CN111598385A - Method and system for determining power utilization behavior based on fuzzy hierarchical analysis and comprehensive evaluation - Google Patents
Method and system for determining power utilization behavior based on fuzzy hierarchical analysis and comprehensive evaluation Download PDFInfo
- Publication number
- CN111598385A CN111598385A CN202010264697.9A CN202010264697A CN111598385A CN 111598385 A CN111598385 A CN 111598385A CN 202010264697 A CN202010264697 A CN 202010264697A CN 111598385 A CN111598385 A CN 111598385A
- Authority
- CN
- China
- Prior art keywords
- index
- matrix
- fuzzy
- evaluation
- determining
- 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.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 241
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 239000011159 matrix material Substances 0.000 claims abstract description 224
- 230000005611 electricity Effects 0.000 claims abstract description 136
- 230000008569 process Effects 0.000 claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 24
- 230000001186 cumulative effect Effects 0.000 claims description 11
- 230000006399 behavior Effects 0.000 abstract description 80
- 238000004364 calculation method Methods 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000010224 classification analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000004148 unit process 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for determining power utilization behaviors based on fuzzy hierarchical analysis and comprehensive evaluation, which comprises the steps of determining a primary characteristic index and a secondary characteristic index for describing the power utilization behaviors of a user, determining an evaluation set matrix according to a selected index system, calculating a judgment matrix constructed by a fuzzy hierarchical analysis method and a fuzzy comprehensive evaluation method and a fuzzy evaluation matrix to obtain a fuzzy comprehensive evaluation set of the user, and judging whether the suspicion of electricity stealing of the user exceeds a reasonable range according to a set threshold value so as to judge an abnormal power utilization user. The invention analyzes the electricity utilization behavior of the user by multiple layers and multiple dimensions, and reserves all required information to the maximum extent under the condition of comprehensively considering multiple factors; meanwhile, the electricity stealing suspicion degree of the user is calculated by adopting a method combining a fuzzy analytic hierarchy process and fuzzy comprehensive evaluation, the one-sidedness of the traditional single characteristic weight calculation method is avoided, and the accuracy of describing the electricity utilization behaviors of the user by different electricity utilization characteristic indexes can be accurately measured.
Description
Technical Field
The invention relates to the technical field of power utilization anomaly detection of a power system, in particular to a method and a system for determining power utilization behaviors based on fuzzy hierarchical analysis and comprehensive evaluation.
Background
At present, the development of the power industry plays an important role in the economic growth of China and is closely related to the daily life of people. However, at present, the power grid has large power transmission and distribution losses in operation, and the losses are divided into technical losses and non-technical losses, and the technical losses are inevitable. The non-technical loss refers to abnormal power utilization of users, such as electricity stealing and the like. According to the related data, the electricity stealing is one of the main reasons for the great increase of the comprehensive value of the line loss of the power grid. The harm caused by electricity stealing is huge, which not only disturbs the normal power market order, but also the electricity stealing dangerous operation may cause equipment short circuit and damage the power line, and also may change the state of the power transmission and distribution equipment, endangering the life safety of peripheral personnel. Traditionally, electricity stealing behavior detection mainly depends on a power supply enterprise sending technical personnel to go on the door to carry out electricity inspection, and the electricity stealing behavior detection device is low in efficiency, high in consumption and huge in manpower and material resource consumption.
Therefore, a method for efficiently and accurately determining the abnormal electricity consumption behavior of the user is urgently needed.
Disclosure of Invention
The invention provides a method and a system for determining power utilization behaviors based on fuzzy hierarchical analysis and comprehensive evaluation, and aims to solve the problem of how to determine abnormal power utilization behaviors of users.
In order to solve the above-mentioned problems, according to an aspect of the present invention, there is provided a method of determining electricity usage behavior based on fuzzy hierarchical analysis and comprehensive evaluation, the method including:
determining a primary index set and a secondary index set according to the category of the target object, and respectively constructing a primary index evaluation set matrix and a secondary index evaluation set matrix;
determining the membership degree of the electricity consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix, and determining the fuzzy evaluation matrix of each secondary index according to the membership degree;
determining a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix;
determining a fuzzy comprehensive evaluation set of each secondary index according to the product of the secondary index weight set matrix and the fuzzy evaluation matrix of each secondary index, and constructing the fuzzy evaluation matrix of the primary index by using the fuzzy comprehensive evaluation set of each secondary index;
determining a primary index weight set matrix by using a fuzzy analytic hierarchy process based on the primary index set;
determining a fuzzy comprehensive evaluation set of the power utilization state according to the product of the primary index weight set matrix and the fuzzy evaluation matrix of the primary index;
and determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states, and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state.
Preferably, the determining a primary index set and a secondary index set according to the category of the target object includes:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
Preferably, the constructing the fuzzy evaluation matrix of each secondary index according to the membership degree includes:
wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1,v2,…,vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1,rj2,…,rjs}，rj1,rj2,…,rjsTo evaluate the rating as vjThe membership range of time.
