CN116596186A - Intelligent management system for electricity consumption big data - Google Patents
Intelligent management system for electricity consumption big data Download PDFInfo
- Publication number
- CN116596186A CN116596186A CN202310538708.1A CN202310538708A CN116596186A CN 116596186 A CN116596186 A CN 116596186A CN 202310538708 A CN202310538708 A CN 202310538708A CN 116596186 A CN116596186 A CN 116596186A
- Authority
- CN
- China
- Prior art keywords
- user
- electricity
- correlation
- electricity consumption
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 254
- 230000002159 abnormal effect Effects 0.000 claims abstract description 109
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 238000013480 data collection Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 27
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 25
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000012545 processing Methods 0.000 abstract description 2
- 230000003203 everyday effect Effects 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 2
- 230000003313 weakening effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process 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
- 238000012216 screening Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
Abstract
The invention relates to the technical field of data processing and discloses an intelligent management system for electricity consumption big data, which comprises a data collection module, a correlation calculation module, a classification module, a correlation revision module, an abnormal coefficient calculation module and an electricity consumption abnormal user acquisition module, so that the problem of inaccurate density clustering results caused by neglecting individual differences due to consideration of single factors is effectively solved, the differences between individuals and group data are found by analyzing the individual and group data, so that abnormal coefficients of users are defined, density clustering is carried out on user groups through the abnormal coefficients, the clustering accuracy is effectively improved, and effective guarantee is provided for electricity consumption detection of users.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to an intelligent management system for electricity consumption big data.
Background
Along with the development of science and technology, the existing utilization scenes of big data are more and more abundant, the big electricity consumption data is one of the big electricity consumption data, and the electricity consumption change of the area and the individual user can be obtained by analyzing the big electricity consumption data, so that problems can be found, or potential hidden dangers can be supervised.
At present, when electricity consumption conditions in an area such as a community or a district are analyzed, electricity consumption data of each user in the area, namely electricity consumption, are mainly clustered to obtain abnormal electricity consumption users, then abnormal users are detected to avoid potential safety hazards in the electricity consumption process, but when electricity consumption big data are clustered, the abnormal electricity consumption users are determined by clustering the electricity consumption of the users in the area usually based on density clustering, and the clustering result is inaccurate due to the fact that the difference between individual users is ignored when the electricity consumption is used for clustering, so that electricity consumption detection of the users is deviated, and the purpose of electricity consumption detection of the users cannot be accurately achieved.
Disclosure of Invention
The invention is used for solving the problem of inaccurate clustering results caused by clustering the data of the electricity consumption of each user in the current area, and provides an intelligent management system for the electricity consumption big data, which can obtain accurate clustering results, and comprises the following components:
and a data collection module: the method comprises the steps of acquiring a power consumption data set of each user in each day and a power consumption data set of each day in an area where the user is located;
and a correlation calculation module: acquiring the correlation between each user and the electricity consumption of the area where the user is located by utilizing the electricity consumption data set of each user acquired by the data collection module;
and a classification module: classifying the users in each area by utilizing the correlation between each user and the power consumption of the area where the user is located, which is acquired by a correlation calculation module, so as to acquire all target users;
a relevance revision module: acquiring historical electricity consumption data and other historical data of all target users obtained in the classification module, and revising the correlation between the target users and the electricity consumption of the area where the target users are located by utilizing whether the historical electricity consumption data and other data of all the target users are abnormal or not;
an anomaly coefficient calculation module: obtaining a correlation value range by utilizing the correlation between each user and the power consumption of the area where the user is located, segmenting the correlation value range to obtain a plurality of sections of correlation value ranges, obtaining the abnormal ratio of each section of value range by utilizing the number of the users contained in each section of correlation value range and the number of all users, and obtaining the abnormal coefficient of each user according to the abnormal ratio of the correlation value range where each user is located and the correlation between each user and the power consumption of the area where the user is located;
the electricity consumption abnormality user acquisition module: clustering the abnormal coefficients of each user in each region obtained by the abnormal coefficient calculation module to obtain users with abnormal electricity consumption.
