CN115022192A - Resource selection method and system for evolutionary game network information system - Google Patents

Resource selection method and system for evolutionary game network information system Download PDF

Info

Publication number
CN115022192A
CN115022192A CN202210615542.4A CN202210615542A CN115022192A CN 115022192 A CN115022192 A CN 115022192A CN 202210615542 A CN202210615542 A CN 202210615542A CN 115022192 A CN115022192 A CN 115022192A
Authority
CN
China
Prior art keywords
decision
node
task
resource
follows
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210615542.4A
Other languages
Chinese (zh)
Other versions
CN115022192B (en
Inventor
张婷婷
宋爱国
董会
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.)
Southeast University
Army Engineering University of PLA
Original Assignee
Southeast University
Army Engineering University of PLA
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 Southeast University, Army Engineering University of PLA filed Critical Southeast University
Priority to CN202210615542.4A priority Critical patent/CN115022192B/en
Publication of CN115022192A publication Critical patent/CN115022192A/en
Application granted granted Critical
Publication of CN115022192B publication Critical patent/CN115022192B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Algebra (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a resource selection method and a system of an evolutionary game network information system in the field of network resource allocation, which comprises the following steps: obtaining a decision space in a military countermeasure network, and constructing a task completion function in the task execution process of each resource node in the decision space; overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model; randomly selecting a strategy to form a decision combination, and calculating the profit value of each resource node for executing the decision combination; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination; selecting resources for the military countermeasure network according to the updated decision combination; after part of physical nodes in the network information system are damaged, the invention accurately provides a resource integration scheme to recover the core capability of the system and improve the survivability of the network information system.

