CN114493238A - Power supply service risk prediction method, system, storage medium and computer equipment - Google Patents
Power supply service risk prediction method, system, storage medium and computer equipment Download PDFInfo
- Publication number
- CN114493238A CN114493238A CN202210075884.1A CN202210075884A CN114493238A CN 114493238 A CN114493238 A CN 114493238A CN 202210075884 A CN202210075884 A CN 202210075884A CN 114493238 A CN114493238 A CN 114493238A
- Authority
- CN
- China
- Prior art keywords
- power supply
- data
- label
- service risk
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 238000009826 distribution Methods 0.000 claims abstract description 111
- 238000012549 training Methods 0.000 claims abstract description 72
- 238000012423 maintenance Methods 0.000 claims description 30
- 230000009466 transformation Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power supply service risk prediction method, a power supply service risk prediction system, a storage medium and computer equipment, wherein the method comprises the following steps: obtaining label types corresponding to various sample data according to historical power supply data; classifying and defining each sample data in sequence according to a preset label definition rule to obtain a data set corresponding to the sample data; summarizing data sets corresponding to all sample data to obtain a training set, and constructing a multi-path decision model according to the training set; the method comprises the steps of obtaining current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output after the decision models analyze the current power supply data of the power distribution equipment, and predicting service risk levels of the power distribution equipment according to the summarized decision results. According to the power supply service risk prediction method provided by the invention, the management and control service is carried out on the power supply network in advance by predicting the fault risk of the power supply network, so that the occurrence of faults is avoided, and the reliability of power supply is ensured.
Description
Technical Field
The invention relates to the technical field of power distribution network fault prediction, in particular to a power supply service risk prediction method, a power supply service risk prediction system, a storage medium and computer equipment.
Background
With the rapid development of national economy, the electricity demand of people is changed from ' power utilization and on ' to ' power utilization, the demand and the dependency of users on electricity are stronger and stronger, and the requirements on the quality of electric energy and the reliability of power supply are higher and higher.
Due to the fact that the power distribution network structure is complex, the types of equipment are various, the difference of operating environments is large, safety risk factors are many, equipment operating data are many and are dispersed in business systems of different departments, a traditional power supply service mode is generally that corresponding service measures are provided according to customer behaviors, then an electric power company dispatches people to carry out on-site investigation and then customs a specific processing scheme, abnormal faults of power supply equipment are usually solved after the abnormal faults happen due to the service processing mode, long-time large-area power failure events easily occur, production and life are affected, and the satisfaction degree of electricity utilization of users is low.
Disclosure of Invention
Based on the above, the present invention provides a power supply service risk prediction method, system, storage medium and computer device, so as to solve the problem that a conventional service method is prone to long-term power failure abnormality due to failure abnormality processing delay.
The power supply service risk prediction method provided by the invention is applied to a power supply system, and comprises the following steps:
the method comprises the steps of obtaining historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprise a plurality of sample data, and obtaining label types corresponding to the sample data according to the historical power supply data;
calling a preset label definition rule corresponding to sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
summarizing data sets corresponding to all sample data to obtain a training set, and constructing a multi-path decision model according to the training set;
the method comprises the steps of obtaining current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output after all decision models analyze the current power supply data of the power distribution equipment, and predicting service risk levels of the power distribution equipment according to the summarized decision results.
In summary, according to the power supply service risk prediction method, the power supply data of the power supply equipment is analyzed to predict the fault risk of the power supply equipment, so that the fault hidden danger is eliminated in advance, and the power supply reliability is ensured. The method comprises the steps of collecting historical power supply data of a plurality of power distribution equipment to obtain a plurality of sample data, extracting preset label definition rules according to label types of the sample data, classifying and defining each sample data according to the label definition rules to obtain a training set for constructing a decision model, constructing a multi-path decision model according to the training set, and analyzing a decision result by monitoring the current power supply data of any power distribution equipment in the power distribution network to effectively judge the service risk level of the power distribution equipment, namely effectively monitoring and predicting the whole power distribution network to effectively avoid possible faults, ensure the reliability of power supply and improve the satisfaction degree of power consumption of a user.
