CN117495350A - Clock operation and maintenance method, system, equipment and storage medium based on clock networking - Google Patents
Clock operation and maintenance method, system, equipment and storage medium based on clock networking Download PDFInfo
- Publication number
- CN117495350A CN117495350A CN202311470786.9A CN202311470786A CN117495350A CN 117495350 A CN117495350 A CN 117495350A CN 202311470786 A CN202311470786 A CN 202311470786A CN 117495350 A CN117495350 A CN 117495350A
- Authority
- CN
- China
- Prior art keywords
- clock
- maintenance
- cost
- error
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 183
- 230000006855 networking Effects 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims description 50
- 239000013598 vector Substances 0.000 claims description 28
- 230000009471 action Effects 0.000 claims description 24
- 238000013507 mapping Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000036541 health Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 241000700605 Viruses Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000004044 response Effects 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
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to the technical field of clock networking, in particular to a clock operation and maintenance method, a system, equipment and a storage medium based on clock networking.
Description
Technical Field
The invention relates to the technical field of clock networking, in particular to a clock operation and maintenance method, a system, equipment and a storage medium based on clock networking.
Background
The clock networking is an important time service infrastructure, is widely applied to the fields of financial transactions, communication networks, internet of things and the like, and has a key meaning for ensuring time synchronization and frequency stability of a system. The traditional clock networking precision time system operation and maintenance method is generally based on manual adjustment and experience rules, and has the following problems:
human error: manual adjustment is susceptible to operator skill level and subjective awareness, resulting in errors that reduce the accuracy and stability of the system.
Timeliness: the traditional operation and maintenance method generally needs regular manual intervention and adjustment, cannot realize real-time operation and maintenance decision, and cannot timely cope with system abnormality and change.
Complex decisions: the operation and maintenance of the clock networking precision time system involves a plurality of factors, such as clock frequency, network connection quality, environmental change and the like, and the traditional method cannot accurately evaluate and optimize the factors, so that decision making is complicated and the efficiency is low.
Disclosure of Invention
The invention aims to provide a clock operation and maintenance method, a system, equipment and a storage medium based on clock networking.
The technical scheme of the invention is as follows:
a clock operation and maintenance method based on clock networking, comprising the following operations:
s1, acquiring time data, environment data and historical operation and maintenance data of a clock, performing standardized processing on the environment data after cleaning processing, performing normalized processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain key performance indexes;
s2, the key performance indexes are subjected to feature mapping processing to obtain feature data; the characteristic data are subjected to thermal coding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
s3, acquiring operation and maintenance cost and clock error of the operation and maintenance strategy, and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing the operation and maintenance strategy; if the operation and maintenance cost is higher than the cost range or the clock error is higher than the error range, executing S4;
s4, if the operation and maintenance cost is higher than the cost range, the clock error is not higher than the error range, and according to the priority level of the action in the operation and maintenance strategy, the action with the level larger than the level threshold is executed; and if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
The key performance indexes comprise fault frequency, clock precision, temperature, humidity and power supply voltage.
If the operation and maintenance cost and the clock error of the operation and maintenance strategy in the step S3 are lower than the cost range and the error range, placing the operation and maintenance strategy and the corresponding risk probability distribution information in a historical experience revising area; and when the information entropy of the risk probability distribution information and the historical risk probability distribution information in the S2 is smaller than the entropy threshold value, directly executing a corresponding historical operation and maintenance strategy.
And presetting the size and the stride of a sliding window, wherein the sliding window selects a time sequence, and performs the feature extraction processing in the S2 together with the corresponding state vector.
The operation and maintenance strategy comprises the following steps: the fault maintenance, the clock parameter adjustment, the temperature adjustment, the humidity adjustment and the power supply voltage adjustment are sequentially and respectively set into a first grade, a second grade, a third grade, a fourth grade and a fifth grade from high to low.
The operation of the feature mapping process of S2 specifically includes: and respectively matching the clock health state, the clock precision, the temperature, the humidity and the power supply voltage obtained based on the key performance indexes with corresponding preset classification rules, outputting corresponding classification values, and combining to obtain the characteristic data.
The operation of obtaining the state vector in S2 specifically includes: and mapping all the classified values in the characteristic data to obtain a binary integer set, and connecting the binary integer set to obtain the state vector.
A clock operation and maintenance system based on clock networking, comprising:
the key performance index generation module is used for acquiring time data, environment data and historical operation and maintenance data of the clock, carrying out standardization processing on the environment data after cleaning processing, carrying out normalization processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain a key performance index;
the operation and maintenance strategy generation module is used for obtaining characteristic data through characteristic mapping processing of the key performance indexes; the characteristic data are subjected to thermal coding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
the operation and maintenance strategy execution module is used for acquiring operation and maintenance cost and clock error of the operation and maintenance strategy and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing the operation and maintenance strategy; if the operation and maintenance cost is higher than a cost range or the clock error is higher than an error range, executing an operation and maintenance action executing module;
the operation and maintenance action execution module is used for executing actions with the level greater than a level threshold according to the priority level of the actions in the operation and maintenance strategy if the operation and maintenance cost is higher than a cost range and the clock error is not higher than an error range; and if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
An operation and maintenance device of a clock networking system comprises a processor and a memory, wherein the processor realizes the clock operation and maintenance method based on clock networking when executing a computer program stored in the memory.
A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the clock networking-based clock operation and maintenance method described above.
The invention has the beneficial effects that:
according to the clock operation and maintenance method based on the clock networking, clock data are collected, key performance indexes are extracted, after feature mapping, thermal encoding, feature extraction and matching are carried out on the key performance indexes, corresponding operation and maintenance strategies are generated, operation and maintenance cost and clock error of the current operation and maintenance strategies are judged, the size of a cost range and an error range are judged, the processing method is flexibly adjusted according to different results, intelligent clock operation and maintenance management is achieved, environmental changes and requirements can be responded timely, operation and maintenance management becomes efficient and accurate, complexity of manual intervention and decision is reduced, and operation and maintenance efficiency and stability are improved.
Detailed Description
The clock operation and maintenance method based on the clock networking system comprises the following operations:
s1, acquiring time data, environment data and historical operation and maintenance data of a clock, performing standardized processing on the environment data after cleaning processing, performing normalized processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain key performance indexes;
s2, the key performance indexes are subjected to feature mapping processing to obtain feature data; the characteristic data are subjected to thermal coding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
s3, acquiring operation and maintenance cost and clock error of the operation and maintenance strategy, and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing the operation and maintenance strategy; if the operation and maintenance cost is higher than the cost range or the clock error is higher than the error range, executing S4;
s4, if the operation and maintenance cost is higher than the cost range, the clock error is not higher than the error range, and according to the priority level of the action in the operation and maintenance strategy, the action with the level larger than the level threshold is executed; and if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
S1, acquiring time data, environment data and historical operation and maintenance data of a clock, performing standardization processing on the environment data after cleaning processing, performing normalization processing on the time data and the historical operation and maintenance data to obtain a clock networking data set, and extracting the clock data set to obtain key performance indexes.
The clock networking is a time service platform formed by integrating information technologies such as a mobile communication network, the Internet, big data and the like with a clock. In the clock networking, a master clock acquires standard time of navigation satellites (GPS and Beidou) through an NIP server and the like, and then transmits the time to a sub clock through an application server and the like, so that normal operation and maintenance of the clock networking are realized.
In order to realize stable operation of the clock networking, original data related to clock operation and performance in the clock networking are collected, wherein the original data comprise time data of a master clock and a slave clock, environment data (temperature and humidity) of the master clock and the slave clock, historical operation and maintenance data (failure times, failure time and operation and maintenance results). The data can be obtained by means of sensors, log files, etc. And cleaning the obtained data, wherein the cleaning comprises selecting a subset, renaming column names, deleting repeated values, processing missing values, unifying, sorting data and processing abnormal values so as to ensure the quality and consistency of the data. Then, the environment data is further standardized, and the operation of the standardized processing is specifically as follows: and obtaining the maximum value and the minimum value in the environment data, obtaining the range of the maximum value and the minimum value, subtracting the minimum value from the environment data, and dividing the environment data by the range to obtain the standardized environment data. And respectively carrying out normalization processing on the time data and the historical operation data, and eliminating abnormal values.
Key performance indicators include failure frequency, clock accuracy, temperature, humidity, and supply voltage, which are used to describe the operating state and environmental conditions of the clock.
S2, performing feature mapping treatment on the key performance indexes to obtain feature data; the mapping table is subjected to thermal coding treatment, and state vector codes are obtained after connection; the state vector codes are subjected to feature extraction processing to obtain risk probability distribution information; and carrying out feature matching processing on the risk probability distribution information to obtain an operation and maintenance strategy.
The feature mapping process operates as follows: and (3) respectively matching the clock health state, the clock precision, the temperature, the humidity and the power supply voltage which are obtained based on the key performance indexes with corresponding preset classification rules, outputting corresponding classification values, and combining to obtain the characteristic data. The method can also be as follows: training the neural network by using the clock networking key data set to obtain a training neural network, and processing key performance indexes by the training neural network to obtain characteristic data.
The characteristic data are: the clock health state (obtained by comparing the fault frequency, the clock precision change, the temperature change, the humidity change and the power supply voltage change with standard values respectively) has a superior level output of 0, a good level output of 1 and a medium level output of 2; clock accuracy, wherein the clock accuracy is less than 1 mu s output and is 0, and the clock accuracy is not less than 1 mu s output and is 1; the temperature is less than-10 ℃ and output is 0, the output is 1 at-10-50 ℃, and the output is 2 at more than 50 ℃; humidity, humidity <70% output of 0, greater than 70% output of 1; the power supply voltage is smaller than 176V output and is 0, 176-220V output is 1, 220-253V output is 2, and 253V output is 3.
The specific form is as follows:
clock health status: [ "you", "good", "medium" ] = >0,1,2;
clock precision: [ "<1us", "> 1us" ] = >0,1;
temperature: [ "< -10 ℃", "-10 ℃ -50 ℃", ">50 ℃" ] = >0,1,2;
humidity: [ "<70%", "70%" ] = >0,1;
supply voltage: [ "< AC 176V" "" AC 176V-220V "," AC 220V-253V "" > "AC 253V" ] = >0,1,2,3.
The feature data is converted into the state vector, which is beneficial to improving the calculation efficiency. The operation of obtaining the state vector is as follows: all the classified values in the feature data are mapped to obtain a binary integer set, and the binary integer set is connected to obtain a state vector.
The state vector includes:
the clock health state is 100 when the output is 0, 010 when the output is 1, and 001 when the output is 2;
the output is 10 when the clock precision is 0, and is 01 when the clock precision is 1;
the output is 100 when the temperature is 0, 010 when the temperature is 1, and 001 when the temperature is 2;
the output is 10 when the humidity is 0, and 01 when the humidity is 1;
the power supply voltage is 1000 at 0, 0100 at 1, 0010 at 2, and 0001 at 3.
The specific form is as follows:
clock health status: [ "0", "1", "2" ] = >100, 010, 001;
clock precision: [ "0", "1" ] = >10, 01;
temperature: [ "0", "1", "2" ] = >100, 010, 001;
humidity: [ "0", "1" ] = >10, 01;
supply voltage: [ "0", "1", "2", "3" ] = >1000, 0100, 0010, 0001;
for example, when the feature data is [ "0", "1", "0", "3" ], the state vector is: [10001010100010].
