CN111182556A - Wireless network planning design method based on intelligent agent - Google Patents
Wireless network planning design method based on intelligent agent Download PDFInfo
- Publication number
- CN111182556A CN111182556A CN201911417244.9A CN201911417244A CN111182556A CN 111182556 A CN111182556 A CN 111182556A CN 201911417244 A CN201911417244 A CN 201911417244A CN 111182556 A CN111182556 A CN 111182556A
- Authority
- CN
- China
- Prior art keywords
- wireless network
- role
- agent
- knowledge
- inference
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a wireless network planning design method based on an intelligent agent, which utilizes an intelligent agent technology to replace designers to carry out wireless network planning model modeling on a wireless network, confirms the network scale, constructs a network structure, simulates and selects various parameters of the wireless network, and finally outputs the result after engineering optimization. The wireless network planning design method based on the intelligent agent, provided by the invention, is based on the intelligent agent technology and the wireless network planning model, can effectively reduce the cost and the period in the network planning design process on the basis of ensuring the quality of the wireless network planning and design finished products, ensures the communication efficiency and the quality safety of the wireless network, maintains the safety and the stability of the wireless network, and has very wide application prospect.
Description
Technical Field
The invention belongs to the field of wireless network planning and design, and particularly relates to a wireless network planning and design method based on an intelligent agent. .
Background
The wireless network is used as a communication network layer, and the application scenarios of the wireless network are very wide. Mobile communication network, wireless local area network, wireless sensor network, etc. are all important components of wireless network, wherein network technologies such as 5G, RFID, WiMAX, bluetooth, etc. have been widely applied in planning and designing of wireless networks. Because the application scenarios of each wireless network are different, it is necessary to perform demand analysis in combination with the actual scenarios, and perform corresponding estimation, planning and design on the design scale.
The planning and designing process of the wireless network comprises the stages of project establishment in the early stage, project recommendation, feasibility study report compiling, corresponding planning and construction scheme proposing, project approval completion, preliminary design in the project implementation process, construction drawing design and the like. During the planning and design period, professional technicians are required to be matched with each other, more manpower and material resources are required to be invested in each relevant unit, and particularly, under the condition that the project period is short, the quality of finished products planned and designed by the technicians is poor, and the safety quality of project completion is difficult to guarantee.
Disclosure of Invention
In view of the above problems in the prior art, an object of the present invention is to provide a wireless network planning and designing method based on intelligent agents.
The purpose of the invention is realized by the following technical scheme.
A wireless network planning design method based on intelligent agent comprises an intelligent agent model, wherein the intelligent agent model comprises a communication interface module, a processing module, a knowledge base, a control module and an inference machine, the inference machine comprises a type set, a role set and a behavior set, and the type set T is represented by an agent type TiComposition, role set R is formed by proxy roles RiThe behavior set B is composed of agent behaviors BiComposition, wherein i represents a natural number; the design method comprises the following specific steps:
the first step is as follows: the demand analysis is carried out on the planning design of the wireless network, and the network establishment target, the network index, the geographic environment and the coverage purpose are input into the intelligent agent modelThe information of the target area, special requirements and the like is sent to a processing module through a communication interface module, the processing module converts input information into agent language through knowledge representation, requirement analysis is carried out according to the converted input information, and the agent type T of the inference is matched in the type set T of the inference enginei；
The second step is that: modeling simulation is carried out on the wireless network planning design, and an inference machine carries out modeling simulation according to the agent type TiDetermining the agent type T according to the site distribution and service conditioniGenerating an estimation information collection table in the simulation range;
the third step: carrying out scale estimation on the planning design of the wireless network, and matching the agent role R of the turn i in the role set R by the inference machine according to an estimation information acquisition tableiInvoking the proxy role R in the knowledge base according to the targetiThe agent role R in the target execution behavior set B is combined with the knowledgeiAgent behavior under capability BiVarious processing operations of (2);
the fourth step: planning and simulating a wireless network planning design, and continuously matching the proxy role R of the turn j (j is i +1) in the role set R by the inference machine in combination with the network scale estimation resultjValidating the proxy role RjThe proxy role R in the knowledge base is invoked according to the targetjThe agent role R in the target execution behavior set B is combined with the knowledgejAgent behavior under capability BjRecording a simulation result as a candidate solution, wherein j represents a natural number;
the fifth step: stopping judging the wireless network planning design, if the current candidate solution meets the stopping criterion of the optimal solution in the knowledge base, generating engineering parameters, network capacity and a station coverage simulation result of the station by the processing module, and performing the seventh step; otherwise, carrying out the sixth step;
and a sixth step: carrying out knowledge search on the wireless network planning design, searching engineering parameters in a knowledge base by an inference machine, matching and adjusting the wireless network parameters, and returning to the fourth step for cyclic operation;
the seventh step: and (4) designing parameters of the wireless network planning design, summarizing and sorting the generated result of each step of the logical reasoning by the processing module, and generating and outputting a final design report through the communication interface module.
