CN117371996B - Electric power communication analysis method based on big data - Google Patents
Electric power communication analysis method based on big data Download PDFInfo
- Publication number
- CN117371996B CN117371996B CN202311657441.4A CN202311657441A CN117371996B CN 117371996 B CN117371996 B CN 117371996B CN 202311657441 A CN202311657441 A CN 202311657441A CN 117371996 B CN117371996 B CN 117371996B
- Authority
- CN
- China
- Prior art keywords
- power communication
- information
- communication device
- working environment
- historical
- 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.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 256
- 238000004458 analytical method Methods 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 83
- 238000012423 maintenance Methods 0.000 claims abstract description 60
- 230000002159 abnormal effect Effects 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims description 97
- 238000012549 training Methods 0.000 claims description 37
- 238000002372 labelling Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 12
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 11
- 230000005236 sound signal Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 208000032767 Device breakage Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000010301 surface-oxidation reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention provides a power communication analysis method based on big data, which comprises the following steps: acquiring actual operation data of each power communication device at the current moment, a working environment number image of each power communication device at the current moment and historical maintenance information of each power communication device in the power communication system; performing anomaly detection on the actual operation data at the current moment aiming at each electric power communication device to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal; and calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device. According to the method, after the abnormality is detected, the communication capacity of the whole power system is further calculated directly according to the data obtained from the image, and by the method, the workload of maintenance personnel can be reduced, and the efficiency is improved.
Description
Technical Field
The invention relates to the technical field of power communication, in particular to a power communication analysis method based on big data.
Background
In daily life, the power system has a quite important function for guaranteeing daily life, so that the normal communication of the whole power system is quite necessary. In the power system, some power communication equipment is installed at a far distance or a far distance, and some power communication equipment is abnormal at a point, but the whole power system can still normally operate, but if the whole power system is detected and maintained on site at a point of abnormality, the workload of maintenance personnel can be greatly increased, so that a method capable of effectively monitoring the whole power system and reducing the workload of the maintenance personnel is needed.
Disclosure of Invention
The invention aims to provide an electric power communication analysis method based on big data so as to improve the problems.
In order to achieve the above purpose, the embodiment of the present application provides the following technical solutions:
in one aspect, an embodiment of the present application provides a method for analyzing electric power communication based on big data, where the method includes:
acquiring actual operation data of each power communication device at the current moment, a working environment number image of each power communication device at the current moment and historical maintenance information of each power communication device in the power communication system;
Performing anomaly detection on the actual operation data at the current moment aiming at each electric power communication device to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal;
and calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device.
Optionally, performing anomaly detection on the operation data at the current moment to obtain a detection result, including:
acquiring historical data, wherein the historical data comprises actual operation data of the power communication equipment in a preset time period, and the expiration time of the preset time period is the current time; each moment in a preset time period is recorded as a first moment;
calculating the predicted operation data corresponding to each first moment based on the historical data; and carrying out difference value calculation on the actual operation data corresponding to each first moment and the preset operation data, taking an absolute value of a difference value calculation result to obtain a first calculation result corresponding to each first moment, and carrying out anomaly detection according to the first calculation result to obtain the detection result.
Optionally, performing anomaly detection according to the first calculation result to obtain the detection result, including:
determining all clustering centers corresponding to the first calculation results according to the first calculation results; respectively carrying out mean value and variance calculation on all the first calculation results in sequence, and respectively obtaining a second calculation result and a third calculation result in sequence;
clustering all the first calculation results according to a K-means algorithm and a clustering center to obtain clustering results; performing product calculation on the third calculation result and a preset first numerical value to obtain a fourth calculation result, and performing summation calculation on the fourth calculation result and the second calculation result to obtain a fifth calculation result; and obtaining the detection result according to the clustering result and the fifth calculation result.
Optionally, obtaining the detection result according to the clustering result and the fifth calculation result includes:
judging whether a first calculation result corresponding to the current moment does not belong to any cluster, if not, judging that the actual operation data at the current moment is abnormal, otherwise, judging that the actual operation data at the current moment is not abnormal, and obtaining a first detection result; summing the predicted operation data corresponding to each first time with the fifth calculation result to obtain an upper limit value corresponding to each first time, calculating a difference value between the predicted operation data corresponding to each first time and the fifth calculation result to obtain a lower limit value corresponding to each first time, and forming a numerical range according to the upper limit value and the upper limit value; if the actual running data at the current moment is out of the numerical range, judging that the actual running data at the current moment is abnormal, otherwise, judging that the actual running data at the current moment is not abnormal, and obtaining a second detection result;
And analyzing the first detection result and the second detection result, if the first detection result and the second detection result are not abnormal, the final detection result is not abnormal, otherwise, the final detection result is abnormal.
Optionally, determining an influence factor corresponding to the power communication device according to the working environment number image of the power communication device includes:
acquiring working environment images of a plurality of historical power communication devices, and calculating characteristic information of the working environment images of each historical power communication device, wherein the characteristic information comprises length and width information; clustering all the working environment images of the historical power communication equipment according to the characteristic information to obtain a plurality of clusters;
and taking the length and width information of the clustering center of each cluster as target length and width information, adjusting working environment images of a plurality of historical power communication equipment based on the target length and width information to obtain an adjusted image, obtaining an influence factor identification model based on the adjusted image and a neural network model, and inputting the working environment number image of the power communication equipment into the influence factor identification model to obtain an influence factor corresponding to the power communication equipment.
Optionally, adjusting the working environment images of the plurality of historical power communication devices based on the target length and width information to obtain an adjusted image, and obtaining the influence factor recognition model based on the adjusted image and the neural network model, including:
adjusting the working environment image of each historical power communication device corresponding to each cluster, adjusting the length and width information of the working environment image of each historical power communication device into target length and width information corresponding to each cluster, and obtaining a target image after each cluster is adjusted; extracting feature information corresponding to each target image, and clustering the target images according to the feature information to obtain a plurality of clustering results; counting the number of target images contained in each clustering result, taking each target image contained in the clustering result as a first training sample when the number of target images exceeds a preset threshold value, otherwise, taking each target image as a second training sample, and giving weight information to the first training sample and the second training sample, wherein the weight information of the first training sample is larger than the weight information of the second training sample;
after the weight information is given, labeling each first training sample and each second training sample, wherein the labeling information comprises influence factors; training the neural network model after labeling to obtain an influence factor identification model.
Optionally, calculating the current communication capability of the power communication system according to the influencing factors and the historical maintenance information of each power communication device includes:
acquiring environmental temperature information at the current moment, taking the environmental temperature information at the current moment as an influence factor, acquiring weight information of each influence factor, simultaneously assigning a value to each influence factor, and carrying out weighted summation based on the weight information after assigning the value to obtain an influence value; the power communication equipment maintenance information comprises power communication equipment maintenance probability, and the power communication equipment maintenance grade score is determined according to the power communication equipment maintenance probability; multiplying the maintenance information of the power communication equipment with the maintenance grade score of the power communication equipment and the influence value to obtain a sixth calculation result;
and adding the sixth calculation result corresponding to the power communication equipment with abnormal detection result in the power communication system to obtain a seventh calculation result, and subtracting the seventh calculation result from a preset value to obtain the current communication capability of the power communication system.
In a second aspect, an embodiment of the present application provides an electrical power communication analysis device based on big data, where the device includes an acquisition module, a detection module, and a calculation module.
The acquisition module is used for acquiring actual operation data of each electric power communication device at the current moment, a working environment number image of each electric power communication device at the current moment and historical maintenance information of each electric power communication device in the electric power communication system;
the detection module is used for carrying out anomaly detection on the actual operation data at the current moment aiming at each electric power communication device to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal;
and the calculation module is used for calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device.
In a third aspect, embodiments of the present application provide a big data based power communication analysis device, the device including a memory and a processor. The memory is used for storing a computer program; the processor is used for realizing the steps of the power communication analysis method based on big data when executing the computer program.
In a fourth aspect, embodiments of the present application provide a storage medium having a computer program stored thereon, the computer program implementing the steps of the above-described big data based power communication analysis method when executed by a processor.
The beneficial effects of the invention are as follows:
1. in the invention, the abnormality detection is carried out according to the actual operation data at the current moment, so that the result of whether the current operation is abnormal or not can be judged, then if the result is abnormal, the image of the current power communication equipment is analyzed, some influence factors influencing the abnormality are obtained from the image, then the power equipment is subjected to calculation of one communication capacity according to a preset calculation method, the current communication capacity of the power system is obtained based on the communication capacities of all abnormal power equipment, at the moment, the next operation can be carried out according to the current communication capacity of the power system, for example, when the current communication capacity of the power system is smaller than a preset threshold value, warning information can be sent to remind that the current communication capacity of the power equipment cannot meet the normal communication, maintenance is needed urgently, and the like.
2. In the invention, considering that some equipment is installed far away or far away, if the equipment operation data has a little abnormality, maintenance personnel are required to check maintenance, and the workload of the maintenance personnel is greatly increased. According to the method, after the abnormality is detected, the communication capacity of the whole power system is further calculated directly according to the data obtained from the image, and by the method, the workload of maintenance personnel can be reduced, and the efficiency is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a power communication analysis method based on big data according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a power communication analysis device based on big data according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electric power communication analysis device based on big data according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals or letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1
As shown in fig. 1, the present embodiment provides a power communication analysis method based on big data, which includes step S1, step S2 and step S3.
Step S1, acquiring actual operation data of each electric power communication device at the current moment, a working environment number image of each electric power communication device at the current moment and historical maintenance information of each electric power communication device in an electric power communication system;
in this step, the power communication system includes a plurality of power devices; the operation data includes temperature, current information, voltage information, etc., and the operation data in this step may be temperature; the image of the power communication equipment is also required to be included in the working environment number image, the size of the image is not specified, only the image of the power communication equipment and the surrounding environment image are included, the historical maintenance information is the maintenance probability before the current moment, and the probability of occurrence of faults can be understood; the data in the step are all uploaded by the user;
Step S2, aiming at each electric power communication device, carrying out anomaly detection on the actual operation data at the current moment to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal;
in the step, abnormality detection is carried out according to actual operation data at the current moment, so that whether the current operation is abnormal or not can be judged, then if the current operation is abnormal, influence factors corresponding to the power communication equipment can be determined, and then the communication capacity of the abnormal power communication equipment is calculated by integrating the influence factors corresponding to the power communication equipment; the specific implementation steps of the step comprise a step S21 and a step S22;
step S21, acquiring historical data, wherein the historical data comprises actual operation data of the power communication equipment in a preset time period, and the expiration time of the preset time period is the current time; each moment in a preset time period is recorded as a first moment;
in this step, the cut-off time of the preset time period is the current time, that is, the current time is included; meanwhile, in this step, it can be understood that an actual operation data, such as a temperature or other operation data, is collected;
Step S22, calculating the predicted operation data corresponding to each first moment based on the historical data; and carrying out difference value calculation on the actual operation data corresponding to each first moment and the preset operation data, taking an absolute value of a difference value calculation result to obtain a first calculation result corresponding to each first moment, and carrying out anomaly detection according to the first calculation result to obtain the detection result.
In this step, the historical data may be fitted by using an AR model or an ARIMA model, etc., to obtain predicted operation data corresponding to each first time. In addition to the method, other prediction methods can be adopted to obtain the predicted operation data corresponding to each first moment based on the historical data; in this step, abnormality detection is performed according to the first calculation result, and the specific implementation step for obtaining the detection result includes step S221 and step S222;
step S221, determining all clustering centers corresponding to the first calculation results according to the first calculation results; respectively carrying out mean value and variance calculation on all the first calculation results in sequence, and respectively obtaining a second calculation result and a third calculation result in sequence;
step S222, clustering all the first calculation results according to a K-means algorithm and a clustering center to obtain clustering results; performing product calculation on the third calculation result and a preset first numerical value to obtain a fourth calculation result, and performing summation calculation on the fourth calculation result and the second calculation result to obtain a fifth calculation result; and obtaining the detection result according to the clustering result and the fifth calculation result.
In this step, the preset value may be regarded as an adjustment parameter corresponding to the variance, and the specific implementation step for adjusting the variance to obtain the detection result according to the clustering result and the fifth calculation result includes step S2221 and step S2222;
step S2221, determining whether the first calculation result corresponding to the current moment does not belong to any cluster, if not, determining that the actual running data at the current moment is abnormal, otherwise, not abnormal, and obtaining a first detection result; summing the predicted operation data corresponding to each first time with the fifth calculation result to obtain an upper limit value corresponding to each first time, calculating a difference value between the predicted operation data corresponding to each first time and the fifth calculation result to obtain a lower limit value corresponding to each first time, and forming a numerical range according to the upper limit value and the upper limit value; if the actual running data at the current moment is out of the numerical range, judging that the actual running data at the current moment is abnormal, otherwise, judging that the actual running data at the current moment is not abnormal, and obtaining a second detection result;
in this step, the fifth calculation result can be regarded as an adjustment amount of the predicted operation data;
Step S2222, analyzing the first detection result and the second detection result, if the first detection result and the second detection result are both abnormal, the final detection result is not abnormal, otherwise the final detection result is abnormal.
In the steps, two methods are adopted to comprehensively judge whether the current operation data is abnormal, and compared with a single abnormality detection method, the comprehensive detection method in the steps can improve the detection accuracy;
in step S2, when the detection result is abnormal, determining, according to the working environment number image of the power communication device, a specific implementation step of the influence factor corresponding to the power communication device includes step S23 and step S24;
in this step, after determining that the power equipment is abnormal, the communication capability of the power equipment needs to be calculated, and the communication capability is calculated, which is calculated by the influence factor in this embodiment;
step S23, acquiring working environment images of a plurality of historical power communication devices, and calculating characteristic information of the working environment images of each historical power communication device, wherein the characteristic information comprises length and width information; clustering all the working environment images of the historical power communication equipment according to the characteristic information to obtain a plurality of clusters;
In this step, the feature information may also be understood as a size feature, that is, a size feature of an image generated by a height value and a width value of the image, the size feature being expressed as a two-dimensional vector; after clustering is carried out according to the characteristic information, images in the same cluster are similar in size;
and S24, taking the length and width information of the clustering center of each cluster as target length and width information, adjusting the working environment images of a plurality of historical power communication devices based on the target length and width information to obtain adjusted images, obtaining an influence factor identification model based on the adjusted images and a neural network model, and inputting the working environment number images of the power communication devices into the influence factor identification model to obtain influence factors corresponding to the power communication devices.
In the step, the working environment images of a plurality of historical power communication devices are adjusted based on the target length and width information to obtain adjusted images, and the specific implementation steps for obtaining the influence factor identification model based on the adjusted images and the neural network model comprise the steps S241 and S242;
step S241, adjusting the working environment image of each historical power communication device corresponding to each cluster, and adjusting the length and width information of the working environment image of each historical power communication device to be the target length and width information corresponding to each cluster, wherein each cluster is adjusted to obtain a target image; extracting feature information corresponding to each target image, and clustering the target images according to the feature information to obtain a plurality of clustering results; counting the number of target images contained in each clustering result, taking each target image contained in the clustering result as a first training sample when the number of target images exceeds a preset threshold value, otherwise, taking each target image as a second training sample, and giving weight information to the first training sample and the second training sample, wherein the weight information of the first training sample is larger than the weight information of the second training sample;
In the step, one cluster corresponds to one target length and width information, the sizes of images contained in the cluster are all adjusted to be the target length and width information, and after all the images are adjusted, a target image is obtained;
in the step, the fact that the installation positions of all the electric power communication equipment are different is considered, therefore, the working environment images of some electric power communication equipment are easy to collect, some electric power communication equipment are difficult to collect, the size and other relevant information of the finally collected images are possibly inconsistent, the step is based on the characteristic information to carry out clustering treatment, and then the size adjustment is carried out on all the images, so that the method can meet the requirement of sample size consistency in the subsequent training process, and can avoid serious deformation of the images to a certain extent, further is beneficial to improving the accuracy and the precision of the finally trained model;
meanwhile, in the step, the characteristic information corresponding to each target image can be extracted by adopting a conventional characteristic extraction method, the target images are clustered according to the characteristic information to obtain a plurality of clustering results, when the target images contained in the clustering results are more, the proportion of the images in the whole sample is considered to be larger, then the target images in the clustering results are used as important samples, and the given weight information is larger;
Step S242, after the weight information is given, labeling each of the first training sample and the second training sample, where the labeling information includes influence factors; training the neural network model after labeling to obtain an influence factor identification model.
In this step, the first influencing factor may be understood as a factor that can be obtained from an image and that can influence the operation data of the power communication device, and in this step, as a influencing factor that can be obtained from an image and that can influence the temperature of the power communication device, the first influencing factor may include, for example, weather information (whether it rains, snows), illumination intensity information, device breakage information (whether the cable is broken), joint information (joint looseness), surface information (surface oxidation), corrosion information (whether it is corroded), and the like;
and S3, calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device.
The specific implementation steps of the step comprise a step S31 and a step S32;
step S31, acquiring environmental temperature information at the current moment, taking the environmental temperature information at the current moment as an influence factor, acquiring weight information of each influence factor, simultaneously assigning a value to each influence factor, and carrying out weighted summation based on the weight information after assigning the value to obtain an influence value; the power communication equipment maintenance information comprises power communication equipment maintenance probability, and the power communication equipment maintenance grade score is determined according to the power communication equipment maintenance probability; multiplying the maintenance information of the power communication equipment with the maintenance grade score of the power communication equipment and the influence value to obtain a sixth calculation result;
The environmental temperature information at the current moment is the weather temperature at the current moment; a table corresponding to the maintenance probability of the power communication equipment and the maintenance grade of the power communication equipment one by one can be constructed in advance, and the maintenance grade of the power communication equipment can be obtained according to the table and the maintenance probability of the power communication equipment;
and S32, adding sixth calculation results corresponding to the power communication equipment with abnormal detection results in the power communication system to obtain a seventh calculation result, and subtracting the seventh calculation result from a preset value to obtain the current communication capacity of the power communication system.
In this step, the preset value may be 1 or 2, and may be set according to the user's requirement. The communication capability in this step can be understood as the normal degree of the power communication equipment and also as the health degree;
in an embodiment, anomaly detection is performed according to actual operation data at a current moment, so that whether a current operation is abnormal or not can be judged, then if the current operation is abnormal, an image of current power communication equipment is analyzed, influence factors influencing the anomaly are obtained from the image, calculation of one communication capacity is performed on the power equipment according to a preset calculation method, current communication capacity of the power system is obtained based on all communication capacities of the abnormal power equipment, at the moment, next operation can be performed according to the current communication capacity of the power system, for example, when the current communication capacity of the power system is smaller than a preset threshold value, warning information can be sent to remind that the current communication capacity of the power equipment cannot meet normal communication, maintenance is needed urgently, and the like.
In this embodiment, considering that some devices are installed at remote locations or remote locations, if there is a little abnormality in the operation data of the devices, maintenance personnel is required to check the maintenance, and thus the workload of the maintenance personnel is greatly increased. In this embodiment, after the abnormality is detected, the communication capability of the whole power system is further calculated directly according to the data obtained from the image, and by this method, the workload of maintenance personnel can be reduced, and the efficiency can be improved.
Example 2
As shown in fig. 2, the present embodiment provides an electric power communication analysis device based on big data, which includes an acquisition module 701, a detection module 702, and a calculation module 703.
The acquiring module 701 is configured to acquire actual operation data of each electric power communication device at a current time, a working environment number image of each electric power communication device at the current time, and historical maintenance information of each electric power communication device in the electric power communication system;
the detection module 702 is configured to perform anomaly detection on the actual operation data at the current moment for each electric power communication device, obtain a detection result, and determine an influencing factor corresponding to the electric power communication device according to a working environment number image of the electric power communication device when the detection result is abnormal;
And a calculating module 703, configured to calculate the current communication capability of the power communication system according to the influencing factors and the historical maintenance information of each power communication device.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
Example 3
Corresponding to the above method embodiments, the embodiments of the present disclosure further provide a big data based power communication analysis device, and the big data based power communication analysis device described below and the big data based power communication analysis method described above may be referred to correspondingly with each other.
Fig. 3 is a block diagram illustrating a big data based power communication analysis device 800, according to an exemplary embodiment. As shown in fig. 3, the big data based power communication analysis device 800 may include: a processor 801, a memory 802. The big data based power communication analysis device 800 may also include one or more of a multimedia component 803, an I/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the big data based power communication analysis device 800 to perform all or part of the steps of the big data based power communication analysis method. The memory 802 is used to store various types of data to support operation at the big data based power communication analysis device 800, which may include, for example, instructions for any application or method operating on the big data based power communication analysis device 800, as well as application related data, such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM for short), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM for short), programmable Read-Only Memory (Programmable Read-Only Memory, PROM for short), read-Only Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the big data based power communication analysis device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, near field communication (Near FieldCommunication, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-Fi module, bluetooth module, NFC module.
In an exemplary embodiment, the big data based power communication analysis device 800 may be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, abbreviated as ASIC), digital signal processors (DigitalSignal Processor, abbreviated as DSP), digital signal processing devices (Digital Signal Processing Device, abbreviated as DSPD), programmable logic devices (Programmable Logic Device, abbreviated as PLD), field programmable gate arrays (Field Programmable Gate Array, abbreviated as FPGA), controllers, microcontrollers, microprocessors, or other electronic components for performing the big data based power communication analysis methods described above.
