CN110378580A - A kind of electric network fault multi-agent system preferentially diagnostic method and device - Google Patents

A kind of electric network fault multi-agent system preferentially diagnostic method and device Download PDF

Info

Publication number
CN110378580A
CN110378580A CN201910593820.9A CN201910593820A CN110378580A CN 110378580 A CN110378580 A CN 110378580A CN 201910593820 A CN201910593820 A CN 201910593820A CN 110378580 A CN110378580 A CN 110378580A
Authority
CN
China
Prior art keywords
agent
diagnosis
eap
cpu
algorithm
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
Application number
CN201910593820.9A
Other languages
Chinese (zh)
Inventor
王磊
牛林
高洪雨
郭丽娟
张艳杰
关猛
李宏博
郭婷
商玲玲
王玉彬
马梦朝
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
State Grid of China Technology College
Original Assignee
State Grid Corp of China SGCC
State Grid of China Technology College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, State Grid of China Technology College filed Critical State Grid Corp of China SGCC
Priority to CN201910593820.9A priority Critical patent/CN110378580A/en
Publication of CN110378580A publication Critical patent/CN110378580A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5038—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
    • 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
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06316—Sequencing of tasks or work
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G06F2209/5021—Priority
    • 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

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Game Theory and Decision Science (AREA)
  • Test And Diagnosis Of Digital Computers (AREA)

Abstract

Present disclose provides a kind of electric network fault multi-agent system preferentially diagnostic method and devices.Wherein, a kind of electric network fault multi-agent system preferentially diagnostic method, including step (1): building multi-agent system, the multi-agent system form set A={ A by m diagnosis Agent1,A2,…,Am, Ai∈ A, i=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Agent and diagnosis algorithm of each diagnosis corresponds, and is encapsulated by corresponding diagnosis algorithm；Step (2): building task distributes Agent；Task is distributed Agent and is assessed by valuation functions E each diagnosis Agent, and the screening maximum diagnosis Agent of valuation functions E value carries out fault diagnosis as optimal Agent.