Further, the method for obtaining the correlation between each user and the power consumption of the area where the user is located in the correlation calculation module includes:
and obtaining the correlation between each user and the electricity consumption of the area where the user is located by using the covariance of the electricity consumption data in each user electricity consumption data set and the electricity consumption data in the area where the user is located, the standard deviation of the electricity consumption data in each user electricity consumption data set and the standard deviation of the electricity consumption data in the area where the user is located.
Further, the expression for obtaining the correlation between each user and the power consumption of the area where the user is located is:
f i representing the correlation between the ith user and the electricity consumption of the area where the ith user is located, cov (T i T) represents covariance of electricity data in the electricity data set of the ith user and the electricity data set of the region where the ith user is located;representing standard deviation of electricity data in the electricity data set of the ith user; sigma (sigma) T Representation ofStandard deviation of electricity data in the electricity data set of the region where the ith user is located.
Further, the method for obtaining the target user in the classification module is to use each user as the target user when the correlation between the user and the power consumption of the area where the user is located is smaller than or greater than a set correlation threshold.
Further, other historical data of all target users in the relevance revision module at least comprises historical water data and historical gas data.
Further, the method for revising the correlation between the target user and the electricity consumption of the area where the target user is located comprises the following steps:
respectively acquiring historical electricity utilization data average values of all target users, and the electricity-water-gas ratio average value of the historical electricity utilization data average values and the historical water utilization data average values of all target users;
the historical electricity utilization data average value of each target user in all the target users is arranged from small to large to form an average value sequence, and the average value of the average value sequence is used as a step length to traverse the two ends of the average value sequence by taking the middle point in the average value sequence as a starting point, so that abnormal electricity utilization users in all the target users are obtained;
acquiring a water-electricity ratio abnormal user in the target user according to a method for acquiring the abnormal electricity user in the target user;
and revising the correlation of the electricity consumption of the area where the target user is located according to whether the target user is an abnormal electricity consumption user or not and the water-electricity-gas ratio abnormal user.
Further, the method for revising the correlation between the target user and the electricity consumption of the area where the target user is located according to whether the target user is an abnormal electricity consumption user or not and whether the water-electricity-gas ratio is abnormal or not comprises the following steps:
when the target user is not an abnormal electricity user and is a water-electricity-gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 30%;
when the target user is an abnormal electricity utilization user and is not a water, electricity and gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 60%;
when the target user is an abnormal electricity user and is a water, electricity and gas ratio abnormal user, the correlation between the target user and the electricity consumption of the area where the target user is positioned is reduced by 90%.
Further, the expression for obtaining the anomaly coefficient for each user is:
wherein: r is R i An anomaly coefficient for the ith user; f (f) i The method comprises the steps of obtaining the correlation between an ith user and the electricity consumption of the area where the ith user is located; r is R (X，Y) The odds ratio in the relevance value range (X, Y) of the ith user is obtained.
