CN115982577A - Intelligent electricity consumption real-time monitoring method and system - Google Patents
Intelligent electricity consumption real-time monitoring method and system Download PDFInfo
- Publication number
- CN115982577A CN115982577A CN202310270325.0A CN202310270325A CN115982577A CN 115982577 A CN115982577 A CN 115982577A CN 202310270325 A CN202310270325 A CN 202310270325A CN 115982577 A CN115982577 A CN 115982577A
- Authority
- CN
- China
- Prior art keywords
- time
- electricity consumption
- electricity
- matrix
- total
- 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
Images
Classifications
-
- 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
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention relates to the technical field of behavior monitoring, and particularly discloses an intelligent electricity consumption real-time monitoring method and system, wherein the method comprises the steps of acquiring a power supply network containing nodes in a monitoring area input by a worker, and acquiring electricity consumption parameters in real time based on the nodes; establishing an electricity consumption oscillogram according to the electricity consumption parameters; extracting periodic historical data from the electro-oscillogram according to a preset time period, and updating electricity utilization characteristics based on the periodic historical data; and judging whether the electricity utilization behavior in the recent time period is abnormal or not according to the electricity utilization characteristics. The invention acquires power utilization parameters in real time, extracts the characteristics of the power utilization parameters based on a signal processing technology, integrates the power utilization parameters of a plurality of nodes into a matrix similar to an image, extracts the matrix characteristics at regular time by using the existing image recognition technology, judges new power utilization behaviors by the extracted matrix characteristics, and continuously changes the matrix characteristics along with the lapse of time, thereby realizing self-adaptive adjustment.
Description
Technical Field
The invention relates to the technical field of behavior monitoring, in particular to an intelligent electricity consumption real-time monitoring method and system.
Background
The power system can be roughly divided into five main links: power generation, power transmission, power transformation, power distribution and power utilization. The 'power utilization monitoring' refers to the technology of monitoring the tail end of a power distribution link and the aspects of energy consumption, electric energy quality, safety and the like of the power utilization link in real time, and processing, transmitting, storing and visually displaying obtained monitoring data.
The existing electricity utilization detection process is an intelligent monitoring process based on multiple sensing devices, and data acquisition in the mode is comprehensive and rapid and has high identification efficiency. However, the calibration process of the method cannot be self-adaptively matched, the data is complex, a designer needs to make many rules in the identification process, corresponding judgment conditions need to be changed every time the electricity consumption unit is changed, and the research and development pressure and the maintenance pressure are high.
Disclosure of Invention
The present invention provides a method and a system for monitoring power consumption intelligently in real time to solve the problems of the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for intelligent real-time monitoring of electricity usage, the method comprising:
acquiring a power supply network containing nodes in a monitoring area input by a worker, and acquiring power utilization parameters in real time based on the nodes;
establishing an electricity consumption oscillogram according to the electricity consumption parameters; the abscissa of the electro-fluctuation chart is time, the ordinate is divided into a plurality of sections based on node numbers, and the number of the sections is the same as the number of the nodes;
extracting periodic historical data from the electro-fluctuation map according to a preset time period, and updating electricity utilization characteristics based on the periodic historical data;
and judging whether the electricity utilization behavior in the recent time period is abnormal or not according to the electricity utilization characteristics.
As a further scheme of the invention: the method comprises the following steps of obtaining a power supply network containing nodes in a monitoring area input by a worker, and obtaining power utilization parameters in real time based on the nodes, wherein the steps comprise:
receiving boundary information input by a worker, and determining a monitoring area according to the boundary information;
acquiring a central point position in the monitoring area, and acquiring a line containing a direction based on the central point position;
determining an output node on a line containing a direction, and inquiring the theoretical load capacity of the output node;
counting all output nodes and the load quantity thereof, and determining the prediction parameters of each point according to the theoretical load quantity;
and selecting a monitoring end according to the prediction parameters, and acquiring power utilization parameters based on the monitoring end.
As a further scheme of the invention: the step of establishing the power consumption oscillogram according to the power consumption parameters comprises the following steps:
converting the electricity usage parameter into a hopping waveform based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
performing Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
the power curve is inserted at the corresponding ordinate segment according to the waveform function.
As a further scheme of the invention: the step of extracting periodic historical data from the electricity consumption oscillogram according to a preset time period and updating electricity consumption characteristics based on the periodic historical data comprises the following steps:
determining a time period to be detected according to a preset selection rule, and segmenting the time period to be detected according to a preset time cycle to obtain historical data corresponding to different time cycles;
sequentially reading feature matrixes corresponding to all power curves at all times in historical data, and connecting the feature matrixes according to node numbers corresponding to the power curves to obtain a total feature matrix corresponding to a power supply network;
carrying out repeatability judgment on the total feature matrix, and removing the repeated total feature matrix;
and arranging the total characteristic matrix, and updating the electricity utilization characteristics according to the arranged total characteristic matrix.