The knowledge base is constructed based on knowledge representation of the processing module, and the specific method comprises the following steps: the processing module performs knowledge representation on typical design class input information of the existing wireless network; transfer learning is introduced, and a prediction model with rich relevant data is selected when the intelligent agent is trained for the first time; and meanwhile, reinforcement learning is introduced.
The reinforcement learning comprises designing a reward mechanism and adding mutation strategies.
The structural function of the inference engine is as follows:
wherein T is a type set of inference engines and is all inference types TiOne or more times of compounding;
R＝<G，K，C>is the role set of the inference engine, G is the target set under the role of the inference engine, K is the knowledge set under the role of the inference engine, and the structure function of the knowledge set<KT，KF，KD>Is composed of<Type of knowledge, form of knowledge, content>，
The method comprises the following steps that (1) a capacity set under the role of an inference engine is obtained, and P is the processing process of the capacity set under the role of the inference engine;
b is the behavior set of the inference engine, which is all the behaviors of the inference engine Bi(i∈[1，n]) One or more combinations of, i.e. all the capabilities C of the inference enginej(j∈[1，n]) And the capability CjBy one or more processes Pk(k∈[1，n]) Composition, wherein k represents a natural number.
The invention has the beneficial effects that: the invention provides a wireless network planning and designing method based on an intelligent agent, which utilizes knowledge representation to construct a knowledge base and a structure function, introduces an incentive mechanism and adds a mutation strategy, so that the intelligent agent can continuously learn knowledge and expand the knowledge base through self training under good incentive. The intelligent agent under the knowledge base can replace designers to carry out wireless network planning model modeling on the wireless network, confirm the network scale and the network structure, simulate various parameters of the network and select a final result after engineering optimization.
The wireless network planning design method based on the intelligent agent, provided by the invention, is based on the intelligent agent technology and the wireless network planning model, can effectively reduce the cost and the period in the network planning design process on the basis of ensuring the quality of the wireless network planning and design finished products, ensures the communication efficiency and the quality safety of the wireless network, maintains the safety and the stability of the wireless network, and has very wide application prospect.
Drawings
FIG. 1 is an intelligent agent model architecture diagram of the present invention.
FIG. 2 is a flow chart of a design method of the present invention.
Fig. 3 is a radio network control and data flow diagram of the present invention.
Fig. 4 is a graph of simulation results of the present invention.
Detailed Description
As shown in fig. 1 to 4, the design method of the wireless network planning based on the intelligent agent uses the intelligent agent technology to replace designers to perform wireless network planning model modeling on the wireless network, confirm the network scale, construct the network structure, simulate and select various parameters of the wireless network, and finally output the result after engineering optimization.
An Intelligent Agent (IA) technology is a software entity which can sense, characterize and reason a target and autonomously complete a series of operations, and the technology is composed of knowledge characterization and knowledge processing, has the characteristics of autonomy, adaptivity, interactivity, collaboration and the like, can perform knowledge characterization, reasoning and learning on the sensed environment, and can perform global optimization on problems based on certain specific targets.