Description

A kind of electric network fault multi-agent system preferentially diagnostic method and device
Technical field
The disclosure belongs to electric network failure diagnosis field more particularly to a kind of electric network fault multi-agent system preferentially diagnostic method And device.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill Art.
Electric network failure diagnosis increasingly obtains scholar's as the first step to restore electricity after electric power system fault at present Pay attention to.The diagnostic method, such as and/or tree, and/or tree, Petri network etc. for developing comparative maturity at present, can utilize breaker Tripping, protection act information etc. are more accurately diagnosed to be fault element.
Inventors have found that the main problem faced in electric network failure diagnosis at present is:
(1) there are many diagnosis algorithms, but each has the advantage and disadvantage of oneself.And electric network fault is single a bit The simple fault of route, some are to be related to the complex fault of a plurality of route and bus.If only with a kind of diagnosis algorithm to all Failure is diagnosed, then diagnosis efficiency will be extremely inefficient.
(2) none of these methods carries out efficiency evaluation to present diagnosis algorithm.
Summary of the invention
To solve the above-mentioned problems, the first aspect of the disclosure provides a kind of electric network fault multi-agent system and preferentially diagnoses Method utilizes multi-agent system, carries out efficiency evaluation to present diagnosis algorithm, the most for some specific failure selection Suitable algorithm carries out fault diagnosis, improves whole diagnosis efficiency.
To achieve the goals above, the disclosure adopts the following technical scheme that
A kind of electric network fault multi-agent system preferentially diagnostic method, comprising:
Step (1): building multi-agent system, the multi-agent system form set A={ A by m diagnosis Agent1, A2,…,Am, Ai∈ A, i=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each examine Disconnected Agent and diagnosis algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm；
Step (2): building task distributes Agent；Task distributes Agent and diagnoses Agent to each by valuation functions E It is assessed, the screening maximum diagnosis Agent of valuation functions E value carries out fault diagnosis as optimal Agent.
Further, the expression formula of the valuation functions E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention property set having It closes, n indicates the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value are preset And
The advantages of above-mentioned technical proposal, is, diagnoses all resources and the value ratio accordingly having in Agent by each Rate be multiplied after add up and, as it is each diagnosis Agent assessed value, when diagnosis Agent assessed value it is bigger, then illustrate mutually to see patients Disconnected Agent is optimal Agent.
Wherein, resource refers to the attribute relevant to fault diagnosis that Agent program has；
It is when the reason of the assessed value of diagnosis Agent is bigger, then the corresponding diagnosis Agent of explanation is optimal Agent:
The attribute of the Agent of disclosure setting is all, to efficiency of fault diagnosis more related, attribute relevant to fault diagnosis Value is bigger, and assessed value is higher, therefore this more suitable failure of Agent.
Further, resource RjThe value ratio W havingjDynamic adjustment can be carried out according to demand.
The advantages of above-mentioned technical proposal, is, carries out being worth ratio possessed by dynamic adjustresources according to demand, improve Valuation functions more accurately filter out optimal Agent.
Further, the expression formula of the valuation functions E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP= 1；UCPUAverage CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is The fault-tolerance of Agent program；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, Quantitative criteria are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
The advantages of above-mentioned technical proposal, is that the disclosure carries out assessment diagnosis Agent in terms of two of multi-agent system Competitiveness, first is that hardware resource competitiveness, second is that task competitiveness.Wherein hardware resource competitiveness is mainly from examining Average CPU usage (UCPU) and two factor analyses of memory usage (URAM) when disconnected Agent test run, and task competes The major parameter of ability is the fault-tolerance and auxiliary program treatment effeciency of program, improves valuation functions and more accurately filters out Optimal Agent.
Further, the expression formula of the fault-tolerance FT of Agent program are as follows:
FT=max (x)/y；
Wherein, FT refers to that diagnosis Agent receives y item key warning message, if in x loss of learning or occurred abnormal It still is able to be accurately judged to fault element in the case where change.
Further, if comprising p simple wiring substations and q complicated wiring substation in power supply interrupted district, in core The expression formula of the operational efficiency EAP of data preprocessing procedures is carried out before diagnostic program operation are as follows:
EAP=OPT (O (f (p)), O (f (q)))/(p+q)
Wherein, OPT () is that calculation method takes major function；O () is the time complexity calculating function for diagnosing Agent； Simple wiring, which refers to, only has a bus inside each substation；Complicated wiring, which refers to inside substation, at least two buses.
Further, the diagnosis algorithm is Petri network algorithm, and/or tree algorithm, Bayes net algorithm and expert system Any algorithm in system algorithm.