Further, the sample data includes basic attribute data, historical operating state data, historical operating environment data, location feature data, and user feature data, and the step of classifying and defining each sample data in sequence according to the preset tag definition rule includes:
classifying the basic attribute data into operation age data, capacity data, power supply radius data and overhaul record data;
comparing the commissioning age data of the power distribution equipment with a preset commissioning age threshold value, and defining commissioning age labels of the corresponding power distribution equipment according to a comparison result, wherein the defined equipment result comprises a new commissioning equipment sub-label, an old equipment sub-label and a general equipment sub-label;
comparing the capacity data with a device configuration capacity threshold value so as to define a capacity label of the device corresponding to the capacity data according to a comparison result, wherein the definition result comprises a tape splicing capacity high sub-label, a tape splicing capacity low sub-label and a tape splicing capacity general sub-label;
matching the power supply radius data with a set power supply radius threshold value, and defining a power supply radius label of equipment corresponding to the power supply radius data according to a matching result, wherein the defined equipment result comprises a power supply radius qualified sub-label, a power supply radius overrun sub-label and a power supply radius serious overrun sub-label;
and judging whether the equipment corresponding to the overhaul record data has integral overhaul transformation or not according to the overhaul record data, if so, defining the corresponding power distribution equipment as an overall overhaul transformation sub-tag, and if not, defining the corresponding power distribution equipment as a partial overhaul transformation sub-tag.
Further, the step of classifying and defining each sample data in sequence according to the preset label definition rule further includes:
classifying the historical operating state data into load fault data, power failure fault data, low-voltage fault data and three-phase unbalance fault data;
and counting the load fault occurrence frequency of the corresponding power distribution equipment within a first preset time according to the load fault data, comparing the load fault occurrence frequency with a preset load fault frequency threshold value, and defining the corresponding power distribution equipment by using a load label according to a comparison result, wherein the defined equipment result comprises a normal sub-label, a heavy load sub-label, an overload sub-label and a heavy overload sub-label.
Further, the step of summarizing the data sets corresponding to all the sample data to obtain a training set, and constructing a multi-path decision model according to the training set includes:
if the size of the training set is N, randomly and replaceably extracting N training samples from the training set to obtain a training sample set for training a decision model, and repeatedly extracting K times to generate K groups of training sample sets;
and acquiring all the sub-label names, acquiring the feature dimension of the training sample set according to all the sub-label names, randomly selecting m sub-labels from the training sample set according to the feature dimension, and constructing a plurality of decision models according to the m sub-labels corresponding to each training sample set.
Further, the step of obtaining current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output by all decision models after analyzing the current power supply data of the power distribution equipment, and predicting the service risk level of the power distribution equipment according to the summarized decision results further includes:
inputting current power supply data into the decision model, and generating a service risk value of the power distribution equipment on a forecast day;
and evaluating a service risk level according to the service risk value of the power distribution equipment on the prediction day, and sending a corresponding early warning strategy to a power supply network management platform according to the service risk level.
Further, the method further comprises:
if the service risk value is within a first early warning threshold value, setting the service risk value as a first-level service risk level;
if the service risk value is within a second early warning threshold value, setting the service risk value as a secondary service risk grade;
and if the service risk value is within a third early warning threshold value, setting the service risk value as a third-level service risk level.
Further, the step of sending a corresponding early warning policy to a power supply network management platform according to the service risk level includes:
if the service risk level of the power supply equipment is predicted to be one level, actively generating a fault maintenance work order, and sending the fault maintenance work order to the power supply network management platform, wherein the fault maintenance work order comprises a fault reason and maintenance measures of the power supply equipment;
if the service risk level of the power supply equipment is predicted to be in a second level, actively generating hidden fault danger reminding information, and sending the hidden fault danger reminding information to the power supply network management platform, wherein the hidden fault danger reminding information comprises one or more maintenance project types;
and if the service risk level of the power supply equipment is predicted to be three levels, actively generating power failure reminding information, and sending the power failure reminding information to a power supply management platform.
The power supply service risk prediction system according to the embodiment of the invention is applied to a power supply system, and comprises:
the tag type acquisition module is used for acquiring historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprises a plurality of sample data so as to acquire tag types corresponding to the sample data according to the historical power supply data;
the label definition executing module is used for calling a preset label definition rule corresponding to the sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
the model construction module is used for summarizing the data sets corresponding to all the sample data to obtain a training set and constructing a multi-path decision model according to the training set;
and the risk prediction module is used for acquiring the current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output by all decision models after analyzing the current power supply data of the power distribution equipment, and predicting the service risk level of the power distribution equipment according to the summarized decision results.
Another aspect of the present invention also provides a storage medium storing one or more programs that, when executed, implement the power supply service risk prediction method as described above.
Another aspect of the present invention also provides a computer device comprising a memory and a processor, wherein:
the memory is used for storing computer programs;
the processor is configured to implement the power supply service risk prediction method when executing the computer program stored in the memory.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a power supply service risk prediction method according to a first embodiment of the present invention;
fig. 2 is a flowchart of a power supply service risk prediction method according to a second embodiment of the present invention;
FIG. 3 is a flow chart of decision model construction according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a power supply service risk prediction system according to a third embodiment of the present invention.