Preferably, the determining a secondary index weight set matrix a by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix comprises:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
Preferably, the determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state includes:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
According to another aspect of the present invention, there is provided a system for determining electricity usage behavior based on fuzzy hierarchy analysis and comprehensive evaluation, the system comprising:
the index set and index evaluation set matrix determining unit is used for determining a primary index set and a secondary index set according to the category of the target object and respectively constructing a primary index evaluation set matrix and a secondary index evaluation set matrix V;
the fuzzy evaluation matrix determining unit of the secondary indexes is used for determining the membership degree of the electricity consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix V and determining the fuzzy evaluation matrix R of each secondary index according to the membership degree;
the secondary index weight set matrix determining unit is used for determining a secondary index weight set matrix A by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix V;
the fuzzy evaluation matrix determining unit of the primary index is used for determining a fuzzy comprehensive evaluation set B of each secondary index according to the product of the secondary index weight set matrix A and the fuzzy evaluation matrix R of each secondary index, and constructing a fuzzy evaluation matrix R' of the primary index by using the fuzzy comprehensive evaluation set B of each secondary index;
the first-level index weight set matrix determining unit is used for determining a first-level index weight set matrix A' by using a fuzzy analytic hierarchy process based on the first-level index set;
the power utilization state fuzzy comprehensive evaluation set determining unit is used for determining a power utilization state fuzzy comprehensive evaluation set according to the product of the primary index weight set matrix and the primary index fuzzy evaluation matrix R';
and the power utilization behavior determining unit is used for determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state.
Preferably, the index set and index evaluation set matrix determining unit determines a primary index set and a secondary index set according to the category of the target object, and includes:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
Preferably, the fuzzy evaluation matrix determining unit of the secondary indexes constructs a fuzzy evaluation matrix of each secondary index according to the membership degree, and includes:
wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1,v2,…,vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1,rj2,…,rjs}，rj1,rj2,…,rjsTo evaluate the rating as vjThe membership range of time.
Preferably, the determining unit of the secondary index weight set matrix determines the secondary index weight set matrix a by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix, and includes:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
Preferably, the determining unit of the power consumption behavior determines the occurrence probability of each power consumption state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power consumption states, and determines the power consumption behavior of the target object according to the occurrence probability of each power consumption state, including:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
The invention provides a method and a system for determining power consumption behaviors based on fuzzy hierarchical analysis and comprehensive evaluation, which comprises the steps of firstly determining a primary characteristic index and a secondary characteristic index for describing the power consumption behaviors of a user, and determining an evaluation set matrix according to a selected index system; then, calculating a judgment matrix constructed by a fuzzy analytic hierarchy process and a fuzzy comprehensive evaluation method and a fuzzy comprehensive evaluation matrix to obtain a fuzzy comprehensive evaluation set; and finally, judging whether the electricity utilization behavior of the user is abnormal or not according to a set threshold value. According to the invention, by establishing a primary index system and a secondary index system of the power utilization behavior of the user, the power utilization behavior of the user can be analyzed in multiple layers and multiple dimensions, and all required information is reserved to the greatest extent under the condition of comprehensively considering multiple factors; meanwhile, the method combining the fuzzy analytic hierarchy process and the fuzzy comprehensive evaluation is adopted to calculate the electricity stealing suspicion degree of the user, the one-sidedness of the traditional single characteristic weight calculation method is avoided, the accuracy of describing the electricity utilization behaviors of the user by different electricity utilization characteristic indexes can be accurately measured, and the efficiency and the accuracy of detecting the abnormal electricity utilization behaviors are improved.
Drawings
A more complete understanding of exemplary embodiments of the present invention may be had by reference to the following drawings in which:
FIG. 1 is a flow diagram of a method 100 for determining power usage behavior based on fuzzy hierarchy analysis and comprehensive evaluation in accordance with an embodiment of the present invention;
fig. 2 is a block diagram of exemplary features according to an embodiment of the present invention.
FIG. 3 is a flow chart of determining power usage behavior of a single-phase user based on fuzzy hierarchy analysis and comprehensive evaluation according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a system 400 for determining power usage behavior based on fuzzy hierarchy analysis and comprehensive evaluation according to an embodiment of the present invention.
Detailed Description
The exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, however, the present invention may be embodied in many different forms and is not limited to the embodiments described herein, which are provided for complete and complete disclosure of the present invention and to fully convey the scope of the present invention to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the accompanying drawings is not intended to be limiting of the invention. In the drawings, the same units/elements are denoted by the same reference numerals.
Unless otherwise defined, terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Further, it will be understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense.
The intelligent electric meter can accurately record and report the electricity consumption data of the user at a high frequency, and a key foundation is laid for accurately identifying electricity stealing behaviors. Although the user can still adopt various technical means to manipulate or tamper with the reported electric quantity data, the electricity stealing behavior can be identified according to the electricity consumption data of the metering master station. Regardless of how the user steals electricity, their motivation is to reduce the amount of electricity used to earn the amount of differential gain, regardless of peak-to-valley electricity rates, and often to show a significant reduction in electricity usage on the electricity load curve. The existing electricity stealing detection is based on the premise that some related indexes are derived and defined according to the electricity load curve, and then clustering or classification analysis is carried out to identify abnormal users with sudden change of electricity consumption. Through analyzing the electricity stealing means commonly adopted by users in the electricity stealing process, the electricity stealing characteristics of different electricity stealing means are different. Therefore, the relevant characteristic indexes describing electricity stealing means can be further selected according to different electricity stealing characteristics, and the electricity stealing behavior of the user can be detected in multiple layers and multiple angles. Therefore, the embodiment of the invention provides a method and a system for determining power utilization behaviors based on fuzzy hierarchical analysis and comprehensive evaluation.