The second aspect of the disclosure provides a kind of electric network fault multi-agent system preferentially diagnostic device, utilizes more agencies System carries out efficiency evaluation to present diagnosis algorithm, carries out event for some specific failure selection algorithm the most suitable Barrier diagnosis, improves whole diagnosis efficiency.
To achieve the goals above, the disclosure adopts the following technical scheme that
A kind of electric network fault multi-agent system preferentially diagnostic device, comprising:
Multi-agent system；The multi-agent system forms set A={ A by m diagnosis Agent1,A2,…,Am, Ai∈ A, I=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each diagnosis Agent is examined with one Disconnected algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm；
Task distributes Agent, is assessed by valuation functions E each diagnosis Agent, screens valuation functions E The maximum diagnosis Agent of value carries out fault diagnosis as optimal Agent.
Further, the expression formula of the valuation functions E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention property set having It closes, n indicates the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value are preset And
Further, the expression formula of the valuation functions E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP= 1；UCPUAverage CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is The fault-tolerance of Agent program；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, Quantitative criteria are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
The third aspect of the disclosure provides a kind of computer readable storage medium.
A kind of computer readable storage medium of the disclosure, is stored thereon with computer program, which is held by processor The step of electric network fault multi-agent system as described above preferentially in diagnostic method is realized when row.
The beneficial effect of the disclosure is:
The disclosure constructs multi-agent system and task distributes Agent, and wherein multi-agent system is by m diagnosis Agent；Each Agent and diagnosis algorithm of diagnosis corresponds, and is encapsulated by corresponding diagnosis algorithm；Task distribution Agent is by commenting Estimate function E to assess each diagnosis Agent, screens the maximum diagnosis Agent of valuation functions E value as optimal Agent carries out fault diagnosis, efficiency evaluation is carried out to present diagnosis algorithm, from time complexity, rate of correct diagnosis, applicability Etc. many aspects, it is unified to evaluate, carry out fault diagnosis for some specific failure selection algorithm the most suitable in this way, improve The diagnosis efficiency of whole multi-agent system.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is a kind of electric network fault multi-agent system preferentially diagnostic method flow chart of the embodiment of the present disclosure.
Fig. 2 is a kind of electric network fault multi-agent system preferentially diagnostic device structural schematic diagram that the embodiment of the present disclosure provides.
Specific embodiment
The disclosure is described further with embodiment with reference to the accompanying drawing.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another It indicates, all technical and scientific terms used herein has usual with disclosure person of an ordinary skill in the technical field The identical meanings of understanding.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
Term is explained:
FT, fault tolerance, the fault-tolerance of program；
EAP, efficiency of auxiliary program, auxiliary program treatment effeciency.
MAS, Multi-Agent System, multi-agent system.
Agent: agency；
Agent is a kind of intelligent integrated program established on the basis of high-performance calculation, and MAS is for different in system The characteristics of Agent, is distributed by description to problem, materialization and task, Task-decomposing to multiple Agent or some most Excellent Agent is completed, and thought is suitble to the intelligent solution of extensive diagnosis problem.
As shown in Figure 1, a kind of electric network fault multi-agent system of the embodiment of the present disclosure preferentially diagnostic method, comprising:
Multi-agent system is constructed, the multi-agent system forms set, each diagnosis Agent and one by m diagnosis Agent A diagnosis algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm；
Building task distributes Agent；Task is distributed Agent and is commented by valuation functions E each diagnosis Agent Estimate, the screening maximum diagnosis Agent of valuation functions E value carries out fault diagnosis as optimal Agent.
It is described in detail the scheme of the embodiment of the present disclosure combined with specific embodiments below:
Embodiment 1
A kind of electric network fault multi-agent system of the present embodiment preferentially diagnostic method, comprising:
Step (1): building multi-agent system, the multi-agent system form set A={ A by m diagnosis Agent1, A2,…,Am, Ai∈ A, i=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each examine Disconnected Agent and diagnosis algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm.
Specifically, the diagnosis algorithm is including but not limited to Petri network algorithm, and/or tree algorithm, Bayes net algorithm With expert system algorithm.
Step (2): building task distributes Agent；Task distributes Agent and diagnoses Agent to each by valuation functions E It is assessed, the screening maximum diagnosis Agent of valuation functions E value carries out fault diagnosis as optimal Agent；The assessment letter The expression formula of number E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention property set having It closes, n indicates the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value are preset And
