CN111652325A - Enterprise power consumption mode identification method and device based on clustering and storage medium - Google Patents
Enterprise power consumption mode identification method and device based on clustering and storage medium Download PDFInfo
- Publication number
- CN111652325A CN111652325A CN202010599537.XA CN202010599537A CN111652325A CN 111652325 A CN111652325 A CN 111652325A CN 202010599537 A CN202010599537 A CN 202010599537A CN 111652325 A CN111652325 A CN 111652325A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- data
- time
- power
- electricity
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 230000005611 electricity Effects 0.000 claims abstract description 115
- 230000002159 abnormal effect Effects 0.000 claims abstract description 10
- 238000003909 pattern recognition Methods 0.000 claims description 24
- 238000013499 data model Methods 0.000 claims description 12
- 238000012567 pattern recognition method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 238000000926 separation method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 230000003245 working effect Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 206010033799 Paralysis Diseases 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Power Sources (AREA)
Abstract
The invention discloses a clustering-based enterprise power consumption mode identification method, which is characterized in that historical power consumption data of an enterprise are processed, time interval points of an enterprise power consumption mode and the enterprise power consumption mode are found out, a power consumption model of the enterprise power consumption mode is established, and then the enterprise power consumption data obtained in real time are matched with the power consumption model to obtain the current power consumption mode of the enterprise and the problem that whether the power consumption data is abnormal or not, and the like. The invention also provides a device for identifying the enterprise electricity utilization mode based on clustering and a storage medium.
Description
Technical Field
The invention relates to the field of power utilization, in particular to a clustering-based enterprise power utilization pattern recognition method and device and a storage medium.
Background
At present, the existing enterprises generally realize the prevention of the electricity safety aspect by installing the related equipment such as the electricity safety socket. Once the power utilization of an enterprise fails, the power utilization paralysis of the whole enterprise can be caused, and the production of the enterprise is influenced. Because enterprises use different electric quantities in different time periods, the selection of the electric safety socket is difficult; meanwhile, the electricity safety socket can only give an alarm when the electricity consumption exceeds a certain time, and the risk of enterprise electricity utilization cannot be pre-warned in advance.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a clustering-based enterprise power utilization pattern recognition method, which can solve the problems that the enterprise power utilization abnormity cannot be early-warned and the like in the prior art.
The invention also aims to provide an enterprise power consumption pattern recognition device based on clustering, which can solve the problems that the enterprise power consumption abnormity cannot be early warned and the like in the prior art.
The invention also aims to provide a storage medium which can solve the problems that the enterprise power utilization abnormity cannot be early warned and the like in the prior art.
One of the purposes of the invention is realized by adopting the following technical scheme:
the enterprise power utilization pattern recognition method based on clustering comprises the following steps:
an acquisition step: acquiring daily electricity utilization data of enterprises in a preset time period; the electricity consumption data comprises current data and acquisition time;
clustering: clustering the daily power utilization data of the enterprise by adopting a mixed Gaussian model according to the preset cluster number to obtain a plurality of clustering result sets corresponding to the daily power utilization data of the enterprise;
a mode dividing step: taking the daily electricity utilization data of the enterprises as objects, and obtaining time interval points of the enterprise electricity utilization modes, the enterprise electricity utilization modes and the start and stop times of the enterprise electricity utilization modes according to each clustering result set;
a model generation step: merging the daily power utilization data of the enterprises in a preset time period according to the time interval points of the enterprise power utilization modes and the enterprise power utilization modes to obtain a power utilization data model of the enterprise power utilization modes; the power utilization data model of the enterprise power utilization mode comprises the starting and ending time of each enterprise power utilization mode, current data of each enterprise power utilization mode, the acquisition time of the current data, the distribution characteristics of the current data and the change characteristics of the current data;
pattern recognition: the method comprises the steps of acquiring the electricity utilization data of an enterprise in a current period of time in real time, matching and identifying the electricity utilization data of the enterprise in the current period of time with an electricity utilization data model of an enterprise electricity utilization mode to obtain the enterprise electricity utilization mode of the enterprise in the current period of time, and judging whether the electricity utilization data of the enterprise are abnormal or not.