Fig. 1 is a flow chart of a method 100 for determining power usage behavior based on fuzzy hierarchy analysis and comprehensive evaluation in accordance with an embodiment of the present invention. As shown in fig. 1, the method for determining power consumption behavior based on fuzzy hierarchical analysis and comprehensive evaluation provided by the embodiment of the present invention can analyze the power consumption behavior of a user in multiple levels and multiple dimensions by establishing a primary and secondary index system of the power consumption behavior of the user, and retain all required information to the maximum extent in the case of comprehensively considering multiple factors; meanwhile, the method combining the fuzzy analytic hierarchy process and the fuzzy comprehensive evaluation is adopted to calculate the electricity stealing suspicion degree of the user, the one-sidedness of the traditional single characteristic weight calculation method is avoided, the accuracy of describing the electricity utilization behaviors of the user by different electricity utilization characteristic indexes can be accurately measured, and the efficiency and the accuracy of detecting the abnormal electricity utilization behaviors are improved. The method 100 for determining power utilization behavior based on fuzzy hierarchical analysis and comprehensive evaluation provided by the embodiment of the invention comprises the following steps of starting from step 101, determining a primary index set and a secondary index set according to the category of a target object in step 101, and respectively constructing a primary index evaluation set matrix and a secondary index evaluation set matrix.
Preferably, the determining a primary index set and a secondary index set according to the category of the target object includes:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
In the embodiment of the present invention, according to the common electricity stealing forms (under-voltage method, under-current method, spread spectrum method, phase shift method) of users, the structure for determining the typical characteristics capable of describing the electricity using behaviors of single-phase users and three-phase users is shown in fig. 2, the result divided into the primary index and the secondary index is shown in table 1, and the calculation method of each secondary index is shown in table 2. When the electricity utilization behavior of the target user is determined, the primary index set and the secondary index set can be determined according to actual requirements, and indexes in the primary index set and indexes in the secondary index set are in one-to-one correspondence.
TABLE 1 characteristic index selection results
TABLE 2 two-stage index calculation
In the embodiment of the invention, a two-level index evaluation set matrix V ═ V is set1,v2,…,vm]And according to the selected secondary index set, self-defining setting can be carried out on elements in the secondary index evaluation set matrix. For example, a secondary index evaluation set matrix V ═ V is determined1,v2,v3]If the index exceeds the set threshold by 1.5 times or more, the index approaches the set threshold, and the index is within 0.5 times of the set threshold]. Setting a primary index evaluation set matrix V '═ V'1，v′2，…，v′s]And determining elements in the primary index evaluation set matrix according to the type of the power utilization state. For example, if the types of power usage states include: if the electricity is seriously stolen, stolen and normal, a primary index evaluation set matrix V ═ V is set1，v2，v3]When the electricity is stolen seriously, the electricity is stolen normally]。
In step 102, the membership degree of the electricity consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix is determined, and the fuzzy evaluation matrix of each secondary index is determined according to the membership degree.
Preferably, the constructing the fuzzy evaluation matrix of each secondary index according to the membership degree includes:
wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1，v2，…，vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1，rj2，...，rjs}，rj1，rj2，...，rjsTo evaluate the rating as vjThe membership range of time.
In an embodiment of the present invention, a set of secondary indices U ═ U is set1，u2，…，un]Wherein u is1，u2，…，unRespectively representing each secondary index, and a secondary index evaluation set matrix V ═ V1，v2，…，vm]The second-level index weight set matrix a ═ a1，a2，…，am]，aiFor the ith secondary index, the weighted value of the element in the set matrix V is evaluated, and
the single-factor fuzzy evaluation of the ith secondary index is a fuzzy subset matrix R on Vj＝{rj1，rj2，...，rjs) And the number of s is determined according to the type of the power utilization state. Accordingly, a fuzzy evaluation matrix R of the ith secondary index can be constructedIndex iComprises the following steps:
for example, when s is 3, the fuzzy evaluation matrix R of the i-th secondary indexIndex iComprises the following steps:
wherein r isj1，rj2，rj3Represents a secondary index uiIs rated by vjMembership range of time rj1Is an upper bound, rj3Is the lower bound.
In an embodiment of the invention, the degree of membership is determined using expert scoring. Determining a secondary index evaluation set matrix V ═ V1,v2,v3]If the index exceeds the set threshold by 1.5 times or more, the index approaches the set threshold, and the index is within 0.5 times of the set threshold]. According to each secondary index, a secondary index evaluation set matrix V ═ V1,v2,v3]Quantifying the elements in each secondary index evaluation set matrix, determining the membership degree, and forming a fuzzy evaluation matrix R of each secondary indexIndex i。
In step 103, a secondary index weight set matrix is determined by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix.
Preferably, the determining a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix comprises:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
In the embodiment of the invention, the secondary index weight set matrix A is calculated by a fuzzy analytic hierarchy process according to the acceptable degree of the secondary index exceeding the set threshold value.
Firstly, a fuzzy judgment matrix is constructed, and importance degrees of the index exceeding a set threshold by more than 1.5 times, the index approaching the set threshold and the index being lower than the set threshold by within 0.5 time are compared to judge through a standard value. The relationship between the scale value and the importance is shown in table 3.