The following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are presented in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a flowchart of a power supply service risk prediction method according to a first embodiment of the present invention is shown, applied to a power supply system, the method includes steps S01 to S04, where:
step S01: the method comprises the steps of obtaining historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprise a plurality of sample data, and obtaining label types corresponding to the sample data according to the historical power supply data;
it can be understood that the power supply network includes several power distribution devices, and in this step, historical power supply data of the power distribution devices in the power distribution network needs to be collected to form sample data, where the tag types of the sample data at least include a basic attribute tag, a historical operating state tag, a historical operating environment tag, a location feature tag, and a user feature tag.
It should be noted that, because the power supply network rack is complex, the power supply data is dispersed in different service systems, the power supply system can only call relevant data from each service system, and the service systems all correspond to one sample data, so that the power supply system can obtain various label types of each sample data according to the source of the sample data when acquiring historical power supply data.
Step S02: calling a preset label definition rule corresponding to sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
it should be noted that after the tag type of each sample data is obtained, the power supply system may specifically retrieve the tag definition rule corresponding to each sample data according to the tag type, where the step of the tag definition rule includes:
the power supply system classifies the basic attribute data into operation age data, capacity data, power supply radius data and overhaul record data;
after classifying the basic attribute data, the power supply system compares the operational life data of the power distribution equipment with a preset operational life threshold value, and the corresponding distribution equipment is defined by the operational age label according to the comparison result, the defined equipment result includes a new operational equipment sub-label, an old equipment sub-label and a general equipment sub-label, specifically, in this embodiment, two operational age threshold values are set, which are respectively 3 years and 10 years, namely, when the power supply system judges that the commissioning life data of the power distribution equipment is less than 3 years, the power distribution equipment is defined as a new commissioning equipment sub-label, when the power supply system judges that the commissioning life data of the power distribution equipment is between 3 and 10 years, the power distribution equipment is defined as a general equipment sub-label, and when the power supply system judges that the commissioning age data of the power distribution equipment is more than 10 years, the power distribution equipment is defined as an old equipment sub-label.
Further, the power supply system compares the capacity data with a device configuration capacity threshold value, so as to define a capacity label of the device corresponding to the capacity data according to a comparison result, where the defined device result includes a splicing capacity high sub-label, a splicing capacity low sub-label, and a splicing capacity general sub-label, specifically, the capacity data includes a splicing capacity and a splicing subscriber number, when the splicing capacity is higher than the configuration high capacity threshold value set in the configuration, the splicing capacity high sub-label is marked, when the splicing capacity is smaller than the configuration low capacity threshold value in the configuration, the splicing capacity low sub-label is marked, and when the splicing capacity is between the splicing capacity high capacity threshold value and the splicing capacity low threshold value, the splicing capacity general sub-label is marked. The power supply system can also match the number of the connected users with the set number of the connected users, when the number of the connected users is higher than the value of the configured number of the connected users, the corresponding power distribution equipment is marked as the number of the connected users to be more, when the number of the connected users is smaller than the value of the configured number of the connected users to be less, the number of the connected users is marked as less, and when the number of the connected users is between the number of the connected users and the number of the connected users to be less, the number of the connected users is marked as general.
It can be understood that, in order to accurately analyze the influence of the capacity data characteristics on the prediction risk, the power supply system further calculates the average capacity of the users according to the splicing capacity and the number of the spliced users, matches the obtained average capacity of the users with the set splicing capacity grade, marks the average capacity of the users as high when the average capacity of the users is higher than a configured high capacity value in the configuration, marks the average capacity of the users as medium when the average capacity of the users is between the high average capacity of the users and the low average capacity of the users, and marks the average capacity of the users as low when the average capacity of the users is higher than a configured low capacity value in the configuration.
And matching the power supply radius data with a set power supply radius threshold value, and defining a power supply radius label of equipment corresponding to the power supply radius data according to a matching result, wherein the defined equipment result comprises a power supply radius qualified sub-label, a power supply radius overrun sub-label and a power supply radius serious overrun sub-label.
The power supply system still according to overhaul record data judge with whether there is whole maintenance transformation in the equipment that overhaul record data correspond, if then with the distribution equipment definition that corresponds for the overall maintenance transformation sub-label, if otherwise define for partial maintenance transformation sub-label, specifically speaking, power supply system judges whether the distribution equipment that corresponds has carried out the maintenance according to overhaul record data, if say again that overhaul record data acquire the maintenance scope, whether overhaul to the totality according to overhaul the scope judgement, if not overhaul, then define as not overhauing the sub-label. If the maintenance is carried out, the maintenance range is marked as a total maintenance modification sub-label or a partial maintenance modification sub-label according to the corresponding maintenance range, in conclusion, the definition and classification of the basic attribute data are completed according to the label definition rule, and a plurality of sub-labels are obtained.