The intelligent agent technology is completed by an intelligent agent model which is a general modelThe system comprises a signal interface module, a processing module, a knowledge base, a control module and an inference machine; the inference engine comprises a type set, a role set and a behavior set, wherein the type set T is represented by an agent type TiComposition, role set R is formed by proxy roles RiThe behavior set B is composed of agent behaviors BiComposition, wherein i represents a natural number.
The grammatical structure of the communication interface module is based on communication languages such as intelligent agent SACL, KQML and the like, and the interactive communication between the software/hardware of each module in the intelligent agent model, the intelligent agent model and other external intelligent agents, users and networks can be realized.
The processing module can receive the input information of the communication interface module and convert the input information into the intelligent agent language based on the knowledge representation technology; and the result after the intelligent inference of the inference engine can be converted into the target language and forwarded to the communication interface module for result output.
The knowledge base stores the knowledge required by the inference engine for reasoning, and the knowledge data conform to the rule grammar of the inference engine and are the basis for the inference engine to carry out intelligent activities such as reasoning, design and the like.
The control module can carry out self control according to the agent state, and intelligent control among all modules of the intelligent agent model is realized.
The inference engine is the core of the intelligent agent and consists of an agent type, an agent role and an agent behavior; the agent type comprises types such as a communication agent, a control agent, a design agent and the like; the agent role is composed of knowledge, targets and abilities, the knowledge comprises various knowledge types, forms and contents, and each ability also comprises a plurality of processing procedures; the agent behavior comprises a plurality of capabilities of various roles, and each capability comprises a plurality of processing procedures; the inference engine has interactive capability, can select the agent type according to the interactive information, match the corresponding role and call the knowledge in the knowledge base for inference, and adopts a specific inference control algorithm to execute the behavior under the role.
The specific steps of the design method are as follows.
The first step is as follows: the demand analysis is carried out on the planning design of the wireless network, and a network establishing target, network indexes and a place are input into the intelligent agent modelInformation such as management environment, coverage target area, special requirements and the like is sent to a processing module through a communication interface module, the processing module converts input information into agent language through knowledge representation, requirement analysis is carried out according to the converted input information, and the agent type T of the inference is matched in a type set T of an inference enginei。
The second step is that: modeling simulation is carried out on the wireless network planning design, and an inference machine carries out modeling simulation according to the agent type TiDetermining the agent type T according to the site distribution and service conditioniAnd generating an estimated information collection table.
The third step: carrying out scale estimation on the planning design of the wireless network, and matching the agent role R of the turn i in the role set R by the inference machine according to an estimation information acquisition tableiIncluding confirming target parameters such as uplink/downlink data rate, bound carrier, transmission power, etc., and invoking the proxy role R in the knowledge base according to the targetiThe agent role R in the target execution behavior set B is combined with the knowledgeiAgent behavior under capability BiVarious processing operations of (2); for example, the network capacity and coverage are estimated, a propagation model is selected and corrected by CW test or drive test data to generate the single-site coverage radius and the number of sites.
The fourth step: planning and simulating a wireless network planning design, and continuously matching the proxy role R of the round j (j is i +1) in the role set R by the inference machine in combination with the estimation result of the network scale (the single-site coverage radius and the number of sites)jValidating the proxy role RjThe proxy role R in the knowledge base is invoked according to the targetjThe agent role R in the target execution behavior set B is combined with the knowledgejAgent behavior under capability BjAnd (4) various processing operations, such as adding an alternative site for simulation, and recording a simulation result as a candidate solution, wherein j represents a natural number.
The fifth step: stopping judging the wireless network planning design, if the current candidate solution meets the stopping criterion of the optimal solution in the knowledge base, generating engineering parameters, network capacity and a station coverage simulation result of the station by the processing module, and performing the seventh step; otherwise, the sixth step is performed.
And a sixth step: and (4) carrying out knowledge search on the wireless network planning design, searching engineering parameters in a knowledge base by the inference machine, matching and adjusting the wireless network parameters, and returning to the fourth step for circulating operation.
The seventh step: and (4) designing parameters of the wireless network planning design, summarizing and sorting the generated result of each step of the logical reasoning by the processing module, and generating and outputting a final design report through the communication interface module.
Furthermore, the knowledge base in the intelligent agent model is constructed based on the knowledge representation of the processing module, and two processes of self-training and logical reasoning need to be completed.