Further, the acquiring step includes: and collecting the electricity utilization data of enterprises through the installed air switch at regular time.
Further, the timed time is set according to the working property of the enterprise.
Further, the clustering step is preceded by:
denoising: and denoising the daily electricity utilization data of the enterprise, and removing wrong current data.
Further, the denoising step comprises denoising the daily electricity utilization data of the enterprise by a 3 sigma method.
Further, the power consumption pattern dividing step comprises the following steps:
a pretreatment step: preprocessing the current data in each clustering result set to remove discrete current data;
further, the pattern division step specifically includes: firstly, marking each clustering result set to obtain a plurality of groups of marked current data; each group of current data comprises the acquisition time and the mark of the current data; one cluster result set corresponds to one set of current data; then sorting each group of current data according to acquisition time, calculating each group of current data to obtain a separation point with the minimum information entropy, searching acquisition time corresponding to the separation point, and recording each acquisition time as a time interval point of an enterprise power utilization mode; and finally, calculating time interval points of the enterprise electricity utilization modes according to the current data of all the groups to obtain all the enterprise electricity utilization modes and the starting and ending time of each enterprise electricity utilization mode.
Further, the enterprise power utilization pattern recognition method comprises the early warning steps of:
when the electricity utilization data of the enterprise in the current period of time is not matched with the current data of the corresponding enterprise electricity utilization mode, the electricity utilization data of the enterprise in the current period of time is abnormal, and early warning notice is issued to enterprise staff.
The second purpose of the invention is realized by adopting the following technical scheme:
the device for identifying the enterprise power consumption pattern based on the clustering comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the computer program is an enterprise power consumption pattern identification program, and the processor realizes the steps of the method for identifying the enterprise power consumption pattern based on the clustering adopted by one of the purposes of the invention when executing the enterprise power consumption pattern identification program.
The third purpose of the invention is realized by adopting the following technical scheme:
a storage medium being a computer readable storage medium having stored thereon a computer program being an enterprise power pattern recognition program, which when executed by a processor, performs the steps of a cluster-based enterprise power pattern recognition method as employed in one of the objects of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
according to the method, historical electricity utilization data of an enterprise are processed, the electricity utilization modes of the enterprise are divided based on a Gaussian mixture model, and an electricity utilization model of the electricity utilization modes of the enterprise is established; then match through the power consumption model with real-time enterprise power consumption data and enterprise's power consumption mode of establishing, and then can judge the current power consumption mode that the enterprise is located in real time and whether have the abnormal conditions, realize real time monitoring and the early warning function to enterprise power consumption data, solved among the prior art can only realize the prevention to the aspect of power consumption safety through relevant equipment such as power consumption safety socket and can not in time discover unusual or trouble and lead to enterprise power consumption paralysis scheduling problem.
Drawings
FIG. 1 is a flow chart of a clustering-based enterprise electricity pattern recognition method provided by the present invention;
fig. 2 is a block diagram of an enterprise electricity pattern recognition device based on clustering according to the present invention.
In the figure: 11. a memory; 12. a processor; 13. a communication bus; 14. a network interface.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Example one
According to the invention, historical data of the power utilization of the enterprise is analyzed to obtain power utilization modes of the enterprise under various conditions, corresponding power utilization models are established, then the power utilization models are summarized in the actual production process, the data of the power utilization of the enterprise are collected in real time and compared with the power utilization models stored in the system, so that the power utilization risks in the production process of the enterprise can be early warned and monitored, and the potential power utilization risks can be identified.
As shown in fig. 1, the present invention provides a preferred embodiment, a method for identifying an enterprise electricity consumption pattern based on clustering, comprising the following steps:
and step S1, acquiring historical electricity utilization data of the enterprise. Wherein, historical power consumption data accessible is gathered the air switch of enterprise's installation. That is, current data of an enterprise is collected at regular time through an air switch. The timing time can be set according to the working characteristics of the enterprise, for example, the current data of the enterprise is collected once every 3 minutes through the air switch, and the current data of the enterprise is collected once every 5 minutes through the air switch.
In addition, the working characteristics of enterprises are different, and the power utilization modes of the enterprises are different.
