CN110415136B - Service capability evaluation system and method for power dispatching automation system - Google Patents
Service capability evaluation system and method for power dispatching automation system Download PDFInfo
- Publication number
- CN110415136B CN110415136B CN201810390966.9A CN201810390966A CN110415136B CN 110415136 B CN110415136 B CN 110415136B CN 201810390966 A CN201810390966 A CN 201810390966A CN 110415136 B CN110415136 B CN 110415136B
- Authority
- CN
- China
- Prior art keywords
- rule
- data
- attribute
- service capability
- monitoring 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.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 71
- 230000010354 integration Effects 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims description 30
- 230000002123 temporal effect Effects 0.000 claims description 18
- 238000005192 partition Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 108010028984 3-isopropylmalate dehydratase Proteins 0.000 claims description 3
- 238000005304 joining Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 5
- 230000008859 change Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a service capability evaluation system and method for a power dispatching automation system. The method comprises the following steps: the acquisition/integration module acquires monitoring data; the business relation engine module predefines business associated data; the rule engine module establishes an object rule, a hierarchy rule and a system rule; and the service capability index evaluation engine module outputs an object service capability index, a hierarchy service capability index and a system service capability index according to the collected monitoring data and the collected business association data and the calling object rule, the hierarchy rule and the system rule. The invention can be used as a main index for measuring the running condition of the full-automatic machine room and each concerned application system and providing the service capability for the outside, and is used for guiding the actual management and operation and maintenance work, and meanwhile, the change of the service capability index directly reflects the change trend of the availability and the reliability of the system, thereby being beneficial to the managers to detect the hidden trouble in advance and prevent the hidden trouble in the bud.
Description
Technical Field
The invention belongs to the field of operation management of an electric power dispatching automation system, and provides a system and a method for evaluating service capacity of the electric power dispatching automation system.
Background
The electric power dispatching automation machine room is an infrastructure for electric power informatization and automation construction, has the characteristics of high complexity, high investment and high technical density, and directly influences the safety of a power grid and the safety production of electric power under the operation condition. At present, safety protection systems are built in electric power machine rooms of all levels of units, such as an IT operation and maintenance system, a machine room environment, video monitoring, entrance guard, fire fighting and the like, but most of various systems manage and independently operate the machine rooms from a certain aspect, information and services are mutually covered but not shared, various problems are difficult to be considered and processed from the whole system of the machine rooms, various indexes and factors are difficult to be integrated, and the operation condition of an application system is accurately evaluated.
In addition, the automatic power dispatching machine room has clear industrial characteristics, such as safety requirements of 'secondary security' and the like, and the difficulty is caused to the deployment and the maximum effectiveness of a plurality of general products.
Disclosure of Invention
Aiming at the defects in the prior art, the safe, efficient and economic operation of the environment, equipment and application of the electric power machine room is ensured, multiple factors such as the equipment, the application, the system, the network and the power environment in the electric power automation machine room need to be looked at by a systematic thinking mode and a systematic research method, barriers among various operation and maintenance auxiliary systems are broken, various data are summarized, an accurate, reasonable and fine evaluation model is established for the operation condition of the whole machine room and each application system, and accurate index data are provided. The invention provides a system and a method for evaluating service capacity of an electric power dispatching automation system, which are used as a main index for measuring running conditions of a full-automatic machine room and each concerned application system and providing service capacity to the outside, and are used for guiding actual management and operation and maintenance work.
The technical scheme adopted by the invention for realizing the purpose is as follows: a power dispatching automation system service capability assessment system, comprising:
the acquisition/integration module acquires monitoring data through a communication protocol or a data integration means and outputs the monitoring data to the service capability index evaluation engine module;
the service relation engine module is used for predefining service associated data among various services of the application system to the service capability index evaluation engine module;
the rule engine module is used for establishing an object rule, a hierarchy rule and a system rule and outputting the object rule, the hierarchy rule and the system rule to the service capability index evaluation engine module;
and the service capability index evaluation engine module outputs an object service capability index, a hierarchy service capability index and a system service capability index according to the acquired monitoring data and the service associated data and the object rule, the hierarchy rule and the system rule provided by the calling rule engine module.