The advantages of above-mentioned technical proposal, is, diagnoses all resources and the value ratio accordingly having in Agent by each Rate be multiplied after add up and, as it is each diagnosis Agent assessed value, when diagnosis Agent assessed value it is bigger, then illustrate mutually to see patients Disconnected Agent is optimal Agent.
Wherein, resource refers to the attribute relevant to fault diagnosis that Agent program has；
It is when the reason of the assessed value of diagnosis Agent is bigger, then the corresponding diagnosis Agent of explanation is optimal Agent:
The attribute of the Agent of the present embodiment setting is all, to efficiency of fault diagnosis more related, category relevant to fault diagnosis Property value is bigger, and assessed value is higher, therefore this more suitable failure of Agent.
Specifically, resource RjThe value ratio W havingjDynamic adjustment can be carried out according to demand.
The advantages of above-mentioned technical proposal, is, carries out being worth ratio possessed by dynamic adjustresources according to demand, improve Valuation functions more accurately filter out optimal Agent.
The present embodiment constructs multi-agent system and task distributes Agent, and wherein multi-agent system is by m diagnosis Agent；Often Agent and diagnosis algorithm of a diagnosis corresponds, and is encapsulated by corresponding diagnosis algorithm；Task distribution Agent passes through Valuation functions E assesses each diagnosis Agent, screens the maximum diagnosis Agent of valuation functions E value as optimal Agent carries out fault diagnosis, efficiency evaluation is carried out to present diagnosis algorithm, from time complexity, rate of correct diagnosis, applicability Etc. many aspects, it is unified to evaluate, carry out fault diagnosis for some specific failure selection algorithm the most suitable in this way, improve The diagnosis efficiency of whole multi-agent system.
Embodiment 2
Present embodiments provide a kind of electric network fault multi-agent system preferentially diagnostic method, comprising:
Step (a): building multi-agent system, the multi-agent system form set A={ A by m diagnosis Agent1, A2,…,Am, Ai∈ A, i=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each examine Disconnected Agent and diagnosis algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm.
Specifically, the diagnosis algorithm is including but not limited to Petri network algorithm, and/or tree algorithm, Bayes net algorithm With expert system algorithm.
Step (b): building task distributes Agent；Task distributes Agent and diagnoses Agent to each by valuation functions E It is assessed, the screening maximum diagnosis Agent of valuation functions E value carries out fault diagnosis as optimal Agent；The assessment letter The expression formula of number E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP= 1；UCPUAverage CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is The fault-tolerance of Agent program；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, Quantitative criteria are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
Wherein, UCPUAnd URAMIt is by realizing that running each Agent obtains.UCPUExactly run electricity when Agent Brain CPU is averaged occupancy；URAMComputer when being exactly operational diagnostics Agent is averaged memory usage.
For example, user requires diagnosis speed-priority, such WCPU、WRAMThe amount of characterization Agent arithmetic speed can be arranged It is larger；User requires diagnostic accuracy preferential, such WFT、WEAPWhat the amount of characterization Agent operation accuracy can be arranged It is larger.
The present embodiment carries out the competitiveness of assessment diagnosis Agent in terms of two of multi-agent system, first is that hardware provides Source competitiveness, second is that task competitiveness.Wherein hardware resource competitiveness is mainly from average when diagnosis Agent test run Two factor analyses of CPU usage (UCPU) and memory usage (URAM), and the major parameter of task competitiveness is program Fault-tolerance and auxiliary program treatment effeciency, improve valuation functions and more accurately filter out optimal Agent.
Specifically, the expression formula of the fault-tolerance FT of Agent program are as follows:
FT=max (x)/y；
Wherein, FT refers to that diagnosis Agent receives y item key warning message, if in x loss of learning or occurred abnormal It still is able to be accurately judged to fault element in the case where change.
If being transported comprising p simple wiring substations and q complicated wiring substation in kernel diagnosis program in power supply interrupted district The expression formula of the operational efficiency EAP of data preprocessing procedures is carried out before row are as follows:
EAP=OPT (O (f (p)), O (f (q)))/(p+q)
Wherein, OPT () is that calculation method takes major function；O () is the time complexity calculating function for diagnosing Agent； Simple wiring, which refers to, only has a bus inside each substation；Complicated wiring, which refers to inside substation, at least two buses.
Time complexity calculates the method that function calculates: Agent program is up to several heavy for circulations, and only one weight is then Time complexity is O (q), and double is then O (q2), and so on, if there is two points then be O (logq), two points of for example quick powers, Binary chop, if one one two points of for circulating sleeve, time complexity is then O (qlogq).