The beneficial effects of the invention are as follows: screening all target users in the area by acquiring the correlation of electricity consumption of each user and the area where the user is located, revising the correlation of the target users and the electricity consumption of the area where the target users are located by utilizing historical electricity consumption data of all the target users and whether other data are abnormal or not, segmenting the value of the acquired correlation, acquiring an abnormal coefficient of each user by utilizing the abnormal ratio of each segment and the users contained in the segment, and clustering the abnormal coefficient of each user in the area to acquire the final abnormal electricity consumption user; the problem that density clustering results are inaccurate due to the fact that individual variability is ignored only due to single factor consideration is effectively solved, the individual variability is found by analyzing individual and group data, so that the abnormal coefficient of a user is defined, density clustering is conducted on the user group through the abnormal coefficient, the clustering accuracy is effectively improved, and effective guarantee is provided for electricity utilization detection of the user.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a block diagram of a system of the present invention;
fig. 2 is a graph of electricity consumption at different times of the day for a user in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
As shown in fig. 1, this embodiment provides an intelligent management system for electricity consumption big data, including:
and a data collection module: the method comprises the steps of acquiring a power consumption data set of each user in each day and a power consumption data set of each day in an area where the user is located; in the embodiment, when electricity consumption data of each user in a community is acquired, the electricity consumption condition of a household ammeter of each user is acquired in real time, specifically when the electricity consumption data of each user is acquired, the electricity consumption data of each user is sent to a data collection module at a processing center end, the electricity consumption data of the community is obtained by superposing the electricity consumption data of each user in the community, specifically, the electricity consumption data of each user in the area is acquired every two hours in each day, and an electricity consumption data set of each user in a day is obtained: t (T) i ＝{T 1 ，T 2 ，T 3 ，...，T 12 }；
The electricity consumption data set in the whole area is as follows: t= { T 1 ，T 2 ，T 3 ，...，T 12 }；
Wherein: t (T) i The method comprises the steps that an ith user electricity sales quantity data set in an area is represented, and T represents an integral electricity utilization data set in the area; in this embodiment, every 2 hours is a time period, T 1 Representing the sales power from 0 to 2, and so on up to T 12 The electricity sales data sets of the ith user in different time periods every day and the electricity sales data sets of the ith user in different time periods every day in the area can be obtained;
after the electricity data of each user and the electricity data of the area in different time of each day are obtained, in order to accurately analyze the electricity data, the electricity time periods of each day are different among the users in the area due to different professions and work and rest habits, but in general, because the users in the same area always have similarity, the electricity time periods of each user are fixed in the whole area, the fixation also has certain correlation with the area, for example, most households in the whole area are office workers, the electricity time periods of the early work and evening every day are approximately similar, so that the fluctuation time periods of the electricity data in the area also tend to be the same, and the electricity consumption amounts among the users are different; the electricity consumption of different users in each time period is counted, and the electricity consumption of the same user in each time period is compared, so that the similarity degree of the electricity consumption habit of the user in the group and other individuals in the group can be reflected.
And counting the power consumption data of each user in different time periods every day and the power consumption data of the user in different time periods every day in the area, and calculating the correlation of the two power consumption data according to the fluctuation condition of the data. The higher the correlation indicates that the power consumption time period and the region of the user are more similar, and the lower the correlation indicates that the power consumption time period of the user is less similar to that of other users;
for this reason, the present embodiment sets a correlation calculation module for acquiring the electricity consumption correlation of each user and the area where the user is located in one day;
and a correlation calculation module: acquiring the correlation between each user and the electricity consumption of the area where the user is located by utilizing the electricity consumption data set of each user acquired by the data collection module;
in the process of calculating the correlation between each user and the electricity consumption of the area where the user is located, firstly, the covariance Cov (T i T), standard deviation of electricity data in each user electricity data setAnd standard deviation sigma of electricity data in the electricity data set of the area where the user is located T The method comprises the steps of carrying out a first treatment on the surface of the The main purpose of acquiring the covariance of each user electricity data set and the electricity data in the electricity data set of the area where the user is located is to obtain the total error between each user and the area where the user is located, and the main purpose is to obtain the deviation degree of each electricity data in the set and the data mean value, and the expression of the covariance and the standard deviation obtained in the embodiment is a technical means conventional to those skilled in the art, and the embodiment does not describe in detail that a specific value is obtained if the covariance and the standard deviation are adopted specifically;