Description

Resource selection method and system for evolutionary game network information system
Technical Field
The invention belongs to the field of network resource allocation, and particularly relates to a resource selection method and system for an evolutionary game network information system.
Background
At present, the selection of the battle resources in China mainly depends on a plan, the plan which is similar to the situation of the current battlefield is selected, and then the node resources are selected according to the plan to complete the task. Along with the development of artificial intelligence technology, AI technology is more and more applied to the battlefield, and resource integration by means of a plan has obvious disadvantages. On one hand, with the use of a large amount of intelligent and unmanned equipment, the capability of the intelligent and unmanned equipment is changed through self-learning and does not accord with the design basis of a plan; on the other hand, the current battle is a battle style with quick decision and dynamic interference, and the plan is difficult to cover the complex future battlefield situation, so that the resource integration is not accurate, and the dynamic adjustment of the resource combination efficiency is low. Therefore, how to accurately provide a resource integration scheme according to the battlefield situation in the future battlefield in a high dynamic environment is a difficult problem to be solved urgently in the construction of a network information system.
Disclosure of Invention
The invention aims to provide a resource selection method and a resource selection system for an evolutionary game network information system, which accurately provide a resource integration scheme to recover the core capability of the system and improve the survivability of the network information system after part of physical nodes in the network information system are damaged.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention provides a resource selection method of an evolutionary game network information system, which comprises the following steps:
obtaining a decision space in a military countermeasure network, and constructing a task completion function in the task execution process of each resource node in the decision space;
overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model;
randomly selecting a strategy to form a decision combination, and calculating the profit value of each resource node for executing the decision combination; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination; and selecting resources for the military countermeasure network according to the updated decision combination.
Preferably, the decision space is a set S of surviving resource nodes; the resource node set s comprises a sensing node, an intelligence processing node, a decision node and a fire node.
Preferably, the method for constructing the task completion function in the process of executing the task by the sensing node includes:
the sensing node provides a high-precision sensing range AoH of:
Figure BDA0003674136540000021
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000022
the sensing node provides a medium precision sensing range AoM as follows:
Figure BDA0003674136540000023
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000024
the sensing node provides a high-precision sensing range AoL of:
Figure BDA0003674136540000025
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000026
in the formula, s i Denoted as resource nodes, S' is denoted as a set of resource nodes performing tasks,
Figure BDA0003674136540000027
minus (·) is expressed as a subtractive calculation of range; ins (-) is expressed as the intersection calculation of the ranges; s i .cl＝O b Representing the resource node as a sensing node; s i Selecting a high-precision perception value range as Do ═ H; s i D, M is expressed as the accuracy perception value range in the selection; s i Let Do-L denote to select a low-precision perceptual value range; x and y represent input variables; oo x And Oo y Expressed as the center of a circle of the sensing range; s i Ro is expressed as the radius of the sensing range.
Preferably, the method for constructing the task completion function in the process of executing the task by the intelligence processing node comprises the following steps:
the intelligence analysis force Co in the process of executing the task is as follows:
Figure BDA0003674136540000031
the task completion degree function of the information processing node has the expression formula as follows:
Figure BDA0003674136540000032
in the formula, s i .cl＝O r Representing resource nodes as intelligence processingA node; s i Po is expressed as a nodal analysis force constant; col (Col) i Expressed as intelligence analysis capability lower limit; cou i Expressed as the intelligence analysis capability upper limit.
Preferably, the expression of the task completion function in the process of executing the task by the decision node is as follows:
the decision force Cd in the task execution process is as follows:
Figure BDA0003674136540000033
the task completion degree function of the decision node has the expression formula as follows:
Figure BDA0003674136540000034
in the formula, s i D denotes a resource node as a decision node; s is i Pd is expressed as a node decision force constant; cdl i Expressed as a decision-making capability lower bound; cdu i Expressed as the decision capability upper bound.
Preferably, the expression of the task completion function in the task execution process of the fire node is as follows:
the firepower node provides a high-precision sensing range AaH of:
Figure BDA0003674136540000041
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000042
