CN114826782A - Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm - Google Patents
Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm Download PDFInfo
- Publication number
- CN114826782A CN114826782A CN202210738152.6A CN202210738152A CN114826782A CN 114826782 A CN114826782 A CN 114826782A CN 202210738152 A CN202210738152 A CN 202210738152A CN 114826782 A CN114826782 A CN 114826782A
- Authority
- CN
- China
- Prior art keywords
- heterogeneous
- negative feedback
- sdn controller
- mode
- optimization 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1433—Vulnerability analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
- H04L63/205—Network architectures or network communication protocols for network security for managing network security; network security policies in general involving negotiation or determination of the one or more network security mechanisms to be used, e.g. by negotiation between the client and the server or between peers or by selection according to the capabilities of the entities involved
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Genetics & Genomics (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a multi-mode arbitration negative feedback system based on a multi-objective optimization algorithm, which comprises a multi-mode arbitration module and a negative feedback optimization module; the multi-mode arbitrating module comprises a heterogeneous pool unit and a multi-mode arbitrator; the heterogeneous pool unit contains at least 3 heterogeneous SDN controllers; a multi-mode resolver performs consistency resolution on information distribution in a flow table of an output result set of the heterogeneous SDN controller; when the multi-mode resolver finds disturbance, the multi-mode resolver transmits a decision result and information distribution in a flow table of an input set of the heterogeneous SDN controller to the negative feedback optimization module, dynamically adjusts selection weight of the heterogeneous SDN controller through a multi-objective optimization algorithm, generates a preferred selection strategy to counter the disturbance of the multi-mode resolver through factors such as total confidence, processing time of the SDN controller, cleaning time, stability of the processing time, resource consumption cost and the like, achieves dynamic selection of the heterogeneous SDN controller, and improves safety defense capability of the system.
Description
Technical Field
The invention belongs to the technical field of mimicry defense, and particularly relates to a multi-mode arbitration negative feedback system based on a multi-objective optimization algorithm.
Background
With the rapid development of network technologies, SDN (software defined networking) can improve the operation speed of the network by deploying, managing and programming the network. In this centralized network management approach, the basic network infrastructure and applications are separated from each other. So that the system is gradually applied by each large enterprise. However, the current SDN controller is basically ineffective in responding to unknown vulnerability threats and cannot make corresponding dynamic adjustments.
The uniqueness of the SDN controller is changed by introducing a heterogeneous SDN controller, and a selection strategy of the disturbed SDN controller is dynamically changed by introducing a multi-objective algorithm, so that the robustness of the mimicry system is increased. The defense capability against unknown threats launched with unknown vulnerabilities is improved overall.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a multi-mode arbitration negative feedback system based on a multi-objective optimization algorithm.
The technical scheme adopted by the invention for solving the technical problems is as follows: a multi-mode arbitration negative feedback system based on a multi-objective optimization algorithm comprises a multi-mode arbitration module and a negative feedback optimization module; the multimode arbitration module comprises a heterogeneous pool unit and a multimode arbitrator; the heterogeneous pool unit comprises a heterogeneous pool selector and at least 3 heterogeneous SDN controllers; the multi-mode resolver performs consistency resolution on information distribution in a flow table of an output result set of the heterogeneous SDN controller, and issues a resolution result to a switch and a negative feedback optimization module; when the multi-mode resolver finds disturbance, the resolver transmits a decision result and information distribution in a flow table of an input set of the heterogeneous SDN controller to the negative feedback module, and dynamically adjusts the selection weight of the SDN controller in the heterogeneous pool through a multi-objective optimization algorithm; and the negative feedback optimization module issues the selection strategy in the negative feedback iteration result to the heterogeneous pool selector, and the heterogeneous pool selector selects the heterogeneous SDN controller in the next period according to the issued strategy.
Further, the multi-mode resolver issues the decision result data set and the input parameters to the negative feedback optimization module only when the multi-mode resolver is disturbed.