In consideration of the fact that the time correlation between the data generated by the clock networking is large, in order to facilitate the time sequence of capturing the data, the size and the stride of the sliding window are preset, a time sequence is selected by the sliding window, and the feature extraction processing in the step S2 is executed together with the corresponding state vector. The specific operation is as follows: firstly, determining the size of a sliding window, namely, inputting a plurality of continuous states as a training sample each time, determining a stride, namely, sliding forward each time for a plurality of steps, and repeating the steps to obtain a series of time sequences and corresponding state vectors.
The state vector is subjected to feature extraction processing to obtain risk probability information of instability of the secondary clock and the primary clock, risk probability distribution information is obtained, and an operation and maintenance strategy for maintaining the clock networking system is obtained according to matching of the risk probability distribution information with a risk feature database and a risk response strategy database. The operation of obtaining the operation and maintenance strategy can be realized through a deep reinforcement learning model, and the deep reinforcement learning model is the prior art, so that the description is not excessive.
The actions of the operation and maintenance strategy include: the fault maintenance, the clock parameter adjustment, the temperature adjustment, the humidity adjustment and the power supply voltage adjustment are sequentially and respectively set into a first grade, a second grade, a third grade, a fourth grade and a fifth grade from high to low.
The specific form is as follows:
the first level in the action-fault maintenance, including system virus cleaning, system risk restarting, system operation correction and manual detection and maintenance, can solve the system operation maintenance risk caused by external influence. The five action priorities are in a decreasing trend, that is, the current operation and maintenance strategy shows that the temperature is higher than the specified threshold value, the temperature needs to be adjusted, but the clock health state is medium at the moment, and the fault maintenance is needed, so that the fault maintenance operation should be preferentially selected to be executed at the moment, and the stable operation of the system is ensured.
S3, acquiring operation and maintenance cost and clock error of an operation and maintenance strategy, and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing an operation and maintenance strategy; if the operation and maintenance cost is higher than the cost range or the clock error is higher than the error range, S4 is executed.
According to actions in the operation and maintenance strategy, calculating corresponding operation and maintenance cost and clock errors caused in the operation and maintenance process, and then judging whether the operation and maintenance cost and the clock errors are respectively higher than a cost range and an error range and are high in cost and error; and if the operation and maintenance cost and the clock error are not higher than the cost range and the error range respectively and are not high in cost and error, the operation and maintenance strategy is executed with confidence.
In order to improve the calculation efficiency, the historical operation and maintenance strategy is positively strengthened, so that the historical high-quality operation and maintenance strategy is optimized when the operation and maintenance strategy is formulated, and time is saved in sequence. Therefore, if the operation and maintenance cost and the clock error of the operation and maintenance strategy in the step S3 are respectively lower than the cost range and the error range, the operation and maintenance strategy and the corresponding risk probability distribution information are placed in the historical experience return visit area with low cost and low error; and when the information entropy of the risk probability distribution information and the historical risk probability distribution information in the S2 is smaller than the entropy threshold value, directly executing a corresponding historical operation and maintenance strategy.
In addition, the operation and maintenance strategy is subjected to scoring treatment and is placed in a historical experience return visit area together with corresponding risk probability distribution information; if the number of the historical operation and maintenance strategies corresponding to the current risk probability distribution information is more than 1, executing the historical operation and maintenance strategy with the assigned value maximum value; and if the number of the historical operation and maintenance strategies with the maximum value is more than 1, executing the historical operation and maintenance strategies in the latest time.
S4, if the operation and maintenance cost is higher than the cost range, the clock error is not higher than the error range, and according to the priority level of the action in the operation and maintenance strategy, the action with the level greater than the level threshold is executed; if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel in the clock networking is changed.
If the operation and maintenance cost is higher than the cost range, the clock error is not higher than the error range and is not high, and in order to reduce the cost, the operation with the level higher than the level threshold is executed according to the priority level of the operation and maintenance strategy, namely, the operation is executed according to the operation priority level of the operation and maintenance strategy, and the number of the executed operations is not less than the threshold, so that the consumption cost of the operation is saved. If the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and is high, and in order to ensure the normal operation and maintenance of the system, the server channel in the clock networking system is changed, in particular, the server channel of an NIP server between the master clock and the satellite is changed, or the server channel of an application server between the master clock and the sub clock is changed.
The embodiment also provides a clock operation and maintenance system based on clock networking, which comprises:
the key performance index generation module is used for acquiring time data, environment data and historical operation and maintenance data of the clock, carrying out standardization processing on the environment data after cleaning processing, carrying out normalization processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain a key performance index;
the operation and maintenance strategy generation module is used for obtaining characteristic data through characteristic mapping processing of the key performance indexes; the characteristic data is subjected to thermal encoding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
the operation and maintenance strategy execution module is used for acquiring operation and maintenance cost and clock error of the operation and maintenance strategy and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing an operation and maintenance strategy; if the operation and maintenance cost is higher than the cost range or the clock error is higher than the error range, executing the operation and maintenance action executing module;
the operation and maintenance action execution module is used for executing actions with the level greater than the level threshold according to the priority level of the actions in the operation and maintenance strategy if the operation and maintenance cost is higher than the cost range and the clock error is not higher than the error range; if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
The embodiment also provides operation and maintenance equipment of the clock networking system, which comprises a processor and a memory, wherein the processor realizes the clock operation and maintenance method based on the clock networking when executing the computer program stored in the memory.
The present embodiment also provides a computer readable storage medium for storing a computer program, where the computer program when executed by a processor implements the clock operation and maintenance method based on clock networking.
According to the clock operation and maintenance method based on clock networking, clock data are collected, key performance indexes are extracted, after feature mapping, thermal encoding, feature extraction and matching are carried out on the key performance indexes, corresponding operation and maintenance strategies are generated, operation and maintenance cost and clock errors of the current operation and maintenance strategies are judged, the sizes of a cost range and an error range are judged, the processing method is flexibly adjusted according to different results, intelligent clock operation and maintenance management is achieved, environmental changes and requirements can be responded timely, operation and maintenance management becomes efficient and accurate, complexity of manual intervention and decision is reduced, and operation and maintenance efficiency and stability are improved.
Claims (10)
1. A clock operation and maintenance method based on clock networking, which is characterized by comprising the following operations:
s1, acquiring time data, environment data and historical operation and maintenance data of a clock, performing standardized processing on the environment data after cleaning processing, performing normalized processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain key performance indexes;
s2, the key performance indexes are subjected to feature mapping processing to obtain feature data; the characteristic data are subjected to thermal coding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
s3, acquiring operation and maintenance cost and clock error of the operation and maintenance strategy, and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing the operation and maintenance strategy; if the operation and maintenance cost is higher than the cost range or the clock error is higher than the error range, executing S4;
s4, if the operation and maintenance cost is higher than the cost range, the clock error is not higher than the error range, and according to the priority level of the action in the operation and maintenance strategy, the action with the level larger than the level threshold is executed; and if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
2. The clock operation and maintenance method according to claim 1, wherein the key performance indicators include failure frequency, clock accuracy, temperature, humidity, supply voltage.
3. The method according to claim 1, wherein if the operation cost and clock error of the operation policy in S3 are lower than the cost range and the error range, the operation policy and the corresponding risk probability distribution information are placed in a historical experience revising area; and when the information entropy of the risk probability distribution information and the historical risk probability distribution information in the S2 is smaller than the entropy threshold value, directly executing a corresponding historical operation and maintenance strategy.
4. The clock operation and maintenance method according to claim 1, wherein a size and a stride of a sliding window are preset, the sliding window selecting a time sequence, and the feature extraction processing in S2 is performed together with a corresponding state vector.
5. The clock operation and maintenance method according to claim 1, wherein the operation and maintenance policy actions include: the fault maintenance, the clock parameter adjustment, the temperature adjustment, the humidity adjustment and the power supply voltage adjustment are sequentially and respectively set into a first grade, a second grade, a third grade, a fourth grade and a fifth grade from high to low.
6. The clock operation and maintenance method according to claim 1, wherein the operation of the feature mapping process of S2 is specifically:
and respectively matching the clock health state, the clock precision, the temperature, the humidity and the power supply voltage obtained based on the key performance indexes with corresponding preset classification rules, outputting corresponding classification values, and combining to obtain the characteristic data.
7. The clock operation and maintenance method according to claim 1, wherein the operation of obtaining the state vector in S2 is specifically:
and mapping all the classified values in the characteristic data to obtain a binary integer set, and connecting the binary integer set to obtain the state vector.
8. A clock operation and maintenance system based on clock networking, comprising:
the key performance index generation module is used for acquiring time data, environment data and historical operation and maintenance data of the clock, carrying out standardization processing on the environment data after cleaning processing, carrying out normalization processing on the time data and the historical operation and maintenance data to obtain a clock data set, and extracting the clock data set to obtain a key performance index;
the operation and maintenance strategy generation module is used for obtaining characteristic data through characteristic mapping processing of the key performance indexes; the characteristic data are subjected to thermal coding treatment, and a state vector is obtained after connection; the state vector is subjected to feature extraction processing to obtain risk probability distribution information; the risk probability distribution information is subjected to feature matching processing to obtain an operation and maintenance strategy;
the operation and maintenance strategy execution module is used for acquiring operation and maintenance cost and clock error of the operation and maintenance strategy and judging whether the operation and maintenance cost and the clock error are higher than a cost range and an error range; if the operation and maintenance cost and the clock error are not higher than the cost range and the error range, executing the operation and maintenance strategy; if the operation and maintenance cost is higher than a cost range or the clock error is higher than an error range, executing an operation and maintenance action executing module;
the operation and maintenance action execution module is used for executing actions with the level greater than a level threshold according to the priority level of the actions in the operation and maintenance strategy if the operation and maintenance cost is higher than a cost range and the clock error is not higher than an error range; and if the operation and maintenance cost is not higher than the cost range, the clock error is higher than the error range, and the server channel of the clock networking is changed.
9. An operation and maintenance device of a clock networking system, comprising a processor and a memory, wherein the processor implements the clock networking-based clock operation and maintenance method according to any one of claims 1-7 when executing a computer program stored in the memory.
10. A computer readable storage medium for storing a computer program, wherein the computer program when executed by a processor implements the clock networking based clock operation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311470786.9A CN117495350B (en) | 2023-11-06 | 2023-11-06 | Clock operation and maintenance method, system, equipment and storage medium based on clock networking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311470786.9A CN117495350B (en) | 2023-11-06 | 2023-11-06 | Clock operation and maintenance method, system, equipment and storage medium based on clock networking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117495350A true CN117495350A (en) | 2024-02-02 |
| CN117495350B CN117495350B (en) | 2024-05-24 |
Family
ID=89673924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311470786.9A Active CN117495350B (en) | 2023-11-06 | 2023-11-06 | Clock operation and maintenance method, system, equipment and storage medium based on clock networking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117495350B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110677210A (en) * | 2019-08-21 | 2020-01-10 | 华为技术有限公司 | Clock compensation method, equipment and system |