For example, when an enterprise works in a common office building, and the power consumption in three periods of time after working in the daytime, working at night and working at night are obviously different, the working mode of the enterprise is 3 at this time. In addition, the current can be observed and set by drawing a change image of the current, and the setting can be carried out according to specific business requirements.
The invention is in a mode of establishing a model, so that the collected historical electricity utilization data can take enterprise electricity utilization data in a certain preset time period as an object, such as one month.
And step S2, carrying out denoising processing on the historical electricity utilization data of the enterprise. The denoising processing is carried out on the historical electricity utilization data, so that the subsequent clustering effect is improved.
Because the current data of the enterprise power utilization are collected once by the air switch at intervals, the collected current data may be inaccurate due to the existence of internal factors or external factors, for example, the current data close to 0 may occur occasionally. Therefore, the invention removes the inaccurate data in a denoising mode, thereby improving the effect of subsequent clustering.
Preferably, the method adopts a 3 sigma method to carry out denoising processing on the historical electricity utilization data. The 3 σ method is to calculate the standard deviation σ for all the historical power consumption data and then remove the current data that exceeds the mean ± 3 σ.
And step S3, clustering the daily electricity consumption data of the enterprise by adopting a mixed Gaussian model according to the preset cluster number to form a plurality of clustering result sets. Due to the collection time of the power utilization data of the enterprise, the collection time is recommended to be carried out in units of 24 hours. The invention divides the enterprise electricity utilization modes by taking day (24 hours) as a unit and taking the daily enterprise electricity utilization data as an object. That is, the daily electricity consumption data form a plurality of corresponding clustering result sets.
And step S4, preprocessing the enterprise electricity utilization data in each clustering result set.
Since there may be individual discrete points in the time dimension of the clustered enterprise electricity consumption data, and these discrete points may have adverse effects on the subsequent calculation results, these discrete points are first removed by preprocessing.
And step S5, taking the daily electricity consumption data of the enterprise as the object, and obtaining the time interval point of the enterprise electricity consumption mode, the enterprise electricity consumption mode and the starting and ending time of the enterprise electricity consumption mode according to each clustering result set.
The enterprise power utilization mode referred by the invention is set according to the business properties of the integrated enterprise collected by the clustering result, and has no fixed mode.
For example, for enterprise users in an office building, before and after work in the morning, the power consumption data of the enterprise are obviously different, and the power consumption data of the enterprise gradually increases with the start of work of the enterprise staff until the power consumption data of the enterprise becomes stable in the second half hour after work. At this time, the working time is also the time interval point of the power utilization mode of the enterprise.
Similarly, before and after work at night, the enterprise electricity utilization data may be obviously different, and the work time is also the time interval point of the enterprise electricity utilization mode. In addition, generally speaking, when the number of workers in the enterprise is large after the staff goes off duty, the time of going off duty may not be the time interval point of the power consumption mode of the enterprise. Assuming that the enterprise employee generally leaves the company gradually one hour after the next shift, the hour after the next shift may be a time interval point of the enterprise power consumption pattern. Thus, the enterprise power utilization mode can be obtained through the time interval points.
For another example, for an enterprise whose working place is in a factory building and belongs to industrial production, the industrial production enterprise generally belongs to a three-shift working mode, such as white shift, middle shift, and night shift. Therefore, the enterprise power utilization mode is different from the enterprise power utilization mode working in the office building.
Therefore, the enterprise power utilization pattern is not clearly defined and obvious in meaning, is determined according to the clustering result, and has no fixed pattern.
Step S5 specifically includes the following steps:
firstly, marking each clustering result set, and further obtaining a plurality of groups of marked current data, wherein each group of current data comprises a mark and acquisition time. One cluster result set corresponds to one set of current data. A category is marked on each clustering result set corresponding to the daily electricity utilization data of the enterprise.
And then sequencing each group of data according to the acquisition time, calculating each group of current data to obtain a separation point with the minimum information entropy, searching the acquisition time corresponding to the separation point, and recording each acquisition time as a time interval point of the enterprise power utilization mode.
And finally, calculating time interval points of the enterprise electricity utilization modes according to the current data of all the groups to obtain all the air pressure electricity utilization modes and the start-stop time of each enterprise electricity utilization mode.