First, self-training requires a large number of training samples: the typical design of a point-line-surface coverage area map, a telephone traffic distribution map and the like of the existing wireless network is used as the input of an intelligent agent, and the knowledge representation of an agent language is carried out on the input through a communication interface module, so that the input information is converted into the agent language by a processing module for the convenience of subsequent processing.
Secondly, the intelligent agent model has good prior knowledge by using the transfer learning technology: the method is characterized in that a prediction model with rich relevant data is selected when an intelligent agent model is trained for the first time, for example, a wireless network typical design scheme matching model with excellent quality results is selected, so that the intelligent agent model can learn knowledge in a fast mode in the initial training process, and the initial learning efficiency is improved.
Meanwhile, reinforcement learning needs to be introduced during self-training, including designing reward mechanisms and adding mutation strategies. The method specifically defines the learning and irrevocable rewards of the intelligent agent, randomly adds variable rationality planning to improve the capability of the intelligent agent for solving the unexpected problems in time, so that the intelligent agent performs self-training by continuously trial and error, modifying the strategy and autonomously changing the learning mode under a good training mechanism, iterates the learned knowledge and expands the knowledge base.
The intelligent agent model after self-training can carry out logical reasoning according to input information, including matching agent types, generating service roles and behaviors, carrying out estimation statistics on network parameters, capacity and coverage rate, selecting and correcting a propagation model according to test data, carrying out state analysis and design on the network by combining simulation data such as station numbers, coverage radius, carrier power and the like, and finally outputting a scheme report.
Further, the structure function of the inference engine in the intelligent agent model is as follows:
wherein T is a type set of inference engines and is all inference types TiOne or more times of compounding;
R＝<G，K，C>is the role set of the inference engine, G is the target set under the role of the inference engine, K is the knowledge set under the role of the inference engine, and the structure function of the knowledge set<KT，KF，KD>Is composed of<Type of knowledge, form of knowledge, content>，
The method comprises the following steps that (1) a capacity set under the role of an inference engine is obtained, and P is the processing process of the capacity set under the role of the inference engine;
b is the behavior set of the inference engine, which is all the behaviors of the inference engine Bi(i∈[1，n]) One or more combinations of, i.e. all the capabilities C of the inference enginej(j∈[1，n]) And the capability CjBy one or more processes Pk(k∈[1，n]) Composition, wherein k represents a natural number.
FIG. 1 is an intelligent agent model architecture diagram of the present invention. The model consists of an input module, an output module, a communication interface module, a knowledge base, a processing module (server), an inference engine and a control module (workstation).
The communication interface module can realize the communication between the software/hardware of each module, the intelligent agent and other intelligent agents, users and networks. The knowledge base is based on knowledge representation technology, input information of the intelligent agent is represented as agent learnable knowledge, reinforcement learning is introduced, and an incentive mechanism and a mutation strategy are designed, so that the intelligent agent can perform self training, continuously learn knowledge and expand the knowledge base in a good training mechanism through a method of continuously trial and error and automatically changing a learning mode after errors are found. Meanwhile, transfer learning is introduced, and a prediction model with rich relevant data, such as a wireless network typical design scheme matching model with excellent quality results, is selected when the agent is trained for the first time, so that the agent can learn knowledge in a faster mode in the initial training process, and the initial learning efficiency is improved. The processing module (server) can process the information in the knowledge base after input matching and send the information to the inference engine to match the agent type and generate the matched role and behavior. The control module (workstation) can realize the control of the intelligent agent modules.
The inference engine is composed of a type set, a role set and a behavior set. The role set is a triplet containing role knowledge, goals and capabilities; each role has a respective knowledge set, and the knowledge of the role is stored in a mode of < knowledge type, knowledge form, knowledge content >; each role has its own capability set, and each capability set has a different processing procedure. The behavior set comprises different capability sets, and each capability set has different processing procedures. And the inference machine selects different agent types according to the input, further matches the agent roles under the agent types, and correspondingly completes and outputs the agent behaviors under the roles.