For example, the Agent of Petri network algorithm, the time complexity for handling simple wiring is O (logN), and complicated wiring is O (N2)；The Agent of and/or tree algorithm (And/Or Tree, AOT), the time complexity for handling simple wiring is O (N), and complexity connects Line is O (NLogN).It can be seen that Petri network is dominant in terms of handling simple wiring, and and/or tree algorithm is in terms of handling complicated wiring It is dominant, therefore the EAP of Petri network algorithm is expressed as EAPPetri=p/p+q；The EAP of and/or tree algorithm is expressed as EAPAOT=q/p+q.
Such as:
Fault condition 1: failure is related to Liang Ge substation, a complicated wiring, a simple wiring.User requires speed excellent First.It is as shown in table 1 to assess parameter.
1 environment 1 of table assesses parameter
It wherein, is the value ratio set by being required according to user in bracket.
According to formula E=WCPU(1-UCPU)+WRAM(1-URAM)+WFTFT+WEAPEAP can acquire commenting for Petri network algorithm Valuation EPetri=0.633, the assessed value E of and/or tree algorithmAOT=0.607, EPetri>EAOT, therefore, select Petri network Agent As optimal diagnosis Agent.
Fault condition 2: failure is related to Liang Ge substation, a complicated wiring, a simple wiring.User requires diagnosis quasi- It is really preferential.It is as shown in table 2 to assess parameter.
2 environment 2 of table assesses parameter
It wherein, is the value ratio set by being required according to user in bracket.
According to formula E=WCPU(1-UCPU)+WRAM(1-URAM)+WFTFT+WEAPEAP can acquire EPetri=0.482, EAOT= 0.518, EPetri<EAOT, therefore, select and/or tree Agent as optimal diagnosis Agent.
Fault condition 3: failure is related to four substations, three complicated wiring, a simple wiring.User requires speed excellent First.It is as shown in table 3 to assess parameter.
3 environment 3 of table assesses parameter
It wherein, is the value ratio set by being required according to user in bracket.
According to formula E=WCPU(1-UCPU)+WRAM(1-URAM)+WFTFT+WEAPEAP can acquire EPetri=0.583, EAOT= 0.657, EPetri<EAOT, therefore, select and/or tree Agent as optimal diagnosis Agent.
The present embodiment distributes Agent by building multi-agent system and task, and wherein multi-agent system is diagnosed by m Agent；Agent and diagnosis algorithm of each diagnosis corresponds, and is encapsulated by corresponding diagnosis algorithm；Task distribution Agent assesses each diagnosis Agent by valuation functions E, screens the maximum diagnosis Agent of valuation functions E value Fault diagnosis is carried out as optimal Agent, efficiency evaluation is carried out to present diagnosis algorithm, it is correct from time complexity, diagnosis The many aspects such as rate, applicability, it is unified to evaluate, failure is carried out for some specific failure selection algorithm the most suitable in this way Diagnosis, improves the diagnosis efficiency of whole multi-agent system.
Embodiment three
As shown in Fig. 2, present embodiments providing a kind of electric network fault multi-agent system preferentially diagnostic device, comprising:
Multi-agent system；The multi-agent system forms set A={ A by m diagnosis Agent1,A2,…,Am, Ai∈ A, I=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each diagnosis Agent is examined with one Disconnected algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm；
Task distributes Agent, is assessed by valuation functions E each diagnosis Agent, screens valuation functions E The maximum diagnosis Agent of value carries out fault diagnosis as optimal Agent.
In one embodiment, the expression formula of the valuation functions E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention property set having It closes, n indicates the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value are preset And
In another embodiment, the expression formula of the valuation functions E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP= 1；UCPUAverage CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is The fault-tolerance of Agent program；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, Quantitative criteria are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
Example IV
Present embodiments provide a kind of computer readable storage medium.
A kind of computer readable storage medium of the present embodiment, is stored thereon with computer program, and the program is by processor The step in embodiment one or embodiment two is realized when execution.
The present embodiment distributes Agent by building multi-agent system and task, and wherein multi-agent system is diagnosed by m Agent；Agent and diagnosis algorithm of each diagnosis corresponds, and is encapsulated by corresponding diagnosis algorithm；Task distribution Agent assesses each diagnosis Agent by valuation functions E, screens the maximum diagnosis Agent of valuation functions E value Fault diagnosis is carried out as optimal Agent, efficiency evaluation is carried out to present diagnosis algorithm, it is correct from time complexity, diagnosis The many aspects such as rate, applicability, it is unified to evaluate, failure is carried out for some specific failure selection algorithm the most suitable in this way Diagnosis, improves the diagnosis efficiency of whole multi-agent system.
It should be understood by those skilled in the art that, embodiment of the disclosure can provide as method, system or computer program Product.Therefore, the shape of hardware embodiment, software implementation or embodiment combining software and hardware aspects can be used in the disclosure Formula.Moreover, the disclosure, which can be used, can use storage in the computer that one or more wherein includes computer usable program code The form for the computer program product implemented on medium (including but not limited to magnetic disk storage and optical memory etc.).
The disclosure is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present disclosure Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random AccessMemory, RAM) etc..
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.