TABLE 3 corresponding relationship table of scale values and importance
The comparison is carried out by experts, and the fuzzy numbers (l) are respectively given by dividing 3-bit experts into examples1,m1,u1)、(l2,m2,u2)、(l3,m3,u3) The 3 fuzzy numbers are integrated into one
The above steps are repeated until all comparison results become a fuzzy number. Respectively aiming at C by 3 experts1Index exceeding the set threshold by more than 1.5 times, C2Index close to the set threshold value, C3The index was scored within 0.5 times lower than the set threshold, and the results are shown in Table 4.
Table 4 expert scoring table
C1And C2The 3 comparative fuzzy values of (a) can be integrated into one fuzzy value by the following method:
therefore C1And C2In contrast, the importance levels are: (0.39, 0.67, 1.00), similar calculations for comparative blur values among other factors can yield a blur matrix of:
then, C is calculated1: index is more than 1.5 times of the set threshold value, C2: index close to set threshold value, C3: the index is lower than the integrated weight of the three within 0.5 times of the set threshold value. According to
Wherein a isijAs a fuzzy matrix FCM1C is obtained by calculation1: index is more than 1.5 times of the set threshold value, C2: index close to set threshold value, C3: the initial weight within 0.5 times of the index lower than the set threshold is as follows: dc1＝(0.1509，0.2897，0.5083)，Dc2＝(0.1690，0.3310，0.5314)，Dc3＝(0.1368，0.2731，0.5314)，Dc4＝(0.0658，0.1062，0.2014)。
Then, pair C is defined by the triangular fuzzy number likelihood function1: index is more than 1.5 times of the set threshold value, C2: index close to set threshold value, C3: and performing defuzzification processing on the initial weight within 0.5 time of the index lower than the set threshold. If the fuzzy number M is known1(l1，m1，u1) And M2(l2，m2，u2)，M1＞M2Is defined by a trigonometric fuzzy function as:
the likelihood that one ambiguity number is greater than the other K ambiguity numbers is defined as:
P(M≥M1，M2，......Mk)＝min P(M≥M1)，i＝1，2，...k，
with Dc1The deblurring of (d) is an example:
P(Dc1≥Dc3)＝1，
therefore Dc1Defuzzification to obtain:
d(Dc1)＝minV(Dc1≥Dc2，Dc3)＝min(0.8913，1，1)＝0.8913，
by the same token, obtain Dc2、Dc3The defuzzified values are respectively: 0.8622, and 0.2452.
Finally, D isc1、Dc2、Dc3The defuzzified numerical value is subjected to per unit processing to obtain a second-level index weight set matrix A which is as follows:
in step 104, a fuzzy comprehensive evaluation set of each secondary index is determined according to the product of the secondary index weight set matrix and the fuzzy evaluation matrix of each secondary index, and the fuzzy evaluation matrix of the primary index is constructed by using the fuzzy comprehensive evaluation set of each secondary index.
In the embodiment of the present invention, the fuzzy comprehensive evaluation set B for each secondary index can be calculated based on the fuzzy comprehensive evaluation set calculation formula B ═ a · R. Taking a single-phase user as an example, if the secondary indicators include: the accumulated fluctuation rate of daily electricity, the sudden drop rate of current and the percentage of under-voltage can be determined, and fuzzy comprehensive evaluation sets of secondary indexes are respectively as follows: b, daily electric quantity accumulated fluctuation rate, B current sudden drop rate and B under-voltage percentage; the fuzzy evaluation matrix R' of the constructed primary index is as follows:
in step 105, a primary index weight set matrix is determined using a fuzzy analytic hierarchy process based on the primary index set.
In step 106, a fuzzy comprehensive evaluation set of the power utilization state is determined according to the product of the primary index weight set matrix and the fuzzy evaluation matrix of the primary index.
In an embodiment of the present invention, a primary index set matrix U ' ═ U ' is assumed '1，u′2，…，u′n]Of u's'1，u′2，…，u′nEach represents a primary index, and a primary index evaluation set matrix V '═ V'1，v′2，…，v′m]And the primary index weight set matrix A '═ a'1，a′2，…，a′n]Of a'iIs a weighted value of the ith primary index, and
according to the calculated fuzzy comprehensive evaluation set B daily electricity quantity accumulated fluctuation rate, B current sudden drop rate, B under-voltage percentage and the like of each secondary index, taking a single-phase user as an example, a fuzzy evaluation matrix R' of the primary index is obtained:
in the embodiment of the invention, the types of the electricity utilization states correspond to the elements in the primary index evaluation set one by one. The types of power usage states include: if the electricity is seriously stolen, stolen and normal, a primary index evaluation set matrix V ═ V is constructed correspondingly1，v2，v3]When the electricity is stolen seriously, the electricity is stolen normally]. According to the importance degree of the first-level index to judging the electricity stealing of the user, a first-level index weight set matrix A' is calculated by a fuzzy analytic hierarchy process, and for a single-phase user, the method comprises the following steps: a '═ a'Cumulative fluctuation rate of daily electricity，a′Sudden drop rate of current，a′Percentage of under-voltageRatio of]. And calculating to obtain a suspected electricity stealing fuzzy comprehensive evaluation set B 'of the user according to a fuzzy comprehensive evaluation set calculation formula B' ═ A '. R'.