| CN112686568A (en) * | 2021-01-11 | 2021-04-20 | 南方电网数字电网研究院有限公司 | Operation and maintenance strategy generation processing method, device, system, equipment and storage medium |
| CN113722817A (en) * | 2021-08-08 | 2021-11-30 | 中国航空工业集团公司沈阳飞机设计研究所 | Distributed simulation system operation scheduling platform |
| CN114511112A (en) * | 2022-01-24 | 2022-05-17 | 北京通建泰利特智能系统工程技术有限公司 | Intelligent operation and maintenance method and system based on Internet of things and readable storage medium |
| WO2022127924A1 (en) * | 2020-12-18 | 2022-06-23 | 华为技术有限公司 | Method and device for selecting clock source |
| CN115587673A (en) * | 2022-11-10 | 2023-01-10 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state prediction method and system |
| CN116684031A (en) * | 2023-06-30 | 2023-09-01 | 南方电网电力科技股份有限公司 | Clock correction method and related device of intelligent electric energy meter |
-
2023
- 2023-11-06 CN CN202311470786.9A patent/CN117495350B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110677210A (en) * | 2019-08-21 | 2020-01-10 | 华为技术有限公司 | Clock compensation method, equipment and system |
| WO2022127924A1 (en) * | 2020-12-18 | 2022-06-23 | 华为技术有限公司 | Method and device for selecting clock source |
| CN112686568A (en) * | 2021-01-11 | 2021-04-20 | 南方电网数字电网研究院有限公司 | Operation and maintenance strategy generation processing method, device, system, equipment and storage medium |
| CN113722817A (en) * | 2021-08-08 | 2021-11-30 | 中国航空工业集团公司沈阳飞机设计研究所 | Distributed simulation system operation scheduling platform |
| CN114511112A (en) * | 2022-01-24 | 2022-05-17 | 北京通建泰利特智能系统工程技术有限公司 | Intelligent operation and maintenance method and system based on Internet of things and readable storage medium |
| CN115587673A (en) * | 2022-11-10 | 2023-01-10 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state prediction method and system |
| CN116684031A (en) * | 2023-06-30 | 2023-09-01 | 南方电网电力科技股份有限公司 | Clock correction method and related device of intelligent electric energy meter |
Non-Patent Citations (1)
| Title |
|---|
| 王波;石泽琼;史亚萍;董言治;: "基于钟联网的公共时钟诊断服务系统设计", 物联网技术, no. 08, 20 August 2017 (2017-08-20), pages 100 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117495350B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021129086A1 (en) | Traffic prediction method, device, and storage medium | |
| CN114116828A (en) | Association rule analysis method, device and storage medium for multidimensional network index | |
| CN111881961A (en) | Power distribution network fault risk grade prediction method based on data mining | |
| CN112614010A (en) | Load prediction method and device, storage medium and electronic device | |
| CN111598457A (en) | Method and device for determining quality of power wireless network | |
| CN117311295B (en) | Production quality improving method and system based on wireless network equipment | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN117495350B (en) | Clock operation and maintenance method, system, equipment and storage medium based on clock networking | |
| CN107666403B (en) | Index data acquisition method and device | |
| WO2024066720A1 (en) | Indicator threshold determination method and apparatus, storage medium, and electronic apparatus | |
| CN110995396B (en) | Compression method of communication messages of electricity consumption information acquisition system based on hierarchical structure | |
| CN112508254A (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN112307648A (en) | Method for evaluating reliability model of satellite communication system | |
| CN112561388A (en) | Information processing method, device and equipment based on Internet of things | |
| CN116029491B (en) | Power dispatching management system and control method thereof | |
| CN110582091B (en) | Method and apparatus for locating wireless quality problems | |
| CN114756722B (en) | Multi-data centralized management control system and method | |
| CN112101798A (en) | Power equipment service life management method based on big data technology | |
| CN114580758B (en) | Multi-city automatic energy load prediction method and system | |
| CN112749513B (en) | Intelligent unified method of power supply module | |
| CN110687346A (en) | Method for checking and optimizing power grid voltage abnormity reason data | |
| CN113656267B (en) | Device energy efficiency calculation method and device, electronic device and storage medium | |
| WO2022156743A1 (en) | Feature construction method and apparatus, model training method and apparatus, and device and medium | |
| CN115392615A (en) | Data missing value completion method and system for generating countermeasure network based on information enhancement | |
| CN114861869A (en) | Method and terminal for rapidly positioning optimal level of deep convolutional network |
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 |