Fig. 2 is a scheme flow diagram of the present invention. The scheme realizes the requirement analysis, modeling simulation, scale estimation, planning simulation, stop judgment, knowledge search and parameter design of the wireless network planning design.
In the implementation process, information collection is firstly carried out on a networking target, network indexes, a geographic environment, a coverage target area and special requirements, so that site distribution, a service model and a simulation range are established, and an estimation information collection table is generated. And secondly, setting estimation parameters, estimating the network capacity and the coverage area, selecting a propagation model, correcting the propagation model through testing, and confirming the coverage radius and the number of stations of a single station. And finally, simulating and recording the current simulation result as a candidate solution. And if the current candidate solution does not meet the stop criterion of the optimal solution in the knowledge base, searching engineering parameters in the knowledge base to adjust the wireless network parameters, and returning the parameters to simulate again. And if the current candidate solution meets the stop criterion of the optimal solution in the knowledge base, outputting the simulation result of the site, and finally designing and generating a report for the network according to the engineering parameters and the cell parameters.
Fig. 3 is a radio network control and data flow diagram of the present invention. The wireless network consists of an application service sublayer, a communication network sublayer and a physical perception sublayer. The control flow of the application service sublayer passes from the application layer to the data layer through the control layer, is sent to the application layer of the communication network sublayer through the control layer to the data layer, and is sent to the control layer of the physical perception sublayer to be finally converged to the data layer. And the data layer of the physical perception sublayer feeds data to flow through the data layer of the communication network sublayer to the data layer of the application service sublayer.
Fig. 4 is a graph of simulation results of the present invention. The wireless network is simulated by combining a network planning station, the edge rate is set to be more than or equal to 22.4Kbps, the bandwidth is set to be more than or equal to 7M, and coverage simulation is performed according to the condition that the simulation meets various urban building densities and various communication services. The diagram shows that the simulation area has the RSRP ≧ -115 proportion reaching 100%, and the SINR ≧ -3 proportion reaching 94.96%, so that the scheme provided by the invention has a good coverage effect.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the technical solutions of the present invention, and it should be noted that those skilled in the art, on the premise of the technical solutions of the present invention, may make further improvements and changes, and these improvements and changes should be covered within the protection scope of the present invention.
Claims (4)
1. A wireless network planning design method based on intelligent agent is characterized by comprising an intelligent agent model, wherein the intelligent agent model comprises a communication interface module, a processing module, a knowledge base, a control module and an inference machine, the inference machine comprises a type set, a role set and a behavior set, and the type set T is represented by an agent type TiComposition, role set R is formed by proxy roles RiThe behavior set B is composed of agent rowsIs BiComposition, wherein i represents a natural number; the design method comprises the following specific steps:
the first step is as follows: the method comprises the steps of carrying out demand analysis on the planning design of the wireless network, inputting information such as a networking target, network indexes, geographic environment, coverage target area, special requirements and the like into an intelligent agent model, sending the information to a processing module through a communication interface module, converting input information into agent language through knowledge representation by the processing module, carrying out demand analysis according to the converted input information, and matching agent type T of the inference in a type set T of an inference enginei；
The second step is that: modeling simulation is carried out on the wireless network planning design, and an inference machine carries out modeling simulation according to the agent type TiDetermining the agent type T according to the site distribution and service conditioniGenerating an estimation information collection table in the simulation range;
the third step: carrying out scale estimation on the planning design of the wireless network, and matching the agent role R of the turn i in the role set R by the inference machine according to an estimation information acquisition tableiInvoking the proxy role R in the knowledge base according to the targetiThe agent role R in the target execution behavior set B is combined with the knowledgeiAgent behavior under capability BiVarious processing operations of (2);
the fourth step: planning and simulating a wireless network planning design, and continuously matching the proxy role R of the turn j (j is i +1) in the role set R by the inference machine in combination with the network scale estimation resultjValidating the proxy role RjThe proxy role R in the knowledge base is invoked according to the targetjThe agent role R in the target execution behavior set B is combined with the knowledgejAgent behavior under capability BjRecording a simulation result as a candidate solution, wherein j represents a natural number;
the fifth step: stopping judging the wireless network planning design, if the current candidate solution meets the stopping criterion of the optimal solution in the knowledge base, generating engineering parameters, network capacity and a station coverage simulation result of the station by the processing module, and performing the seventh step; otherwise, carrying out the sixth step;
and a sixth step: carrying out knowledge search on the wireless network planning design, searching engineering parameters in a knowledge base by an inference machine, matching and adjusting the wireless network parameters, and returning to the fourth step for cyclic operation;
the seventh step: and (4) designing parameters of the wireless network planning design, summarizing and sorting the generated result of each step of the logical reasoning by the processing module, and generating and outputting a final design report through the communication interface module.