Further, the power supply system classifies the historical operating state data into load fault data, power failure fault data, low voltage fault data and three-phase unbalanced fault data, counts the load fault occurrence frequency of the corresponding power distribution equipment within a first preset time according to the load fault data, compares the load fault occurrence frequency with a preset load fault frequency threshold value, defines the load label of the corresponding power distribution equipment according to the comparison result, and defines the equipment result to include a normal sub-label, a heavy load sub-label, an overload sub-label and a heavy overload sub-label, specifically, in this embodiment, the first preset time is set to 1 month, i.e. the equipment is counted according to the heavy overload occurrence frequency within nearly 1 month, if no heavy load exists, the equipment is marked as normal, if the equipment is counted according to the heavy load occurrence frequency within nearly 1 month, if heavy load exists, the equipment is marked as heavy load, and counting the overload times within the last 1 month according to the statistics, if the overload times are less than the serious overload threshold value, marking the overload, counting the overload times within the last 1 month according to the statistics, and if the overload times are greater than the serious overload threshold value, marking the overload.
The power failure event that power distribution equipment exists is analyzed according to the power failure fault data in the second preset time, and the power failure fault data include power failure time, power failure event type and power failure household number, and in this embodiment, the second preset time is 2 months, and the concrete analysis process is: when the power failure type is judged to be 'failure power failure', the time of power failure exceeds the time threshold value of single failure power failure time, the time is marked as the time of single failure power failure exceeding, when the power failure type is 'planned power failure', the time of power failure exceeds the time threshold value of single planned power failure time, the time is marked as the time of single failure power failure exceeding, when the power failure type is 'failure power failure', the number of users exceeds the time threshold value of single failure power failure, when the power failure type is 'planned power failure', the number of users exceeds the time threshold value of single failure power failure, the number of users exceeds, when the number of users exceeds the time threshold value of power failure, the number of users is marked as the number of power failure exceeding, and the equipment without power failure event is marked as the power failure. Further, the power failure times of the power distribution equipment in the second preset time are counted according to the power failure events, if the power failure times are smaller than a threshold set by occasional power failure, the power failure times are marked as occasional power failure, if the power failure times are larger than the threshold set by occasional power failure and smaller than the threshold set by serious frequent power failure, the power failure times are marked as frequent power failure, and if the power failure times are larger than the threshold set by serious frequent power failure, the power failure times are marked as serious frequent power failure.
Furthermore, the sub-labels without low voltage, general low voltage, serious low voltage, and especially serious low voltage can be defined according to the low voltage fault data, and the sub-labels without three-phase imbalance, general three-phase imbalance, serious three-phase imbalance, and especially serious three-phase imbalance can be defined according to the three-phase imbalance fault data.
It should be noted that after all sample data is analyzed and defined, a plurality of sub-tags are obtained, and a corresponding determination result is marked under each sub-tag, where the determination result includes two types, namely power off and power off.
Step S03: summarizing data sets corresponding to all sample data to obtain a training set, and constructing a multi-path decision model according to the training set;
it should be noted that the sub-labels after the classification definition and the corresponding determination results are summarized, so as to obtain a training set for training the decision model, and further construct the multi-path decision model.
Step S04: the method comprises the steps of obtaining current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output after all decision models analyze the current power supply data of the power distribution equipment, and predicting service risk levels of the power distribution equipment according to the summarized decision results.
It should be noted that, in the actual prediction process, it is only necessary to obtain the current power supply data of the power distribution equipment in real time to input the data into the multi-path decision model, so that each path of decision model outputs the judgment result of power failure or power outage according to the data, and then all the judgment results are summarized to obtain the current service risk level.
Furthermore, the power failure result and the power outage result both correspond to a risk value, so that the power supply system can acquire the total predicted risk value of the power supply equipment, and then acquire the corresponding service risk grade according to the total predicted risk value, so that management service personnel can know whether the power supply hidden danger exists in the power distribution equipment according to the grade, and then make an avoidance plan in the past, thereby ensuring the safe operation of the power supply equipment and improving the reliability of power supply.