In step 107, the occurrence probability of each power utilization state in the primary index evaluation set matrix is determined according to the fuzzy comprehensive evaluation set of the power utilization states, and the power utilization behavior of the target object is determined according to the occurrence probability of each power utilization state.
Preferably, the determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state includes:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
In the embodiment of the invention, taking a single-phase user as an example, the preset power utilization state is "normal", and the preset probability threshold is 0.5. If the primary index weight set matrix A ' is obtained through calculation [ ' a 'Cumulative fluctuation rate of daily electricity，a′Sudden drop rate of current，a′Percentage of under-voltage]＝[0.45，0.35，0.20]The fuzzy comprehensive evaluation set matrix R' of the power utilization state is as follows:
then B 'is obtained [0.452, 0.255, 0.293] according to the formula B' a 'R' of the fuzzy comprehensive evaluation set. Therefore, it can be found that the probability of occurrence of the power consumption state being "serious electricity stealing" is 0.452, the probability of occurrence of the power consumption state being "electricity stealing" is 0.255, and the probability of occurrence of the power consumption state being "normal" is 0.293 in the detection range. Since 0.293 is less than 0.5, it is determined that the power consumption behavior of the user at this time belongs to the abnormal power consumption behavior, and suspicion of electricity stealing exists.
Fig. 3 is a flowchart for determining power utilization behavior of a single-phase user based on fuzzy hierarchical analysis and comprehensive evaluation according to an embodiment of the present invention. As shown in fig. 3, the step of determining the power consumption behavior of the single-phase user based on the fuzzy hierarchical analysis and the comprehensive evaluation includes:
s1, constructing a primary index system and a secondary index system, and determining a primary index set and a secondary index set;
s2, constructing a secondary index evaluation set matrix V;
s3, quantifying each evaluation index in the V according to the membership degree of the secondary index to the secondary index evaluation set matrix V, determining the membership degree, and determining the fuzzy evaluation matrix R of each secondary index;
s4, calculating a secondary index weight set matrix A by a fuzzy analytic hierarchy process according to the acceptable degree of the secondary index exceeding a preset threshold;
s5, calculating to obtain a fuzzy comprehensive evaluation set B of each secondary index according to a fuzzy comprehensive evaluation set calculation formula B ═ A · R, and determining a fuzzy evaluation matrix R' of the primary index by using the fuzzy comprehensive evaluation set B of each secondary index;
s6, constructing a primary index evaluation set matrix V ', and calculating a primary index weight matrix A';
s8, calculating a fuzzy comprehensive evaluation set of each power utilization state according to a fuzzy comprehensive evaluation set calculation formula B ═ A · R;
and S9, judging whether the power utilization behavior of the user exceeds a reasonable range according to a preset probability threshold value, and determining the electricity stealing user.
The following specifically exemplifies embodiments of the present invention
Taking the electricity utilization condition of a single-phase user in 7 days a week as an example, calculating the cumulative fluctuation rate, the current sudden drop rate and the undervoltage percentage mean value of the daily electricity consumption in 7 days, further calculating the occurrence probability of the electricity utilization state of the user by a fuzzy analytic hierarchy process and fuzzy comprehensive evaluation, and finally judging whether the electricity stealing suspicion degree of the user exceeds a reasonable range according to a threshold value. The index data for 7 days are shown in table 5.
TABLE 5 Single-phase user 7-day index data sheet
According to the 7-day average value of the cumulative fluctuation rate of the daily electricity consumption of the secondary indexes, the sudden drop rate of the current and the percentage of undervoltage, an evaluation set matrix V-V1,v2,v3]If the index exceeds the set threshold by 1.5 times or more, the index approaches the set threshold, and the index is within 0.5 times of the set threshold]Quantifying each rating index to determine the degree of membership to form a fuzzy evaluation matrix R:
calculating a secondary index weight set matrix A by a fuzzy analytic hierarchy process according to the acceptable degree of the secondary index exceeding a set threshold, firstly, constructing a fuzzy judgment matrix, and respectively carrying out comparison on C by 3 experts1Index exceeding the set threshold by more than 1.5 times, C2Index close to the set threshold value, C3The index was scored within 0.5 times lower than the set threshold, and the results are shown in Table 6.
Table 6 expert scoring table
Calculating fuzzy matrix, defuzzifying and making per unit process to obtain two-stage index weight set matrix A [0.418,0.309,0.272 ]]From BCumulative fluctuation rate of daily electricity＝A*RCumulative fluctuation rate of daily electricity、BSudden drop rate of current＝A*RSudden drop rate of current、BPercentage of under-voltage＝A*RPercentage of under-voltageCalculating to obtain a fuzzy comprehensive evaluation set of each secondary index as follows:
Bcumulative fluctuation rate of daily electricity＝[0.515,0.401,0.285]，
BSudden drop rate of current＝[0.416，0.315，0.227]，
BPercentage of under-voltage＝[0.405，0.243，0.169]，
Therefore, the fuzzy evaluation matrix of the first-level index is as follows:
determining a first-level index weight set matrix A' by a fuzzy analytic hierarchy process, wherein for a single-phase user: a '═ a'Cumulative fluctuation rate of daily electricity，a′Sudden drop rate of current，a′Percentage of under-voltageRatio of]＝[0.512，0.387，0.101]The user B ═ 0.466, 0.352, 0.251 is calculated by the fuzzy comprehensive evaluation set calculation formula B ═ a' · R ″]. It shows that the probability of the occurrence of the serious electricity stealing event of the user is 0.466 in the detection range, and the occurrence of the electricity stealing eventThe probability of an "event is 0.352 and the probability of a" normal "event occurring is 0.251. If the preset probability threshold value of 'normal' is set to be 0.5, since 0.251 is less than 0.5, the user is suspected to have electricity stealing and should be used as a key inspection object.