As a further scheme of the invention: the step of carrying out repeatability judgment on the total feature matrix and rejecting the repeated total feature matrix comprises the following steps:
reading adjacent total feature matrixes in sequence;
randomly selecting data in the two total feature matrixes according to the squares with preset sizes;
calculating a difference value of the selected data, and increasing a preset value by the similarity score when the difference value is smaller than a preset difference condition;
circularly executing until the similarity score reaches a preset similarity score threshold value, and randomly reserving any total feature matrix;
and when the random selection times reach a preset time threshold or the data of the total characteristic matrix are selected at least once, jumping out of the cycle.
As a further scheme of the invention: the step of arranging the total characteristic matrix and updating the electricity utilization characteristics according to the arranged total characteristic matrix comprises the following steps of:
extracting two-dimensional features in the total feature matrix according to a preset image recognition algorithm;
matching a target matrix in all the total feature matrixes of other time periods according to the two-dimensional features;
when the number of the matched target matrixes reaches a preset number threshold, marking a total characteristic matrix where the two-dimensional characteristics are located;
and counting the marked total characteristic matrix as the electricity utilization characteristics.
As a further scheme of the invention: the step of judging whether the electricity utilization behavior in the recent time period is abnormal according to the electricity utilization characteristics comprises the following steps:
calculating the relative time of the electricity consumption behavior; the relative time is the difference between the actual time and the starting time of the latest time period;
inquiring a total characteristic matrix in the electricity utilization characteristics according to the relative time to be used as a reference total characteristic matrix;
acquiring a total characteristic matrix of the electricity consumption behaviors, and comparing the total characteristic matrix of the electricity consumption behaviors with a reference total characteristic matrix;
and judging whether the electricity utilization behavior is abnormal or not according to the comparison result.
The technical scheme of the invention also provides an intelligent power consumption real-time monitoring system, which comprises:
the power utilization parameter acquisition module is used for acquiring a power supply network containing nodes in a monitoring area input by a worker and acquiring power utilization parameters in real time based on the nodes;
the fluctuation map establishing module is used for establishing a power consumption fluctuation map according to the power consumption parameters; the abscissa of the electro-oscillogram is time, the ordinate is divided into a plurality of sections based on the node number, and the number of the sections is the same as the number of the nodes;
the characteristic updating module is used for extracting periodic historical data from the electricity consumption fluctuation graph according to a preset time period and updating electricity consumption characteristics based on the periodic historical data;
and the abnormity determining module is used for determining whether the electricity utilization behavior in the recent time period is abnormal according to the electricity utilization characteristics.
As a further scheme of the invention: the electricity consumption parameter acquisition module comprises:
the monitoring area determining unit is used for receiving boundary information input by a worker and determining a monitoring area according to the boundary information;
the line acquisition unit is used for acquiring a central point position in the monitoring area and acquiring a line containing a direction based on the central point position;
the load inquiry unit is used for determining an output node on a line containing a direction and inquiring the theoretical load of the output node;
the parameter prediction unit is used for counting all the output nodes and the load capacity thereof and determining the prediction parameters of each point according to the theoretical load capacity;
and the monitoring end selecting unit is used for selecting a monitoring end according to the prediction parameters and acquiring power utilization parameters based on the monitoring end.
As a further scheme of the invention: the fluctuation graph establishing module comprises:
a parameter conversion unit for converting the electricity consumption parameter into a hopping waveform based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
the waveform processing unit is used for carrying out Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
the longitudinal coordinate segmentation unit is used for determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
and the curve inserting unit is used for inserting the power curve at the corresponding ordinate section according to the waveform function.
Compared with the prior art, the invention has the beneficial effects that: the invention acquires the electricity utilization parameters in real time, extracts the characteristics of the electricity utilization parameters based on a signal processing technology, integrates the electricity utilization parameters of a plurality of nodes into a matrix similar to an image, extracts the matrix characteristics at regular time by using the existing image recognition technology, judges the new electricity utilization behavior by the extracted matrix characteristics, and continuously changes the matrix characteristics along with the passage of time, thereby realizing self-adaptive adjustment.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 is a flow chart of a real-time monitoring method for intelligent power consumption.
Fig. 2 is a first sub-flow diagram of the intelligent real-time monitoring method.
Fig. 3 is a second sub-flowchart of the intelligent real-time monitoring method.
Fig. 4 is a third sub-flowchart of the intelligent real-time monitoring method for electricity consumption.
FIG. 5 is a fourth sub-flowchart of the intelligent real-time monitoring method for electricity consumption.
Fig. 6 is a block diagram of the structure of the intelligent real-time monitoring system for electricity consumption.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Fig. 1 is a flow chart of a smart electricity consumption real-time monitoring method, in an embodiment of the present invention, the smart electricity consumption real-time monitoring method includes:
step S100: acquiring a power supply network containing nodes in a monitoring area input by a worker, and acquiring power utilization parameters in real time based on the nodes;
the monitoring area is input by workers, each node is determined in the monitoring area, and a power supply network containing the node can be obtained, wherein the node refers to a node with power interaction; for example, if the monitoring area is a residential area, the node is a power supply node of each household; the electricity utilization parameter can be voltage or current, and is generally limited to current.