Different enterprises have different working properties and different power utilization modes.
The power utilization data are linked with the working modes of the enterprises in a hooking mode, the working modes of the enterprises are reflected through the power utilization data, and the power utilization risks of the enterprises can be pre-warned in advance and the working modes of the enterprises can be monitored through analysis of the power utilization modes of the enterprises, so that more values are realized.
And step S6, merging the daily electricity utilization data of the enterprises in the preset time period according to the time interval points of the enterprise electricity utilization modes and the enterprise electricity utilization modes to obtain an electricity utilization data model of the enterprise electricity utilization modes.
The power utilization data model of the enterprise power utilization mode comprises the starting and ending time of each enterprise power utilization mode, the current data of each enterprise power utilization mode, the collection time of the current data, the current data distribution characteristics and the current data change characteristics.
And step S7, acquiring the electricity utilization data of the enterprise in the current period of time in real time.
And S8, matching and comparing the power utilization data of the enterprise in the current period with the power utilization data model of the enterprise power utilization mode, further obtaining the enterprise power utilization mode of the enterprise in the current period, and judging whether the power utilization data of the enterprise is abnormal or not.
And step S9, when the power utilization data of the enterprise in the current period is judged to be abnormal, timely reminding relevant workers of the enterprise.
For example, when the acquired enterprise power consumption data is not matched with the power consumption data in the corresponding type of enterprise power consumption mode, it is indicated that the current enterprise power consumption data may have abnormality, and the enterprise staff is notified in time, so that the enterprise staff can find the abnormality of the enterprise power consumption in time, power consumption accidents are avoided, and the early warning function of the enterprise power consumption is achieved.
Example two
The invention provides an enterprise power utilization pattern recognition device based on clustering. As shown in fig. 2, an internal structure of the device for identifying an enterprise electricity consumption pattern based on clustering according to an embodiment of the present invention is schematically illustrated.
In this embodiment, the clustering-based enterprise electricity pattern recognition device may be a PC (personal computer), or may be a terminal device such as a smart phone, a tablet computer, or a portable computer. The enterprise electricity utilization pattern recognition device based on clustering at least comprises: a processor 12, a communication bus 13, a network interface 14, and a memory 11.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may be an internal storage unit of the cluster-based enterprise power pattern recognition apparatus in some embodiments, such as a hard disk of the cluster-based enterprise power pattern recognition apparatus. The memory 11 may also be an external storage device of the cluster-based enterprise power pattern recognition apparatus in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the cluster-based enterprise power pattern recognition apparatus. Further, the memory 11 may also include both an internal storage unit and an external storage device of the cluster-based enterprise power pattern recognition apparatus. The memory 11 may be used to store not only application software installed in the cluster-based enterprise electricity pattern recognition apparatus and various types of data, such as codes of an enterprise electricity pattern recognition program, but also temporarily store data that has been output or will be output.
The processor 12 may be, in some embodiments, a Central Processing Unit (CPU), controller, microcontroller, microprocessor or other data Processing chip, and is used for executing program codes stored in the memory 11 or Processing data, such as executing an enterprise power pattern recognition program.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication link between the cluster-based enterprise power pattern recognition apparatus and other electronic devices.
Optionally, the cluster-based enterprise power consumption pattern recognition apparatus may further include a user interface, the user interface may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface may further include a standard wired interface and a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the cluster-based enterprise power pattern recognition apparatus and for displaying a visual user interface.
While fig. 2 shows only a cluster-based enterprise power pattern recognition arrangement having components 11-14 and an enterprise power pattern recognition program, those skilled in the art will appreciate that the configuration shown in fig. 2 does not constitute a limitation of a cluster-based enterprise power pattern recognition arrangement and may include fewer or more components than shown, or some components in combination, or a different arrangement of components.