Traditionally, electricity stealing behavior detection mainly depends on a power supply enterprise sending technical personnel to go on the door to carry out electricity inspection, and the electricity stealing behavior detection device is low in efficiency, high in consumption and huge in manpower and material resource consumption. The intelligent electric meter can accurately record and report the electricity consumption data of the user at a high frequency, and a key foundation is laid for accurately identifying electricity stealing behaviors. Although the user can still adopt various technical means to manipulate or tamper with the reported electric quantity data, the electricity stealing behavior can be identified according to the electricity consumption data of the metering master station. The invention analyzes the electricity stealing means commonly adopted by the user in the electricity stealing process, the electricity stealing characteristics of different electricity stealing means are different, and the related characteristic indexes describing the electricity stealing means can be further selected according to different electricity stealing characteristics, thereby detecting the electricity stealing behavior of the user through multiple layers and multiple angles.
The electricity stealing suspicion prediction method based on hierarchical analysis and fuzzy comprehensive evaluation selects characteristic indexes for single-phase users and three-phase users respectively, the constructed fuzzy comprehensive evaluation set fuses a plurality of characteristic index data of the users for analyzing the electricity stealing risks of the users, and by setting a proper threshold value, the electricity stealing identification accuracy is improved, so that the method has the following outstanding advantages: (1) a first-level and second-level characteristic index frameworks of a user are constructed from four dimensions of electricity consumption, current, voltage and power factor, and electricity stealing detection can be performed on the user through multiple dimensions and multiple levels; (2) the method combining the hierarchical analysis and the fuzzy comprehensive evaluation is adopted to quantify the electricity stealing risk of the user, the one-sidedness of the traditional single characteristic weight calculation method is avoided, and the accuracy of the description of the electricity utilization behavior of the user by different electricity utilization characteristic indexes can be accurately measured.
Fig. 4 is a schematic diagram of a system 400 for determining power usage behavior based on fuzzy hierarchy analysis and comprehensive evaluation according to an embodiment of the present invention. As shown in fig. 4, a system 400 for determining power consumption behavior based on fuzzy hierarchical analysis and comprehensive evaluation according to an embodiment of the present invention includes: an index set and index evaluation set matrix determination unit 401, a fuzzy evaluation matrix determination unit 402 of a secondary index, a secondary index weight set matrix determination unit 403, a fuzzy evaluation matrix determination unit 404 of a primary index, a primary index weight set matrix determination unit 405, a fuzzy comprehensive evaluation set determination unit 406 of an electricity utilization state, and an electricity utilization behavior determination unit 407.
Preferably, the index set and index evaluation set matrix determining unit 401 is configured to determine a primary index set and a secondary index set according to the category of the target object, and respectively construct a primary index evaluation set matrix and a secondary index evaluation set matrix.
Preferably, the index set and index evaluation set matrix determining unit 401 determines a primary index set and a secondary index set according to the category of the target object, including:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
Preferably, the fuzzy evaluation matrix determining unit 402 of the secondary indexes is configured to determine a membership degree of the power consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix, and determine the fuzzy evaluation matrix of each secondary index according to the membership degree.
Preferably, the fuzzy evaluation matrix determining unit 402 of the secondary indexes constructs the fuzzy evaluation matrix of each secondary index according to the membership degree.
Wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1，v2，…，vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1，rj2，...，rjs}，rj1，rj2，...，rjsTo evaluate the rating as vjThe membership range of time.
Preferably, the secondary index weight set matrix determining unit 403 is configured to determine a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix.
Preferably, the determining unit 403 for the secondary index weight set matrix determines the secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix, including:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
Preferably, the fuzzy evaluation matrix determining unit 404 of the primary index is configured to determine a fuzzy comprehensive evaluation set of each secondary index according to a product of the secondary index weight set matrix and the fuzzy evaluation matrix of each secondary index, and construct the fuzzy evaluation matrix of the primary index by using the fuzzy comprehensive evaluation set of each secondary index.
Preferably, the primary index weight set matrix determining unit 405 is configured to determine a primary index weight set matrix by using a fuzzy analytic hierarchy process based on the primary index set.
Preferably, the fuzzy comprehensive evaluation set determining unit 406 is configured to determine the fuzzy comprehensive evaluation set of the power utilization state according to a product of the primary index weight set matrix and the fuzzy evaluation matrix of the primary index.
Preferably, the power utilization behavior determining unit 407 is configured to determine an occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states, and determine the power utilization behavior of the target object according to the occurrence probability of each power utilization state.
Preferably, the determining unit 407 of power consumption behavior determines the occurrence probability of each power consumption state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of power consumption states, and determines the power consumption behavior of the target object according to the occurrence probability of each power consumption state, including:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
The system 400 for determining power consumption behavior based on fuzzy hierarchical analysis and comprehensive evaluation according to the embodiment of the present invention corresponds to the method 100 for determining power consumption behavior based on fuzzy hierarchical analysis and comprehensive evaluation according to another embodiment of the present invention, and is not described herein again.