Step S200: establishing an electricity consumption fluctuation graph according to the electricity consumption parameters; the abscissa of the electro-oscillogram is time, the ordinate is divided into a plurality of sections based on the node number, and the number of the sections is the same as the number of the nodes;
counting the electricity consumption parameters of all the nodes, and establishing an electricity consumption fluctuation graph; in the coordinate axis of the electro-oscillogram, the abscissa is time, the ordinate is divided into a plurality of sections, and different sections correspond to different nodes.
Step S300: extracting periodic historical data from the electro-oscillogram according to a preset time period, and updating electricity utilization characteristics based on the periodic historical data;
the time period is generally in units of days, electricity utilization data (historical data) are extracted in the electricity utilization oscillogram in the period of days, electricity utilization characteristics are determined according to the extracted electricity utilization data, and if the electricity utilization characteristics exist, the electricity utilization characteristics are updated;
step S400: judging whether the electricity utilization behavior in the recent time period is abnormal or not according to the electricity utilization characteristics;
the electricity utilization characteristics determined by the historical data can judge whether the new electricity utilization behavior is abnormal or not, and if the new electricity utilization behavior is abnormal, some warning information is generated.
Fig. 2 is a first sub-flow diagram of the intelligent real-time electricity consumption monitoring method, wherein a power supply network with nodes is acquired from a monitoring area input by a worker, and the step of acquiring electricity consumption parameters in real time based on the nodes comprises the following steps:
step S101: receiving boundary information input by a worker, and determining a monitoring area according to the boundary information;
the monitoring area is input by the staff.
Step S102: acquiring a central point position in the monitoring area, and acquiring a line containing a direction based on the central point position;
acquiring a central point position in a monitoring area, wherein the central point position is a power supply end, such as a machine room in a cell; all lines take output point positions as starting points; and taking the output point position as a reference, and acquiring other lines containing a direction, wherein the direction is the current direction.
Step S103: determining an output node on a line containing a direction, and inquiring the theoretical load capacity of the output node;
the power consumption of different output nodes has a limit (theoretical load capacity), and the limit is determined by a unit connected with the output nodes; the theoretical load is generally expressed in terms of impedance.
Step S104: counting all output nodes and the load quantity thereof, and determining the prediction parameters of each point according to the theoretical load quantity;
counting all output nodes and load quantities thereof, establishing a circuit diagram, performing theoretical calculation on the circuit diagram, and determining the predicted current of each output node; it is worth mentioning that there is an impact between the different loading amounts, which needs to be considered as a whole.
Step S105: selecting a monitoring end according to the prediction parameters, and acquiring power utilization parameters based on the monitoring end;
and selecting the specification of the monitoring end according to the predicted current, and acquiring current data based on the monitoring end.
Fig. 3 is a second sub-flow chart of the intelligent electricity consumption real-time monitoring method, wherein the step of establishing an electricity consumption oscillogram according to the electricity consumption parameters comprises:
step S201: converting the electricity utilization parameters into hopping waveforms based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
when the electricity consumption parameter is current, the current is arranged according to the time information, and point-connection is performed in a preset coordinate axis, so that a hopping waveform can be obtained.
Step S202: carrying out Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
the fourier transform is a special integral transform, which can express a certain function satisfying a certain condition as a linear combination or integral of a sine basis function, and is a common means in the technical field of signal processing; the jump waveform is subjected to Fourier transform, the jump waveform can be represented by a plurality of items of trigonometric functions, and the characteristics of the trigonometric functions can be taken as the characteristics of the jump waveform.
It is worth mentioning that the period of the electricity consumption behavior is in days, that is, the electricity consumption behaviors of each day are approximately similar, at this time, the hopping waveform which is actually a non-periodic signal can be regarded as a periodic signal in days, and the hopping waveform can be converted into the sum of a polynomial trigonometric function by directly calculating the fourier series; and selecting the first items to obtain the triangular function characteristics of the first items, so as to obtain the characteristics of the hopping waveform, wherein the characteristics of the hopping waveform are expressed by a matrix.
Step S203: determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
step S204: inserting a power curve at the corresponding vertical coordinate section according to the waveform function;
and determining the vertical coordinate span and unit of the hopping waveform in the coordinate axis according to the amplitude of the characteristic matrix, and then inserting the hopping waveform into the coordinate axis.
The above process is simple, and it can be understood that a plurality of hopping waveforms are sequentially arranged from top to bottom and share the same time axis.
The power curve is formed by combining finite terms of Fourier series of a hopping waveform, and is fit to the hopping waveform.