the fire node provides a middle precision perception range AaM as follows:
Figure BDA0003674136540000043
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000044
the firepower node provides a high-precision sensing range AaL of:
Figure BDA0003674136540000045
s.t.(x-s o .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000046
in the formula, s i A indicates that a resource node is a sensing node; s i Selecting a high-precision firepower value range as Da-H; s is i Da ═ M denotes the accuracy fire value range in the selection; s i Da ═ L represents the selection of a low-precision fire value range; oa is x ，Oa y The coordinates of the center of the circle expressed as the sensing range; s i Ra is expressed as the fire range radius.
Preferably, the expression formula of the task objective function is as follows:
Figure BDA0003674136540000047
in the formula, ω i And expressing the demand degree of executing the task for the ith resource node.
Preferably, the expression formula of the energy consumption constraint is as follows:
Figure BDA0003674136540000051
in the formula, R 'is represented as a fault power supply line set R' i Denoted as faulty supply line; r' i Rs represents the set of nodes on the faulty supply line; r' i REn represents the upper energy consumption limit; s j En represents the total energy consumption of each resource node.
Preferably, the expression formula of the profit value of each resource node executing the decision combination is as follows:
Figure BDA0003674136540000052
Figure BDA0003674136540000053
Figure BDA0003674136540000054
in the formula, T' is expressed as a decision combination; when the resource node set S 'is feasible to execute the decision combination T', the decision combination T 'is recorded as T' 1; otherwise, it is recorded as T' ═ 0.
Preferably, the method for performing evolution solution on the military countermeasure game decision model and updating the decision combination according to the individual income value comprises the following steps:
the resource nodes are used as game individuals to sequentially execute the decision combination and then reverse the decision combination, and the game individuals continue to execute the reverse decision combination;
comparing the profit values in the process of executing the decision combination and executing the inverse decision combination, and updating the profit values into the decision combination according to the profit values;
and after a perturbation process with the probability p is added, a strategy is randomly selected again to form a new decision combination for evolution iteration, and when the number of the evolution iteration reaches a set threshold value, the decision combination is output.
Preferably, the decision combination is optimized by a monte carlo counterfactual regret value minimization algorithm.
The invention provides a control system for selecting resources of an evolutionary game network information system in a second aspect, which comprises:
the acquisition module is used for acquiring a decision space in a military countermeasure network;
the model construction module is used for constructing a task completion function in the task execution process of each resource node in the decision space; overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model;
the evolution module is used for randomly selecting strategies to form decision combinations and calculating the profit values of the decision combinations executed by the resource nodes; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination;
and the execution module is used for selecting resources for the military countermeasure network according to the updated decision combination.
Compared with the prior art, the invention has the beneficial effects that:
the method randomly selects strategies to form decision combinations, and calculates the profit value of each resource node for executing the decision combinations; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination; selecting resources for the military countermeasure network according to the updated decision combination; after part of physical nodes in the network information system are damaged, the invention accurately provides a resource integration scheme to recover the core capability of the system and improve the survivability of the network information system.
Drawings
Fig. 1 is a flowchart of an evolutionary gaming network information system resource selection method provided in an embodiment of the present invention;
FIG. 2 is a graph comparing the number of iterations of the present invention with a GA algorithm, provided by an embodiment of the present invention;
fig. 3 is a graph comparing the number of iterations with and without perturbation limitation provided by the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Example one
As shown in fig. 1, this embodiment provides a method for selecting an evolutionary game network information system resource, including:
obtaining a decision space in a military countermeasure network, wherein the decision space is a surviving resource node set S; the resource node set s comprises a sensing node, an information processing node, a decision node and a fire node; as shown in table 1;
TABLE 1 node resource Attribute
Figure BDA0003674136540000071
The method for constructing the task completion function in the task execution process of each resource node in the decision space comprises the following steps:
the sensing node provides a high-precision sensing range AoH as follows:
Figure BDA0003674136540000072
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000073
the sensing node provides a medium precision sensing range AoM as follows:
Figure BDA0003674136540000074
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000081