In the embodiment of the enterprise electricity pattern recognition device based on clustering shown in fig. 2, an enterprise electricity pattern recognition program is stored in the memory 11; when the processor 12 executes the enterprise power consumption pattern recognition program stored in the memory 11, the following steps are implemented:
an acquisition step: acquiring daily electricity utilization data of enterprises in a preset time period; the electricity consumption data comprises current data and acquisition time;
clustering: clustering the daily power utilization data of the enterprise by adopting a mixed Gaussian model according to the preset cluster number to obtain a plurality of clustering result sets corresponding to the daily power utilization data of the enterprise;
a mode dividing step: taking the daily electricity utilization data of the enterprises as objects, and obtaining time interval points of the enterprise electricity utilization modes, the enterprise electricity utilization modes and the start and stop times of the enterprise electricity utilization modes according to each clustering result set;
a model generation step: merging the daily power utilization data of the enterprises in a preset time period according to the time interval points of the enterprise power utilization modes and the enterprise power utilization modes to obtain a power utilization data model of the enterprise power utilization modes; the power utilization data model of the enterprise power utilization mode comprises the starting and ending time of each enterprise power utilization mode, current data of each enterprise power utilization mode, the acquisition time of the current data, the distribution characteristics of the current data and the change characteristics of the current data;
pattern recognition: the method comprises the steps of acquiring the electricity utilization data of an enterprise in a current period of time in real time, matching and identifying the electricity utilization data of the enterprise in the current period of time with an electricity utilization data model of an enterprise electricity utilization mode to obtain the enterprise electricity utilization mode of the enterprise in the current period of time, and judging whether the electricity utilization data of the enterprise are abnormal or not.
Further, the acquiring step includes: and collecting the electricity utilization data of enterprises through the installed air switch at regular time.
Further, the timed time is set according to the working property of the enterprise.
Further, the clustering step is preceded by:
denoising: and denoising the daily electricity utilization data of the enterprise, and removing wrong current data.
Further, the denoising step comprises denoising the daily electricity utilization data of the enterprise by a 3 sigma method.
Further, the power consumption pattern dividing step comprises the following steps:
a pretreatment step: preprocessing the current data in each clustering result set to remove discrete current data;
further, the pattern division step specifically includes: firstly, marking each clustering result set to obtain a plurality of groups of marked current data; each group of current data comprises the acquisition time and the mark of the current data; one cluster result set corresponds to one set of current data; then sorting each group of current data according to acquisition time, calculating each group of current data to obtain a separation point with the minimum information entropy, searching acquisition time corresponding to the separation point, and recording each acquisition time as a time interval point of an enterprise power utilization mode; and finally, calculating time interval points of the enterprise electricity utilization modes according to the current data of all the groups to obtain all the enterprise electricity utilization modes and the starting and ending time of each enterprise electricity utilization mode.
Further, the enterprise power utilization pattern recognition method comprises the early warning steps of:
when the electricity utilization data of the enterprise in the current period of time is not matched with the current data of the corresponding enterprise electricity utilization mode, the electricity utilization data of the enterprise in the current period of time is abnormal, and early warning notice is issued to enterprise staff.
EXAMPLE III
A storage medium, which is a computer readable storage medium, on which an enterprise power pattern recognition program is stored, the enterprise power pattern recognition program being a computer program, and the enterprise power pattern recognition program, when executed by a processor, implements the steps of the clustering-based enterprise power pattern recognition method as employed in an embodiment provided by the present invention.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. The method for identifying the enterprise power consumption mode based on clustering is characterized by comprising the following steps of:
an acquisition step: acquiring daily electricity utilization data of enterprises in a preset time period; the electricity consumption data comprises current data and acquisition time;
clustering: clustering the daily power utilization data of the enterprise by adopting a mixed Gaussian model according to the preset cluster number to obtain a plurality of clustering result sets corresponding to the daily power utilization data of the enterprise;
a mode dividing step: taking the daily electricity utilization data of the enterprises as objects, and obtaining time interval points of the enterprise electricity utilization modes, the enterprise electricity utilization modes and the start and stop times of the enterprise electricity utilization modes according to each clustering result set;
a model generation step: merging the daily power utilization data of the enterprises in a preset time period according to the time interval points of the enterprise power utilization modes and the enterprise power utilization modes to obtain a power utilization data model of the enterprise power utilization modes; the power utilization data model of the enterprise power utilization mode comprises the starting and ending time of each enterprise power utilization mode, current data of each enterprise power utilization mode, the acquisition time of the current data, the distribution characteristics of the current data and the change characteristics of the current data;
pattern recognition: the method comprises the steps of acquiring the electricity utilization data of an enterprise in a current period of time in real time, matching and identifying the electricity utilization data of the enterprise in the current period of time with an electricity utilization data model of an enterprise electricity utilization mode to obtain the enterprise electricity utilization mode of the enterprise in the current period of time, and judging whether the electricity utilization data of the enterprise are abnormal or not.