after covariance and standard deviation are obtained, the following expression is adopted to obtain the correlation between each user and the electricity consumption of the area where the user is located;
the expression is:
f i representing the correlation between the ith user and the electricity consumption of the area where the ith user is located, cov (T i T) represents covariance of electricity data in the electricity data set of the ith user and the electricity data set of the region where the ith user is located;representing standard deviation of electricity data in the electricity data set of the ith user; sigma (sigma) T Indicating the i-th user is locatedStandard deviation of electricity consumption data in the electricity consumption data set of the region;
in the day, whether the electricity consumption data set of the user or the electricity consumption data set of the area where the user is located, a graph shown in fig. 2 is formed through the electricity consumption data set, A, B and C curves in the graph respectively represent fluctuation conditions of electricity consumption of the user A, the user B and the user C in the day, and a D curve in the graph represents fluctuation conditions of the average value of the electricity consumption data of the area where the user is located; the representation of the correlation is calculated from a correlation coefficient, the nature of which is the tendency to the mean of the data in the collection, the size of the mean being determined by the majority of the individuals in the population. If the correlation is reflected on the image, the change conditions of the curve fluctuation of the individual and the population are approximately similar (the data fluctuation of the user B and the user C wander around the curve of the regional electricity consumption data D, the correlation among the three is higher, and the data fluctuation condition of the user A is obviously different from the population, which indicates that the correlation between the two is lower). After obtaining the correlation between each user and the electricity data in the area where the user is located, the user with high correlation needs to be screened out to be used as a target user; because the obtained correlation between each user and the area is relatively low, the difference between the electricity consumption data of the user in one day and the electricity consumption data of the area is relatively large, the correlation is relatively high, the difference between the electricity consumption data of the user and the area electricity consumption data is relatively small, the correlation is only the similarity of fluctuation between each user and the area user, the low correlation indicates that the similarity is not large, the users with high correlation can be clustered directly in the later clustering process, the similarity of curves is high, but the similarity of the electricity consumption data cannot be indicated, for example, although the correlation between one user and the area is relatively high, the fluctuation is relatively similar, but the electricity consumption of the user in each time period is far higher than that of the ordinary user, and the similarity of the final curve is relatively high.
The method comprises the steps that a classification module is adopted to extract target users in an area, namely all users with high correlation are screened, and specifically, the correlation between each user and the electricity consumption of the area where the user is located, which is obtained by a correlation calculation module, is utilized to classify the users in each area, so that all the target users are obtained; and when the correlation between each user and the electricity consumption of the area where the user is located is smaller than or equal to a set correlation threshold value, the user is taken as a target user, and the correlation threshold value is 0.4.
After all the target users are obtained, as the correlation between the electricity consumption data of the target users and the electricity consumption data of the areas is higher, the higher correlation indicates that the fitting degree of the electricity consumption time period of the user and the area where the user is located is higher, but the discrete degree in the area of the target users also needs to be considered; although the correlation is high, since many life data are closely related to electricity consumption in life at present, it is necessary to adopt other life data to reduce the correlation of electricity consumption, and in this embodiment, the correlation is reduced by selecting the index of the ratio of the historical gas consumption, the heat consumption, the water consumption and the historical electricity consumption of the residents in life, and in this embodiment, the ratio of the historical gas consumption, the water consumption and the historical electricity consumption is specifically adopted to determine.
Historical electricity consumption data is also an index which can reflect the degree of abnormality; although the electricity consumption time period of the user with high correlation is similar to that of other users in the area, whether the electricity consumption of the user is abnormal or not is considered for the user in the electricity consumption time period which is too much or too little compared with that of the other users.
The use proportion of water, electricity and gas can reflect whether the electricity consumption condition of the user is in a reasonable range to a certain extent. When each household or unit uses water, electricity and heat, the water, electricity and heat can have a normal dosage range, and the use proportion of the water, electricity and heat can be different according to different living and production demands; if a user's utility ratio is significantly above normal, this may indicate that the user's resource is being consumed too much in this regard, and may also suggest that they are wasting or abusing the use of the resource; the ratio of water, electricity and gas can be used as a reference factor, so that if the ratio of water, electricity and gas used by a certain user is more than the ratio of the water, the gas and the gas used by the certain user in the group in excess, whether the electricity utilization behavior of the certain user is abnormal or not can be considered.
The correlation revision module is adopted to revise the correlation between the electricity consumption data of the target user with high correlation and the electricity consumption data of the area where the target user is located, specifically, the historical electricity consumption data and other historical data of all the target users obtained in the classification module are obtained, and whether the historical electricity consumption data and other data of all the target users are abnormal is utilized to revise the correlation between the target user and the electricity consumption data of the area where the target user is located;
the embodiment specifically comprises the steps of obtaining historical electricity utilization data average values of all target users; the historical electricity utilization data is obtained according to the data acquired before;
the historical electricity utilization data average value of each target user in all the target users is arranged from small to large to form an average value sequence, and the average value of the average value sequence (obtained by averaging all the data in the average value sequence) is used as a step length to traverse the two ends of the average value sequence by taking the key point in the average value sequence as a starting point, so that abnormal electricity utilization users in all the target users are obtained; specifically, traversing from the center to the two sides through the obtained step length, stopping traversing when no data point exists in the traversed step length, wherein the target user corresponding to the data point outside the traversing stopping point is an abnormal user, so that the abnormal data which is too large or too small in the historical data can be obtained as the abnormal user;
similarly, acquiring a historical electricity consumption data average value, a historical water consumption data average value and a historical gas consumption data average value of a target user, and comparing the historical electricity consumption data average value, the historical water consumption data average value and the historical gas consumption data average value to obtain an electricity-water-gas ratio average value;
then, the obtained electric water gas ratio average value of each target user in all target users is arranged from small to large to form a proportional average value sequence, and the average value of the proportional average value sequence (the average value is obtained by solving the average value of all data in the average value sequence) is traversed towards the two ends of the average value sequence by taking the middle point in the proportional average value sequence as a starting point; the step length is the average value of the proportional average value sequence and is a value, so when an abnormal value is obtained, the step length is traversed from the center to the two sides, when no data point exists in the traversed step length, the traversing is stopped, and at the moment, the target user corresponding to the data point outside the traversing stopping point is an abnormal user, so that the abnormal data which is too large or too small in the historical data can be obtained, namely the water-electricity ratio abnormal user;
the occurrence of abnormality in the historical electricity consumption data indicates that although the user has high correlation with the overall electricity consumption of the group, the electricity consumption is too much or too little compared with most individuals in the group, and the historical electricity consumption data is obviously abnormal compared with other users in the area;
the historical electricity consumption data refers to a time period obtained when the data is analyzed, for example, abnormal users need to be screened according to the data in one week, the data in one week of the users is analyzed according to the above, and the historical data can be one month or one quarter, so long as the data of the user group is analyzed in the same time period.
Revising the correlation between the target user and the electricity consumption of the area where the target user is located according to whether the target user is an abnormal electricity consumption user or not and whether the water-electricity-gas ratio is abnormal; comprising the following steps:
when the target user is not an abnormal electricity user and is not a water, electricity and gas ratio abnormal user, the correlation between the target user and the electricity consumption of the area where the target user is positioned is not revised;
when the target user is not an abnormal electricity user and is a water-electricity-gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 30%;
when the target user is an abnormal electricity utilization user and is not a water, electricity and gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 60%;
when the target user is an abnormal electricity user and is a water, electricity and gas ratio abnormal user, the correlation between the target user and the electricity consumption of the area where the target user is positioned is reduced by 90%.
The degree of weakening of the correlation is different according to different corresponding results by judging whether the result values of the data in the two aspects are abnormal, so that user groups with too high discrete degrees in high correlation users can be screened into user groups with lower correlation;
the method comprises the steps of weakening the correlation of a high-correlation user group according to historical electricity consumption data of users, the use proportion of water, electricity and gas and the discrete degree of other users of the group, obtaining the correlation of the revised target users of all target users and the electricity consumption of the area where the target users are located, and obtaining the correlation of all users and the electricity consumption of the area where the users are located.