Further, if and only if the multi-mode resolver is disturbed, the multi-mode resolver marks 1 or more heterogeneous SDN controllers causing the disturbance as a cleaned state, and suspends the task until the negative feedback optimization module executes the selection strategy and then executes a cleaning reset task.
Further, the multi-decision module transmits parameters required by initialization of the multi-objective optimization algorithm in the negative feedback optimization module to the negative feedback optimization module only when the multi-decision device is disturbed, wherein the parameters comprise current selection weights of all heterogeneous SDN controllers, historical average values of processing time of all heterogeneous SDN controllers, historical average values of cleaning time of all heterogeneous SDN controllers, and historical average values of resource consumption cost of all heterogeneous SDN controllers.
Furthermore, when the multi-resolver is disturbed, the negative feedback optimization module receives parameters transmitted by the multi-resolver and initializes the parameters of the algorithm model, performs iterative computation according to a multi-target optimization algorithm based on a genetic algorithm, and issues an output heterogeneous SDN controller selection strategy to the heterogeneous pool selector.
Further, the heterogeneous SDN controller causing disturbance is cleaned after the negative feedback optimization module selects strategy updating iteration is completed, the selection weight of the cleaned heterogeneous SDN controller is updated according to the selected strategy, and meanwhile, the cleaning time is used for updating the historical average cleaning time of the heterogeneous SDN controller.
Further, the multi-objective optimization algorithm considers the total confidence, the processing time of the SDN controller, the cleaning time, the stability of the processing time and the resource consumption cost; the processing time, the cleaning time and the resource consumption cost of the heterogeneous SDN controller are historical average values, and the heterogeneous SDN controller is updated after each negative feedback process is executed.
The multi-objective optimization algorithm comprises the following steps:
s1: initializing parameters of the algorithm model according to the parameters transmitted by the multi-mode resolver;
s2: obtaining a first generation filial generation population through three basic operations of selection, crossing and variation of a genetic algorithm after non-dominated sorting;
s3: from the second generation, merging the parent population and the offspring population, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting proper individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population;
s4: generating a new filial generation population through the basic operation of a genetic algorithm, and repeating the steps until the requirement is met;
s5: issuing the output optimal heterogeneous SDN controller selection strategy to a heterogeneous pool selector, starting to execute a suspended heterogeneous SDN controller cleaning task, and respectively recording and calculating cleaning time and then updating historical data.
Compared with the prior art, the invention has the following beneficial effects: the system comprises a multi-mode arbitration module and a negative feedback optimization module; the multi-mode arbitrating module comprises a heterogeneous pool unit and a multi-mode arbitrator; the heterogeneous pool unit comprises a heterogeneous pool selector and heterogeneous SDN controllers with the same functions and different architectures, the heterogeneous SDN controllers with different architectures comprise different backdoors and vulnerabilities, and the heterogeneous selector preferentially selects the heterogeneous SDN controller with higher robustness according to a selection strategy, so that the system has greatly increased resistance to different unknown vulnerability threats. In addition, the negative feedback optimization module performs iterative optimization based on a plurality of parameters transmitted by the multi-mode resolver after each disturbance of the multi-mode resolver through a multi-objective optimization algorithm based on a genetic algorithm, and finally generates a better heterogeneous SDN controller selection strategy so as to resist the next possible unknown vulnerability threat and improve the endogenous security of the system.
Drawings
FIG. 1 is a system framework diagram of the present invention;
FIG. 2 is a flow chart of the multi-objective optimization algorithm of the present invention;
fig. 3 is a heterogeneous SDN controller cleaning flow diagram causing a disturbance in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention.
As shown in FIG. 1, the multi-mode arbitration negative feedback system based on multi-objective optimization algorithm of the present invention comprises a multi-mode arbitration module and a negative feedback optimization module; the multi-mode arbitrating module comprises a heterogeneous pool unit and a multi-mode arbitrator; the heterogeneous pool unit comprises a heterogeneous pool selector and at least 3 heterogeneous SDN controllers; in each heterogeneous SDN control layer, heterogeneous SDN controllers are used for simultaneously processing input requests, and an output result set of each heterogeneous SDN controller in a unit time is submitted to a multi-module resolver; the multi-mode arbitrator carries out consistency arbitration on the information distribution in the flow table of the output result set and sends the arbitration result to the switch; and after each judgment, the negative feedback optimization module adjusts the confidence of the corresponding heterogeneous SDN controller according to the judgment result, realizes the dynamic selection of the heterogeneous SDN controllers in the heterogeneous pool unit, and records the output result of each heterogeneous SDN controller and the judgment result.
And if the multimode arbitrator is disturbed, the multimode arbitrator sends the arbitrating result data set and the input parameters to the negative feedback optimization module.
And if and only when the multi-mode resolver is disturbed, the multi-mode resolver marks 1 or more heterogeneous SDN controllers causing the disturbance as a belt cleaning state, and suspends the task until the negative feedback optimization module executes the selection strategy and then executes a cleaning reset task.
And if and only if the multi-decision device is disturbed, the multi-decision module transmits parameters required by initialization of the multi-objective optimization algorithm in the negative feedback optimization module to the negative feedback optimization module, wherein the parameters comprise the current selection weight of each heterogeneous SDN controller, the historical average value of processing time of each heterogeneous SDN controller, the historical average value of cleaning time of each heterogeneous SDN controller and the historical average value of resource consumption cost of each heterogeneous SDN controller.
And if the multi-resolver is disturbed, the negative feedback optimization module receives the parameters transmitted by the multi-resolver and initializes the parameters of the algorithm model, iterative computation is carried out according to a multi-target optimization algorithm based on a genetic algorithm, and the output heterogeneous SDN controller selection strategy is issued to the heterogeneous pool selector.
And cleaning the heterogeneous SDN controller causing disturbance after the negative feedback optimization module selects strategy updating iteration to finish, updating the selection weight of the cleaned heterogeneous SDN controller according to the selected strategy, and updating the historical average cleaning time of the heterogeneous SDN controller by the cleaning time.
The multi-objective optimization algorithm considers the total confidence, the processing time of the SDN controller, the cleaning time, the stability of the processing time and the resource consumption cost; the processing time, the cleaning time and the resource consumption cost of the heterogeneous SDN controller are historical average values, and the heterogeneous SDN controller is updated after each negative feedback process is executed.
As shown in FIG. 2, the multi-objective optimization algorithm includes the following steps:
s1: initializing parameters of the algorithm model according to the parameters transmitted by the multi-mode resolver;
s2: obtaining a first generation filial generation population through three basic operations of selection, crossing and variation of a genetic algorithm after non-dominated sorting;
s3: from the second generation, merging the parent population and the offspring population, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting proper individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population;
s4: generating a new filial generation population through the basic operation of a genetic algorithm, and repeating the steps until the requirement is met;
s5: issuing the output optimal heterogeneous SDN controller selection strategy to a heterogeneous pool selector, starting to execute a suspended heterogeneous SDN controller cleaning task, and respectively recording and calculating cleaning time and then updating historical data.
The specific operation process of the multi-mode arbitration negative feedback system is as follows:
the method comprises the following steps: and in unit request processing time, randomly selecting N heterogeneous SDN controllers () from the heterogeneous pool units according to weight values, and if m heterogeneous SDN controllers meeting the multi-decision result exist in the last unit request time, selecting N-m heterogeneous SDN controllers from the heterogeneous pool units.
The heterogeneous SDN controllers in the heterogeneous pool units need to comply with the following requirements:
1. the heterogeneous SDN controllers in the heterogeneous pool units are heterogeneous SDN controllers with completely different architectures and equivalent functions;
2. the number of heterogeneous SDN controllers for simultaneously processing the input requests by using the heterogeneous SDN controllers is at least 3, and the number of the heterogeneous SDN controllers in each time of processing the input requests is smaller than that of the heterogeneous SDN controllers in the heterogeneous pool unit.