the sensing node provides a high-precision sensing range AoL of:
Figure BDA0003674136540000082
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000083
in the formula, s i Denoted as resource nodes, S' is denoted as a set of resource nodes performing tasks,
Figure BDA0003674136540000086
minus (·) is expressed as a subtractive calculation of range; ins (-) is expressed as the intersection calculation of the ranges; s i .cl＝O b Representing the resource node as a sensing node; s i Selecting a high-precision perception value range as Do ═ H; s i D, M is expressed as the accuracy perception value range in the selection; s is i Let Do-L denote to select a low-precision perceptual value range; oo x And Oo y Expressed as the center of the sensing range; s i Ro is expressed as the radius of the sensing range.
Wherein, the expression formula of the intersection calculation of the range is as follows:
Ins(f 1 (x，y)，f 2 (x，y))＝{(x，y)|
(x，y)∈f 1 (x，y)∧(x，y)∈f 2 (x，y)}
the expression formula for the subtractive calculation of the range is:
Figure BDA0003674136540000084
in the formula, f 1 (. and f) 2 (. cndot.) is expressed as an arbitrary function, and x and y represent input variables.
The method for constructing the task completion function in the task execution process of the information processing node comprises the following steps:
the intelligence analysis force Co in the process of executing the task is as follows:
Figure BDA0003674136540000085
the task completion degree function of the information processing node has the expression formula as follows:
Figure BDA0003674136540000091
in the formula, s i .cl＝O r The resource node is represented as an information processing node; s i Po is expressed as a nodal analysis force constant; col (Col) i Expressed as intelligence analysis capability lower limit; cou i Expressed as the intelligence analysis capability upper limit.
The expression of the task completion function in the process of executing the task by the decision node is as follows:
the decision force Cd in the task execution process is as follows:
Figure BDA0003674136540000092
the task completion degree function of the decision node has the expression formula as follows:
Figure BDA0003674136540000093
in the formula, s i D denotes a resource node as a decision node; s i Pd is expressed as a node decision force constant; cdl i Expressed as a decision-making capability lower bound; cdu i Expressed as the decision capability upper bound.
The expression of the task completion function in the task execution process of the fire node is as follows:
the firepower node provides a high-precision sensing range AaH of:
Figure BDA0003674136540000094
s.t.(x-s o .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000095
the fire node provides a middle precision perception range AaM as follows:
Figure BDA0003674136540000096
s.t.(x-s i .Oa x ( 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000101
the firepower node provides a high-precision sensing range AaL as follows:
Figure BDA0003674136540000102
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure BDA0003674136540000103
in the formula, s i A indicates that the resource node is a sensing node; s i Selecting a high-precision firepower value range as Da-H; s i Da ═ M denotes the accuracy fire value range in the selection; s i Da ═ L represents the selection of a low-precision fire value range; oa is x ，Oa y Circle center coordinates expressed as a sensing range; s i Ra is expressed as the fire range radius.
Overlapping the task completion degree functions of all the resource nodes to obtain a task objective function, wherein the expression formula of the task objective function is as follows:
Figure BDA0003674136540000104
in the formula, ω i And expressing the demand degree of executing the task for the ith resource node.
Adding energy consumption constraint to a task objective function to establish a military countermeasure game decision model; the expression formula of the energy consumption constraint is as follows:
Figure BDA0003674136540000105
in the formula, R 'is represented as a fault power supply line set R' i Denoted as faulty supply line; r' i Rs represents the set of nodes on the faulty supply line; r' i REn represents the upper energy consumption limit; (ii) a s j En represents the total energy consumption of each resource node.
The expression formula of the military countermeasure game decision model is as follows:
Figure BDA0003674136540000111
randomly selecting a strategy to form a decision combination, and calculating the profit value of each resource node for executing the decision combination; the expression formula of the profit value of each resource node executing the decision combination is as follows:
Figure BDA0003674136540000112
Figure BDA0003674136540000113
Figure BDA0003674136540000114
in the formula, T' is expressed as a decision combination; when the resource node set S 'is feasible to execute the decision combination T', the decision combination T 'is recorded as T' 1; otherwise, it is recorded as T' ═ 0.
The method for carrying out evolution solution on the military countermeasure game decision model and updating the decision combination according to the individual income value comprises the following steps:
the resource nodes are used as game individuals to sequentially execute the decision combination and then reverse the decision combination, and the game individuals continue to execute the reverse decision combination;
comparing the profit values in the process of executing the decision combination and executing the inverse decision combination, and updating the profit values into the decision combination according to the profit values;