The invention has been described with reference to a few embodiments. However, other embodiments of the invention than the one disclosed above are equally possible within the scope of the invention, as would be apparent to a person skilled in the art from the appended patent claims.
Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a/an/the [ device, component, etc ]" are to be interpreted openly as referring to at least one instance of said device, component, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A method for determining electricity usage behavior based on fuzzy hierarchical analysis and comprehensive evaluation, the method comprising:
determining a primary index set and a secondary index set according to the category of the target object, and respectively constructing a primary index evaluation set matrix and a secondary index evaluation set matrix;
determining the membership degree of the electricity consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix, and determining the fuzzy evaluation matrix of each secondary index according to the membership degree;
determining a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix;
determining a fuzzy comprehensive evaluation set of each secondary index according to the product of the secondary index weight set matrix and the fuzzy evaluation matrix of each secondary index, and constructing the fuzzy evaluation matrix of the primary index by using the fuzzy comprehensive evaluation set of each secondary index;
determining a primary index weight set matrix by using a fuzzy analytic hierarchy process based on the primary index set;
determining a fuzzy comprehensive evaluation set of the power utilization state according to the product of the primary index weight set matrix and the fuzzy evaluation matrix of the primary index;
and determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states, and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state.
2. The method of claim 1, wherein determining a set of primary metrics and a set of secondary metrics according to a category of a target object comprises:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
3. The method of claim 1, wherein constructing the fuzzy evaluation matrix for each secondary index according to membership comprises:
wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1,v2,…,vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1,rj2,…,rjs}，rj1,rj2,…,rjsTo evaluate the rating as vjThe membership range of time.
4. The method of claim 1, wherein determining a secondary index weight set matrix a using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix comprises:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
5. The method according to claim 1, wherein the determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state comprises:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
6. A system for determining electricity usage behavior based on fuzzy hierarchical analysis and comprehensive evaluation, the system comprising:
the index set and index evaluation set matrix determining unit is used for determining a primary index set and a secondary index set according to the category of the target object and respectively constructing a primary index evaluation set matrix and a secondary index evaluation set matrix;
the fuzzy evaluation matrix determining unit of the secondary indexes is used for determining the membership degree of the electricity consumption data corresponding to each secondary index in the secondary index set to the secondary index evaluation set matrix and determining the fuzzy evaluation matrix of each secondary index according to the membership degree;
the secondary index weight set matrix determining unit is used for determining a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix;
the fuzzy evaluation matrix determining unit of the primary index is used for determining a fuzzy comprehensive evaluation set of each secondary index according to the product of the secondary index weight set matrix and the fuzzy evaluation matrix of each secondary index, and constructing the fuzzy evaluation matrix of the primary index by using the fuzzy comprehensive evaluation set of each secondary index;
the first-level index weight set matrix determining unit is used for determining a first-level index weight set matrix by using a fuzzy analytic hierarchy process based on the first-level index set;
the power utilization state fuzzy comprehensive evaluation set determining unit is used for determining a power utilization state fuzzy comprehensive evaluation set according to the product of the primary index weight set matrix and the primary index fuzzy evaluation matrix;
and the power utilization behavior determining unit is used for determining the occurrence probability of each power utilization state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power utilization states and determining the power utilization behavior of the target object according to the occurrence probability of each power utilization state.
7. The system according to claim 6, wherein the index set and index evaluation set matrix determination unit determines a primary index set and a secondary index set according to a category of the target object, and includes:
when the category of the target object is a single-phase user, the primary index set comprises: at least one of daily electricity usage, single phase current, and single phase voltage;
when the primary index set comprises the daily electricity consumption, the secondary index set comprises: cumulative fluctuation rate of daily electricity; when the primary index set includes single phase current, the secondary index set includes: the current dip rate; when the primary index set includes a single-phase voltage, the secondary index set includes: a voltage dip rate;
when the user category of the target object is a three-phase user, the primary index set includes: at least one of daily active power, three-phase current, three-phase voltage and power factor; when the primary index set includes daily active power, the secondary index set includes: daily active power fluctuation rate; when the primary index set includes three-phase current, the secondary index set includes: the current sudden drop rate of the A phase, the B phase and the C phase; when the first level index set includes a three-phase voltage, the second level index set includes: the percentage of under-voltage of phases A, B, and C; when the primary index set includes a power factor, the secondary index set includes: power factor dip rate.
8. The system of claim 6, wherein the fuzzy evaluation matrix determining unit of the secondary indexes constructs a fuzzy evaluation matrix of each secondary index according to the degree of membership, and comprises:
wherein R isIndex iA fuzzy evaluation matrix of the ith secondary index; m is a two-level index evaluation set matrix V ═ V1,v2,…,vm]The number of middle elements; the evaluation grade of the ith secondary index is vjFuzzy subset matrix R ofj＝{rj1,rj2,…,rjs}，rj1,rj2,…,rjsTo evaluate the rating as vjThe membership range of time.