The acquisition/integration module comprises:
the monitoring data acquisition module acquires monitoring data from the monitored equipment through SNMP and IPMI protocols or interfaces;
the monitoring data integration module collects monitoring data in a webservice, shared database and shared data file mode, and carries out data structure conversion when the data structures of the collected monitoring data are not consistent.
And the automatic system safety partition processing module is used for carrying out safety partition storage on the monitoring data acquired by the monitoring data acquisition module and the monitoring data integration module so as to realize communication and monitoring data summarization among the safety partitions.
The monitoring data includes data of the following objects: equipment monitoring data, application monitoring data, network monitoring data, system monitoring data and power environment monitoring data;
the attributes of the monitoring data include: the system comprises a CPU utilization rate, a CPU temperature, a memory use condition, a network port state, a hard disk hardware state, a hard disk logic partition condition, network port flow data, power module operation data, a machine room UPS operation condition, a machine room temperature and humidity and network dynamic topology data.
The service associated data comprises data association among systems, service flow association, application system deployment association and association relation with a machine room operating environment.
The rule engine module comprises an object rule unit, a hierarchy rule unit and a system rule unit;
the object rule unit includes:
i. selecting characteristic attributes, namely filtering the monitoring data and the service associated data according to whether the attributes of the monitoring data and the service associated data accord with characteristic attribute rules or not, and reserving the monitoring data and the service associated data which accord with the attribute rules as the data after the characteristic attributes are selected;
marking the data set, namely adding marking information to the data with the selected characteristic attributes according to the types of the marking information, and acquiring the data which accords with the marking information as training data;
learning the rule, namely learning by applying training data and generating an object rule set to obtain an object service capability index;
the hierarchical rule unit acquires a hierarchical service capability index according to the following hierarchical rules:
the system rule unit acquires a system service capability index according to the following system rules:
wherein N is the number of objects, M is the number of levels, and the object weight and the level weight are preset parameters.
The attribute rules include: attributes of interest to the business system, attributes of failure, and attributes provided by the associated support system.
The marking information is used for marking the running result of the monitoring data selected by the current characteristic attribute in the actual application environment; the tag information categories include: external system flags, expert settings, special events.
The rule learning, which is to apply training data to learn and generate an object rule set, and obtain an object service capability index, includes:
a. defining a training data set (attributes) i Property value i，j ) (ii) a Defining a Boolean function T i (Attribute) i Property value i，j ) For judging attributes i And attribute value i，j Whether or not the relation T is satisfied i Calculating; wherein, the attribute i Representing the ith attribute, attribute value i，j A jth attribute value representing an ith attribute;
b. selecting one of the label information as a learning topic;
c. when i =1, for the 1 st attribute, T is assigned 1 (Properties) 1 Property value 1，j ) Rule R of putting to null Air conditioner Then generate oneA temporary rule R Temporal rules According to a temporary rule R Temporal rules For the training data set (attributes) i Property value i，j ) The data in the step (1) are matched, and the result is consistent with the current learning subject and is 'covered positive example', otherwise, is 'covered negative example'; calculating the accuracy; the "accuracy = covering positive case number/total number of training data",
d. for the ith attribute (i)>1) Handlebar T i (Properties) i Property value i，j ) To temporary rules R Temporal rules In (c), a new temporary rule R 'is generated' Temporal rules According to a new provisional rule R' Temporal rules For the training data set (attributes) i Property value i，j ) The data in the step (1) are matched, and the result is consistent with the current learning subject and is 'covered positive example', otherwise, is 'covered negative example'; calculating the accuracy;
e. corresponding to each attribute i, selecting new temporary rules R 'corresponding to the first n accuracy rates according to the sequence of the accuracy rates from high to low' Temporal rules Joining to a temporary rule set R Temporary rule set Obtaining a temporary rule set R Temporary rule set A corresponding candidate data set; return d replace training data set with candidate data set (Attribute) i Property value i，j ) Performing the subsequent steps;
f. generating a current subject rule set R until all i attributes in the training data are traversed Current topic rule set ；
g. Until all learning subjects finish learning and generating the object rule set R Object rule set ＝{R p }，R p = { R (attribute) 1 Property value 1 ) Λ R (attribute) p Property value p ) → object service capability index };
wherein n is more than or equal to 1 and is a system parameter; the candidate dataset is a training dataset (attributes) i Property value i，j ) A subset of (a); r (Attribute) p Property value p ) Is a Boolean function for determining attributes p And attribute value p Whether a relational R operation is satisfied; wherein, the attribute p Represents the p-th attribute, genusSex value p The attribute value representing the p-th attribute.