after a perturbation process with the probability p is added, a strategy is randomly selected again to form a new decision combination for evolution iteration, and the decision combination is optimized through a Monte Carlo regret value minimization algorithm; when the evolution iteration number reaches a set threshold value, outputting a decision combination; and selecting resources for the military countermeasure network according to the updated decision combination.
To ensure computational efficiency, the algorithm has two evolution rounds for each generation of evolution. The algorithm aims at searching to obtain a subset which enables the target function to be maximum, and strategy combinations corresponding to Nash equilibrium, which cannot be reached in a certain situation within 2 rounds, can be obtained by evolution of other initial strategies.
Simulation test
The invention selects to carry out simulation experiment on a Netlogo platform. And constructing a data set of the related information of four types of equipment, namely 80 radars, an intelligence analysis system, a decision system and a missile, and screening the attribute values in the table 1 from the data set to form a node resource list.
Describing tasks according to requirements, adding constraint conditions according to lines, and when the tasks are constructed, the number of nodes required for complete completion of the tasks is about 25, namely the node resources are set to have 68.75% of redundancy.
The experimental parameters are set to pr which is 0.4, the physical node loss event is simulated, the disturbance probability p which is 0.04 is set for the EGA-RO algorithm, the cross probability pc which is 0.75 and the variation probability pm which is 0.01 are set for the GA, and the termination condition is set to be evolution or evolution generation to 200 generations.
The experimental result can obviously show that the task completion degree of the integration scheme required by the EGA-RO algorithm is obviously higher than that of the GA algorithm, so that the effect of the resource optimization algorithm can be verified more reliably, and under different damage probabilities, disturbance probabilities, cross probabilities and variation probabilities, 36 groups of comparison tests are carried out to obtain data as shown in table 2; the experimental result can obviously show that the task completion degree of the integration scheme required by the EGA-RO algorithm is obviously higher than that of the GA algorithm, so that the effect of the resource optimization algorithm is more reliably verified
TABLE 2 EGA-RO algorithm vs. GA algorithm under different parameters
Figure BDA0003674136540000121
Figure BDA0003674136540000131
Figure BDA0003674136540000141
As shown in fig. 2, for 10 sets of data with the same effect obtained by the two algorithms, the experiment further compares the algebra of the optimal value corresponding to the scheme; according to the experimental data analysis, the EGA-RO algorithm provided by the invention has a proportion of 72.2% to obtain a solution with a better effect than that of a basic genetic algorithm (GA algorithm) based method, and when the same solution is obtained, the average algebra of the optimal scheme of the EGA-RO algorithm is 38, and the average algebra of the optimal scheme of the genetic algorithm is 95.8. The analysis result can show that the resource optimization method provided by the invention has obvious advantages over the conventional optimization method based on genetic algorithm when solving the research problem of the invention.
Secondly, based on the improvement of the algorithm adding the perturbation process limitation, the experiment compares the algorithm with the algorithm without the perturbation process limitation. In the experiment, the damage event is simulated by the damage probability pr of 0.4 and the damage probability pr of 0.5 respectively, the resource integration scheme is solved by the same damage result and the same initial strategy by the same disturbance probability p of 0.04, and the two algorithms are repeated for 10 times respectively.
As shown in fig. 3, when the damage probability pr is 0.4, there is 50% increase disturbance-limited resource and the preferred algorithm gm is lower than the no-disturbance limit. When the damage probability increases to pr 0.5, there is an increased 70% disturbance-limited resource-the preferred algorithm gm is lower than the no-disturbance limit. When pr is 0.4, the gm with/without disturbance limitation is respectively 29.7 and 46.6, and when pr is 0.4, the gm with/without disturbance limitation is respectively 23.5 and 40.1, and according to the analysis of experimental data, the addition of the disturbance limitation can lead the gm average to be advanced by 17, namely the addition of the disturbance limitation effectively improves the algorithm efficiency.
Example two
The embodiment provides a control system for resource selection of an evolved game network information system, where the control system provided in this embodiment can be applied to the control method in the first embodiment, and the control system includes:
the acquisition module is used for acquiring a decision space in a military countermeasure network;
the model construction module is used for constructing a task completion function in the task execution process of each resource node in the decision space; overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model;
the evolution module is used for randomly selecting strategies to form decision combinations and calculating the profit values of the decision combinations executed by the resource nodes; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination;
and the execution module is used for selecting resources for the military countermeasure network according to the updated decision combination.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (10)