9. The system of claim 6, wherein the secondary index weight set matrix determination unit determines a secondary index weight set matrix by using a fuzzy analytic hierarchy process based on the secondary index evaluation set matrix, and comprises:
performing value scaling according to the importance between each element in the secondary index evaluation set matrix to obtain a fuzzy judgment matrix;
determining the initial weight of each element according to the fuzzy judgment matrix;
and performing defuzzification processing on the initial weight of each element, performing per unit processing on the weight obtained through the defuzzification processing, and determining a secondary index weight set matrix.
10. The system according to claim 6, wherein the power consumption behavior determination unit determines the occurrence probability of each power consumption state in the primary index evaluation set matrix according to the fuzzy comprehensive evaluation set of the power consumption states, and determines the power consumption behavior of the target object according to the occurrence probability of each power consumption state, and includes:
elements in the fuzzy comprehensive evaluation set of the power utilization state and the power utilization state in the primary index evaluation set are in one-to-one correspondence to determine the occurrence probability of each power utilization state;
comparing the occurrence probability of the preset power utilization state with a preset probability threshold value, and acquiring a comparison result;
if the comparison result indicates that the occurrence probability of the preset power utilization state is smaller than a preset probability threshold, determining that the power utilization behavior of the target object belongs to abnormal power utilization behavior; otherwise, determining that the electricity utilization behavior of the target object belongs to the normal electricity utilization behavior.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010264697.9A CN111598385B (en) | 2020-04-07 | 2020-04-07 | Method and system for determining electricity consumption behavior based on fuzzy analytic hierarchy process and comprehensive evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010264697.9A CN111598385B (en) | 2020-04-07 | 2020-04-07 | Method and system for determining electricity consumption behavior based on fuzzy analytic hierarchy process and comprehensive evaluation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598385A true CN111598385A (en) | 2020-08-28 |
| CN111598385B CN111598385B (en) | 2023-05-26 |
Family
ID=72188651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010264697.9A Active CN111598385B (en) | 2020-04-07 | 2020-04-07 | Method and system for determining electricity consumption behavior based on fuzzy analytic hierarchy process and comprehensive evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598385B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015070466A1 (en) * | 2013-11-18 | 2015-05-21 | 国家电网公司 | Security risk assessment method and apparatus |
| CN106940833A (en) * | 2017-01-13 | 2017-07-11 | 国网浙江省电力公司经济技术研究院 | A kind of power grid enterprises' sale of electricity side methods of risk assessment based on fuzzy number and improved AHP method |
| CN109685296A (en) * | 2017-10-18 | 2019-04-26 | 国家电网公司 | The power information acquisition system fuzzy synthetic appraisement method of meter and historic state |
-
2020
- 2020-04-07 CN CN202010264697.9A patent/CN111598385B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015070466A1 (en) * | 2013-11-18 | 2015-05-21 | 国家电网公司 | Security risk assessment method and apparatus |
| CN106940833A (en) * | 2017-01-13 | 2017-07-11 | 国网浙江省电力公司经济技术研究院 | A kind of power grid enterprises' sale of electricity side methods of risk assessment based on fuzzy number and improved AHP method |
| CN109685296A (en) * | 2017-10-18 | 2019-04-26 | 国家电网公司 | The power information acquisition system fuzzy synthetic appraisement method of meter and historic state |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598385B (en) | 2023-05-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105825298B (en) | Power grid metering early warning system and method based on load characteristic estimation | |
| CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
| CN103337043B (en) | The method for early warning of electric power communication device running status and system | |
| CN106651169A (en) | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system | |
| CN107633354A (en) | A kind of integrated evaluating method stood with straight-flow system running status health degree | |
| CN106447205A (en) | Method for evaluating state of distribution automation terminal based on analytic hierarchy process | |
| CN104715318A (en) | Multi-dimensional operational risk evaluating method for communication network | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| CN113922412B (en) | New energy multi-station short-circuit ratio panoramic evaluation method, system, storage medium and computing equipment | |
| CN110223193A (en) | The method of discrimination and system of operation of power networks state are used for based on fuzzy clustering and RS-KNN model | |
| CN111797892B (en) | Electric power market generator market force monitoring method based on random forest regression | |
| CN107563620A (en) | A kind of integrated evaluating method based on equipment life-cycle information | |
| CN112215480A (en) | Power equipment risk assessment method and device and storage medium | |
| CN108053095A (en) | A kind of electrical energy power quality disturbance affair character extracting method and system | |
| CN111310854A (en) | Low false alarm rate electricity stealing detection secondary screening method based on electricity load fingerprint | |
| CN112418638A (en) | Early warning system and early warning method for operation and maintenance risks of DC power supply system for station | |
| CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
| CN115796708A (en) | Intelligent quality inspection method, system and medium for big data for engineering construction | |
| Zhang et al. | Real-time burst detection based on multiple features of pressure data | |
| CN112015724A (en) | Method for analyzing metering abnormality of electric power operation data | |
| CN111832955B (en) | Contact network state evaluation method based on reliability and multivariate statistics | |
| CN117349624A (en) | Electric power energy monitoring method, system, terminal equipment and storage medium | |
| CN111598385B (en) | Method and system for determining electricity consumption behavior based on fuzzy analytic hierarchy process and comprehensive evaluation | |
| CN109376990B (en) | Method and system for determining critical removal time of power system based on Simese network model | |
| CN107491862A (en) | The method and device of power grid risk evaluation and test |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |