CN117687884A - Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station - Google Patents
Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station Download PDFInfo
- Publication number
- CN117687884A CN117687884A CN202311744667.8A CN202311744667A CN117687884A CN 117687884 A CN117687884 A CN 117687884A CN 202311744667 A CN202311744667 A CN 202311744667A CN 117687884 A CN117687884 A CN 117687884A
- Authority
- CN
- China
- Prior art keywords
- execution
- data
- ticket
- maintenance
- power grid
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012423 maintenance Methods 0.000 title claims abstract description 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 71
- 238000012544 monitoring process Methods 0.000 claims abstract description 47
- 238000010801 machine learning Methods 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 24
- 230000007246 mechanism Effects 0.000 claims abstract description 23
- 230000004044 response Effects 0.000 claims description 43
- 238000004458 analytical method Methods 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 40
- 230000005856 abnormality Effects 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 23
- 238000001514 detection method Methods 0.000 claims description 18
- 238000007619 statistical method Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 10
- 230000001419 dependent effect Effects 0.000 claims description 10
- 238000013468 resource allocation Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000006978 adaptation Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000000611 regression analysis Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000005096 rolling process Methods 0.000 claims description 4
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 abstract description 6
- 230000002265 prevention Effects 0.000 abstract description 4
- 238000003860 storage Methods 0.000 description 14
- 238000003909 pattern recognition Methods 0.000 description 9
- 230000002068 genetic effect Effects 0.000 description 7
- 230000001965 increasing effect Effects 0.000 description 5
- 238000002922 simulated annealing Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000013499 data model Methods 0.000 description 4
- 238000012067 mathematical method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000001934 delay Effects 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000012896 Statistical algorithm Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An intelligent optimization method and system for operation and maintenance operation tickets of a power grid dispatching automation master station comprises the following steps: step 1: an intelligent optimization module is introduced into an operation ticket system of an operation and maintenance automatic main station of power grid dispatching, and the execution process of the operation ticket is monitored and optimized in real time; step 2: automatically adjusting the execution sequence of the operation ticket by monitoring the system state and the operation ticket execution condition in real time; step 3: continuously learning and optimizing the operation steps by utilizing a historical operation record and a machine learning algorithm; step 4: an exception handling mechanism is added to rapidly respond and handle the emergency exception; step 5: and the system data is counted and analyzed, so that the prediction accuracy is improved, and the support is improved for operation and maintenance personnel. Through the solution of automatic, high-efficiency and low-risk maintenance scheduling automatic system software, the functions of automatic execution, batch execution, error checking prevention, result checking, history record and the like of the scheduling automatic system operation ticket are realized, and the system operation maintenance efficiency is improved.
Description
Technical Field
The invention belongs to the field of machine learning, and particularly relates to an intelligent optimization method and system for operation and maintenance operation tickets of an automatic main station of power grid dispatching.
Background
With the continuous improvement of the automation degree of power grid dispatching, the operation and maintenance workload is gradually increased, and the traditional operation and maintenance mode cannot meet the requirements of high efficiency and accuracy. Therefore, the invention provides an intelligent optimization method based on a machine learning algorithm, aiming at improving the working efficiency and performance of an operation ticket system of a power grid dispatching automation master station.
In this context, the operation and maintenance work of the grid dispatching automation master is facing increasing challenges. The traditional operation and maintenance mode cannot meet the high-efficiency and accurate requirements of the modern power grid, so that a more advanced method is needed to be searched for to improve the working efficiency and the performance of the operation and maintenance operation ticket system.
Prior art document 1 (CN 111178699B) discloses a method for constructing a scheduling operation ticket intelligent checking system, which combines a reorganized scheduling ticket data model M2 with an acquired scheduling ticket data model M1 to form a data model M3; the data model M3 is calculated using a rule learning algorithm and a rule base is generated. The disadvantage of the prior art document 1 is that the prior art document 1 is mainly used for intelligent checking of the operation of primary equipment (such as switches, lines, buses, transformers, etc.) of the power grid. The prior art is not effectively applicable to the management of automation system software. The software operation comprises complex logic processing and diversified interaction modes, and is far more complex and variable than the operation of the entity equipment. The prior art lacks understanding and processing capabilities of the operating characteristics of software and cannot adapt to changing software environments and requirements. And the prior art fails to provide functions of real-time monitoring and automatic adjustment of operation and maintenance of an automatic main station for power grid dispatching, and fails to feed back system states and operation execution conditions in real time.
The prior art document 2 (CN 102751785B) provides a modular sequence control system and its implementation method, where the operation ticket acquisition module acquires the operation content and transmits the information of the operation content to the operation configuration module, the operation configuration module transmits the information to the operation simulation module to perform correctness checking, if the configuration is correct, the information is returned to the state monitoring module to perform specific operation control, and if the configuration is incorrect, the information is returned to the operation control module to perform modification; the five-prevention locking association module obtains the results of each single-step operation five-prevention locking and transmits the results to the state monitoring module, and after the five-prevention locking meets the operation requirement, the sequence control system can send GOOSE linkage information to the controlled equipment through the video linkage module, and the operation record inquiry module records the history and log of the success or failure of the operation. The disadvantage of the prior art document 2 is the lack of dynamic adjustment capability: the system can not provide a function of automatically adjusting the execution sequence, can not adjust the execution sequence of the operation ticket in real time according to the system state and the operation execution condition, can meet the execution requirement of the operation ticket of the primary equipment of the power grid, but can not meet the requirement on the condition that the running environment and the condition of the automatic system software are continuously changed, and can dynamically adjust the operation sequence, so that the improvement of the efficiency and the adaptability of the operation ticket is important; optimization is not performed using machine learning: the technology does not adopt a machine learning algorithm to continuously learn and optimize operation steps, which means that the technology cannot automatically adapt to new situations or optimize operation strategies; the exception handling mechanism is not enough: although the system has an operation record query module to record the success or failure of an operation, there is a lack of effective exception handling mechanisms to quickly respond to and handle sudden exceptions, which may result in reduced stability and reliability of the system.