The heterogeneous SDN controllers with the heterogeneous structures mean that the structural compositions and the implementation principles thereof are different, but the same outputs have the same effect for the same inputs, that is, each heterogeneous SDN controller has a unique vulnerability and backgate, and thus heterogeneous SDN controllers with completely different architectures may not simultaneously fail heterogeneous SDN controllers with the same functions under the same attack. In each request processing period, the multi-module arbitrator judges that only two possibilities exist according to the result of arbitrating the similarity, wherein the similarity is greater than or equal to a threshold value, or the similarity is smaller than the threshold value, so that in order to guarantee the feasibility of arbitrating multiple requests each time, it is necessary to guarantee that the number of heterogeneous SDN controllers participating in request processing must be greater than the number of possibilities, that is, not less than 3. In addition, the number of heterogeneous SDN controllers represents the diversity of the system, and it can be intuitively considered that the sensing accuracy of the threat is improved by increasing the number of heterogeneous SDN controllers in a unit request processing period, but the working cost of the system is increased at the same time.
Step two: for the same request, the request is distributed to a plurality of heterogeneous SDN controllers selected from the heterogeneous pool units at the same time and then processed, a processing result and a set of output results of each heterogeneous SDN controller in unit time are submitted to a multi-mode resolver, and meanwhile, the output result of each heterogeneous SDN controller is recorded.
Step three: the multimode arbitrator performs consistency arbitration on information distribution in the flow table of the output result set, and the method specifically comprises the following steps: and drawing flow table information distribution in unit time, calculating distribution similarity by the multi-mode arbitrator, performing multi-arbitration to output arbitration results, recording the arbitration results, and issuing the arbitration results to the switch.
Drawing flow table information distribution to count the contents of the flow table in the heterogeneous SDN controller, including match fields and instructions;
calculating the similarity is to calculate the mutual similarity of the content distribution of the flow table information by a similarity calculation method;
and if the similarity of the output results of more than half of the heterogeneous SDN controllers is determined to be greater than or equal to a specified threshold value, issuing the calculation result of the heterogeneous SDN controller with the highest weight value in the part of the heterogeneous SDN controllers to the router.
Step four: after each arbitration, the negative feedback optimization module adjusts the confidence of the corresponding heterogeneous SDN controller according to the arbitration result, and records the output result and the arbitration result of each heterogeneous SDN controller, as shown in fig. 3; the specific method comprises the following steps: counting the resolution result of the resolver, and taking the heterogeneous SDN controller with the largest weight value in the heterogeneous SDN controllers which meet the requirement as one of the heterogeneous SDN controllers selected in the next request processing period; in addition, the similarity of the arbitration result is calculated, and the negative feedback optimization module judges whether the heterogeneous SDN controller in the request processing period needs to be cleaned and reset according to the similarity statistics. If the similarity is smaller than the threshold, the heterogeneous SDN controller needs to be cleaned and reset the weight value, and the heterogeneous SDN controller is placed in the heterogeneous pool unit again after the operation is completed. If the similarity is greater than or equal to the threshold, adjusting the weight of the heterogeneous SDN controller, if the weight exceeds the maximum value, not changing the weight, and otherwise, increasing the weight.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents or improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A multi-mode arbitration negative feedback system based on a multi-objective optimization algorithm is characterized in that: the system comprises a multi-mode arbitration module and a negative feedback optimization module; the multi-mode arbitrating module comprises a heterogeneous pool unit and a multi-mode arbitrator; the heterogeneous pool unit comprises a heterogeneous pool selector and at least 3 heterogeneous SDN controllers; the multi-mode resolver performs consistency resolution on information distribution in a flow table of an output result set of the heterogeneous SDN controller, and issues a resolution result to a switch and a negative feedback optimization module; when the multi-mode resolver finds disturbance, the resolver transmits a decision result and information distribution in a flow table of an input set of the heterogeneous SDN controller to the negative feedback module, and dynamically adjusts the selection weight of the SDN controller in the heterogeneous pool through a multi-objective optimization algorithm; and the negative feedback optimization module issues the selection strategy in the negative feedback iteration result to the heterogeneous pool selector, and the heterogeneous pool selector selects the heterogeneous SDN controller in the next period according to the issued strategy.
2. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 1, characterized in that: and if the multimode arbitrator is disturbed, the multimode arbitrator sends the arbitrating result data set and the input parameters to the negative feedback optimization module.
3. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 2, wherein: and if and only when the multi-mode resolver is disturbed, the multi-mode resolver marks 1 or more heterogeneous SDN controllers causing the disturbance as a to-be-cleaned state, and suspends the task until the negative feedback optimization module executes the selection strategy and then executes a cleaning reset task.
4. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 3, wherein: and if and only if the multi-decision device is disturbed, the multi-decision module transmits parameters required by initialization of the multi-objective optimization algorithm in the negative feedback optimization module to the negative feedback optimization module, wherein the parameters comprise the current selection weight of each heterogeneous SDN controller, the historical average value of processing time of each heterogeneous SDN controller, the historical average value of cleaning time of each heterogeneous SDN controller and the historical average value of resource consumption cost of each heterogeneous SDN controller.
5. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 4, wherein: and if the multi-resolver is disturbed, the negative feedback optimization module receives the parameters transmitted by the multi-resolver and initializes the parameters of the algorithm model, iterative computation is carried out according to a multi-target optimization algorithm based on a genetic algorithm, and the output heterogeneous SDN controller selection strategy is issued to the heterogeneous pool selector.
6. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 5, wherein: and cleaning the heterogeneous SDN controller causing disturbance after the negative feedback optimization module selects strategy updating iteration to finish, updating the selection weight of the cleaned heterogeneous SDN controller according to the selected strategy, and updating the historical average cleaning time of the heterogeneous SDN controller by the cleaning time.
7. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 6, wherein: the multi-objective optimization algorithm considers the total confidence, the processing time of the SDN controller, the cleaning time, the stability of the processing time and the resource consumption cost; the processing time, the cleaning time and the resource consumption cost of the heterogeneous SDN controller are historical average values, and the heterogeneous SDN controller is updated after each negative feedback process is executed.
8. The multi-objective optimization algorithm-based multi-mode arbitration negative feedback system according to claim 7, wherein: the multi-objective optimization algorithm comprises the following steps:
s1: initializing parameters of the algorithm model according to the parameters transmitted by the multi-mode resolver;
s2: obtaining a first generation filial generation population through three basic operations of selection, crossing and variation of a genetic algorithm after non-dominated sorting;
s3: from the second generation, merging the parent population and the offspring population, performing rapid non-dominant sorting, simultaneously performing crowding degree calculation on the individuals in each non-dominant layer, and selecting proper individuals according to the non-dominant relationship and the crowding degree of the individuals to form a new parent population;
s4: generating a new filial generation population through the basic operation of a genetic algorithm, and repeating the steps until the requirement is met;
s5: issuing the output optimal heterogeneous SDN controller selection strategy to a heterogeneous pool selector, starting to execute a suspended heterogeneous SDN controller cleaning task, and respectively recording and calculating cleaning time and then updating historical data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738152.6A CN114826782A (en) | 2022-06-28 | 2022-06-28 | Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210738152.6A CN114826782A (en) | 2022-06-28 | 2022-06-28 | Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114826782A true CN114826782A (en) | 2022-07-29 |
Family
ID=82522913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210738152.6A Pending CN114826782A (en) | 2022-06-28 | 2022-06-28 | Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114826782A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108415425A (en) * | 2018-02-08 | 2018-08-17 | 东华大学 | It is a kind of that swarm algorithm is cooperateed with based on the Distributed Cluster robot for improving gene regulatory network |
| CN111385299A (en) * | 2020-03-05 | 2020-07-07 | 之江实验室 | Multi-mode arbitration system based on time iteration and negative feedback mechanism |
| CN111741069A (en) * | 2020-05-22 | 2020-10-02 | 南京邮电大学 | Hierarchical data center resource optimization method and system based on SDN and NFV |
| US20210226994A1 (en) * | 2017-07-19 | 2021-07-22 | Shanghai Hongzhen Information Science & Technology Co., Ltd. | Output-decision-based negative feedback control method and system |
| CN113703908A (en) * | 2020-05-21 | 2021-11-26 | 迪莲娜(上海)大数据服务有限公司 | Mimicry virtual network management system |
-
2022
- 2022-06-28 CN CN202210738152.6A patent/CN114826782A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210226994A1 (en) * | 2017-07-19 | 2021-07-22 | Shanghai Hongzhen Information Science & Technology Co., Ltd. | Output-decision-based negative feedback control method and system |
| CN108415425A (en) * | 2018-02-08 | 2018-08-17 | 东华大学 | It is a kind of that swarm algorithm is cooperateed with based on the Distributed Cluster robot for improving gene regulatory network |
| CN111385299A (en) * | 2020-03-05 | 2020-07-07 | 之江实验室 | Multi-mode arbitration system based on time iteration and negative feedback mechanism |
| CN113703908A (en) * | 2020-05-21 | 2021-11-26 | 迪莲娜(上海)大数据服务有限公司 | Mimicry virtual network management system |
| CN111741069A (en) * | 2020-05-22 | 2020-10-02 | 南京邮电大学 | Hierarchical data center resource optimization method and system based on SDN and NFV |
Non-Patent Citations (3)
| Title |
|---|
| P. YI ET AL: "A safe and reliable heterogeneous controller deployment approach in SDN", 《CHINA COMMUNICATIONS》 * |
| 刘璐等: "基于邻域和变异算子组合优化的MOEA/D算法", 《计算机工程》 * |
| 刘祖源: "《船体型线多学科设计优化》", 30 November 2010 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110138612B (en) | Cloud software service resource allocation method based on QoS model self-correction | |
| CN111385299B (en) | Multi-mode arbitration system based on time iteration and negative feedback mechanism | |
| CN112884136B (en) | Bounded clustering projection synchronous regulation control method and system for coupled neural network | |
| Ma et al. | Real-time virtual machine scheduling in industry IoT network: A reinforcement learning method | |
| Wei et al. | Research on cloud design resources scheduling based on genetic algorithm | |
| CN109445386A (en) | A kind of most short production time dispatching method of the cloud manufacturing operation based on ONBA | |
| Cheng et al. | H₂O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers | |
| Pooranian et al. | Using imperialist competition algorithm for independent task scheduling in grid computing | |
| CN115981562A (en) | Data processing method and device | |
| Anita et al. | Solution of unit commitment problem using shuffled frog leaping algorithm | |
| Bhatnagar et al. | Stochastic algorithms for discrete parameter simulation optimization | |
| CN109871682B (en) | Execution unified control method of heterogeneous virtual machine platform | |
| CN113240100B (en) | Parallel computing method and system based on discrete Hopfield neural network | |
| Lian | A united search particle swarm optimization algorithm for multiobjective scheduling problem | |
| Manavi et al. | Resource allocation in cloud computing using genetic algorithm and neural network | |
| Xie et al. | Cloud computing resource scheduling based on improved differential evolution ant colony algorithm | |
| CN114826782A (en) | Multi-mode arbitration negative feedback system based on multi-objective optimization algorithm | |
| Zhang et al. | A dynamic placement policy of virtual machine based on MOGA in cloud environment | |
| Shi et al. | AdaptScale: an adaptive data scaling controller for improving the multiple performance requirements in clouds | |
| CN111626425A (en) | Quantum register allocation method and system for two-dimensional neighbor quantum computing architecture | |
| Yu et al. | An evolution-based dynamic scheduling algorithm in grid computing environment | |
| Lian et al. | A discrete particle swarm optimization algorithm for job-shop scheduling problem to maximizing production | |
| Park et al. | Gemma: reinforcement learning-based graph embedding and mapping for virtual network applications | |
| Min et al. | Immunization strategy based on discrete particle swarm optimization algorithm in BBV network | |
| Zhong et al. | An efficient memetic algorithm for job scheduling in computing grid |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220729 |