2. The method for cluster-based enterprise power pattern recognition according to claim 1, wherein the obtaining step comprises: and collecting the electricity utilization data of enterprises through the installed air switch at regular time.
3. The method according to claim 2, wherein the timing time is set according to the working property of the enterprise.
4. The method for cluster-based enterprise power pattern recognition according to claim 1, wherein the clustering step comprises, before:
denoising: and denoising the daily electricity utilization data of the enterprise, and removing wrong current data.
5. The method for identifying enterprise electricity consumption patterns based on clustering as claimed in claim 4, wherein the denoising step comprises denoising the daily electricity consumption data of the enterprise by a 3 σ method.
6. The method for cluster-based enterprise power consumption pattern recognition according to claim 1, wherein the power consumption pattern classification step comprises, before:
a pretreatment step: and preprocessing the current data in each clustering result set to remove discrete current data.
7. The method for identifying enterprise electricity utilization patterns based on clustering according to claim 1, wherein the pattern classification step specifically comprises: firstly, marking each clustering result set to obtain a plurality of groups of marked current data; each group of current data comprises the acquisition time and the mark of the current data; one cluster result set corresponds to one set of current data; then sorting each group of current data according to acquisition time, calculating each group of current data to obtain a separation point with the minimum information entropy, searching acquisition time corresponding to the separation point, and recording each acquisition time as a time interval point of an enterprise power utilization mode; and finally, calculating time interval points of the enterprise electricity utilization modes according to the current data of all the groups to obtain all the enterprise electricity utilization modes and the starting and ending time of each enterprise electricity utilization mode.
8. The cluster-based enterprise power consumption pattern recognition method of claim 1, wherein the enterprise power consumption pattern recognition method comprises an early warning step:
when the electricity utilization data of the enterprise in the current period of time is not matched with the current data of the corresponding enterprise electricity utilization mode, the electricity utilization data of the enterprise in the current period of time is abnormal, and early warning notice is issued to enterprise staff.
9. An enterprise electricity pattern recognition device based on clustering, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the computer program is an enterprise electricity pattern recognition program, and is characterized in that: the processor when executing the enterprise power pattern recognition program performs the steps of the cluster-based enterprise power pattern recognition method according to any one of claims 1-8.
10. A storage medium which is a computer-readable storage medium having a computer program stored thereon, the computer program being an enterprise power pattern recognition program, characterized in that: the enterprise power pattern recognition program when executed by a processor implements the steps of the cluster-based enterprise power pattern recognition method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599537.XA CN111652325B (en) | 2020-06-28 | 2020-06-28 | Enterprise power consumption mode identification method and device based on clustering and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010599537.XA CN111652325B (en) | 2020-06-28 | 2020-06-28 | Enterprise power consumption mode identification method and device based on clustering and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111652325A true CN111652325A (en) | 2020-09-11 |
| CN111652325B CN111652325B (en) | 2022-09-13 |
Family
ID=72347483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010599537.XA Active CN111652325B (en) | 2020-06-28 | 2020-06-28 | Enterprise power consumption mode identification method and device based on clustering and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652325B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633666A (en) * | 2020-12-18 | 2021-04-09 | 国网安徽省电力有限公司合肥供电公司 | Power enterprise user rework condition monitoring method based on K-means clustering algorithm |
| CN117666449A (en) * | 2024-01-31 | 2024-03-08 | 四川水利职业技术学院 | Based on computer data acquisition analysis monitored control system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358838A1 (en) * | 2013-06-04 | 2014-12-04 | International Business Machines Corporation | Detecting electricity theft via meter tampering using statistical methods |