1. A resource selection method for an evolutionary game network information system is characterized by comprising the following steps:
acquiring a decision space in a military countermeasure network, and constructing a task completion function in the task execution process of each resource node in the decision space;
overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model;
randomly selecting a strategy to form a decision combination, and calculating the profit value of each resource node for executing the decision combination; carrying out evolution solution on the military countermeasure game decision model according to the income value and updating the decision combination; and selecting resources for the military countermeasure network according to the updated decision combination.
2. The method for selecting the information system resources of the evolved game network according to claim 1, wherein the decision space is a set S of surviving resource nodes; the resource node set s comprises a sensing node, an intelligence processing node, a decision node and a fire node.
3. The method for selecting the information system resources of the evolved game network according to claim 2, wherein the method for constructing the task completion function in the process of executing the task by the sensing node comprises the following steps:
the sensing node provides a high-precision sensing range AoH of:
Figure FDA0003674136530000011
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000012
the sensing node provides a medium precision sensing range AoM as follows:
Figure FDA0003674136530000013
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000021
the sensing node provides a high-precision sensing range AoL of:
Figure FDA0003674136530000022
s.t.(x-s i .Oo x ) 2 +(y-s i .Oo y ) 2 ≤s i .ro 2
the sensing node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000023
in the formula, s i Denoted as resource nodes, S' is denoted as a set of resource nodes performing tasks,
Figure FDA0003674136530000024
minus (·) is expressed as a subtractive calculation of range; ins (-) is expressed as the intersection calculation of the ranges; s i .cl＝O b Representing the resource node as a sensing node; s is i Selecting a high-precision perception value range as Do ═ H; s i D, M is expressed as the accuracy perception value range in the selection; s is i L represents selecting a low-precision perception value range; x and y represent input variables; oo x And Oo y Expressed as the center of a circle of the sensing range; s i Ro is expressed as the radius of the sensing range.
4. The evolutionary gaming network information system resource selection method of claim 3, wherein the method for constructing the task completion function in the process of executing the task by the intelligence processing node comprises:
the intelligence analysis force Co in the process of executing the task is as follows:
Figure FDA0003674136530000025
the task completion degree function of the information processing node has the expression formula as follows:
Figure FDA0003674136530000026
in the formula, s i .cl＝O r The resource node is represented as an information processing node; s i Po is expressed as a nodal analysis force constant; col (Col) i Expressed as intelligence analysis capability lower limit; cou i Expressed as the intelligence analysis capability upper limit.
5. The evolutionary gaming network information system resource selection method of claim 4, wherein the task completion function in the process of executing the task by the decision node has an expression as follows:
the decision force Cd in the task execution process is as follows:
Figure FDA0003674136530000031
the task completion degree function of the decision node has the expression formula as follows:
Figure FDA0003674136530000032
in the formula, s i D denotes a resource node as a decision node; s i Pd is expressed as a node decision force constant; cdl i Expressed as a decision-making capability lower bound; cdu i Expressed as the decision capability upper bound.
6. The method for selecting the evolved game network information system resource according to claim 3, wherein the expression of the task completion function in the process of executing the task by the firepower node is as follows:
the firepower node provides a high-precision sensing range AaH of:
Figure FDA0003674136530000033
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000034
the fire node provides a middle precision perception range AaM as follows:
Figure FDA0003674136530000035
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of a high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000041
the firepower node provides a high-precision sensing range AaL of:
Figure FDA0003674136530000042
s.t.(x-s i .Oa x ) 2 +(y-s i .Oa y ) 2 ≤s i .ra 2
the firepower node executes the completion degree of the high-precision monitoring task, and the expression formula is as follows:
Figure FDA0003674136530000043
in the formula, s i A indicates that the resource node is a sensing node; s is i And Da ═ H represents the selected high-accuracy fire value range; s i Da ═ M denotes the accuracy fire value range in the selection; s is i Da ═ L represents the selection of a low-precision fire value range; oa is x ，Oa y Circle center coordinates expressed as a sensing range; s i Ra is expressed as fire range radius.
7. The method for selecting the evolved game network information system resource according to claim 1, wherein the expression formula of the energy consumption constraint is as follows:
Figure FDA0003674136530000044
in the formula, R 'is represented as a fault power supply line set R' i Denoted as faulty supply line; r' i Rs represents the set of nodes on the faulty supply line; r' i REn represents the upper energy consumption limit; s j En represents the total energy consumption of each resource node.
8. The method for selecting the evolutionary game network information system resource of claim 7, wherein the expression formula of the profit value of each resource node executing the decision combination is as follows:
Figure FDA0003674136530000045
Figure FDA0003674136530000051
Figure FDA0003674136530000052
in the formula, T' is expressed as a decision combination; when the resource node set S ' executes the decision combination T ' to be feasible, recording as T ' being 1; otherwise, it is recorded as T' ═ 0.
9. The method for selecting the information system resources of the evolutionary game network according to claim 8, wherein the method for evolutionarily solving the military countermeasure game decision model and updating the decision combination according to the individual profit value comprises the following steps:
the resource nodes are used as game individuals to sequentially execute the decision combination and then reverse the decision combination, and the game individuals continue to execute the reverse decision combination;
comparing the profit values in the process of executing the decision combination and executing the inverse decision combination, and updating the profit values into the decision combination according to the profit values;
and after a perturbation process with the probability p is added, a strategy is randomly selected again to form a new decision combination for evolution iteration, and when the number of the evolution iteration reaches a set threshold value, the decision combination is output.
10. A control system for resource selection of an evolved game network information system is characterized by comprising:
the acquisition module is used for acquiring a decision space in a military countermeasure network;
the model construction module is used for constructing a task completion function in the task execution process of each resource node in the decision space; overlapping the task completion degree functions of all resource nodes to obtain a task objective function, and adding energy consumption constraint to the task objective function to establish a military countermeasure game decision model;
the evolution module is used for randomly selecting strategies to form decision combinations and calculating the profit values of the decision combinations executed by the resource nodes; carrying out evolution solution on the military countermeasure game decision model according to the individual income value and updating the decision combination;
and the execution module is used for selecting resources for the military countermeasure network according to the updated decision combination.
CN202210615542.4A 2022-06-01 2022-06-01 Resource selection method and system for evolutionary game network information system Active CN115022192B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210615542.4A CN115022192B (en) 2022-06-01 2022-06-01 Resource selection method and system for evolutionary game network information system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210615542.4A CN115022192B (en) 2022-06-01 2022-06-01 Resource selection method and system for evolutionary game network information system