In summary, according to the power supply service risk prediction method, the fault risk of the power supply network is predicted by analyzing the power supply data of the power supply network, so that the hidden fault danger is eliminated in advance, and the power supply reliability is ensured. The method comprises the steps of collecting historical power supply data of a plurality of power distribution equipment to obtain a plurality of sample data, extracting preset label definition rules according to label types of the sample data, classifying and defining each sample data according to the label definition rules to obtain a training set for constructing a decision model, constructing a multi-path decision model according to the training set, analyzing a decision result by monitoring the current power supply data of any power distribution equipment in a power distribution network, and judging the service risk level of the power distribution equipment in a limited manner, namely realizing effective monitoring and prediction of the whole power distribution network, effectively avoiding possible faults, ensuring the reliability of power supply and improving the satisfaction degree of power consumption of a user.
Referring to fig. 2, a flowchart of a power supply service risk prediction method according to a second embodiment of the present invention is shown, the method includes steps S11 to S16, wherein:
step S11: the method comprises the steps of obtaining historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprise a plurality of sample data, and obtaining label types corresponding to the sample data according to the historical power supply data;
step S12: calling a preset label definition rule corresponding to sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
step S13: if the size of the training set is N, randomly and replaceably extracting N training samples from the training set to obtain a training sample set for training a decision model, and repeatedly extracting K times to generate K groups of training sample sets;
referring to fig. 3, a flowchart of a decision model building process is shown, when a decision model is actually built, before training samples are extracted from a training set, the previously extracted training samples need to be put back into the training set, and each training sample set includes N training samples.
It should be noted that, the specific numerical values of K and N in this embodiment are both related to the amount of sample data acquired, if the numerical values of K and N are too large, the calculation difficulty is increased, and if the numerical values of K and N are too small, the decision accuracy may be lowered.
Step S14: acquiring all the sub-label names, acquiring the feature dimension of the training sample set according to all the sub-label names, randomly selecting m sub-labels from the training sample set according to the feature dimension, and constructing a plurality of decision models according to the m sub-labels corresponding to each training sample set;
it should be noted that the detailed sub-label names are actually old equipment sub-labels, new equipment sub-labels, power supply radius qualified sub-labels, power supply radius over-limit sub-labels, and the like, that is, the sub-label names include all sub-labels obtained by defining results, and in the process of randomly selecting a plurality of m sub-labels, the value of m needs to be much smaller than the characteristic dimension of the training sample set to ensure that the decision tree can grow to a large extent, and the decision tree is the decision model.
Step S15: inputting current power supply data into the decision model, and generating a service risk value of the power distribution equipment on a forecast day;
in the step, if the service risk value is within a first early warning threshold value, setting the service risk value as a first-level service risk level; if the service risk value is within a second early warning threshold value, setting the service risk value as a secondary service risk grade; if the service risk value is within the third early warning threshold value, setting the service risk value as a third-level service risk level, and setting different risk levels can be favorable for making an early warning strategy with stronger pertinence.
Step S16: evaluating a service risk level according to a service risk value of the power distribution equipment on a prediction day, and sending a corresponding early warning strategy to a power supply network management platform according to the service risk level;
further, the early warning strategies corresponding to different service risks include: if the service risk level of the power supply equipment is predicted to be one level, the hidden danger of the power distribution equipment is indicated to be the highest at this moment, based on the situation, the power supply system actively generates a fault maintenance work order and sends the fault maintenance work order to the power supply network management platform, the fault maintenance work order comprises the fault reason and the maintenance measures of the power supply equipment, so that the fault maintenance work order is distributed to power supply service management personnel, and the power supply service management personnel can conduct targeted investigation and rectification.
If the service risk level of the power supply equipment is predicted to be in a second level, actively generating fault hidden danger reminding information, wherein the situation shows that some hidden dangers which are not very urgent exist in the power distribution equipment and the power distribution equipment needs to be maintained at the moment;
if the service risk level of the power supply equipment is predicted to be three levels, the fact that the power distribution equipment has an emergency on the predicted day is indicated, if the power distribution equipment encounters severe weather and other conditions, the power supply system actively generates power failure reminding information at the moment, and the power failure reminding information is sent to the power supply management platform, so that damage to the power distribution equipment caused by an emergency is avoided.
In summary, according to the power supply service risk prediction method, the fault risk of the power supply network is predicted by analyzing the power supply data of the power supply network, so that the hidden fault danger is eliminated in advance, and the power supply reliability is ensured. The method comprises the steps of collecting historical power supply data of a plurality of power distribution equipment to obtain a plurality of sample data, extracting preset label definition rules according to label types of the sample data, classifying and defining each sample data according to the label definition rules to obtain a training set for constructing a decision model, constructing a multi-path decision model according to the training set, analyzing a decision result by monitoring the current power supply data of any power distribution equipment in a power distribution network, and judging the service risk level of the power distribution equipment in a limited manner, namely realizing effective monitoring and prediction of the whole power distribution network, effectively avoiding possible faults, ensuring the reliability of power supply and improving the satisfaction degree of power consumption of a user.