2. The intelligent agent-based wireless network planning and design method of claim 1, wherein the knowledge base is constructed based on knowledge characterization of the processing module, and the specific method is as follows: the processing module performs knowledge representation on typical design class input information of the existing wireless network; transfer learning is introduced, and a prediction model with rich relevant data is selected when the intelligent agent is trained for the first time; and meanwhile, reinforcement learning is introduced.
3. The intelligent agent-based wireless network planning and design method of claim 2, wherein the reinforcement learning comprises designing reward mechanism and adding mutation strategy.
4. The intelligent agent-based wireless network planning and design method of claim 3, wherein the structure function of the inference engine is:
wherein T is a type set of inference engines and is all inference types TiOne or more times of compounding;
R＝<G，K，C>is the role set of the inference engine, G is the target set under the role of the inference engine, K is the knowledge set under the role of the inference engine, and the structure function of the knowledge set<KT，KF，KD>Is composed of<Type of knowledge, form of knowledge, content>，
The method comprises the following steps that (1) a capacity set under the role of an inference engine is obtained, and P is the processing process of the capacity set under the role of the inference engine;
b is the behavior set of the inference engine, which is all the behaviors of the inference engine Bi(i∈[1，n]) One or more combinations of, i.e. all the capabilities C of the inference enginej(j∈[1，n]) And the capability CjBy one or more processes Pk(k∈[1，n]) Composition, wherein k represents a natural number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417244.9A CN111182556B (en) | 2019-12-31 | 2019-12-31 | Wireless network planning design method based on intelligent agent |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911417244.9A CN111182556B (en) | 2019-12-31 | 2019-12-31 | Wireless network planning design method based on intelligent agent |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111182556A true CN111182556A (en) | 2020-05-19 |
| CN111182556B CN111182556B (en) | 2022-09-30 |
Family
ID=70657765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911417244.9A Active CN111182556B (en) | 2019-12-31 | 2019-12-31 | Wireless network planning design method based on intelligent agent |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111182556B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022121559A1 (en) * | 2020-12-07 | 2022-06-16 | 中兴通讯股份有限公司 | Mobile communication system control method, network management and control agent, system, and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103583017A (en) * | 2011-06-09 | 2014-02-12 | 皇家飞利浦有限公司 | Method for configuring a network |
| CN104219404A (en) * | 2013-05-31 | 2014-12-17 | 中国电信股份有限公司 | Communication network emergency plan drill method, system and server |
| US9220123B1 (en) * | 2014-07-10 | 2015-12-22 | International Business Machines Corporation | Peer-to-peer sharing of network resources |
| US20170244744A1 (en) * | 2016-02-24 | 2017-08-24 | Verodin, Inc. | Systems and methods for attack simulation on a production network |
| CN109560968A (en) * | 2018-12-20 | 2019-04-02 | 中国电子科技集团公司第三十研究所 | A kind of the Internet resources intelligent planning and configuration method of dynamic strategy driving |
| CN110418354A (en) * | 2019-08-06 | 2019-11-05 | 北京邮电大学 | It is a kind of that propagation model wireless network planning method is exempted from based on machine learning |
-
2019
- 2019-12-31 CN CN201911417244.9A patent/CN111182556B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103583017A (en) * | 2011-06-09 | 2014-02-12 | 皇家飞利浦有限公司 | Method for configuring a network |
| CN104219404A (en) * | 2013-05-31 | 2014-12-17 | 中国电信股份有限公司 | Communication network emergency plan drill method, system and server |
| US9220123B1 (en) * | 2014-07-10 | 2015-12-22 | International Business Machines Corporation | Peer-to-peer sharing of network resources |