Fig. 4 is a third sub-flowchart of the intelligent real-time monitoring method for electricity consumption, wherein the step of extracting periodic historical data from an electricity consumption oscillogram according to a preset time period and updating electricity consumption characteristics based on the periodic historical data comprises:
step S301: determining a time period to be detected according to a preset selection rule, and segmenting the time period to be detected according to a preset time cycle to obtain historical data corresponding to different time cycles;
the process of extracting the electricity utilization characteristics from the electricity utilization oscillogram is the core content of the technical scheme of the invention, firstly, periodic historical data needs to be extracted from the electricity utilization oscillogram, the period is one day, and the selection range (the period to be detected) can be one week or one month before the current time.
Step S302: sequentially reading feature matrixes corresponding to all power curves at all times in historical data, and connecting the feature matrixes according to node numbers corresponding to the power curves to obtain a total feature matrix corresponding to a power supply network;
the method comprises the steps of obtaining power curves and characteristic matrixes of the power curves at different moments in a certain period according to a preset sampling frequency, and then arranging the characteristic matrixes according to node positions corresponding to the power curves to obtain a total characteristic matrix corresponding to a power supply network.
Step S303: carrying out repeatability judgment on the total feature matrix, and removing the repeated total feature matrix;
in a period, the total feature matrix of adjacent time instants may be the same, and at this time, one total feature matrix is reserved.
Step S304: arranging the total characteristic matrix, and updating the electricity utilization characteristics according to the arranged total characteristic matrix;
and after the repeated total characteristic matrix is removed, analyzing the reserved total characteristic matrix to determine the electricity utilization characteristics.
In an example of the technical solution of the present invention, the step of performing a repetitiveness determination on the total feature matrix and eliminating the repeated total feature matrix includes:
reading adjacent total feature matrixes in sequence; the repeatability judgment is carried out in adjacent total feature matrixes, and the adjacent is adjacent in time; if repeated, one is culled, if not repeated, all are retained, and the process is repeated.
Randomly selecting data in the two total feature matrixes according to the squares with preset sizes;
calculating a difference value of the selected data, and increasing a preset value by the similarity score when the difference value is smaller than a preset difference condition;
circularly executing until the similarity score reaches a preset similarity score threshold value, and randomly reserving any total feature matrix;
judging whether the repeated process is a small cycle, sequentially selecting partial contents (selected by the grids), comparing the difference between the partial contents, if the partial contents are the same as the partial contents, increasing a numerical value for the similarity score, and if the partial contents are different from the similarity score, reducing the similarity score or keeping the similarity score unchanged; continuously repeating the process until the similarity score reaches a preset similarity score threshold value; when the random selection times reach a preset time threshold or the data of the total characteristic matrix are selected at least once, circulation can be skipped.
It should be noted that, because each part of the total feature matrix corresponds to a node, each numerical value in the total feature matrix is very important, and in the process of repeated determination, the two total feature matrices can be directly subjected to xor operation (different 1, the same 0), and the difference points can be directly determined; in this case, the accuracy and the comprehensiveness of information are higher, but small changes caused by fluctuation are also retained, and the data rejection rate is not high in the process of repeated judgment.
In an example of the technical solution of the present invention, the step of arranging the total feature matrix and updating the power consumption feature according to the arranged total feature matrix includes:
extracting two-dimensional features in the total feature matrix according to a preset image recognition algorithm;
matching a target matrix in all the total feature matrixes of other time periods according to the two-dimensional features;
when the number of the matched target matrixes reaches a preset number threshold, marking a total characteristic matrix where the two-dimensional characteristics are located;
and counting the marked total characteristic matrix as the electricity utilization characteristics.
The core of the technical scheme of the invention is that the working states of all nodes are reflected by the total characteristic matrix, and at the moment, the total characteristic matrix can be rapidly identified by using the existing image identification algorithm (the image is also a matrix), and the electricity utilization characteristics are extracted; the process of extracting the electricity utilization characteristics comprises the steps of firstly extracting two-dimensional characteristics in a certain total characteristic matrix, then judging whether the two-dimensional characteristics appear in other total characteristic matrices, if the two-dimensional characteristics appear in a plurality of total characteristic matrices, the total characteristic matrices can be regarded as the electricity utilization characteristics, of course, the corresponding total characteristic matrices can also be regarded as the total characteristic matrices in a normal state, and the process of directly taking the total characteristic matrices as the electricity utilization characteristics is also a feasible scheme.
The most common two-dimensional features can be analogized to image contours, that is, the image recognition algorithm is a contour recognition algorithm, and the identified contour internal mean value, contour internal numerical quantity, gravity center position, contour shape and the like of different contours are taken as the two-dimensional features.