Referring to fig. 4, a schematic structural diagram of a power supply service risk prediction system in a third embodiment of the present invention is shown, and is applied to a power supply system, where the power supply service risk prediction system includes:
the tag type obtaining module 10 is configured to obtain historical power supply data of a plurality of power distribution devices, where the historical power supply data includes a plurality of sample data, and obtain tag types corresponding to the various sample data according to the historical power supply data;
the tag definition executing module 20 is configured to retrieve a preset tag definition rule corresponding to sample data from a preset database according to a tag type corresponding to the sample data, and classify and define each sample data in sequence according to the preset tag definition rule to obtain a data set corresponding to the sample data, where the data set includes a sub-tag and a determination result corresponding to the sub-tag;
the model construction module 30 is configured to summarize data sets corresponding to all sample data to obtain a training set, and construct a multi-path decision model according to the training set;
further, the model building module 30 further includes:
the system comprises a sample extraction unit, a decision model generation unit and a decision model generation unit, wherein the sample extraction unit is used for randomly and replaceably extracting N training samples from a training set to obtain the training sample set used for training the decision model if the size of the training set is N, and repeatedly extracting K times to generate K groups of training sample sets;
and the model training unit is used for acquiring all the sub-label names, acquiring the characteristic dimension of the training sample set according to all the sub-label names, randomly selecting m sub-labels from the training sample set according to the characteristic dimension, and constructing a plurality of decision models according to the m sub-labels corresponding to each training sample set.
And the risk prediction module 40 is configured to obtain current power supply data of any power distribution device in the power distribution network, summarize decision results output by all the decision models after analyzing the current power supply data of the power distribution device, and predict a service risk level of the power distribution device according to the summarized decision results.
Further, the risk prediction module 40 further includes:
the risk value prediction unit is used for inputting the current power supply data into the decision model and generating a service risk value of the power distribution equipment on a prediction day;
the early warning strategy generation unit evaluates a service risk level according to a service risk value of the power distribution equipment on a prediction day, and sends a corresponding early warning strategy to a power supply network management platform according to the service risk level;
the risk grade setting unit is used for setting a first-grade service risk grade if the service risk value is within a first early warning threshold value;
if the service risk value is within a second early warning threshold value, setting the service risk value as a secondary service risk grade;
and if the service risk value is within a third early warning threshold value, setting the service risk value as a third-level service risk level.
The early warning strategy setting unit is used for actively generating a fault maintenance work order and sending the fault maintenance work order to the power supply network management platform if the service risk level of the power supply equipment is predicted to be one level, wherein the fault maintenance work order comprises a fault reason and maintenance measures of the power supply equipment;
if the service risk level of the power supply equipment is predicted to be in a second level, actively generating hidden fault danger reminding information, and sending the hidden fault danger reminding information to the power supply network management platform, wherein the hidden fault danger reminding information comprises one or more maintenance project types;
and if the service risk level of the power supply equipment is predicted to be three levels, actively generating power failure reminding information, and sending the power failure reminding information to a power supply management platform.
In summary, according to the power supply service risk prediction system, the fault risk of the power supply network is predicted by analyzing the power supply data of the power supply network, so that the hidden fault danger is eliminated in advance, and the power supply reliability is ensured. The method comprises the steps of collecting historical power supply data of a plurality of power distribution equipment to obtain a plurality of sample data, extracting preset label definition rules according to label types of the sample data, classifying and defining each sample data according to the label definition rules to obtain a training set for constructing a decision model, constructing a multi-path decision model according to the training set, analyzing a decision result by monitoring the current power supply data of any power distribution equipment in a power distribution network, and judging the service risk level of the power distribution equipment in a limited manner, namely realizing effective monitoring and prediction of the whole power distribution network, effectively avoiding possible faults, ensuring the reliability of power supply and improving the satisfaction degree of power consumption of a user.
In another aspect, the present invention further provides a computer storage medium, on which one or more programs are stored, and the programs, when executed by a processor, implement the power supply service risk prediction method described above.
In another aspect, the present invention further provides a vehicle, including a memory and a processor, where the memory is used for storing a computer program, and the processor is used for executing the computer program stored in the memory, so as to implement the power supply service risk prediction method described above.
Those of skill in the art will understand that the logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be viewed as implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A power supply service risk prediction method is applied to a power supply system, and comprises the following steps:
the method comprises the steps of obtaining historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprise a plurality of sample data, and obtaining label types corresponding to the sample data according to the historical power supply data;
calling a preset label definition rule corresponding to sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
summarizing data sets corresponding to all sample data to obtain a training set, and constructing a multi-path decision model according to the training set;
the current power supply data of any power distribution equipment in the power distribution network are obtained, decision results output after the decision models analyze the current power supply data of the power distribution equipment are collected, and the service risk level of the power distribution equipment is predicted according to the collected decision results.
2. The power supply service risk prediction method according to claim 1, wherein the sample data includes basic attribute data, historical operating state data, historical operating environment data, location characteristic data, and user characteristic data, and the step of sequentially classifying and defining each sample data according to the preset tag definition rule includes:
classifying the basic attribute data into operation age data, capacity data, power supply radius data and overhaul record data;
comparing the commissioning age data of the power distribution equipment with a preset commissioning age threshold value, and defining commissioning age labels of the corresponding power distribution equipment according to a comparison result, wherein the defined equipment result comprises a new commissioning equipment sub-label, an old equipment sub-label and a general equipment sub-label;
comparing the capacity data with a device configuration capacity threshold value so as to define a capacity label of the device corresponding to the capacity data according to a comparison result, wherein the definition result comprises a tape splicing capacity high sub-label, a tape splicing capacity low sub-label and a tape splicing capacity general sub-label;
matching the power supply radius data with a set power supply radius threshold value, and defining a power supply radius label of equipment corresponding to the power supply radius data according to a matching result, wherein the defined equipment result comprises a power supply radius qualified sub-label, a power supply radius overrun sub-label and a power supply radius serious overrun sub-label;
and judging whether the equipment corresponding to the overhaul record data has integral overhaul transformation or not according to the overhaul record data, if so, defining the corresponding power distribution equipment as an overall overhaul transformation sub-tag, and if not, defining the corresponding power distribution equipment as a partial overhaul transformation sub-tag.
3. The power supply service risk prediction method according to claim 2, wherein the step of classifying and defining each sample data in turn according to the preset tag definition rule further comprises:
classifying the historical operating state data into load fault data, power failure fault data, low-voltage fault data and three-phase unbalance fault data;
and counting the load fault occurrence frequency of the corresponding power distribution equipment within a first preset time according to the load fault data, comparing the load fault occurrence frequency with a preset load fault frequency threshold value, and defining the corresponding power distribution equipment by using a load label according to a comparison result, wherein the defined equipment result comprises a normal sub-label, a heavy load sub-label, an overload sub-label and a heavy overload sub-label.
4. The power supply service risk prediction method according to claim 3, wherein the step of summarizing the data sets corresponding to all the sample data to obtain a training set, and constructing a multi-path decision model according to the training set comprises:
if the size of the training set is N, randomly and replaceably extracting N training samples from the training set to obtain a training sample set for training a decision model, and repeatedly extracting K times to generate K groups of training sample sets;
and acquiring all the sub-label names, acquiring the feature dimension of the training sample set according to all the sub-label names, randomly selecting m sub-labels from the training sample set according to the feature dimension, and constructing a plurality of decision models according to the m sub-labels corresponding to each training sample set.
5. The power supply service risk prediction method according to claim 1, wherein the step of obtaining current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output by all decision models after analyzing the current power supply data of the power distribution equipment, and predicting the service risk level of the power distribution equipment according to the summarized decision results further comprises:
inputting current power supply data into the decision model, and generating a service risk value of the power distribution equipment on a forecast day;
and evaluating a service risk level according to the service risk value of the power distribution equipment on the prediction day, and sending a corresponding early warning strategy to a power supply network management platform according to the service risk level.
6. The power supply service risk prediction method of claim 5, further comprising:
if the service risk value is within a first early warning threshold value, setting the service risk value as a first-level service risk level;
if the service risk value is within a second early warning threshold value, setting the service risk value as a secondary service risk grade;
and if the service risk value is within a third early warning threshold value, setting the service risk value as a third-level service risk level.
7. The power supply service risk prediction method according to claim 6, wherein the step of sending a corresponding early warning policy to a power supply network management platform according to the service risk level comprises:
if the service risk level of the power supply equipment is predicted to be one level, actively generating a fault maintenance work order, and sending the fault maintenance work order to the power supply network management platform, wherein the fault maintenance work order comprises a fault reason and maintenance measures of the power supply equipment;
if the service risk level of the power supply equipment is predicted to be in a second level, actively generating hidden fault danger reminding information, and sending the hidden fault danger reminding information to the power supply network management platform, wherein the hidden fault danger reminding information comprises one or more maintenance project types;
and if the service risk level of the power supply equipment is predicted to be three levels, actively generating power failure reminding information, and sending the power failure reminding information to a power supply management platform.
8. A power supply service risk prediction system is applied to a power supply system, and comprises:
the tag type acquisition module is used for acquiring historical power supply data of a plurality of power distribution devices, wherein the historical power supply data comprises a plurality of sample data so as to acquire tag types corresponding to the sample data according to the historical power supply data;
the label definition executing module is used for calling a preset label definition rule corresponding to the sample data from a preset database according to the label type corresponding to the sample data, and classifying and defining each sample data in sequence according to the preset label definition rule to obtain a data set corresponding to the sample data, wherein the data set comprises sub-labels and judgment results corresponding to the sub-labels;
the model building module is used for summarizing the data sets corresponding to all the sample data to obtain a training set and building a multi-path decision model according to the training set;
and the risk prediction module is used for acquiring the current power supply data of any power distribution equipment in the power distribution network, summarizing decision results output by all decision models after analyzing the current power supply data of the power distribution equipment, and predicting the service risk level of the power distribution equipment according to the summarized decision results.
9. A storage medium, comprising: the storage medium stores one or more programs which, when executed by a processor, implement the power supply service risk prediction method of any one of claims 1-7.
10. A computer device, wherein the vehicle comprises a memory and a processor, wherein:
the memory is used for storing computer programs;
the processor is configured to implement the power supply service risk prediction method according to any one of claims 1 to 7 when executing the computer program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210075884.1A CN114493238A (en) | 2022-01-23 | 2022-01-23 | Power supply service risk prediction method, system, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210075884.1A CN114493238A (en) | 2022-01-23 | 2022-01-23 | Power supply service risk prediction method, system, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114493238A true CN114493238A (en) | 2022-05-13 |
Family
ID=81472784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210075884.1A Pending CN114493238A (en) | 2022-01-23 | 2022-01-23 | Power supply service risk prediction method, system, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114493238A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116365513A (en) * | 2023-04-17 | 2023-06-30 | 国网江苏省电力有限公司 | Command network interaction method and system based on power grid situation |
| CN116704735A (en) * | 2023-08-08 | 2023-09-05 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
-
2022
- 2022-01-23 CN CN202210075884.1A patent/CN114493238A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116365513A (en) * | 2023-04-17 | 2023-06-30 | 国网江苏省电力有限公司 | Command network interaction method and system based on power grid situation |
| CN116365513B (en) * | 2023-04-17 | 2023-10-27 | 国网江苏省电力有限公司 | Command network interaction method and system based on power grid situation |
| CN116704735A (en) * | 2023-08-08 | 2023-09-05 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
| CN116704735B (en) * | 2023-08-08 | 2023-11-03 | 湖南江河能源科技股份有限公司 | Hydropower station intelligent alarm method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106154209B (en) | Electrical energy meter fault prediction technique based on decision Tree algorithms | |
| CN116862199A (en) | Building construction optimizing system based on big data and cloud computing | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN114493238A (en) | Power supply service risk prediction method, system, storage medium and computer equipment | |
| CN112561736A (en) | Fault diagnosis system and method for relay protection device of intelligent substation | |
| MX2013000577A (en) | Machine learning for power grids. | |
| CN106842106A (en) | Electrical energy meter fault Forecasting Methodology and device | |
| CN106570567A (en) | Main network maintenance multi-constraint multi-target evaluation expert system and optimization method | |
| CN109255524A (en) | A kind of measuring equipment data analyzing evaluation method and system | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN115619382A (en) | Power dispatching visual management method and system | |
| CN108596450B (en) | Power grid risk early warning method and system | |
| CN114169709A (en) | State evaluation method and device for secondary equipment of transformer substation, storage medium and equipment | |
| CN117349624A (en) | Electric power energy monitoring method, system, terminal equipment and storage medium | |
| CN108446202A (en) | A kind of judgment method of the safe condition of calculator room equipment | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN112036725A (en) | Electric energy meter fault identification method | |
| CN116756966A (en) | Power grid fault early warning method, system, terminal equipment and storage medium | |
| CN115965266A (en) | Intelligent analysis system based on big data | |
| CN112015724A (en) | Method for analyzing metering abnormality of electric power operation data | |
| CN115603459A (en) | Digital twin technology-based power distribution network key station monitoring method and system | |
| CN115146715A (en) | Power utilization potential safety hazard diagnosis method, device, equipment and storage medium | |
| CN115358336A (en) | Power utilization abnormity detection method and device and electronic equipment | |
| CN114626433A (en) | Fault prediction and classification method, device and system for intelligent electric energy meter | |
| CN111260150A (en) | Communication equipment operation risk early warning method and communication management 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 |