| US20170244744A1 (en) * | 2016-02-24 | 2017-08-24 | Verodin, Inc. | Systems and methods for attack simulation on a production network |
| CN109560968A (en) * | 2018-12-20 | 2019-04-02 | 中国电子科技集团公司第三十研究所 | A kind of the Internet resources intelligent planning and configuration method of dynamic strategy driving |
| CN110418354A (en) * | 2019-08-06 | 2019-11-05 | 北京邮电大学 | It is a kind of that propagation model wireless network planning method is exempted from based on machine learning |
Non-Patent Citations (4)
| Title |
|---|
| JIN GOO KANG，JU WOOK JANG，ETC.: "A network management system for u-city", 《13TH INTERNATIONAL CONFERENCE ON ADVANCED COMMUNICATION TECHNOLOGY (ICACT2011)》 * |
| 何汉明: "基于角色的多智能体社会模型研究与应用", 《中国优秀博硕士学位论文全文数据库 (博士)信息科技辑》 * |
| 董俊华等: "4G无线网络规划与仿真方法浅析", 《移动通信》 * |
| 郑国惠: "TD-LTE无线网络规划设计与优化方法分析", 《互联网天地》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022121559A1 (en) * | 2020-12-07 | 2022-06-16 | 中兴通讯股份有限公司 | Mobile communication system control method, network management and control agent, system, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111182556B (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Resource allocation for multicell device-to-device communications underlaying 5G networks: A game-theoretic mechanism with incomplete information | |
| CN105813017B (en) | Technology for carrying out dynamic network optimization using geo-location and network modelling | |
| Huang et al. | A game-theoretic resource allocation approach for intercell device-to-device communications in cellular networks | |
| Wilhelmi et al. | Usage of network simulators in machine-learning-assisted 5G/6G networks | |
| Bacci et al. | Understanding game theory via wireless power control [lecture notes] | |
| CN109068350A (en) | A kind of autonomous network selection system and method for the terminal of Wireless Heterogeneous Networks | |
| Najla et al. | Predicting device-to-device channels from cellular channel measurements: A learning approach | |
| Foni et al. | Evaluation methodologies for the NB-IOT system: Issues and ongoing efforts | |
| Shodamola et al. | A machine learning based framework for KPI maximization in emerging networks using mobility parameters | |
| Dawy et al. | A wireless communications laboratory on cellular network planning | |
| CN111182556B (en) | Wireless network planning design method based on intelligent agent | |
| Fernandes et al. | Comparison of artificial intelligence and semi-empirical methodologies for estimation of coverage in mobile networks | |
| Hu et al. | A study of LTE network performance based on data analytics and statistical modeling | |
| US11570063B2 (en) | Quality of experience optimization system and method | |
| CN114828045A (en) | Network optimization method and device, electronic equipment and computer readable storage medium | |
| US8880052B2 (en) | Evolving algorithms for network node control in a telecommunications network by genetic programming | |
| Zeng et al. | An efficient neural network optimized by fruit fly optimization algorithm for user equipment association in software‐defined wireless sensor network | |
| Dridi et al. | Reinforcement Learning Vs ILP Optimization in IoT support of Drone assisted Cellular Networks | |
| Zhao et al. | Design of jiutian intelligent network simulation platform | |
| Zhang et al. | Towards Net-Zero Carbon Emissions in Network AI for 6G and Beyond | |
| US9047570B2 (en) | Evolving algorithms for telecommunications network nodes by genetic programming | |
| Cuiñas et al. | Exploring the application of design thinking methodology in cellular communications network planning and deployment | |
| Gao et al. | Learning networking by reproducing research results in an ns-3 simulation networking laboratory course | |
| Rose et al. | Evolution from network planning to SON management using the simulator for mobile networks (SiMoNe) | |
| KR20220055363A (en) | A method for controlling a state control parameter for adjusting a state of a network of a base station using one of a plurality of models and an electronic device performing the same |
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 |