Claims (10)

1. a kind of electric network fault multi-agent system preferentially diagnostic method characterized by comprising
Step (1): building multi-agent system, the multi-agent system form set A={ A by m diagnosis Agent1,A2,…, Am, Ai∈ A, i=1,2 ..., m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Each diagnosis Agent and diagnosis algorithm corresponds, and is encapsulated by corresponding diagnosis algorithm；
Step (2): building task distributes Agent；Task is distributed Agent and is carried out by valuation functions E to each diagnosis Agent Assessment, the screening maximum diagnosis Agent of valuation functions E value carry out fault diagnosis as optimal Agent.
2. a kind of electric network fault multi-agent system as described in claim 1 preferentially diagnostic method, which is characterized in that the assessment The expression formula of function E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention attribute set having, n Indicate the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value preset and
3. a kind of electric network fault multi-agent system as claimed in claim 2 preferentially diagnostic method, which is characterized in that resource RjTool Some value ratio WjDynamic adjustment can be carried out according to demand.
4. a kind of electric network fault multi-agent system as described in claim 1 preferentially diagnostic method, which is characterized in that the assessment The expression formula of function E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP=1；UCPU Average CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is Agent journey The fault-tolerance of sequence；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, quantitative criteria Are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
5. a kind of electric network fault multi-agent system as claimed in claim 4 preferentially diagnostic method, which is characterized in that Agent journey The expression formula of the fault-tolerance FT of sequence are as follows:
FT=max (x)/y；
Wherein, FT refers to that diagnosis Agent receives y item key warning message, if in x loss of learning or be distorted In the case of still be able to be accurately judged to fault element.
6. a kind of electric network fault multi-agent system as claimed in claim 4 preferentially diagnostic method, which is characterized in that set power failure area Comprising p simple wiring substations and q complicated wiring substation in domain, it is pre- that data are carried out before kernel diagnosis program is run The expression formula of the operational efficiency EAP of processing routine are as follows:
EAP=OPT (O (f (p)), O (f (q)))/(p+q)
Wherein, OPT () is that calculation method takes major function；O () is the time complexity calculating function for diagnosing Agent；Simply Wiring, which refers to, only has a bus inside each substation；Complicated wiring, which refers to inside substation, at least two buses.
7. a kind of electric network fault multi-agent system as described in claim 1 preferentially diagnostic method, which is characterized in that the diagnosis Algorithm is any algorithm in Petri network algorithm, and/or tree algorithm, Bayes net algorithm and expert system algorithm.
8. a kind of electric network fault multi-agent system preferentially diagnostic device characterized by comprising
Multi-agent system；The multi-agent system forms set A={ A by m diagnosis Agent1,A2,…,Am, Ai∈ A, i=1, 2,…,m；AiIndicate that i-th diagnosis Agent, m are the positive integer more than or equal to 2；Agent and diagnosis of each diagnosis is calculated Method corresponds, and is encapsulated by corresponding diagnosis algorithm；
Task distributes Agent, is assessed by valuation functions E each diagnosis Agent, screens valuation functions E value Maximum diagnosis Agent carries out fault diagnosis as optimal Agent.
9. a kind of electric network fault multi-agent system as claimed in claim 8 preferentially diagnostic device, which is characterized in that the assessment The expression formula of function E are as follows:
Wherein, RjIndicate j-th of resource, Rj∈ R, R={ R1,R2,…,Rn, R indicates AiThe resource contention attribute set having, n Indicate the number of elements in resource contention attribute set R；WjIndicate resource RjThe value ratio having, value preset and
Or
The expression formula of the valuation functions E are as follows:
E=WCPU*(1-UCPU)+WRAM*(1-URAM)+WFT*FT+WEAP*EAP
Wherein, WCPU、WRAM、WFTAnd WEAPRespectively UCPU、URAM, FT, EAP value ratio, WCPU+WRAM+WFT+WEAP=1；UCPU Average CPU usage when to diagnose Agent test run；URAMMemory rate when to diagnose Agent test run；FT is Agent journey The fault-tolerance of sequence；EAP refers to the operational efficiency that data preprocessing procedures are carried out before the operation of kernel diagnosis program, quantitative criteria Are as follows: with time complexity to refer to, advantage operation task accounts for the ratio of entire task processing queue.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor It realizes when execution such as the step in electric network fault multi-agent system of any of claims 1-7 preferentially diagnostic method.
CN201910593820.9A 2019-07-03 2019-07-03 A kind of electric network fault multi-agent system preferentially diagnostic method and device Pending CN110378580A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910593820.9A CN110378580A (en) 2019-07-03 2019-07-03 A kind of electric network fault multi-agent system preferentially diagnostic method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910593820.9A CN110378580A (en) 2019-07-03 2019-07-03 A kind of electric network fault multi-agent system preferentially diagnostic method and device