| CN108632097A (en) * | 2018-05-14 | 2018-10-09 | 平安科技（深圳）有限公司 | Recognition methods, terminal device and the medium of abnormal behaviour object |
| CN108830324A (en) * | 2018-06-20 | 2018-11-16 | 国网上海市电力公司 | A kind of public building multiplexing electric abnormality method of discrimination based on data mining technology |
| CN110458719A (en) * | 2019-05-21 | 2019-11-15 | 国家电网有限公司 | A kind of dispatching method of electric network and system for power grid enterprises |
-
2020
- 2020-06-28 CN CN202010599537.XA patent/CN111652325B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358838A1 (en) * | 2013-06-04 | 2014-12-04 | International Business Machines Corporation | Detecting electricity theft via meter tampering using statistical methods |
| CN108632097A (en) * | 2018-05-14 | 2018-10-09 | 平安科技（深圳）有限公司 | Recognition methods, terminal device and the medium of abnormal behaviour object |
| CN108830324A (en) * | 2018-06-20 | 2018-11-16 | 国网上海市电力公司 | A kind of public building multiplexing electric abnormality method of discrimination based on data mining technology |
| CN110458719A (en) * | 2019-05-21 | 2019-11-15 | 国家电网有限公司 | A kind of dispatching method of electric network and system for power grid enterprises |
Non-Patent Citations (1)
| Title |
|---|
| 胡阳春: "基于改进k 均值聚类算法的电力负荷模式识别方法研究", 《中国优秀博硕士学位论文全文数据库（硕士） 工程科技II辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112633666A (en) * | 2020-12-18 | 2021-04-09 | 国网安徽省电力有限公司合肥供电公司 | Power enterprise user rework condition monitoring method based on K-means clustering algorithm |
| CN117666449A (en) * | 2024-01-31 | 2024-03-08 | 四川水利职业技术学院 | Based on computer data acquisition analysis monitored control system |
| CN117666449B (en) * | 2024-01-31 | 2024-04-12 | 四川水利职业技术学院 | Based on computer data acquisition analysis monitored control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111652325B (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726731B (en) | Power consumption abnormality detection method, device, equipment and readable storage medium | |
| CN102165644B (en) | Automatic discovery of physical connectivity between power outlets and IT equipment | |
| CN111652325B (en) | Enterprise power consumption mode identification method and device based on clustering and storage medium | |
| CN108776276B (en) | Power consumption abnormity detection method and system | |
| CN103200050A (en) | Server hardware state monitoring method and server hardware state monitoring system | |
| CN113344452B (en) | Park energy consumption management and control method and system, intelligent terminal and storage medium | |
| CN110766590A (en) | Street lamp predictive maintenance system and method based on deep learning | |
| CN105550939A (en) | Knitting production management system terminal | |
| WO2020000738A1 (en) | Gaussian distribution-based timed task abnormality monitoring method, electronic device, and medium | |
| CN112181967A (en) | Method and device for monitoring source data quality, computer equipment and medium | |
| CN116027725A (en) | Group control optimization analysis system based on high-efficiency machine room | |
| CN111047162A (en) | Campus potential safety hazard troubleshooting system and method | |
| CN111784042B (en) | Power utilization node safety risk prediction method and device and storage medium | |
| CN112907911A (en) | Intelligent anomaly identification and alarm algorithm based on equipment process data | |
| CN115719139A (en) | Dispatching self-checking system for power grid dispatching operation management | |
| CN115561700A (en) | Method and device for analyzing metering standard of direct current electric energy meter | |
| CN114140241A (en) | Abnormity identification method and device for transaction monitoring index | |
| Imanishi et al. | Time-series decomposition of power demand data to extract uncertain features | |
| CN112578759A (en) | Multi-terminal data acquisition method and device based on MES system | |
| CN113129464B (en) | Office equipment automatic control method, office equipment automatic control device, office equipment automatic control server and storage medium | |
| CN113253007B (en) | Multi-dimensional intelligent anti-electricity-stealing accurate positioning method and system for special transformer user | |
| CN109816168A (en) | A kind of data forecasting system for electrical equipment | |
| CN112818648A (en) | Automatic leading-in method and system for power grid energy management system signboards | |
| CN111258865B (en) | Processor, alarm data management system and method of multi-informatization system | |
| CN109615555B (en) | User abnormal electricity behavior identification method and system based on integrated learning algorithm |
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 |