Fig. 5 is a fourth sub-flow chart of the intelligent real-time electricity consumption monitoring method, wherein the step of determining whether the electricity consumption behavior in the recent time period is abnormal according to the electricity consumption characteristics includes:
step S401: calculating the relative time of the electricity consumption behavior; the relative time is the difference between the actual time and the starting time of the latest time period;
step S402: inquiring a total characteristic matrix in the electricity utilization characteristics according to the relative time to be used as a reference total characteristic matrix;
step S403: acquiring a total characteristic matrix of the electricity consumption behavior, and comparing the total characteristic matrix of the electricity consumption behavior with a reference total characteristic matrix;
step S404: and judging whether the electricity utilization behavior is abnormal or not according to the comparison result.
Step S401 to step S404 are application processes, and when a certain time is analyzed, the time of the time relative to the whole period is calculated, and a total feature matrix (electricity utilization feature) around is queried according to the relative time as reference data; and calculating a total characteristic matrix at a certain moment based on the existing process, and comparing the two total characteristic matrices to judge whether the electricity consumption behavior is abnormal.
It should be noted that the power consumption behavior determined as abnormal is not necessarily true, and needs to be further determined.
In summary, the core idea of the technical scheme of the invention is to judge whether the electricity utilization behavior of the whole area has an obvious unstable phenomenon on the whole, and the method is mainly used for monitoring the electricity utilization process of an unmanned area or a regular enterprise.
Fig. 6 is a block diagram illustrating a structure of an intelligent real-time monitoring system for electricity consumption, in an embodiment of the present invention, the system 10 includes:
the power utilization parameter acquisition module 11 is used for acquiring a power supply network containing nodes in a monitoring area input by a worker and acquiring power utilization parameters in real time based on the nodes;
the fluctuation map establishing module 12 is used for establishing an electricity consumption fluctuation map according to the electricity consumption parameters; the abscissa of the electro-oscillogram is time, the ordinate is divided into a plurality of sections based on the node number, and the number of the sections is the same as the number of the nodes;
the characteristic updating module 13 is configured to extract periodic historical data from the electricity consumption fluctuation graph according to a preset time period, and update electricity consumption characteristics based on the periodic historical data;
and the abnormity determining module 14 is used for determining whether the electricity utilization behavior in the recent time period is abnormal according to the electricity utilization characteristics.
The electricity parameter acquisition module 11 includes:
the monitoring area determining unit is used for receiving boundary information input by a worker and determining a monitoring area according to the boundary information;
the line acquisition unit is used for acquiring a central point position in the monitoring area and acquiring a line containing a direction based on the central point position;
the load inquiry unit is used for determining an output node on a line containing a direction and inquiring the theoretical load of the output node;
the parameter prediction unit is used for counting all the output nodes and the load capacity thereof and determining the prediction parameters of each point according to the theoretical load capacity;
and the monitoring end selecting unit is used for selecting a monitoring end according to the prediction parameters and acquiring power utilization parameters based on the monitoring end.
The fluctuation map creation module 12 includes:
a parameter conversion unit for converting the electricity consumption parameter into a hopping waveform based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
the waveform processing unit is used for carrying out Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
the longitudinal coordinate segmentation unit is used for determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
and the curve inserting unit is used for inserting the power curve at the corresponding ordinate section according to the waveform function.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A real-time monitoring method for intelligent electricity consumption is characterized by comprising the following steps:
acquiring a power supply network containing nodes in a monitoring area input by a worker, and acquiring power utilization parameters in real time based on the nodes;
establishing an electricity consumption fluctuation graph according to the electricity consumption parameters; the abscissa of the electro-fluctuation chart is time, the ordinate is divided into a plurality of sections based on node numbers, and the number of the sections is the same as the number of the nodes;
extracting periodic historical data from the electro-oscillogram according to a preset time period, and updating electricity utilization characteristics based on the periodic historical data;
and judging whether the electricity utilization behavior in the recent time period is abnormal or not according to the electricity utilization characteristics.
2. The intelligent electricity real-time monitoring method according to claim 1, wherein the power supply network including nodes is obtained in a monitoring area input by a worker, and the step of obtaining electricity utilization parameters in real time based on the nodes comprises:
receiving boundary information input by a worker, and determining a monitoring area according to the boundary information;
acquiring a central point position in the monitoring area, and acquiring a line containing a direction based on the central point position;
determining an output node on a line containing a direction, and inquiring the theoretical load capacity of the output node;
counting all output nodes and load quantities thereof, and determining prediction parameters of all points according to the theoretical load quantities;
and selecting a monitoring end according to the prediction parameters, and acquiring power utilization parameters based on the monitoring end.
3. The method according to claim 1, wherein the step of establishing an electrical usage oscillogram according to the electrical usage parameters comprises:
converting the electricity usage parameter into a hopping waveform based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
carrying out Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
the power curve is inserted at the corresponding ordinate segment according to the waveform function.
4. The intelligent electricity consumption real-time monitoring method according to claim 1, wherein the step of extracting periodic historical data from the electricity consumption fluctuation chart according to a preset time period and updating the electricity consumption characteristics based on the periodic historical data comprises:
determining a time period to be detected according to a preset selection rule, and segmenting the time period to be detected according to a preset time cycle to obtain historical data corresponding to different time cycles;
sequentially reading feature matrixes corresponding to all power curves at all times in historical data, and connecting the feature matrixes according to node numbers corresponding to the power curves to obtain a total feature matrix corresponding to a power supply network;
carrying out repeatability judgment on the total characteristic matrix, and rejecting the repeated total characteristic matrix;
and arranging the total characteristic matrix, and updating the electricity utilization characteristics according to the arranged total characteristic matrix.
5. The method according to claim 4, wherein the step of repeatedly determining the total feature matrix and eliminating the repeated total feature matrix comprises:
reading adjacent total feature matrixes in sequence;
randomly selecting data in the two total feature matrixes according to the squares with preset sizes;
calculating a difference value of the selected data, and increasing a preset value by the similarity score when the difference value is smaller than a preset difference condition;
circularly executing until the similarity score reaches a preset similarity score threshold value, and randomly reserving any total feature matrix;
and when the random selection times reach a preset time threshold or the data of the total characteristic matrix are selected at least once, jumping out of the cycle.
6. The intelligent real-time electricity consumption monitoring method according to claim 4, wherein the step of arranging the total feature matrix and updating the electricity consumption feature according to the arranged total feature matrix comprises:
extracting two-dimensional features in the total feature matrix according to a preset image recognition algorithm;
matching a target matrix in all the total feature matrixes of other time periods according to the two-dimensional features;
when the number of the matched target matrixes reaches a preset number threshold, marking a total characteristic matrix where the two-dimensional characteristics are located;
and counting the marked total characteristic matrix as the electricity utilization characteristics.
7. The intelligent electricity consumption real-time monitoring method according to claim 4, wherein the step of determining whether the electricity consumption behavior in the recent time period is abnormal according to the electricity consumption characteristics comprises:
calculating the relative time of the electricity consumption behavior; the relative time is the difference between the actual time and the starting time of the latest time period;
inquiring a total feature matrix in the electricity utilization features according to the relative time to serve as a reference total feature matrix;
acquiring a total characteristic matrix of the electricity consumption behavior, and comparing the total characteristic matrix of the electricity consumption behavior with a reference total characteristic matrix;
and judging whether the electricity utilization behavior is abnormal or not according to the comparison result.
8. The utility model provides an wisdom power consumption real-time monitoring system which characterized in that, the system includes:
the power utilization parameter acquisition module is used for acquiring a power supply network containing nodes in a monitoring area input by a worker and acquiring power utilization parameters in real time based on the nodes;
the fluctuation chart establishing module is used for establishing an electricity consumption fluctuation chart according to the electricity consumption parameters; the abscissa of the electro-oscillogram is time, the ordinate is divided into a plurality of sections based on the node number, and the number of the sections is the same as the number of the nodes;
the characteristic updating module is used for extracting periodic historical data from the electro-fluctuation map according to a preset time period and updating the electricity utilization characteristics based on the periodic historical data;
and the abnormity judging module is used for judging whether the electricity utilization behavior in the recent time period is abnormal or not according to the electricity utilization characteristics.
9. The intelligent real-time monitoring system for electricity consumption according to claim 8, wherein the electricity consumption parameter acquiring module comprises:
the monitoring area determining unit is used for receiving boundary information input by a worker and determining a monitoring area according to the boundary information;
the line acquisition unit is used for acquiring a central point position in the monitoring area and acquiring a line containing a direction based on the central point position;
the load inquiry unit is used for determining an output node on a line containing a direction and inquiring the theoretical load of the output node;
the parameter prediction unit is used for counting all the output nodes and the load capacity thereof and determining the prediction parameters of each point according to the theoretical load capacity;
and the monitoring end selecting unit is used for selecting a monitoring end according to the prediction parameters and acquiring the power utilization parameters based on the monitoring end.
10. The system according to claim 9, wherein the fluctuation map creation module comprises:
a parameter conversion unit for converting the electricity consumption parameter into a hopping waveform based on the time information; the hopping waveform is a function of an electricity usage parameter with respect to time;
the waveform processing unit is used for carrying out Fourier transform on the hopping waveform to obtain a waveform function and a characteristic matrix thereof; the number of terms of the waveform function is a preset value, and the characteristic matrix is a matrix formed by trigonometric function characteristic matrixes with different numbers of terms; the trigonometric function is characterized by amplitude, frequency and phase;
the longitudinal coordinate segmentation unit is used for determining a longitudinal coordinate segmentation result of the node according to the characteristic matrix; the ordinate segmentation result comprises units and spans;
and the curve inserting unit is used for inserting the power curve at the corresponding ordinate section according to the waveform function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310270325.0A CN115982577B (en) | 2023-03-20 | 2023-03-20 | Intelligent electricity utilization real-time monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310270325.0A CN115982577B (en) | 2023-03-20 | 2023-03-20 | Intelligent electricity utilization real-time monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115982577A true CN115982577A (en) | 2023-04-18 |
| CN115982577B CN115982577B (en) | 2023-09-08 |
Family
ID=85958582
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310270325.0A Active CN115982577B (en) | 2023-03-20 | 2023-03-20 | Intelligent electricity utilization real-time monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115982577B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117630543A (en) * | 2023-11-30 | 2024-03-01 | 国网湖北省电力有限公司超高压公司 | Transformer fault state supervision method and system based on Internet of things data |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909487A (en) * | 2017-01-18 | 2017-06-30 | 北京盛世全景科技股份有限公司 | It is applied to the method for early warning and device of information system |
| CN112633316A (en) * | 2020-10-22 | 2021-04-09 | 国网山东省电力公司潍坊供电公司 | Load prediction method and device based on boundary estimation theory |
| KR102268274B1 (en) * | 2020-12-04 | 2021-06-23 | 아신씨엔티 주식회사 | Sensor node and system for monitoring the conditon of facilities |
| WO2021179572A1 (en) * | 2020-03-12 | 2021-09-16 | 平安科技（深圳）有限公司 | Operation and maintenance system anomaly index detection model optimization method and apparatus, and storage medium |
| CN113642858A (en) * | 2021-07-29 | 2021-11-12 | 河南北斗电气设备有限公司 | Intelligent power utilization management system based on cloud platform database |
| CN114519651A (en) * | 2022-01-25 | 2022-05-20 | 国网黑龙江省电力有限公司 | Intelligent power distribution method based on electric power big data |
| CN114548832A (en) * | 2022-04-22 | 2022-05-27 | 北京千尧新能源科技开发有限公司 | Wind power equipment state evaluation method and system based on big data |
| CN114564683A (en) * | 2022-02-25 | 2022-05-31 | 中用科技有限公司 | Garden intelligent power consumption monitoring system |
| CN114660384A (en) * | 2022-03-15 | 2022-06-24 | 国网浙江省电力有限公司杭州供电公司 | Anti-electricity-stealing monitoring system and method of electricity utilization information acquisition system |
| CN114819665A (en) * | 2022-05-05 | 2022-07-29 | 国网江苏省电力有限公司南通供电分公司 | Distributed energy management-based abnormity early warning method and system |
| CN114862293A (en) * | 2022-07-09 | 2022-08-05 | 山东恒迈信息科技有限公司 | Intelligent electricity safety management method and system |
| CN115206077A (en) * | 2022-09-14 | 2022-10-18 | 江苏南瓯物联网科技有限公司 | Intelligent air switch big data monitoring and early warning system and method |
| CN115291046A (en) * | 2022-09-30 | 2022-11-04 | 南京鼎研电力科技有限公司 | Power grid power distribution abnormity identification method based on power grid operation big data |
| CN115459434A (en) * | 2022-08-12 | 2022-12-09 | 北京圣福伦电气技术有限公司 | Intelligent electricity consumption monitoring method and system for industrial enterprise |
| CN115549078A (en) * | 2022-10-12 | 2022-12-30 | 国网山西省电力公司 | Power grid integration planning method based on digital twinning |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
| CN115689016A (en) * | 2022-10-31 | 2023-02-03 | 国网上海市电力公司 | Power consumption prediction method and device for business expansion new installation customer |
| CN115684908A (en) * | 2022-10-28 | 2023-02-03 | 云南电网有限责任公司文山供电局 | State monitoring method for power GIS equipment, storage medium and electronic device |
-
2023
- 2023-03-20 CN CN202310270325.0A patent/CN115982577B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909487A (en) * | 2017-01-18 | 2017-06-30 | 北京盛世全景科技股份有限公司 | It is applied to the method for early warning and device of information system |
| WO2021179572A1 (en) * | 2020-03-12 | 2021-09-16 | 平安科技（深圳）有限公司 | Operation and maintenance system anomaly index detection model optimization method and apparatus, and storage medium |
| CN112633316A (en) * | 2020-10-22 | 2021-04-09 | 国网山东省电力公司潍坊供电公司 | Load prediction method and device based on boundary estimation theory |
| KR102268274B1 (en) * | 2020-12-04 | 2021-06-23 | 아신씨엔티 주식회사 | Sensor node and system for monitoring the conditon of facilities |
| CN113642858A (en) * | 2021-07-29 | 2021-11-12 | 河南北斗电气设备有限公司 | Intelligent power utilization management system based on cloud platform database |