Publications (1)

Publication Number Publication Date
CN110378580A true CN110378580A (en) 2019-10-25

Family

ID=68251869

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910593820.9A Pending CN110378580A (en) 2019-07-03 2019-07-03 A kind of electric network fault multi-agent system preferentially diagnostic method and device

Country Status (1)

Country Link
CN (1) CN110378580A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112055068A (en) * 2020-08-28 2020-12-08 合肥工业大学 Distribution method, device, terminal and storage medium of multi-agent system master control node

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103439629A (en) * 2013-08-05 2013-12-11 国家电网公司 Power distribution network fault diagnosis system based on data grid
CN105894213A (en) * 2016-04-27 2016-08-24 东北大学 Multi-agent grid fault diagnosis system and method based on blackboard model
CN109426912A (en) * 2017-08-31 2019-03-05 阿里巴巴集团控股有限公司 Air control system optimization method, system, device and electronic equipment

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103439629A (en) * 2013-08-05 2013-12-11 国家电网公司 Power distribution network fault diagnosis system based on data grid
CN105894213A (en) * 2016-04-27 2016-08-24 东北大学 Multi-agent grid fault diagnosis system and method based on blackboard model
CN109426912A (en) * 2017-08-31 2019-03-05 阿里巴巴集团控股有限公司 Air control system optimization method, system, device and electronic equipment

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112055068A (en) * 2020-08-28 2020-12-08 合肥工业大学 Distribution method, device, terminal and storage medium of multi-agent system master control node

Similar Documents

Publication Publication Date Title
CN111553590B (en) Radar embedded health management system
CN107203450A (en) The sorting technique and equipment of failure
CN105719062B (en) A kind of power grid risk considering double probability of malfunction characteristic and weak link appraisal procedure
CN103617561A (en) System and method for evaluating state of secondary device of power grid intelligent substation
CN110221145A (en) Fault Diagnosis for Electrical Equipment method, apparatus and terminal device
CN106209974B (en) A kind of method of data synchronization, equipment and system
CN108228412A (en) A kind of method and device based on system health degree faults of monitoring system and hidden danger
CN109299846A (en) A kind of nuclear power plant equipment analysis method for reliability, system and terminal device
CN108197774A (en) A kind of abnormality diagnostic method and device of distributed photovoltaic power generation amount
CN107679089A (en) A kind of cleaning method for electric power sensing data, device and system
CN108123987A (en) The method and device of master scheduler is determined from cloud computing system
CN109102142A (en) A kind of personnel evaluation methods and system based on evaluation criterion tree
CN105894212A (en) Comprehensive evaluation method for coupling and decoupling ring of electromagnetic ring network
CN110320443A (en) The determination method and system in power failure section in a kind of low-voltage network
CN110378580A (en) A kind of electric network fault multi-agent system preferentially diagnostic method and device
CN106548284A (en) A kind of adaptive mode massing power grid security Alarm Assessment method towards operation regulation and control
CN109325603A (en) Failed request processing method, device and terminal device
CN109559206A (en) A kind of regional enterprises Credit Evaluation System method, apparatus and terminal device
CN107086565B (en) Expected accident automatic selection method based on aggregation theory
Javadi et al. Identification of simultaneously congested transmission lines in power systems operation and market analysis
CN111654417A (en) Evaluation method and device, storage medium, processor and train
CN106708624A (en) Adaptive adjustment method for calculation resources in multiple working areas
CN110415136B (en) Service capability evaluation system and method for power dispatching automation system
CN115392747A (en) Method, device and system for evaluating health degree of power grid regulation and control system and storage medium
CN110361609A (en) Extra-high voltage equipment monitors system and method

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20191025

RJ01 Rejection of invention patent application after publication