Disclosure of Invention
The invention provides an intelligent optimization method and system for operation and maintenance operation tickets of a power grid dispatching automation master station, aiming at solving the problems of working efficiency and performance of the operation and maintenance operation ticket system of the power grid dispatching automation master station. Through the solution of automatic, high-efficiency and low-risk maintenance scheduling automatic system software, the functions of automatic execution, batch execution, error checking prevention, result checking, history record and the like of the scheduling automatic system operation ticket are realized, and the system operation maintenance efficiency is improved. Meanwhile, the scheme has good universality and can be applied to other similar distributed systems.
The invention adopts the following technical scheme.
The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station is characterized by comprising the following steps of:
step 1: an intelligent optimization module is introduced into an operation ticket system of an operation and maintenance automatic main station of power grid dispatching, and the execution process of the operation ticket is monitored and optimized in real time;
step 2: automatically adjusting the execution sequence of the operation ticket by monitoring the system state and the operation ticket execution condition in real time;
step 3: continuously learning and optimizing the operation steps by utilizing a historical operation record and a machine learning algorithm;
Step 4: an exception handling mechanism is added to rapidly respond and handle the emergency exception;
step 5: and the system data is counted and analyzed, so that the prediction accuracy is improved, and the support is improved for operation and maintenance personnel.
In step 1:
the intelligent optimization module comprises:
real-time monitoring unit: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
decision support unit: based on the data analysis result, an optimization algorithm is utilized to provide decision support for the operation ticket execution process, including execution sequence adjustment and resource allocation;
learning and adaptation unit: learning historical operation data by adopting a machine learning algorithm to realize continuous optimization and self-adaptive adjustment of an operation process;
an abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected;
data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
The step 2 is to automatically adjust the execution sequence of the operation ticket by monitoring the system state and the execution condition of the operation ticket in real time, and the method specifically comprises the following steps:
firstly, according to key indexes obtained by real-time monitoring, including system performance indexes, operation execution indexes and resource use conditions, the priority of the operation is estimated based on the indexes, and the execution sequence of the operation ticket is automatically adjusted according to the obtained priority and the dependency relationship between the operations.
The system performance index comprises: the system performance index comprises processing capacity and response time;
the operation execution index comprises an execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
the dependencies include direct dependencies and indirect dependencies:
the direct dependency, i.e. some operational steps, may depend directly on the completion of a previous step;
the indirect dependencies, i.e., certain operations, while not logically directly dependent, are indirectly related due to shared resources or other factors.
The evaluation formula of the operation priority is as follows:
wherein O is operation priority, and the system performance index, the operation execution index and the resource use index are respectively n, m and l, P i 、E j 、R k Respectively representing an ith system performance index, a jth operation execution index and a kth resource use index;the weights of the indexes are respectively, alpha, beta and delta are respectively the balance coefficients of a system performance index, an operation execution index and a resource use index, and epsilon is a preset constant.
The key indexes of the real-time monitoring comprise: system performance index, operation execution index and resource use condition;
wherein the system performance index includes processing capacity and response time;
the operation execution indexes comprise execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
flow and algorithm for adjusting execution sequence of operation ticket:
priority assessment: evaluating the priority of the operation according to the urgency, the influence range and the resource requirement of the operation; priority assessment mainly depends on the following judgment conditions:
influence range: considering the range of influence of operations on the system, operations with wide range of influence may need to be preferentially executed to avoid potential system-level problems;
resource requirements: determining priority according to the demand of the operation on the resource, wherein the operation with high demand of the resource may need to be processed preferentially so as to ensure the effective utilization of the system resource;
Duration of operation: for operations that take longer, it may be necessary to schedule appropriate execution opportunities based on the current state and future predicted state of the system;
historical data and pattern recognition: identifying which operation types generally require preferential treatment through historical operation data analysis;
dependency analysis: analyzing the dependency relationship among the operations, ensuring that the dependency condition is not violated when the sequence is adjusted, wherein the dependency relationship is divided into a direct dependency relationship and an indirect dependency relationship:
direct dependency relationship: some operational steps may depend directly on the completion of the previous step,
indirect dependency relationship: some operations, while not directly logically dependent, may be indirectly related due to shared resources or other factors;
there are several ways to handle dependencies:
rule engine: judging the priority of the operation and the processing dependency relationship based on a predefined rule;
optimization algorithm: automatically calculating an optimal execution sequence by using a mathematical method;
the machine learning method comprises the following steps: dynamically adjusting priorities and processing dependencies using historical data and pattern recognition techniques;
dynamic adjustment algorithm: and a genetic algorithm and a simulated annealing optimization algorithm are applied, and the operation sequence is dynamically adjusted according to the real-time data, so that the overall efficiency and stability are improved.
The step 3 uses a history operation record and a machine learning algorithm to continuously learn and optimize operation steps specifically include:
data preparation: collecting historical operation records, and performing data cleaning and standardization treatment;
characteristic engineering: extracting key features including operation type, execution duration, program output and result state;
model selection and training: selecting a proper model and training by using historical data;
performance evaluation and optimization: and evaluating the performance of the model through the verification set and the test set, and optimizing the model according to feedback.
Step 4 adds an exception handling mechanism, and the fast response and handling of the emergency exception specifically includes:
abnormality detection: real-time monitoring the running state of the system by utilizing an algorithm and a predefined rule to identify an abnormal mode;
abnormality classification: classifying the detected anomalies, including system performance anomalies, operation execution anomalies, system faults, network problems, specifically as follows:
abnormal system performance: the CPU utilization rate exceeds 100% for more than 5 minutes, and the time for executing the command exceeds the history by more than 50%;
operation execution exception: the method comprises the steps of operation failure and inconsistent execution results;
System failure: the integral operation environment of the platform is failed;
data anomalies: data corruption, data loss, data format errors;
response strategy: defining corresponding processing strategies for different types of anomalies, including automatic retry, system rollback, alarm notification, manual intervention, and the following:
abnormal system performance: automatically retrying, checking whether the performance abnormality is an occasional factor, stopping operation if the performance abnormality occurs for a plurality of times, and notifying the manual intervention by an alarm;
operation execution exception: automatically rolling back and optimizing an execution strategy;
system failure: the integral operation environment of the platform fails to be executed, and the alarm notification is manually interfered;
data anomalies: data corruption, data loss, data format errors, automatic rollback and optimization of the execution policy.
And 5, carrying out statistics and analysis on the system data, improving the prediction accuracy, and improving the support for operation and maintenance personnel specifically comprises the following steps:
and 5, carrying out statistics and analysis on the system data, improving the prediction accuracy, and improving the support for operation and maintenance personnel specifically comprises the following steps:
automatically collecting operation and maintenance operation ticket data from a power grid dispatching system every day, including starting and ending time of operation, related resources, fault occurrence conditions and the like, and eliminating abnormal data by using a data cleaning technology;
Performing basic statistical analysis on the cleaned data, calculating average completion time, standard deviation and the like of the operation to know the overall condition of the operation efficiency, counting average time consumption of each operation type, and prompting that the flow efficiency problem possibly exists for the operation with time consumption exceeding a preset value;
displaying the completion time distribution of different operation types by using the histogram and the box diagram;
analyzing the relation between the resource usage and the operation completion time by using regression analysis;
and adjusting the operation flow or the resource allocation according to the analysis result, and continuously monitoring the adjustment effect.
The application simultaneously discloses a grid dispatching automation master station operation and maintenance operation ticket intelligent optimization system based on the method comprises an intelligent optimization module and is characterized in that:
the intelligent optimization module comprises a real-time monitoring unit, a decision support unit, a learning and self-adapting unit, an abnormality detection and response unit and a data statistics analysis unit;
the real-time monitoring unit is used for: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
the decision support unit: based on the data analysis result, an optimization algorithm is utilized to provide decision support for the operation ticket execution process, including execution sequence adjustment and resource allocation;
The learning and adaptation unit: learning historical operation data by adopting a machine learning algorithm to realize continuous optimization and self-adaptive adjustment of an operation process;
the abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected;
the data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
Compared with the prior art, the intelligent optimization method based on the machine learning algorithm provided by the invention aims to solve the problems of working efficiency and performance of an operation ticket system of an operation and maintenance master station of power grid dispatching automation. Through the solution of automatic, high-efficiency and low-risk maintenance scheduling automatic system software, the functions of automatic execution, batch execution, error checking prevention, result checking, history record and the like of the scheduling automatic system operation ticket are realized, and the system operation maintenance efficiency is improved. Meanwhile, the scheme has good universality and can be applied to other similar distributed systems.
Compared with the manual intervention mode in the prior art, the intelligent optimization method based on the machine learning algorithm is adopted, so that the operation steps can be automatically learned and optimized, and the accuracy and efficiency of the operation are improved. In addition, the invention also has built-in exception handling mechanism, can respond to and deal with the sudden abnormal situation fast, guarantee the steady operation of the system. By carrying out statistics and analysis on the system data, decision support is provided for operation and maintenance personnel, and the method is helpful for finding and solving the problems in the system.
In conclusion, the method has high practical value and application prospect, and provides a new thought and method for optimizing the operation ticket system of the power grid dispatching automation master station.
Drawings
FIG. 1 is a flow chart of the optimization method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. The embodiments described herein are merely some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art without making any inventive effort, are within the scope of the present invention.
The specific implementation mode of the invention is as follows:
an intelligent optimization method for operation and maintenance operation tickets of a power grid dispatching automation master station, as shown in figure 1,
the method specifically comprises the following steps:
step 1: an intelligent optimization module is introduced into an operation ticket system of an operation and maintenance automatic main station of power grid dispatching, and the execution process of the operation ticket is monitored and optimized in real time;
step 2: automatically adjusting the execution sequence of the operation ticket by monitoring the system state and the operation ticket execution condition in real time;
step 3: continuously learning and optimizing the operation steps by utilizing a historical operation record and a machine learning algorithm;
step 4: an exception handling mechanism is added to rapidly respond and handle the emergency exception;
step 5: and the system data is counted and analyzed, so that the prediction accuracy is improved, and the support is improved for operation and maintenance personnel.
In step 1:
the intelligent optimization module comprises:
real-time monitoring unit: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
decision support unit: based on the data analysis result, an optimization algorithm comprising a genetic algorithm and a simulated annealing algorithm is utilized to provide decision support for the operation ticket execution process, wherein the decision support comprises execution sequence adjustment and resource allocation;
Learning and adaptation unit: the machine learning algorithm comprises a vector machine and a neural network for learning historical operation data, so that continuous optimization and self-adaptive adjustment of an operation process are realized;
an abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected; including automatically isolating the fault area, starting the standby system, etc.
Data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
The step 2 is to automatically adjust the execution sequence of the operation ticket by monitoring the system state and the execution condition of the operation ticket in real time, and the method specifically comprises the following steps:
the step 2 is to automatically adjust the execution sequence of the operation ticket by monitoring the system state and the execution condition of the operation ticket in real time, and the method specifically comprises the following steps:
firstly, according to key indexes obtained by real-time monitoring, including system performance indexes, operation execution indexes and resource use conditions, the priority of the operation is estimated based on the indexes, and the execution sequence of the operation ticket is automatically adjusted according to the obtained priority and the dependency relationship between the operations.
The system performance index comprises: the system performance index comprises processing capacity and response time;
the operation execution index comprises an execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
the dependencies include direct dependencies and indirect dependencies:
the direct dependency, i.e. some operational steps, may depend directly on the completion of a previous step;
the indirect dependencies, i.e., certain operations, while not logically directly dependent, are indirectly related due to shared resources or other factors.
The evaluation formula of the operation priority is as follows:
wherein O is operation priority, and the system performance index, the operation execution index and the resource use index are respectively n, m and l, P i 、E j 、R k Respectively representing an ith system performance index, a jth operation execution index and a kth resource use index;the weights of the indexes are respectively, alpha, beta and delta are respectively the balance coefficients of a system performance index, an operation execution index and a resource use index, and epsilon is a preset constant.
The key indexes of the real-time monitoring comprise: system performance index, operation execution index, resource usage;
wherein the system performance index includes processing capacity and response time;
The operation execution indexes comprise execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
flow and algorithm for adjusting execution sequence of operation ticket:
priority assessment: the priority of the operation is evaluated according to the urgency, the influence range and the resource requirement of the operation. Priority assessment mainly depends on the following judgment conditions:
influence range: consider the range of impact of an operation on a system. A wide range of operations may need to be performed preferentially to avoid potential system-level problems;
resource requirements: the priority is determined based on the operational demand for resources including computing resources, network bandwidth. Operations with high resource requirements may require priority handling to ensure efficient utilization of system resources;
duration of operation: for operations that take longer, it may be necessary to schedule appropriate execution opportunities based on the current state and future predicted state of the system;
historical data and pattern recognition: identifying which operation types generally require preferential treatment through historical operation data analysis;
dependency analysis: analyzing the dependency relationship among the operations, ensuring that the dependency condition is not violated when the sequence is adjusted, wherein the dependency relationship is divided into a direct dependency relationship and an indirect dependency relationship:
Direct dependency relationship: some of the operational steps may depend directly on the completion of the previous step. For example, a modification of a certain configuration must be made after another operation is completed;
indirect dependency relationship: some operations, while not directly logically dependent, may be indirectly related due to shared resources or other factors;
there are several ways to handle dependencies:
rule engine: judging the priority of the operation and the processing dependency relationship based on a predefined rule;
optimization algorithm: automatically calculating an optimal execution sequence by using a mathematical method comprising a graph theory algorithm and a linear programming;
the machine learning method comprises the following steps: dynamically adjusting priorities and processing dependencies using historical data and pattern recognition techniques;
dynamic adjustment algorithm: and a genetic algorithm and a simulated annealing optimization algorithm are applied, and the operation sequence is dynamically adjusted according to the real-time data, so that the overall efficiency and stability are improved.
Wherein the system performance index includes processing capacity and response time;
the operation execution indexes comprise execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
flow and algorithm for adjusting execution sequence of operation ticket:
Priority assessment: evaluating the priority of the operation according to the urgency, the influence range and the resource requirement of the operation; priority assessment mainly depends on the following judgment conditions:
influence range: considering the range of influence of operations on the system, operations with wide range of influence may need to be preferentially executed to avoid potential system-level problems;
resource requirements: determining priority according to the demand of the operation on the resource, wherein the operation with high demand of the resource may need to be processed preferentially so as to ensure the effective utilization of the system resource;
duration of operation: for operations that take longer, it may be necessary to schedule appropriate execution opportunities based on the current state and future predicted state of the system;
historical data and pattern recognition: identifying which operation types generally require preferential treatment through historical operation data analysis;
dependency analysis: analyzing the dependency relationship among the operations, ensuring that the dependency condition is not violated when the sequence is adjusted, wherein the dependency relationship is divided into a direct dependency relationship and an indirect dependency relationship:
direct dependency relationship: some operational steps may depend directly on the completion of the previous step,
indirect dependency relationship: some operations, while not directly logically dependent, may be indirectly related due to shared resources or other factors;
There are several ways to handle dependencies:
rule engine: judging the priority of the operation and the processing dependency relationship based on a predefined rule;
optimization algorithm: automatically calculating an optimal execution sequence by using a mathematical method;
the machine learning method comprises the following steps: dynamically adjusting priorities and processing dependencies using historical data and pattern recognition techniques;
dynamic adjustment algorithm: and a genetic algorithm and a simulated annealing optimization algorithm are applied, and the operation sequence is dynamically adjusted according to the real-time data, so that the overall efficiency and stability are improved.
System performance index
Processing power: when the CPU occupancy reaches or exceeds 80%, it indicates that the system throughput is approaching a limit. At this time, those operations requiring less CPU should be preferentially performed to reduce the CPU load.
Response time: if the average response time of the system exceeds 2 seconds, this indicates that the system is slow. Operations that optimize the response time of the system, such as adding caches, optimizing queries, etc., should be prioritized.
Operation execution index
Execution progress: for operations that fall behind schedule, such as delays exceeding a predetermined time of 50%, the priority should be raised to ensure completion on time.
Error rate: if the operation error rate exceeds 5%, the priority of the investigation and correction should be immediately increased to reduce the influence of the error on the system.
Resource usage
Memory occupation: when the memory occupation exceeds 80% or a specific value such as 4GB, the operation with low memory requirement should be preferentially processed or the memory cleaning and optimization should be executed.
Network bandwidth: when the network bandwidth utilization exceeds 70%, the operation with lower network bandwidth requirement is preferentially executed, and the network load is reduced.
Specific scene and method for sequential adjustment
Adjustment in emergency situations
High load conditions: when the CPU or memory occupation is continuously over 80%, the priority is immediately adjusted, and the priority of the operation on the resource intensive type is reduced.
The response time is too long: if the system response time lasts more than 2 seconds, the operation capable of rapidly improving the response speed, such as performance optimization, resource reallocation and the like, is preferentially performed.
Adjustment under resource constraints
Memory tension: when the memory occupation exceeds 80% or 4GB, the operation sequence is immediately adjusted, and the operation related to the memory optimization is preferentially executed.
Network congestion: when the network bandwidth usage exceeds 70%, the operation with lower bandwidth demand is preferentially performed, or the operation with high bandwidth demand is performed in a period with lower bandwidth usage.
Adjustment of operational dependencies
Analyzing dependencies between operations ensures that direct or indirect dependency conditions between operations are not violated.
And on the premise of not influencing the dependent conditions, adjusting the priority and the execution sequence according to the indexes.
Description of the embodiments
Rule engine
And establishing a set of rule system, and automatically triggering priority adjustment when the key index is monitored to reach a preset threshold value.
For example, when the CPU occupancy exceeds 80%, the priority of the resource intensive operations is automatically reduced.
Optimization algorithm
Mathematical models and algorithms (e.g., linear programming, genetic algorithms) are used to calculate the optimal execution order of the operations.
The priority of the operation is updated in real time in consideration of the real-time data and the history.
Machine learning method
The priority of the operation is predicted and adjusted by machine learning algorithms (e.g., decision trees, neural networks) using historical operational data and real-time monitoring data.
The machine learning model may dynamically adjust the order of operations based on real-time performance and historical data of the system. The step 3 uses a history operation record and a machine learning algorithm to continuously learn and optimize operation steps specifically include:
data preparation: collecting historical operation records, and performing data cleaning and standardization treatment;
characteristic engineering: extracting key features such as operation type, execution time, program output, result state and the like;
Model selection and training: selecting a proper model and training by using historical data;
performance evaluation and optimization: and evaluating the performance of the model through the verification set and the test set, and optimizing the model according to feedback.
Step 4 adds an exception handling mechanism, and the fast response and handling of the emergency exception specifically includes:
abnormality detection: the system operation state is monitored in real time by utilizing algorithms including a statistical method, machine learning and predefined rules to identify abnormal modes.
Abnormality classification: classifying the detected anomalies, such as system performance anomalies, operation execution anomalies, system faults, network problems, and the like, specifically as follows:
abnormal system performance: if the CPU utilization rate exceeds 100% for more than 5 minutes, the time for executing the command exceeds the history by more than 50%;
operation execution exception: including operation failure, inconsistent execution results, etc.;
system failure: the whole operation environment of the platform is faulty, etc.;
data anomalies: data corruption, data loss, data format errors, etc.;
response strategy: defining corresponding processing strategies for different types of anomalies, including automatic retry, system rollback, alarm notification, manual intervention, and the following:
Abnormal system performance: automatically retrying, checking whether the performance abnormality is an occasional factor, stopping operation if the performance abnormality occurs for a plurality of times, and notifying the manual intervention by an alarm;
operation execution exception: automatically rolling back and optimizing an execution strategy;
system failure: the integral operation environment of the platform fails to be executed, and the alarm notification is manually interfered;
data anomalies: data corruption, data loss, data format errors, etc., automatically rollback and optimize the execution policy.
Wherein the system performance index includes processing capacity and response time;
the operation execution indexes comprise execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
flow and algorithm for adjusting execution sequence of operation ticket:
priority assessment: evaluating the priority of the operation according to the urgency, the influence range and the resource requirement of the operation; priority assessment mainly depends on the following judgment conditions:
influence range: considering the range of influence of operations on the system, operations with wide range of influence may need to be preferentially executed to avoid potential system-level problems;
resource requirements: determining priority according to the demand of the operation on the resource, wherein the operation with high demand of the resource may need to be processed preferentially so as to ensure the effective utilization of the system resource;
Duration of operation: for operations that take longer, it may be necessary to schedule appropriate execution opportunities based on the current state and future predicted state of the system;
historical data and pattern recognition: identifying which operation types generally require preferential treatment through historical operation data analysis;
dependency analysis: analyzing the dependency relationship among the operations, ensuring that the dependency condition is not violated when the sequence is adjusted, wherein the dependency relationship is divided into a direct dependency relationship and an indirect dependency relationship:
direct dependency relationship: some operational steps may depend directly on the completion of the previous step,
indirect dependency relationship: some operations, while not directly logically dependent, may be indirectly related due to shared resources or other factors;
there are several ways to handle dependencies:
rule engine: judging the priority of the operation and the processing dependency relationship based on a predefined rule;
optimization algorithm: automatically calculating an optimal execution sequence by using a mathematical method;
the machine learning method comprises the following steps: dynamically adjusting priorities and processing dependencies using historical data and pattern recognition techniques;
dynamic adjustment algorithm: and a genetic algorithm and a simulated annealing optimization algorithm are applied, and the operation sequence is dynamically adjusted according to the real-time data, so that the overall efficiency and stability are improved.
System performance index
Processing power: when the CPU occupancy reaches or exceeds 80%, it indicates that the system throughput is approaching a limit. At this time, those operations requiring less CPU should be preferentially performed to reduce the CPU load.
Response time: if the average response time of the system exceeds 2 seconds, this indicates that the system is slow. Operations that optimize the response time of the system, such as adding caches, optimizing queries, etc., should be prioritized.
Operation execution index
Execution progress: for operations that fall behind schedule, such as delays exceeding a predetermined time of 50%, the priority should be raised to ensure completion on time.
Error rate: if the operation error rate exceeds 5%, the priority of the investigation and correction should be immediately increased to reduce the influence of the error on the system.
Resource usage
Memory occupation: when the memory occupation exceeds 80% or a specific value such as 4GB, the operation with low memory requirement should be preferentially processed or the memory cleaning and optimization should be executed.
Network bandwidth: when the network bandwidth utilization exceeds 70%, the operation with lower network bandwidth requirement is preferentially executed, and the network load is reduced.
Specific scene and method for sequential adjustment
Adjustment in emergency situations
High load conditions: when the CPU or memory occupation is continuously over 80%, the priority is immediately adjusted, and the priority of the operation on the resource intensive type is reduced.
The response time is too long: if the system response time lasts more than 2 seconds, the operation capable of rapidly improving the response speed, such as performance optimization, resource reallocation and the like, is preferentially performed.
Adjustment under resource constraints
Memory tension: when the memory occupation exceeds 80% or 4GB, the operation sequence is immediately adjusted, and the operation related to the memory optimization is preferentially executed.
Network congestion: when the network bandwidth usage exceeds 70%, the operation with lower bandwidth demand is preferentially performed, or the operation with high bandwidth demand is performed in a period with lower bandwidth usage.
Adjustment of operational dependencies
Analyzing dependencies between operations ensures that direct or indirect dependency conditions between operations are not violated.
And on the premise of not influencing the dependent conditions, adjusting the priority and the execution sequence according to the indexes.
Description of the embodiments
Rule engine
And establishing a set of rule system, and automatically triggering priority adjustment when the key index is monitored to reach a preset threshold value.
For example, when the CPU occupancy exceeds 80%, the priority of the resource intensive operations is automatically reduced.
Optimization algorithm
Mathematical models and algorithms (e.g., linear programming, genetic algorithms) are used to calculate the optimal execution order of the operations.
The priority of the operation is updated in real time in consideration of the real-time data and the history.
Machine learning method
The priority of the operation is predicted and adjusted by machine learning algorithms (e.g., decision trees, neural networks) using historical operational data and real-time monitoring data.
The machine learning model may dynamically adjust the order of operations based on real-time performance and historical data of the system.
And 5, carrying out statistics and analysis on the system data, improving the prediction accuracy, and improving the support for operation and maintenance personnel specifically comprises the following steps:
statistical analysis flow:
1. data collection and cleansing
Operation and maintenance operation ticket data are automatically collected from the power grid dispatching system every day, wherein the operation and maintenance operation ticket data comprise the starting and ending time of operation, related resources, fault occurrence conditions and the like. Abnormal data is culled using a data cleansing technique, such as data whose operating time is not within a normal range (e.g., records of less than 1 minute or more than 24 hours) is marked as abnormal and excluded.
2. Basic statistical analysis
Performing basic statistical analysis on the cleaned data, calculating the average completion time, standard deviation and the like of the operation to understand the overall condition of the operation efficiency, counting the average time consumption of each operation type, and prompting that the time consumption is obviously higher than that of other types of operation, wherein the problem of flow efficiency possibly exists.
3. Data visualization
The histogram and box plot are used to show the completion time distribution for different operation types. For example, finding that certain operation types fluctuate widely in the completion time of certain periods through the box plot suggests that these periods may have resource malallocation or operation peaking problems.
4. Correlation and regression analysis
Regression analysis was used to explore the relationship between resource usage and time of completion of the operation. For example, finding that the resource usage is positively correlated with the operation delay time by linear regression suggests that resource under-allocation may be one cause of the operation delay.
5. Improved measure implementation and effect monitoring
And adjusting the operation flow or the resource allocation according to the analysis result, and continuously monitoring the adjustment effect. For example, for operations that are too time consuming, the execution flow is adjusted and the necessary waiting time is reduced, and then the impact of these adjustments on the overall operating efficiency is monitored.
Through the detailed statistical analysis flow, various problems in operation of the operation and maintenance operation ticket of the power grid dispatching automation master station can be deeply checked, and effective improvement measures can be adopted based on data-driven hole finding, so that the overall operation and maintenance efficiency and the system stability are improved.
Algorithm for data statistics
Descriptive statistical algorithm: for providing a basic description of the data, such as mean, median, standard deviation, etc. The method is suitable for primarily knowing the data characteristics.
Time series analysis: for analyzing time-varying data, such as trends in performance indicators of an automation system over time.
Regression analysis: for determining a relationship between one or more independent variables including the number of operations, the system load, and the dependent variables including the system performance.
And (3) cluster analysis: for grouping data to discover natural distributions or patterns in the data.
Association rule learning: for discovering associations between data items, such as associations between the execution of certain operations and particular types of system exceptions.
Content of analysis:
operational efficiency analysis: the completion time, latency, etc. of the operation is analyzed to identify efficiency bottlenecks.
Failure rate analysis: and counting the frequency, type and distribution of system faults, and identifying high-risk areas.
Resource usage analysis: analyzing the use of resources (such as CPU and memory) and identifying overload or deficiency.
System stability analysis: the system performance indicators, such as response time, system load, etc., are monitored over a long period of time.
The application also discloses an intelligent optimizing system of the operation ticket of the power grid dispatching automation master station based on the method, which comprises an intelligent optimizing module,
The intelligent optimization module comprises a real-time monitoring unit, a decision support unit, a learning and self-adapting unit, an abnormality detection and response unit and a data statistics analysis unit;
the real-time monitoring unit is used for: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
the decision support unit: based on the data analysis result, an optimization algorithm is utilized to provide decision support for the operation ticket execution process, including execution sequence adjustment and resource allocation;
the learning and adaptation unit: learning historical operation data by adopting a machine learning algorithm to realize continuous optimization and self-adaptive adjustment of an operation process;
the abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected;
the data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
Compared with the prior art, the intelligent optimization method based on the machine learning algorithm provided by the invention aims to solve the problems of working efficiency and performance of an operation ticket system of an operation and maintenance master station of power grid dispatching automation. Through the solution of automatic, high-efficiency and low-risk maintenance scheduling automatic system software, the functions of automatic execution, batch execution, error checking prevention, result checking, history record and the like of the scheduling automatic system operation ticket are realized, and the system operation maintenance efficiency is improved. Meanwhile, the scheme has good universality and can be applied to other similar distributed systems.
Compared with the manual intervention mode in the prior art, the intelligent optimization method based on the machine learning algorithm is adopted, so that the operation steps can be automatically learned and optimized, and the accuracy and efficiency of the operation are improved. In addition, the invention also has built-in exception handling mechanism, can respond to and deal with the sudden abnormal situation fast, guarantee the steady operation of the system. By carrying out statistics and analysis on the system data, decision support is provided for operation and maintenance personnel, and the method is helpful for finding and solving the problems in the system.
The invention introduces a comprehensive intelligent optimization module which comprises a real-time monitoring unit, a decision support unit, a learning and self-adapting unit, an abnormality detection and response unit and a data statistics analysis unit. The module not only comprises data processing and rule application, but also fuses complex event processing, machine learning and optimizing algorithms, and provides comprehensive intelligent support for operation ticket execution.
The invention utilizes a machine learning algorithm and combines historical operation data and a pattern recognition technology to realize continuous optimization and self-adaptive adjustment of an operation process, and realizes dynamic adjustment and self-adaptive learning which are not found in the prior art.
The exception handling mechanism in the invention can rapidly identify and respond to the exception state of the system, and adopts an automatic strategy to perform effective intervention, thereby improving the overall stability and reliability of the system and establishing an efficient exception handling mechanism.
Compared with the prior art, the system can better adapt to the continuously-changing operation and maintenance environment through dynamic learning and self-adaptive adjustment, and can quickly respond to various conditions, thereby enhancing the adaptability and flexibility of the system.