A service capability assessment method for a power dispatching automation system comprises the following steps:
step 1: the service ability index evaluation engine module receives the object monitoring data acquired by the acquisition/integration module, and filters the monitoring data according to the characteristic attribute rule to acquire characteristic attribute monitoring data;
and 2, step: the service capability index evaluation engine module receives the characteristic attribute monitoring data and the object service correlation data and calls an object rule provided by the rule engine module to output an object service capability index;
and 3, step 3: the service ability index evaluation engine module receives the service ability indexes of all the objects and calls the level rules provided by the rule engine module to output the level service ability indexes;
and 4, step 4: and the service capability index evaluation engine module receives the hierarchy service capability index and calls the system rule provided by the rule engine module to output the system service capability index.
The invention has the following advantages and beneficial effects:
the method is used as a main index for measuring the running condition of the full-automatic machine room and each concerned application system and providing the service capability for the outside, is used for guiding the actual management and operation and maintenance work, and meanwhile, the change of the service capability index directly reflects the change trend of the availability and the reliability of the system, thereby being beneficial to the managers to detect the hidden trouble in advance and prevent the hidden trouble in the bud.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a schematic diagram of a service capability rule learning flow;
FIG. 3 is a schematic diagram of a system service capability assessment engine module.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples.
The service capability evaluation system of the power dispatching automation system is composed of a monitoring data acquisition/integration module, a business relation engine module, a rule engine module and a service capability index evaluation engine module, and the structures of all the components are shown in figure 1.
1. Monitoring data acquisition/integration module
Various monitoring data are gathered together through a direct acquisition or data integration means, and the monitoring data are output to a service capability index evaluation engine through an interface.
The direct acquisition means that monitoring data is directly acquired from monitored equipment through a certain communication protocol or interface, for example, the CPU load, the memory usage, the network port state, the hard disk logic partition usage and the like of a server can be read through an SNMP protocol; and reading data such as the state of a power module of the server, the temperature of a chassis, the rotating speed of a fan, the state of hardware of a hard disk and the like through an IPMI protocol.
The data integration means is to acquire the monitoring data of the monitored equipment from an external system in a certain interface mode, namely, the monitoring data is acquired indirectly from the external system, which is beneficial to protecting the investment of the existing system and improving the application efficiency of the existing system. If the external system data structure does not meet the requirements of the system, the data structure conversion work is also included, and the data structure conversion is generally completed by developing a data interface.
The automatic system safety partition processing module is used for realizing cross-safety partition summarizing of various monitoring data of an automatic production area and an information area, so that unified processing and service interconnection of the monitoring data of the whole machine room are realized. The module realizes the data exchange protocols of the forward and reverse isolation devices in the power industry and provides the underlying data exchange function on the one hand, and realizes service-level service interfaces including SNMP data cross-region acquisition, SQL cross-region execution, command cross-region execution and the like on the other hand.
The monitoring data attributes include: the system comprises a CPU utilization rate, a CPU temperature, a memory use condition, a network port state, a hard disk hardware state, a hard disk logic partition condition, network port flow data, power module operation data, a machine room UPS operation condition, a machine room temperature and humidity, network dynamic topology data and the like.
