module and a study and judgment module;
the data acquisition module is used for acquiring enterprise energy consumption data;
the preprocessing module is used for preprocessing the enterprise energy consumption data;
the energy consumption calculation module is used for calculating the comprehensive energy consumption of carbon emission of the enterprise;
the curve processing module is used for clustering the enterprise energy consumption curves to obtain standard enterprise energy consumption curves in different energy consumption modes;
the scene division module is used for dividing energy scenes for enterprises;
the clustering processing module is used for determining an optimal clustering number K based on the contour coefficient and the separation index;
the energy consumption interval construction module is used for constructing energy consumption standard intervals of all scenes under different energy consumption modes of an enterprise;
the abnormity determining module is used for determining an enterprise energy consumption abnormity characteristic parameter;
the scene library establishing module is used for establishing an enterprise energy consumption abnormal typical scene library;
the studying and judging module is used for studying and judging the abnormal cause of the energy consumption of the enterprise.
CN202210452617.1A 2022-04-27 2022-04-27 Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene Pending CN115081795A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210452617.1A CN115081795A (en) 2022-04-27 2022-04-27 Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210452617.1A CN115081795A (en) 2022-04-27 2022-04-27 Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene

Publications (1)

Publication Number Publication Date
CN115081795A true CN115081795A (en) 2022-09-20

Family

ID=83247786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210452617.1A Pending CN115081795A (en) 2022-04-27 2022-04-27 Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene

Country Status (1)

Country Link
CN (1) CN115081795A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115329910A (en) * 2022-10-17 2022-11-11 南通坤鹏科技有限公司 Intelligent processing method for enterprise production emission data
CN115471145A (en) * 2022-11-15 2022-12-13 碳管家智能云平台有限公司 Enterprise energy consumption double-control management method, device and medium
CN116050859A (en) * 2022-12-07 2023-05-02 国义招标股份有限公司 Dynamic datum line carbon emission transaction method and system based on big data
CN116893297A (en) * 2023-09-11 2023-10-17 常州旭泰克系统科技有限公司 Method and system for monitoring energy consumption of rotating equipment
CN117610699A (en) * 2023-09-04 2024-02-27 北京中电飞华通信有限公司 Zero-carbon comprehensive energy optimization equipment and method applied to park

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115329910A (en) * 2022-10-17 2022-11-11 南通坤鹏科技有限公司 Intelligent processing method for enterprise production emission data
CN115471145A (en) * 2022-11-15 2022-12-13 碳管家智能云平台有限公司 Enterprise energy consumption double-control management method, device and medium
CN116050859A (en) * 2022-12-07 2023-05-02 国义招标股份有限公司 Dynamic datum line carbon emission transaction method and system based on big data
CN116050859B (en) * 2022-12-07 2023-11-14 国义招标股份有限公司 Dynamic datum line carbon emission transaction method and system based on big data
CN117610699A (en) * 2023-09-04 2024-02-27 北京中电飞华通信有限公司 Zero-carbon comprehensive energy optimization equipment and method applied to park
CN116893297A (en) * 2023-09-11 2023-10-17 常州旭泰克系统科技有限公司 Method and system for monitoring energy consumption of rotating equipment
CN116893297B (en) * 2023-09-11 2024-01-12 常州旭泰克系统科技有限公司 Method and system for monitoring energy consumption of rotating equipment

Similar Documents

Publication Publication Date Title
CN115081795A (en) Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene
CN109034244B (en) Line loss abnormity diagnosis method and device based on electric quantity curve characteristic model
CN113267692B (en) Low-voltage transformer area line loss intelligent diagnosis and analysis method and system
CN113011481B (en) Electric energy meter function abnormality assessment method and system based on decision tree algorithm
CN109583679A (en) A kind of stealing Suspected Degree analysis method of more algorithm fusions
CN114861788A (en) Load abnormity detection method and system based on DBSCAN clustering
CN109947815B (en) Power theft identification method based on outlier algorithm
CN111709668A (en) Power grid equipment parameter risk identification method and device based on data mining technology
CN116148753A (en) Intelligent electric energy meter operation error monitoring system
CN116796403A (en) Building energy saving method based on comprehensive energy consumption prediction of commercial building
CN115905904A (en) Line loss abnormity evaluation method and device for power distribution network feeder line
CN114266457A (en) Method for detecting different loss inducement of distribution line
CN111366889B (en) Abnormal electricity utilization detection method for intelligent electric meter
CN117559443A (en) Ordered power utilization control method for large industrial user cluster under peak load
CN113127464A (en) Agricultural big data environment feature processing method and device and electronic equipment
CN111506636A (en) System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm
CN116307886A (en) Method and device for monitoring production state of enterprise in real time
CN115905319A (en) Automatic identification method and system for abnormal electricity charges of massive users
CN113723671A (en) Data clustering analysis method based on big data of power utilization condition
CN112307671A (en) Method for self-adapting to different large-scale equipment instrument state threshold values
CN114781685B (en) Large user electricity load prediction method and system based on big data mining technology
CN117834455B (en) Electric power Internet of things data transmission simulation method and system
CN111626586B (en) Data quality detection method, device, computer equipment and storage medium
CN115473343B (en) Intelligent gateway multi-master-station parallel access test method
CN117575176B (en) Processing method and system for abnormal value in power data

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