The effective exception handling mechanism reduces the risk in the system operation, improves the reliability and the safety of the operation ticket system of the whole power grid dispatching automation master station, and reduces the operation risk.
The solution provided by the invention is not only suitable for a specific power grid dispatching automation system, but also has good universality, and can be applied to other similar industrial control systems, thereby increasing the practical value and application prospect and having cross-system universality.
The invention automatically adjusts the execution sequence of the operation ticket by monitoring the system state and the execution condition of the operation ticket in real time. This utilizes optimization algorithms and machine learning techniques to achieve dynamic and intelligent operational flow adjustment.
According to the invention, the machine learning algorithm is adopted to learn the historical operation data, so that the continuous optimization and self-adaptive adjustment of the operation steps and the continuous optimization of the machine learning drive are realized, the operation efficiency and accuracy are improved, and the adaptability of the system to new conditions is enhanced.
The invention comprises a full-efficient exception handling mechanism which can quickly identify and respond to the system exception status. The mechanism effectively processes various anomalies through a preset response strategy, and ensures high stability and safety of the system.
The optimization method based on machine learning enables the method to more accurately cope with complex and changing operation demands, and operation accuracy and adaptability are enhanced.
The efficient exception handling and response mechanism ensures the stable operation of the system in the face of various emergency conditions, enhances the stability and safety of the system and reduces the operation risk.
The invention provides more accurate decision support for operation and maintenance personnel through data statistics and analysis, is beneficial to timely finding and solving potential problems in a system, and improves the support capability of operation and maintenance decision.
The invention embodies the innovation and the practicability of the system in the aspect of optimizing the operation ticket system of the power grid dispatching automation master station.
In conclusion, the method has high practical value and application prospect, and provides a new thought and method for optimizing the operation ticket system of the power grid dispatching automation master station.
The present disclosure may be a system, method, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: portable computer disks, hard disks, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static Random Access Memory (SRAM), portable compact disk read-only memory (CD-ROM), digital Versatile Disks (DVD), memory sticks, floppy disks, mechanical coding devices, punch cards or in-groove structures such as punch cards or grooves having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media, as used herein, are not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., optical pulses through fiber optic cables), or electrical signals transmitted through wires.
The computer readable program instructions described herein may be downloaded from a computer readable storage medium to a respective computing/processing device or to an external computer or external storage device over a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and/or edge servers. The network interface card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in the respective computing/processing device.
Computer program instructions for performing the operations of the present disclosure can be assembly instructions, instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, c++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present disclosure are implemented by personalizing electronic circuitry, such as programmable logic circuitry, field Programmable Gate Arrays (FPGAs), or Programmable Logic Arrays (PLAs), with state information of computer readable program instructions, which can execute the computer readable program instructions.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station is characterized by comprising the following steps of:
step 1: an intelligent optimization module is introduced into an operation ticket system of an operation and maintenance automatic main station of power grid dispatching, and the execution process of the operation ticket is monitored and optimized in real time;
step 2: automatically adjusting the execution sequence of the operation ticket by monitoring the system state and the operation ticket execution condition in real time;
step 3: continuously learning and optimizing the operation steps by utilizing a historical operation record and a machine learning algorithm;
step 4: an exception handling mechanism is added to rapidly respond and handle the emergency exception;
step 5: and the system data is counted and analyzed, so that the prediction accuracy is improved, and the support is improved for operation and maintenance personnel.
2. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 1, wherein in step 1:
the intelligent optimization module comprises:
real-time monitoring unit: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
decision support unit: based on the data analysis result, an optimization algorithm is utilized to provide decision support for the operation ticket execution process, including execution sequence adjustment and resource allocation;
learning and adaptation unit: learning historical operation data by adopting a machine learning algorithm to realize continuous optimization and self-adaptive adjustment of an operation process;
an abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected;
data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
3. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 1, wherein,
The step 2 is to automatically adjust the execution sequence of the operation ticket by monitoring the system state and the execution condition of the operation ticket in real time, and the method specifically comprises the following steps:
firstly, according to key indexes obtained by real-time monitoring, including system performance indexes, operation execution indexes and resource use conditions, the priority of the operation is estimated based on the indexes, and the execution sequence of the operation ticket is automatically adjusted according to the obtained priority and the dependency relationship between the operations.
4. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 3, wherein,
the system performance index comprises: the system performance index comprises processing capacity and response time;
the operation execution index comprises an execution progress, delay and error rate;
the resource use condition comprises memory occupation and network bandwidth;
the dependencies include direct dependencies and indirect dependencies:
the direct dependency, i.e. some operational steps, may depend directly on the completion of a previous step;
the indirect dependencies, i.e., certain operations, while not logically directly dependent, are indirectly related due to shared resources or other factors.
5. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 3, wherein,
The evaluation formula of the operation priority is as follows:
wherein O is operation priority, and the system performance index, the operation execution index and the resource use index are respectively n, m and l, P i 、E j 、R k Respectively representing an ith system performance index, a jth operation execution index and a kth resource use index;the weights of the indexes are respectively, alpha, beta and delta are respectively the balance coefficients of a system performance index, an operation execution index and a resource use index, and epsilon is a preset constant.
6. The intelligent optimization method for the operation and maintenance ticket of the power grid dispatching automation master station according to claim 1, wherein the step 3 uses a historical operation record and a machine learning algorithm, and the continuous learning and optimization operation steps specifically comprise:
collecting historical operation records, and performing data cleaning and standardization treatment;
extracting key features including operation type, execution duration, program output and result state;
selecting a proper model and training by using historical data;
and evaluating the performance of the model through the verification set and the test set, and optimizing the model according to feedback.
7. The intelligent optimization method of the operation ticket of the power grid dispatching automation master station according to claim 1, wherein the step 4 is added with an exception handling mechanism, and the quick response and handling of the emergency exception specifically comprises:
Real-time monitoring the running state of the system by utilizing an algorithm and a predefined rule to identify an abnormal mode;
classifying the detected abnormality, including system performance abnormality, operation execution abnormality, system fault and network problem;
corresponding processing strategies are defined for different types of anomalies, including automatic retries, system rollback, alarm notification, manual intervention.
8. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 5, wherein,
the system performance anomalies include CPU usage exceeding 100% for more than 5 minutes, and executing commands exceeding history takes more than 50%;
the operation execution exception comprises operation failure and inconsistent execution results;
the system faults comprise faults of the whole operation environment of the platform;
the data exception includes data corruption, data loss, data format error;
the corresponding processing strategy comprises the following steps:
if the system performance is abnormal, automatically retrying, checking whether the system performance is an occasional factor, and if the system performance is abnormal for a plurality of times, stopping operation, and notifying an alarm to manually intervene;
if the operation execution is abnormal, automatically rolling back and optimizing an execution strategy;
If the system is in fault, the alarm notification is manually interfered;
if the data is abnormal, automatically rolling back and optimizing the execution strategy.
9. The intelligent optimization method for the operation and maintenance operation ticket of the power grid dispatching automation master station according to claim 1, wherein,
and 5, carrying out statistics and analysis on the system data, improving the prediction accuracy, and improving the support for operation and maintenance personnel specifically comprises the following steps:
automatically collecting operation ticket data from a power grid dispatching system every day, wherein the operation ticket data comprises the starting and ending time of operation, related resources and fault occurrence conditions, and eliminating abnormal data by using a data cleaning technology;
performing basic statistical analysis on the cleaned data, calculating the average completion time and standard deviation of the operation to know the overall condition of the operation efficiency, counting the average time consumption of each operation type, and prompting that the flow efficiency problem possibly exists for the operation with the time consumption exceeding a preset value;
displaying the completion time distribution of different operation types by using the histogram and the box diagram;
analyzing the relation between the resource usage and the operation completion time by using regression analysis;
and adjusting the operation flow or the resource allocation according to the analysis result, and continuously monitoring the adjustment effect.
10. A grid dispatching automation master station operation ticket intelligent optimization system according to the method of any one of claims 1-9 comprising an intelligent optimization module, characterized in that:
the intelligent optimization module comprises a real-time monitoring unit, a decision support unit, a learning and self-adapting unit, an abnormality detection and response unit and a data statistics analysis unit;
the real-time monitoring unit is used for: the system is responsible for collecting and monitoring system states, operation execution conditions and network load parameters in real time, and real-time stream processing and analysis of data are realized by using a Complex Event Processing (CEP) technology;
the decision support unit: based on the data analysis result, an optimization algorithm is utilized to provide decision support for the operation ticket execution process, including execution sequence adjustment and resource allocation;
the learning and adaptation unit: learning historical operation data by adopting a machine learning algorithm to realize continuous optimization and self-adaptive adjustment of an operation process;
the abnormality detection and response unit: monitoring the abnormal state of the system in real time by using an abnormality detection algorithm, and starting a preset response mechanism immediately once abnormality is detected;
the data statistics analysis unit: and (5) carrying out deep analysis on the collected data by using a statistical and machine learning method, and identifying potential optimization points and risk factors in the execution process of the operation ticket.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744667.8A CN117687884A (en) | 2023-12-18 | 2023-12-18 | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311744667.8A CN117687884A (en) | 2023-12-18 | 2023-12-18 | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117687884A true CN117687884A (en) | 2024-03-12 |
Family
ID=90126245
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311744667.8A Pending CN117687884A (en) | 2023-12-18 | 2023-12-18 | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117687884A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117950364A (en) * | 2024-03-26 | 2024-04-30 | 南京再造科技有限公司 | Intelligent on-site equipment control system |
-
2023
- 2023-12-18 CN CN202311744667.8A patent/CN117687884A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117950364A (en) * | 2024-03-26 | 2024-04-30 | 南京再造科技有限公司 | Intelligent on-site equipment control system |
| CN117950364B (en) * | 2024-03-26 | 2024-05-31 | 南京再造科技有限公司 | Intelligent on-site equipment control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101984730B1 (en) | Automatic predicting system for server failure and automatic predicting method for server failure | |
| AU2021107643A4 (en) | Method, system, device, computer device and storage medium for elevator fault prediction | |
| CN106844161B (en) | Abnormity monitoring and predicting method and system in calculation system with state flow | |
| CN110498314B (en) | Health assessment method and system for elevator door system, electronic device and storage medium | |
| EP4020315A1 (en) | Method, apparatus and system for determining label | |
| CN117687884A (en) | Intelligent optimization method and system for operation and maintenance operation ticket of power grid dispatching automation master station | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| US11258659B2 (en) | Management and control for IP and fixed networking | |
| CN110955586A (en) | System fault prediction method, device and equipment based on log | |
| CN117422447A (en) | Transformer maintenance strategy generation method, system, electronic equipment and storage medium | |
| CN113723827B (en) | Operation risk diagnosis and operation management and control method and system for subway electromechanical equipment | |
| CN114962390A (en) | Hydraulic system fault diagnosis method and system and working machine | |
| CN117391675B (en) | Data center infrastructure operation and maintenance management method | |
| CN114168375A (en) | Method for quickly positioning and eliminating database system abnormity | |
| US20230034061A1 (en) | Method for managing proper operation of base station and system applying the method | |
| CN115794578A (en) | Data management method, device, equipment and medium for power system | |
| US20220092457A1 (en) | Electronic device and method for analyzing reliability of facility | |
| CN114172708A (en) | Method for identifying network flow abnormity | |
| CN114548769A (en) | Intelligent power grid IT asset big data monitoring system and method | |
| CN111724048A (en) | Characteristic extraction method for finished product library scheduling system performance data based on characteristic engineering | |
| CN114090394B (en) | Distributed server cluster load abnormity analysis method | |
| CN117609740B (en) | Intelligent prediction maintenance system based on industrial large model | |
| CN118092404A (en) | Method and system for preventive maintenance of PLC (programmable logic controller) network based on artificial intelligence | |
| CN118301206A (en) | Intelligent elastic telescoping method and system for micro-service | |
| CN114692996A (en) | Production state optimization method, system and storage medium |
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 |