2. Business relation engine module
The association of each application system is a direct or indirect relationship during the operation of the system, and comprises data association and business process association among systems, and also comprises application system deployment association and association with a machine room operation environment and the like, the association sets form important factors influencing the normal and efficient operation of the application systems, and the business relationship engine is responsible for modeling and managing the association relationships. With the continuous operation of the system, new business relations can be discovered and collected through self algorithms and written into a business relation library after the confirmation of a user, which is beneficial to the continuous evolution and optimization of the system.
3. Rule engine module
The rules engine has a learning function. Rule learning is the process of generating new rules from historical data sets according to a rule learning algorithm defined by the system, and the rule learning step (as shown in fig. 3) includes: object rule making, hierarchy rule making and system rule making;
(1) The object rule making comprises the following steps:
i. training data feature attribute selection
Because the automatic system is a proprietary system of the power industry, the domain knowledge is rich, and the model is complete, the characteristic attributes are determined by service experts, and the data in the special attribute set are sorted according to the priority.
The basis for determining the characteristic attribute mainly comprises two aspects, namely, extracting the domain knowledge, and describing the rule according to the actual operation data as follows:
a) Attributes of interest to the business system: for example, if there is data sharing between two systems, the business impact attribute is the feature attribute.
b) Failed property: and analyzing the historical operation records, and setting the attribute with the fault as the characteristic attribute in priority.
c) Attributes provided by the associated support system: for example, if the evaluation result needs to consider the influence of the temperature factor of the machine room, the related attribute defined by the temperature measurement system of the machine room needs to be defined as the characteristic attribute.
Training dataset tagging
Each sample data is a series of attributes and attribute values, and the training sample data marking is to add marking information to the sample data to mark the running result of the sample data in the actual application environment.
The source of the marking information includes the following cases:
a) External system marking: if the sample data is integrated by the external system and the external system has a judgment result on the operation condition, the result can be used as the marking information.
b) Setting by an expert: the typical runtime segment data is defined by the user expert, and the runtime result is specified.
c) Special events are as follows: if special events occur in the actual operation process, such as server failure, data loss, service interruption, etc., the sample data when these events occur is added with the label information.
And the data set after the marking and the characteristic attribute filtering is the final training data set for rule learning.
Rule Generation
As shown in fig. 2, the goal is to generate an object rule set that covers as much data as possible, including:
a. defining training data sets (attributes) i Property value i，j ) (ii) a Defining a Boolean function T i (Attribute) i Property value i，j ) For determining attributes i And attribute value i，j Whether or not the relation T is satisfied i Calculating; wherein the attribute i Representing the ith attribute, attribute value i，j A jth attribute value representing an ith attribute;
b. selecting one of the label information as a learning topic;
c. when i =1, for the 1 st attribute, T is assigned 1 (Attribute) 1 Property value 1，j ) Rule of putting to empty R Air conditioner Then a temporary rule R is generated Temporal rules According to a temporary rule R Temporal rules For the training data set (attributes) i Property value i，j ) The data in (1) are matched, and the result is consistent with the current learning subject and is 'covering positive example', otherwise, the result is 'covering negative example'; calculating the accuracy; what is needed isThe following "accuracy = covering positive case number/total training data",
d. for the ith attribute (i)>1) Handle T i (Properties) i Property value i，j ) To temporary rules R Temporal rules In, a new temporary rule R 'is generated' Temporal rules According to a new temporary rule R' Temporal rules For the training data set (attributes) i Property value i，j ) The data in the step (1) are matched, and the result is consistent with the current learning subject and is 'covered positive example', otherwise, is 'covered negative example'; calculating the accuracy;
e. corresponding to each attribute i, selecting new temporary rules R 'corresponding to the first n accuracy rates according to the sequence of the accuracy rates from high to low' Temporal rules Joining to a temporary rule set R Temporary rule set Obtaining a temporary rule set R Temporary rule set A corresponding candidate data set; return d replace training data set with candidate data set (Attribute) i Property value i，j ) Performing the subsequent steps;
f. generating a current topic rule set R until all i attributes in the training data are traversed Current topic rule set ；
g. Until all learning subjects finish learning and generating the object rule set R Object rule set ＝{R p }，R p = { R (attribute) 1 Property value 1 ) Λ R (attribute) p Property value p ) → object service capability index };
wherein n is more than or equal to 1 and is a system parameter; the candidate data set is a training data set (attribute) i Property value i，j ) A subset of (a); r (Attribute) p Property value p ) Is a Boolean function for determining attributes p And attribute value p Whether a relational R operation is satisfied; wherein, the attribute p Representing the p-th attribute, attribute value p The attribute value representing the p-th attribute.
The evaluation results of the objects in the system are calculated by a set of regular expressions, each rule being defined by a first-order logical expression. Each rule expresses a logical relationship between several evaluation attribute values of a current evaluation object (e.g., a server). Taking a certain server as an example, assume that its evaluation attributes include: CPU load rate, memory usage rate, system temperature, and port usage rate, a rule for which may be defined as:
(CPU load rate, < 30%) < Λ (memory usage rate, < 25%) < Λ (system temperature, normal range) < Λ (portal usage rate, < 10%) → server service capacity index (X).
(2) The hierarchical rule unit acquires a hierarchical service capability index according to the following hierarchical rules:
(3) The system rule unit acquires a system service capability index according to the following system rules:
wherein N is the number of objects, M is the number of levels, and the object weight and the level weight are preset parameters.
4. Service capability index evaluation engine
The whole automation system consists of a large number of application software, system software, servers, network equipment and the like, and the equipment shares the power environment of the machine room, so that for a certain application system to be evaluated, the application software, the servers, the related network equipment and the machine room environment related to the application system are factors influencing the operation and external service capacity of the application system.
And the service capability index evaluation engine module outputs an object service capability index, a hierarchy service capability index and a system service capability index according to the acquired monitoring data and the service associated data and the object rule, the hierarchy rule and the system rule provided by the calling rule engine module.
The specific steps of the method are shown in fig. 3, and the calculation process is performed according to the hierarchy, namely the object level, the business level and the system level.
The object level is the lowest level, and specific objects such as servers, software processes and the like take object monitoring data and business associated data as basic data, complete object service capability processing by filtering the monitoring data and calling object rules of a rule engine module, and finally output an object service capability evaluation result. Wherein, the attribute of the feature attribute monitoring data and the object service related data is used as the attribute p Innovation rule set R Rule set And acquiring an object service capability index.
And the service level evaluation takes the evaluation result of the object service capability as input data, calls a level rule of the rule engine module to complete evaluation calculation, and outputs the evaluation result of the level service capability.
And the system level evaluation takes the service level service capability evaluation result as input data, calls the system rule of the rule engine module to complete evaluation calculation, and outputs the system service capability evaluation result.
Through actual deployment and application in a plurality of power dispatching automation machine rooms, the system runs well, various monitoring data, business relation data and rule constraints of users are fully fused, and data value is fully mined; the service ability index evaluation method is fully verified and utilized, the defined service ability indexes of various application systems accurately and reasonably show the current running state of the system, play a positive role in actual production and obtain good economic and social benefits.
Claims (7)
1. An electric power dispatching automation system service capability assessment system, characterized by comprising:
the acquisition/integration module acquires and outputs monitoring data to the service capability index evaluation engine module through a communication protocol or a data integration means;
the service relation engine module is used for predefining service associated data among various services of the application system to the service capability index evaluation engine module;
the rule engine module is used for establishing an object rule, a hierarchy rule and a system rule and outputting the object rule, the hierarchy rule and the system rule to the service capability index evaluation engine module; the rule engine module comprises an object rule unit, a hierarchy rule unit and a system rule unit;
the object rule unit comprises:
i. selecting characteristic attributes, namely filtering the monitoring data and the service associated data according to whether the attributes of the monitoring data and the service associated data accord with characteristic attribute rules or not, and reserving the monitoring data and the service associated data which accord with the attribute rules as the data after the characteristic attributes are selected;
marking the data set, namely adding marking information to the data with the selected characteristic attributes according to the types of the marking information, and acquiring the data which accords with the marking information as training data;
learning the rule, namely learning by applying training data and generating an object rule set to obtain an object service capability index; the method comprises the following steps:
a. defining training data sets (attributes) i Property value i，j ) (ii) a Defining a Boolean function T i (Properties) i Property value i，j ) For judging attributes i And attribute value i，j Whether or not the relation T is satisfied i Calculating; wherein, the attribute i Representing the ith attribute, attribute value i，j A jth attribute value representing an ith attribute;
b. selecting one of the label information as a learning topic;
c. when i =1, for the 1 st attribute, T is assigned 1 (Attribute) 1 Property value 1，j ) Rule of putting to empty R Air conditioner Then a temporary rule R is generated Temporal rules According to a temporary rule R Temporal rules For the training data set (attributes) i Property value i，j ) The data in (1) are matched, and the result is consistent with the current learning subject and is 'covering positive example', otherwise, the result is 'covering negative example'; calculating the accuracy; the "accuracy = covering positive examples/total number of training data",
d. for the ith attribute, i>1, treating T i (Attribute) i Property value i，j ) To temporary rules R Temporal rules In (c), a new temporary rule R 'is generated' Temporal rules According to a new temporary rule R' Temporal rules For the training data set (attributes) i Property value i，j ) The data in (1) are matched, and the result is consistent with the current learning subject and is 'covering positive example', otherwise, the result is 'covering negative example'; calculating the accuracy;
e. corresponding to each attribute i, selecting new temporary rules R 'corresponding to the first n accuracy rates according to the sequence of the accuracy rates from high to low' Temporal rules Joining to a temporary rule set R Temporary rule set Obtaining a temporary rule set R Temporary rule set A corresponding candidate data set; return d replace the candidate data set with the training data set (Attribute) i Property value i，j ) Performing the subsequent steps;
f. generating a current topic rule set R until all i attributes in the training data are traversed Current topic rule set ；
g. Until all learning subjects finish learning and generating the object rule set R Object rule set ＝{R p }，R p = { R (attribute) 1 Property value 1 ) Lambada' 8230 ^ R (attribute) p Property value p ) → object service capability index };
wherein n is more than or equal to 1 and is a system parameter; the candidate dataset is a training dataset (attributes) i Property value i，j ) A subset of (a); r (Attribute) p Property value p ) Is a Boolean function for determining attributes p And attribute value p Whether a relation R operation is satisfied; wherein the attribute p Representing the p-th attribute, attribute value p An attribute value representing the p-th attribute;
the hierarchical rule unit acquires a hierarchical service capability index according to the following hierarchical rules:
the system rule unit acquires a system service capability index according to the following system rules:
wherein N is the number of objects, M is the number of levels, and the object weight and the level weight are preset parameters;
and the service capability index evaluation engine module outputs an object service capability index, a hierarchy service capability index and a system service capability index according to the acquired monitoring data and the service association data and the object rule, the hierarchy rule and the system rule provided by the calling rule engine module.
2. The power dispatching automation system service capability assessment system according to claim 1, wherein: the acquisition/integration module comprises:
the monitoring data acquisition module acquires monitoring data from the monitored equipment through SNMP and IPMI protocols or interfaces;
the monitoring data integration module acquires monitoring data in a webservice, shared database and shared data file mode, and performs data structure conversion when the data structures of the acquired monitoring data are inconsistent;
and the automatic system safety partition processing module is used for carrying out safety partition storage on the monitoring data acquired by the monitoring data acquisition module and the monitoring data integration module so as to realize communication and monitoring data summarization among the safety partitions.
3. The system according to claim 1, wherein the system comprises: the monitoring data includes data of the following objects: equipment monitoring data, application monitoring data, network monitoring data, system monitoring data and power environment monitoring data;
the attributes of the monitoring data include: the system comprises a CPU utilization rate, a CPU temperature, a memory use condition, a network port state, a hard disk hardware state, a hard disk logic partition condition, network port flow data, power module operation data, a machine room UPS operation condition, machine room temperature and humidity and network dynamic topology data.
4. The power dispatching automation system service capability assessment system according to claim 1, wherein: the service associated data comprises data association among systems, service flow association, application system deployment association and association relation with the machine room operating environment.
5. The power dispatching automation system service capability assessment system according to claim 1, wherein: the attribute rules include: attributes of interest to the business system, attributes of failure, attributes provided by the associated support system.
6. The power dispatching automation system service capability assessment system according to claim 1, wherein: the marking information is used for marking the running result of the monitoring data selected by the current characteristic attribute in the actual application environment; the tag information categories include: external system flags, expert settings, special events.
7. An electric power dispatching automation system service capability evaluation method, which is implemented based on the electric power dispatching automation system service capability evaluation system of any one of claims 1-6, characterized by comprising the following steps:
step 1: the service ability index evaluation engine module receives the object monitoring data acquired by the acquisition/integration module, and filters the monitoring data according to the characteristic attribute rule to acquire characteristic attribute monitoring data;
step 2: the service capability index evaluation engine module receives the characteristic attribute monitoring data and the object service correlation data and calls an object rule provided by the rule engine module to output an object service capability index;
and step 3: the service ability index evaluation engine module receives the service ability indexes of all the objects and calls the level rules provided by the rule engine module to output the level service ability indexes;
and 4, step 4: and the service capability index evaluation engine module receives the hierarchy service capability index and calls the system rule provided by the rule engine module to output the system service capability index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810390966.9A CN110415136B (en) | 2018-04-27 | 2018-04-27 | Service capability evaluation system and method for power dispatching automation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810390966.9A CN110415136B (en) | 2018-04-27 | 2018-04-27 | Service capability evaluation system and method for power dispatching automation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110415136A CN110415136A (en) | 2019-11-05 |
| CN110415136B true CN110415136B (en) | 2023-04-07 |
Family
ID=68345793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810390966.9A Active CN110415136B (en) | 2018-04-27 | 2018-04-27 | Service capability evaluation system and method for power dispatching automation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415136B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401776A (en) * | 2020-03-27 | 2020-07-10 | 卫健智能(深圳)有限公司 | Public health service quality control method and system |
| CN112684780A (en) * | 2021-01-29 | 2021-04-20 | 郑州铁路职业技术学院 | Control panel interface assembly for railway locomotive |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101208602A (en) * | 2005-04-15 | 2008-06-25 | 贝克顿迪金森公司 | Diagnosis of sepsis |
| CN102122374A (en) * | 2011-03-03 | 2011-07-13 | 江苏方天电力技术有限公司 | Intelligent analysis system for flow abnormity of power automation system |
| CN105046387A (en) * | 2015-01-07 | 2015-11-11 | 泰华智慧产业集团股份有限公司 | Comprehensive analyzing subsystem of digital city monitoring center and working method thereof |
| CN106411609A (en) * | 2016-11-08 | 2017-02-15 | 上海新炬网络信息技术有限公司 | IT software and hardware running state monitoring system |
| CN106600073A (en) * | 2016-12-28 | 2017-04-26 | 携程旅游网络技术（上海）有限公司 | Optimizing method and apparatus for internet based payment risk control system |
| CN106649840A (en) * | 2016-12-30 | 2017-05-10 | 国网江西省电力公司经济技术研究院 | Method suitable for power data quality assessment and rule check |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10664759B2 (en) * | 2014-10-23 | 2020-05-26 | Fair Isaac Corporation | Dynamic business rule creation using scored sentiments |
-
2018
- 2018-04-27 CN CN201810390966.9A patent/CN110415136B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101208602A (en) * | 2005-04-15 | 2008-06-25 | 贝克顿迪金森公司 | Diagnosis of sepsis |
| CN102122374A (en) * | 2011-03-03 | 2011-07-13 | 江苏方天电力技术有限公司 | Intelligent analysis system for flow abnormity of power automation system |
| CN105046387A (en) * | 2015-01-07 | 2015-11-11 | 泰华智慧产业集团股份有限公司 | Comprehensive analyzing subsystem of digital city monitoring center and working method thereof |
| CN106411609A (en) * | 2016-11-08 | 2017-02-15 | 上海新炬网络信息技术有限公司 | IT software and hardware running state monitoring system |
| CN106600073A (en) * | 2016-12-28 | 2017-04-26 | 携程旅游网络技术（上海）有限公司 | Optimizing method and apparatus for internet based payment risk control system |
| CN106649840A (en) * | 2016-12-30 | 2017-05-10 | 国网江西省电力公司经济技术研究院 | Method suitable for power data quality assessment and rule check |
Non-Patent Citations (2)
| Title |
|---|
| 《Relation between Pareto-Optimal Fuzzy Rules and Pareto-Optimal Fuzzy Rule Sets》;Hisao I et al;《IEEE》;20070604;全文 * |
| 《多级分类器构建及在不平衡数据的应用研究》;李莎莎;《中国优秀硕士学位论文全文数据库 信息科技辑》;20160215(第2016年第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110415136A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112102111B (en) | Intelligent processing system for power plant data | |
| CN102752142B (en) | A kind of method for supervising of the information system based on Conceptual Modeling and supervisory control system | |
| CN107294764A (en) | Intelligent supervision method and intelligent monitoring system | |
| CN108092813A (en) | Data center's total management system server hardware Governance framework and implementation method | |
| KR20180108446A (en) | System and method for management of ict infra | |
| CN106600115A (en) | Intelligent operation and maintenance analysis method for enterprise information system | |
| CN110162445A (en) | The host health assessment method and device of Intrusion Detection based on host log and performance indicator | |
| CN103825755A (en) | Power secondary system modeling method and system | |
| CN113347170B (en) | Intelligent analysis platform design method based on big data framework | |
| KR102041545B1 (en) | Event monitoring method based on event prediction using deep learning model, Event monitoring system and Computer program for the same | |
| CN103049365B (en) | Information and application resource running state monitoring and evaluation method | |
| CN112463892A (en) | Early warning method and system based on risk situation | |
| CN110415136B (en) | Service capability evaluation system and method for power dispatching automation system | |
| CN113726559B (en) | Based on artificial intelligence network safety analysis early warning system | |
| CN114385403A (en) | Distributed cooperative fault diagnosis method based on double-layer knowledge graph framework | |
| CN109639475A (en) | Network self-diagnosis Fault Locating Method based on associated diagram | |
| CN109241154A (en) | A kind of distributed data base monitoring analysis method and system | |
| CN117336228A (en) | IGP simulation recommendation method, device and medium based on machine learning | |
| CN114757448B (en) | Manufacturing inter-link optimal value chain construction method based on data space model | |
| CN116594782A (en) | Resource management method and device for exploration data center based on intelligent operation and maintenance system | |
| CN106649034A (en) | Visual intelligent operation and maintenance method and platform | |
| Bychkov et al. | Support for managing the survivability of energy systems based on a combinatorial approach | |
| CN116611813A (en) | Intelligent operation and maintenance management method and system based on knowledge graph | |
| CN115495231A (en) | Dynamic resource scheduling method and system under complex scene of high concurrent tasks | |
| CN110197305B (en) | Relay protection data model searching and optimizing method and system based on shortest path algorithm |
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 |