Then judging the abnormal coefficient of the user by utilizing the obtained correlation;
the method specifically adopts an anomaly coefficient calculation module to execute: obtaining a correlation value range by utilizing the correlation between each user and the power consumption of the area where the user is located, segmenting the correlation value range to obtain a plurality of sections of correlation value ranges, wherein the correlation is 0.2, 0.3, 0.8, 0.1, …, 0.9 and the like, and the minimum value in all the correlations is 0.1 and the maximum value is 0.9, so that the value range is between 0.1 and 0.9; then continuing to segment the range; such as 0.1-0.3;0.4-0.6;0.7-0.9, etc., the present example is illustrative only and is not intended to represent segmentation in terms of such value ranges;
after segmentation, the number of users contained in each segment of correlation value range and the number of all users are utilized to obtain the different-number ratio of each segment of value range; the expression of the abnormal ratio is:
wherein: r is R (X，Y) Representing the different crowds ratio of the users contained in the correlation value interval (X, Y) relative to the total users in the area, N (X，Y) Representing the number of users corresponding to the correlation value interval in (X, Y), N sum Representing the number of total users in the area; the ratio of the number of people in the correlation interval to the total number of people in the group defines the different people ratio, and the smaller the number of people in the correlation interval is, the smaller the different people ratio is.
Obtaining an anomaly coefficient of each user according to the different ratio of the correlation value range of each user and the correlation between each user and the electricity consumption of the area where the user is located;
the expression for obtaining the anomaly coefficient for each user is:
wherein: r is R i An anomaly coefficient for the ith user; f (f) i The method comprises the steps of obtaining the correlation between an ith user and the electricity consumption of the area where the ith user is located; r is R (X，Y) The different-public ratio in the relevance value range (X, Y) of the ith user is obtained; ratio of different masses R (X，Y ) The lower the value in the interval, the anomaly coefficient R defined by the user i i The higher should be, and therefore a nonlinear relationship between the outlier and the outlier coefficient; the different crowding ratio is obtained by counting the number of users in the interval and the total number of groups in which the users are located, and in general, the lower the correlation interval is divided, the fewer the number of users in the interval is, and the lower the different crowding ratio is; however, it is not excluded that in a special case, the number of users with a low correlation interval is greater than that of the correlation interval, and therefore the height of the correlation interval divided and the number of users in the interval are not necessarily proportional. Therefore, in addition to the inter-zone outlier ratio, the correlation f of the users in the zone needs to be recombined i The magnitude of the abnormal coefficients of different users in the same interval are accurately defined, and the lower the correlation of the users in the same correlation interval, the higher the abnormal coefficient.
The electricity consumption abnormality user acquisition module: clustering the abnormal coefficients of each user in each area obtained by the abnormal coefficient calculation module to obtain users with abnormal electricity, specifically clustering the correlations obtained by the users in the areas to obtain abnormal users, and clustering by using a density clustering method in the embodiment.
After the electricity abnormal user is obtained, the electricity abnormal user is sent to the user to be marked as the abnormal electricity user, if the user is abnormal for a short time, the abnormal electricity user is not processed, if the user frequently generates electricity abnormal, an alarm is sent, and management staff in communities detect the electricity consumption condition of the user or check a circuit, so that potential safety hazards of electricity consumption are avoided.
In the process of the embodiment, a data collection module is used for collecting a power consumption data set of time periods in a day in each area and a power consumption data set of each user in the area; the method comprises the steps that collected data are sent to a correlation calculation module, the correlation calculation module calculates the correlation between each user and the electricity consumption of an area where the user is located according to the received data, the calculated data are sent to a classification module, the classification module classifies the users in the area according to the received correlation data, all corresponding target users with high correlation are selected, all obtained target users are sent to a correlation revision module, and after the correlation revision module obtains all target users, historical electricity consumption data, historical water consumption data and historical gas consumption data of all target users are collected; the historical electricity consumption data average value, the historical electricity consumption data average value and the historical gas consumption data average value of each target user are obtained, the historical electricity consumption data average value of each target user is utilized to obtain electricity consumption abnormal users in all the target users, meanwhile, the historical electricity consumption data and the historical gas consumption data of the target users are utilized to obtain the electric-gas proportion value, the electric-gas proportion value of all the target users is utilized to obtain abnormal electric-gas proportion users, then the correlation corresponding to the target users is revised according to the category to which the target users belong, the revised correlation is sent to an abnormal coefficient calculation module to calculate the abnormal coefficient of each user, the abnormal coefficient calculation module is used for calculating the abnormal coefficient of each user and then sending the abnormal coefficient to an electricity consumption abnormal user acquisition module, the abnormal users in all the users are extracted through the electricity consumption abnormal user acquisition module, if the abnormal users are abnormal only in a period of time, no processing is carried out, and when the abnormal users are abnormal for a long time, an alarm is sent out, the abnormal users are detected by staff, and potential safety hazards of electricity consumption are avoided; the problem that density clustering results are inaccurate due to the fact that individual variability is ignored only due to single factor consideration is effectively solved, the individual variability is found by analyzing individual and group data, so that the abnormal coefficient of a user is defined, density clustering is conducted on the user group through the abnormal coefficient, the clustering accuracy is effectively improved, and effective guarantee is provided for electricity utilization detection of the user.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (8)