| CN114519651A (en) * | 2022-01-25 | 2022-05-20 | 国网黑龙江省电力有限公司 | Intelligent power distribution method based on electric power big data |
| CN114564683A (en) * | 2022-02-25 | 2022-05-31 | 中用科技有限公司 | Garden intelligent power consumption monitoring system |
| CN114660384A (en) * | 2022-03-15 | 2022-06-24 | 国网浙江省电力有限公司杭州供电公司 | Anti-electricity-stealing monitoring system and method of electricity utilization information acquisition system |
| CN114548832A (en) * | 2022-04-22 | 2022-05-27 | 北京千尧新能源科技开发有限公司 | Wind power equipment state evaluation method and system based on big data |
| CN114819665A (en) * | 2022-05-05 | 2022-07-29 | 国网江苏省电力有限公司南通供电分公司 | Distributed energy management-based abnormity early warning method and system |
| CN114862293A (en) * | 2022-07-09 | 2022-08-05 | 山东恒迈信息科技有限公司 | Intelligent electricity safety management method and system |
| CN115459434A (en) * | 2022-08-12 | 2022-12-09 | 北京圣福伦电气技术有限公司 | Intelligent electricity consumption monitoring method and system for industrial enterprise |
| CN115206077A (en) * | 2022-09-14 | 2022-10-18 | 江苏南瓯物联网科技有限公司 | Intelligent air switch big data monitoring and early warning system and method |
| CN115291046A (en) * | 2022-09-30 | 2022-11-04 | 南京鼎研电力科技有限公司 | Power grid power distribution abnormity identification method based on power grid operation big data |
| CN115549078A (en) * | 2022-10-12 | 2022-12-30 | 国网山西省电力公司 | Power grid integration planning method based on digital twinning |
| CN115684908A (en) * | 2022-10-28 | 2023-02-03 | 云南电网有限责任公司文山供电局 | State monitoring method for power GIS equipment, storage medium and electronic device |
| CN115689016A (en) * | 2022-10-31 | 2023-02-03 | 国网上海市电力公司 | Power consumption prediction method and device for business expansion new installation customer |
| CN115549313A (en) * | 2022-11-09 | 2022-12-30 | 国网江苏省电力有限公司徐州供电分公司 | Electricity utilization monitoring method and system based on artificial intelligence |
Non-Patent Citations (4)
| Title |
|---|
| JIAWEI LI等: "On-line Monitoring System of Customer Electricity Safety Based on Power Grid Enterprise", 《2022 4TH INTERNATIONAL ACADEMIC EXCHANGE CONFERENCE ON SCIENCE AND TECHNOLOGY INNOVATION (IAECST)》, pages 623 - 626 * |
| LIXIA WANG等: "Real Time Monitoring Method of Power Grid User Side Energy Consumption Data Based on Internet of Things", 《2021 IEEE 21ST INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT)》, pages 759 - 764 * |
| 奚伟钦: "计及分布式光伏发电的电力负荷预测研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, vol. 2023, no. 1, pages 042 - 1737 * |
| 王志男: "基于可信计算的用电信息采集终端信息安全研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, vol. 2019, no. 1, pages 138 - 444 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117630543A (en) * | 2023-11-30 | 2024-03-01 | 国网湖北省电力有限公司超高压公司 | Transformer fault state supervision method and system based on Internet of things data |
| CN117630543B (en) * | 2023-11-30 | 2024-07-30 | 国网湖北省电力有限公司超高压公司 | Transformer fault state supervision method and system based on Internet of things data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115982577B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114298863B (en) | Data acquisition method and system of intelligent meter reading terminal | |
| CN111368890A (en) | Fault detection method and device and information physical fusion system | |
| CN115982577B (en) | Intelligent electricity utilization real-time monitoring method and system | |
| CN116660759B (en) | Battery life prediction method and device based on BMS battery management system | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN117559443A (en) | Ordered power utilization control method for large industrial user cluster under peak load | |
| CN115758151A (en) | Combined diagnosis model establishing method and photovoltaic module fault diagnosis method | |
| CN110956281A (en) | Power equipment abnormity detection alarm system based on Log analysis | |
| CN116611589B (en) | Power failure window period prediction method, system, equipment and medium for main network power transmission and transformation equipment | |
| CN116166655B (en) | Big data cleaning system | |
| CN112215482A (en) | Method and device for identifying user variable relationship | |
| CN115130671B (en) | Training method of equipment comprehensive efficiency prediction model, storage medium and electronic equipment | |
| CN116245212A (en) | PCA-LSTM-based power data anomaly detection and prediction method and system | |
| CN116293454A (en) | Management system, method and medium based on steam pipe network dynamic balance | |
| CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
| CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
| CN112991093B (en) | Electric larceny detection method and system based on edge calculation | |
| CN118213997B (en) | Urban power grid load prediction method based on AHP-gray fuzzy algorithm | |
| CN117575308B (en) | Risk assessment method, device and equipment for distributed power distribution network and storage medium | |
| CN118627920A (en) | Pollution source out-of-limit emission research and judgment method based on pseudo tag semi-supervised learning | |
| Jianquan et al. | Prediction Method of Line Loss Data Based on Hidden Markov Model | |
| CN114676597A (en) | Power distribution network theoretical line loss calculation method based on typical equivalent load distribution curve | |
| Ji et al. | Data Multiple Interpolation Technique Based on Convolutional Neural Networks | |
| CN112966868A (en) | Building load day-ahead prediction method and system |
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 |