In another exemplary embodiment, a computer storage medium is also provided that includes program instructions that, when executed by a processor, implement the steps of the big data based power communication analysis method described above. For example, the computer storage medium may be the memory 802 including the program instructions described above, which are executable by the processor 801 of the big data based power communication analysis device 800 to perform the big data based power communication analysis method described above.
Example 4
Corresponding to the above method embodiments, the present disclosure further provides a storage medium, and a storage medium described below and the above-described big data-based power communication analysis method may be referred to correspondingly to each other.
A storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the big data based power communication analysis method of the above method embodiments.
The storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, etc. that can store various program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The power communication analysis method based on big data is characterized by comprising the following steps of:
acquiring actual operation data of each power communication device at the current moment, a working environment number image of each power communication device at the current moment and historical maintenance information of each power communication device in the power communication system;
Performing anomaly detection on the actual operation data at the current moment aiming at each electric power communication device to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal;
calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device;
determining an influence factor corresponding to the power communication equipment according to the working environment number image of the power communication equipment, wherein the influence factor comprises the following components:
acquiring working environment images of a plurality of historical power communication devices, and calculating characteristic information of the working environment images of each historical power communication device, wherein the characteristic information comprises length and width information; clustering all the working environment images of the historical power communication equipment according to the characteristic information to obtain a plurality of clusters;
the method comprises the steps of taking length and width information of a clustering center of each cluster as target length and width information, adjusting working environment images of a plurality of historical power communication devices based on the target length and width information to obtain adjusted images, obtaining an influence factor identification model based on the adjusted images and a neural network model, and inputting working environment number images of the power communication devices into the influence factor identification model to obtain influence factors corresponding to the power communication devices;
Adjusting the working environment images of the plurality of historical power communication devices based on the target length and width information to obtain an adjusted image, and obtaining an influence factor identification model based on the adjusted image and a neural network model, wherein the method comprises the following steps:
adjusting the working environment image of each historical power communication device corresponding to each cluster, adjusting the length and width information of the working environment image of each historical power communication device into target length and width information corresponding to each cluster, and obtaining a target image after each cluster is adjusted; extracting feature information corresponding to each target image, and clustering the target images according to the feature information to obtain a plurality of clustering results; counting the number of target images contained in each clustering result, taking each target image contained in the clustering result as a first training sample when the number of target images exceeds a preset threshold value, otherwise, taking each target image as a second training sample, and giving weight information to the first training sample and the second training sample, wherein the weight information of the first training sample is larger than the weight information of the second training sample;
after the weight information is given, labeling each first training sample and each second training sample, wherein the labeling information comprises influence factors; training the neural network model after labeling to obtain an influence factor identification model;
Calculating the current communication capacity of the power communication system according to the influencing factors and the historical maintenance information of each power communication device, wherein the method comprises the following steps:
acquiring environmental temperature information at the current moment, taking the environmental temperature information at the current moment as an influence factor, acquiring weight information of each influence factor, simultaneously assigning a value to each influence factor, and carrying out weighted summation based on the weight information after assigning the value to obtain an influence value; the power communication equipment maintenance information comprises power communication equipment maintenance probability, and the power communication equipment maintenance grade score is determined according to the power communication equipment maintenance probability; multiplying the maintenance information of the power communication equipment with the maintenance grade score of the power communication equipment and the influence value to obtain a sixth calculation result;
and adding the sixth calculation result corresponding to the power communication equipment with abnormal detection result in the power communication system to obtain a seventh calculation result, and subtracting the seventh calculation result from a preset value to obtain the current communication capability of the power communication system.
2. The method for analyzing electric power communication based on big data according to claim 1, wherein the step of performing anomaly detection on the operation data at the current time to obtain a detection result comprises:
Acquiring historical data, wherein the historical data comprises actual operation data of the power communication equipment in a preset time period, and the expiration time of the preset time period is the current time; each moment in a preset time period is recorded as a first moment;
calculating the predicted operation data corresponding to each first moment based on the historical data; and carrying out difference value calculation on the actual operation data corresponding to each first moment and the preset operation data, taking an absolute value of a difference value calculation result to obtain a first calculation result corresponding to each first moment, and carrying out anomaly detection according to the first calculation result to obtain the detection result.
3. The method of claim 2, wherein performing anomaly detection according to the first calculation result to obtain the detection result comprises:
determining all clustering centers corresponding to the first calculation results according to the first calculation results; respectively carrying out mean value and variance calculation on all the first calculation results in sequence, and respectively obtaining a second calculation result and a third calculation result in sequence;
clustering all the first calculation results according to a K-means algorithm and a clustering center to obtain clustering results; performing product calculation on the third calculation result and a preset first numerical value to obtain a fourth calculation result, and performing summation calculation on the fourth calculation result and the second calculation result to obtain a fifth calculation result; and obtaining the detection result according to the clustering result and the fifth calculation result.
4. The big data based power communication analysis method of claim 3, wherein obtaining the detection result according to the clustering result and the fifth calculation result comprises:
judging whether a first calculation result corresponding to the current moment does not belong to any cluster, if not, judging that the actual operation data at the current moment is abnormal, otherwise, judging that the actual operation data at the current moment is not abnormal, and obtaining a first detection result; summing the predicted operation data corresponding to each first time with the fifth calculation result to obtain an upper limit value corresponding to each first time, calculating a difference value between the predicted operation data corresponding to each first time and the fifth calculation result to obtain a lower limit value corresponding to each first time, and forming a numerical range according to the upper limit value and the upper limit value; if the actual running data at the current moment is out of the numerical range, judging that the actual running data at the current moment is abnormal, otherwise, judging that the actual running data at the current moment is not abnormal, and obtaining a second detection result;
and analyzing the first detection result and the second detection result, if the first detection result and the second detection result are not abnormal, the final detection result is not abnormal, otherwise, the final detection result is abnormal.
5. An electrical communication analysis device based on big data, comprising:
the acquisition module is used for acquiring actual operation data of each electric power communication device at the current moment, a working environment number image of each electric power communication device at the current moment and historical maintenance information of each electric power communication device in the electric power communication system;
the detection module is used for carrying out anomaly detection on the actual operation data at the current moment aiming at each electric power communication device to obtain a detection result, and determining an influence factor corresponding to the electric power communication device according to the working environment number image of the electric power communication device when the detection result is abnormal;
the calculation module is used for calculating the current communication capacity of the power communication system according to the influence factors and the historical maintenance information of each power communication device;
determining an influence factor corresponding to the power communication equipment according to the working environment number image of the power communication equipment, wherein the influence factor comprises the following components:
acquiring working environment images of a plurality of historical power communication devices, and calculating characteristic information of the working environment images of each historical power communication device, wherein the characteristic information comprises length and width information; clustering all the working environment images of the historical power communication equipment according to the characteristic information to obtain a plurality of clusters;
The method comprises the steps of taking length and width information of a clustering center of each cluster as target length and width information, adjusting working environment images of a plurality of historical power communication devices based on the target length and width information to obtain adjusted images, obtaining an influence factor identification model based on the adjusted images and a neural network model, and inputting working environment number images of the power communication devices into the influence factor identification model to obtain influence factors corresponding to the power communication devices;
adjusting the working environment images of the plurality of historical power communication devices based on the target length and width information to obtain an adjusted image, and obtaining an influence factor identification model based on the adjusted image and a neural network model, wherein the method comprises the following steps:
adjusting the working environment image of each historical power communication device corresponding to each cluster, adjusting the length and width information of the working environment image of each historical power communication device into target length and width information corresponding to each cluster, and obtaining a target image after each cluster is adjusted; extracting feature information corresponding to each target image, and clustering the target images according to the feature information to obtain a plurality of clustering results; counting the number of target images contained in each clustering result, taking each target image contained in the clustering result as a first training sample when the number of target images exceeds a preset threshold value, otherwise, taking each target image as a second training sample, and giving weight information to the first training sample and the second training sample, wherein the weight information of the first training sample is larger than the weight information of the second training sample;
After the weight information is given, labeling each first training sample and each second training sample, wherein the labeling information comprises influence factors; training the neural network model after labeling to obtain an influence factor identification model;
calculating the current communication capacity of the power communication system according to the influencing factors and the historical maintenance information of each power communication device, wherein the method comprises the following steps:
acquiring environmental temperature information at the current moment, taking the environmental temperature information at the current moment as an influence factor, acquiring weight information of each influence factor, simultaneously assigning a value to each influence factor, and carrying out weighted summation based on the weight information after assigning the value to obtain an influence value; the power communication equipment maintenance information comprises power communication equipment maintenance probability, and the power communication equipment maintenance grade score is determined according to the power communication equipment maintenance probability; multiplying the maintenance information of the power communication equipment with the maintenance grade score of the power communication equipment and the influence value to obtain a sixth calculation result;
and adding the sixth calculation result corresponding to the power communication equipment with abnormal detection result in the power communication system to obtain a seventh calculation result, and subtracting the seventh calculation result from a preset value to obtain the current communication capability of the power communication system.
6. An electrical communication analysis apparatus based on big data, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the big data based power communication analysis method according to any of claims 1 to 4 when executing the computer program.
7. A storage medium, characterized by:
the storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the big data based power communication analysis method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657441.4A CN117371996B (en) | 2023-12-06 | 2023-12-06 | Electric power communication analysis method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311657441.4A CN117371996B (en) | 2023-12-06 | 2023-12-06 | Electric power communication analysis method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117371996A CN117371996A (en) | 2024-01-09 |
| CN117371996B true CN117371996B (en) | 2024-03-19 |
Family
ID=89398763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311657441.4A Active CN117371996B (en) | 2023-12-06 | 2023-12-06 | Electric power communication analysis method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117371996B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010504A (en) * | 2021-03-04 | 2021-06-22 | 江苏方天电力技术有限公司 | Electric power data anomaly detection method and system based on LSTM and improved K-means algorithm |
| CN114358152A (en) * | 2021-12-21 | 2022-04-15 | 国网江苏省电力有限公司苏州供电分公司 | Intelligent power data anomaly detection method and system |
| WO2023088315A1 (en) * | 2021-11-19 | 2023-05-25 | 中国华能集团清洁能源技术研究院有限公司 | Power generation device abnormality detection method and system based on deep learning |
| CN116415931A (en) * | 2023-03-14 | 2023-07-11 | 成都电通能源有限公司 | Big data-based power equipment operation state monitoring method and system |
-
2023
- 2023-12-06 CN CN202311657441.4A patent/CN117371996B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010504A (en) * | 2021-03-04 | 2021-06-22 | 江苏方天电力技术有限公司 | Electric power data anomaly detection method and system based on LSTM and improved K-means algorithm |
| WO2023088315A1 (en) * | 2021-11-19 | 2023-05-25 | 中国华能集团清洁能源技术研究院有限公司 | Power generation device abnormality detection method and system based on deep learning |
| CN114358152A (en) * | 2021-12-21 | 2022-04-15 | 国网江苏省电力有限公司苏州供电分公司 | Intelligent power data anomaly detection method and system |
| CN116415931A (en) * | 2023-03-14 | 2023-07-11 | 成都电通能源有限公司 | Big data-based power equipment operation state monitoring method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于改进k-means的电力信息系统异常检测方法;黄林;常健;杨帆;李忆;牛新征;;深圳大学学报(理工版)(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117371996A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112188531B (en) | Abnormality detection method, abnormality detection device, electronic apparatus, and computer storage medium | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN115575584B (en) | Atmospheric environment cadmium content monitoring and early warning method and system | |
| KR102315580B1 (en) | Fire predictive analysis device and method of building | |
| CN116415931A (en) | Big data-based power equipment operation state monitoring method and system | |
| CN115311585A (en) | A discernment detecting system for electric wire netting overhead line foreign matter | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN117114425B (en) | Intelligent early warning method, system and medium for coping with emergency | |
| CN116957309B (en) | Textile scene dynamic monitoring method, system and medium | |
| CN117371996B (en) | Electric power communication analysis method based on big data | |
| CN116739317B (en) | Mining winch automatic management and dispatching platform, method, equipment and medium | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
| CN115524002B (en) | Operation state early warning method, system and storage medium of power plant rotating equipment | |
| CN116050930A (en) | Monitoring disc system, monitoring disc method, storage medium and electronic equipment | |
| CN113671287B (en) | Intelligent detection method, system and readable storage medium for power grid automation terminal | |
| CN115328986A (en) | Power plant safety early warning data analysis processing method and system | |
| CN114358165A (en) | Detection method for preventing ground fault of photovoltaic module based on multi-source data fusion | |
| CN113131476A (en) | Power load prediction method | |
| CN109257206A (en) | A kind of method of data inputting and evaluation diagnostic message feedback | |
| CN117227551B (en) | New energy equipment safety monitoring method, device, equipment and readable storage medium | |
| CN117688464B (en) | Hidden danger analysis method and system based on multi-source sensor data | |
| CN117277566B (en) | Power grid data analysis power dispatching system and method based on big data | |
| CN117197770B (en) | Inspection complete flow data supervision system and method based on Internet of things | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis |
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 |