1. An intelligent management system for electricity consumption big data, which is characterized by comprising:
and a data collection module: the method comprises the steps of acquiring a power consumption data set of each user in each day and a power consumption data set of each day in an area where the user is located;
and a correlation calculation module: acquiring the correlation between each user and the electricity consumption of the area where the user is located by utilizing the electricity consumption data set of each user acquired by the data collection module;
and a classification module: classifying the users in each area by utilizing the correlation between each user and the power consumption of the area where the user is located, which is acquired by a correlation calculation module, so as to acquire all target users;
a relevance revision module: acquiring historical electricity consumption data and other historical data of all target users obtained in the classification module, and revising the correlation between the target users and the electricity consumption of the area where the target users are located by utilizing whether the historical electricity consumption data and other data of all the target users are abnormal or not;
an anomaly coefficient calculation module: obtaining a correlation value range by utilizing the correlation between each user and the power consumption of the area where the user is located, segmenting the correlation value range to obtain a plurality of sections of correlation value ranges, obtaining the abnormal ratio of each section of value range by utilizing the number of the users contained in each section of correlation value range and the number of all users, and obtaining the abnormal coefficient of each user according to the abnormal ratio of the correlation value range where each user is located and the correlation between each user and the power consumption of the area where the user is located;
the electricity consumption abnormality user acquisition module: clustering the abnormal coefficients of each user in each region obtained by the abnormal coefficient calculation module to obtain users with abnormal electricity consumption.
2. The intelligent management system for electricity consumption big data according to claim 1, wherein the method for obtaining the correlation between each user and the electricity consumption of the area where the user is located in the correlation calculation module comprises:
and obtaining the correlation between each user and the electricity consumption of the area where the user is located by using the covariance of the electricity consumption data in each user electricity consumption data set and the electricity consumption data in the area where the user is located, the standard deviation of the electricity consumption data in each user electricity consumption data set and the standard deviation of the electricity consumption data in the area where the user is located.
3. The intelligent management system for electricity consumption big data according to claim 2, wherein the expression for obtaining the correlation between each user and the electricity consumption of the area where the user is located is:
f i representing the correlation between the ith user and the electricity consumption of the area where the ith user is located, cov (T i T) represents covariance of electricity data in the electricity data set of the ith user and the electricity data set of the region where the ith user is located;power usage data set representing the ith userStandard deviation of the power consumption data; sigma (sigma) T And representing the standard deviation of the electricity data in the electricity data set of the region where the ith user is located.
4. The intelligent management system for electricity consumption big data according to claim 1, wherein the method for obtaining the target user in the classification module is to use each user as the target user when the correlation between the user and the electricity consumption of the area where the user is located is smaller than or greater than a set correlation threshold.
5. The intelligent power consumption management system according to claim 1, wherein the other historical data of all target users in the correlation revision module at least comprises historical water consumption data and historical gas consumption data.
6. The intelligent management system for electricity consumption according to claim 5, wherein the method for revising the correlation between the target user and the electricity consumption of the area where the target user is located comprises:
respectively acquiring historical electricity utilization data average values of all target users, and the electricity-water-gas ratio average value of the historical electricity utilization data average values and the historical water utilization data average values of all target users;
the historical electricity utilization data average value of each target user in all the target users is arranged from small to large to form an average value sequence, and the average value of the average value sequence is used as a step length to traverse the two ends of the average value sequence by taking the middle point in the average value sequence as a starting point, so that abnormal electricity utilization users in all the target users are obtained;
acquiring a water-electricity ratio abnormal user in the target user according to a method for acquiring the abnormal electricity user in the target user;
and revising the correlation of the electricity consumption of the area where the target user is located according to whether the target user is an abnormal electricity consumption user or not and the water-electricity-gas ratio abnormal user.
7. The intelligent management system for electricity consumption big data according to claim 6, wherein the method for revising the correlation between the target user and the electricity consumption of the area where the target user is located according to whether the target user is an abnormal electricity consumption user or not and whether the electricity-gas ratio is abnormal comprises the following steps:
when the target user is not an abnormal electricity user and is a water-electricity-gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 30%;
when the target user is an abnormal electricity utilization user and is not a water, electricity and gas ratio abnormal user, reducing the correlation of the target user and the electricity consumption of the area where the target user is positioned by 60%;
when the target user is an abnormal electricity user and is a water, electricity and gas ratio abnormal user, the correlation between the target user and the electricity consumption of the area where the target user is positioned is reduced by 90%.
8. The electricity consumption big data intelligent management system according to claim 1, wherein the expression for obtaining the anomaly coefficient of each user is:
wherein: r is R i An anomaly coefficient for the ith user; f (f) i The method comprises the steps of obtaining the correlation between an ith user and the electricity consumption of the area where the ith user is located; r is R (X,Y) The odds ratio in the relevance value range (X, Y) of the ith user is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310538708.1A CN116596186A (en) | 2023-05-12 | 2023-05-12 | Intelligent management system for electricity consumption big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310538708.1A CN116596186A (en) | 2023-05-12 | 2023-05-12 | Intelligent management system for electricity consumption big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116596186A true CN116596186A (en) | 2023-08-15 |
Family
ID=87598534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310538708.1A Pending CN116596186A (en) | 2023-05-12 | 2023-05-12 | Intelligent management system for electricity consumption big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596186A (en) |
-
2023
- 2023-05-12 CN CN202310538708.1A patent/CN116596186A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rajabi et al. | A comparative study of clustering techniques for electrical load pattern segmentation | |
| CN107742127B (en) | Improved electricity stealing prevention intelligent early warning system and method | |
| CN111860600B (en) | User electricity utilization characteristic selection method based on maximum correlation minimum redundancy criterion | |
| TWI440862B (en) | Electrical detection method and system based on user feedback information | |
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| CN108776939A (en) | The analysis method and system of user power utilization behavior | |
| CN104156403B (en) | A kind of big data normal mode extracting method and system based on cluster | |
| CN105117810A (en) | Residential electricity consumption mid-term load prediction method under multistep electricity price mechanism | |
| CN109947815B (en) | Power theft identification method based on outlier algorithm | |
| CN111680764B (en) | Industry reworking and production-resuming degree monitoring method | |
| CN116797049B (en) | Quantitative evaluation method for differentiated energy-saving potential of power distribution network | |
| CN109583679A (en) | A kind of stealing Suspected Degree analysis method of more algorithm fusions | |
| CN113554361B (en) | Comprehensive energy system data processing and calculating method and processing system | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| CN115794803B (en) | Engineering audit problem monitoring method and system based on big data AI technology | |
| Liu et al. | A moving shape-based robust fuzzy K-modes clustering algorithm for electricity profiles | |
| CN115907822A (en) | Load characteristic index relevance mining method considering region and economic influence | |
| CN114611738A (en) | Load prediction method based on user electricity consumption behavior analysis | |
| CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN112330095A (en) | Quality management method based on decision tree algorithm | |
| CN114266457A (en) | Method for detecting different loss inducement of distribution line | |
| CN114519651A (en) | Intelligent power distribution method based on electric power big data | |
| CN114021808A (en) | Power resource allocation method based on emergency influence grade identification | |
| CN116596186A (en) | Intelligent management system for electricity consumption big data | |
| CN104519511B (en) | A kind of method and apparatus for detecting the mutation of communication network cell scene |
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 |