Publications (2)

Publication Number Publication Date
CN115022192A true CN115022192A (en) 2022-09-06
CN115022192B CN115022192B (en) 2023-05-23

Family

ID=83071068

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210615542.4A Active CN115022192B (en) 2022-06-01 2022-06-01 Resource selection method and system for evolutionary game network information system

Country Status (1)

Country Link
CN (1) CN115022192B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108833401A (en) * 2018-06-11 2018-11-16 中国人民解放军战略支援部队信息工程大学 Network active defensive strategy choosing method and device based on Bayes's evolutionary Game
CN112329348A (en) * 2020-11-06 2021-02-05 东北大学 Intelligent decision-making method for military countermeasure game under incomplete information condition

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108833401A (en) * 2018-06-11 2018-11-16 中国人民解放军战略支援部队信息工程大学 Network active defensive strategy choosing method and device based on Bayes's evolutionary Game
CN112329348A (en) * 2020-11-06 2021-02-05 东北大学 Intelligent decision-making method for military countermeasure game under incomplete information condition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
CRAWLEY E, ETC.: "System Architecture:Strategy and Product Development for Complex Systems", 《HOBOKEN: PEARSON HIGHER EDUCATION》 *
张婷婷等: "全军网络信息体系能力演化分析框架研究", 《指挥与控制学报》 *

Also Published As

Publication number Publication date
CN115022192B (en) 2023-05-23

Similar Documents

Publication Publication Date Title
Cuevas et al. A cuckoo search algorithm for multimodal optimization
CN109039428B (en) Relay satellite single-address antenna scheduling random search method based on conflict resolution
CN109858798B (en) Power grid investment decision modeling method and device for correlating transformation measures with voltage indexes
CN109344969B (en) Neural network system, training method thereof, and computer-readable medium
CN111695754A (en) Electric power Internet of things information security risk assessment method and device
CN114492675A (en) Intelligent fault cause diagnosis method for capacitor voltage transformer
CN110009181A (en) Distribution network transform measure and mistake load figureofmerit relevance method for digging and device
CN109886560A (en) Distribution network transform measure and rate of qualified voltage index relevance method for digging and device
CN111832911A (en) Underwater combat effectiveness evaluation method based on neural network algorithm
CN111461284A (en) Data discretization method, device, equipment and medium
CN111445065A (en) Energy consumption optimization method and system for refrigeration group control of data center
Xu et al. A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions
CN117170980B (en) Early warning method, device, equipment and storage medium for server hardware abnormality
Li et al. Improved shuffled frog leaping algorithm on system reliability analysis
CN115022192A (en) Resource selection method and system for evolutionary game network information system
Bujok Three steps to improve jellyfish search optimiser
CN116054144A (en) Distribution network reconstruction method, system and storage medium for distributed photovoltaic access
CN112434733B (en) Small-sample hard disk fault data generation method, storage medium and computing device
CN115345303A (en) Convolutional neural network weight tuning method, device, storage medium and electronic equipment
CN115185804A (en) Server performance prediction method, system, terminal and storage medium
EP3851921A1 (en) Distributed computer control system and method of operation thereof via collective learning
CN110059880B (en) Service discovery method and device
CN112712178A (en) Bayesian network structure learning method and system based on genetic algorithm
Kang et al. Multi-objective evolutionary optimization of 3D differentiated sensor network deployment
CN112967154B (en) Assessment method and device for Well-rolling of power system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant