A wireless network planning and design method based on AI learning
The wireless network planning and design method based on AI learning automatically adjusts the location and parameters of base stations, solving the problems of long planning cycles and large quality fluctuations in traditional methods, and achieving efficient and accurate wireless network planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INSPUR COMM TECH CO LTD
- Filing Date
- 2026-01-09
- Publication Date
- 2026-05-29
AI Technical Summary
Existing wireless network planning methods suffer from problems such as long cycles, large quality fluctuations, and difficulty in handling complex scenarios by simulation tools in scenarios such as industrial internet and smart parks, and cannot meet the needs of rapid deployment and accurate adaptation.
A wireless network planning and design method based on AI learning is adopted. By analyzing scene characteristics through a large AI model, the location and parameters of base stations are automatically adjusted. Combined with an adapted simulation algorithm model, automatic iterative optimization is achieved until the preset coverage target is met.
It significantly improved planning efficiency, enhanced simulation accuracy and solution adaptability, reduced reliance on manual labor and costs, and significantly improved the implementation effect of the solution.
Smart Images
Figure CN122120780A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of wireless network planning technology, and in particular to a wireless network planning and design method based on AI learning. Background Technology
[0002] With the acceleration of digital transformation in industries such as industrial internet, smart parks, and smart healthcare, the deployment of industry wireless private networks is facing multi-dimensional technical challenges.
[0003] Unlike public network coverage, industry private networks have different requirements for network performance indicators (such as seamless indoor and outdoor coverage, millisecond-level latency, and 99.99% reliability), and need to cope with complex scenario characteristics such as dense building clusters blocking traffic and uneven spatial and temporal distribution of business traffic.
[0004] The current planning paradigm based on human experience has significant shortcomings: Firstly, the traditional iterative process of "site deployment-simulation-adjustment" relies on on-site surveys and parameter optimization by professionals, and the production cycle of a single solution can be as long as several weeks in typical scenarios such as industrial plants and medical complexes. Secondly, the excessive reliance on individual experience in base station site selection and power configuration, coupled with the lack of a quantitative evaluation system, has resulted in a solution quality fluctuation rate exceeding 35%. Third, existing simulation tools struggle to effectively couple multi-dimensional constraints (including spectrum resources, construction costs, electromagnetic radiation, etc.) when dealing with complex factors such as dynamic business hotspots and non-line-of-sight propagation, resulting in a deviation rate of over 20% between planning results and actual deployment effects.
[0005] This inefficient and non-standard traditional model can no longer meet the core demands of "rapid deployment and precise adaptation" for industry private networks, and there is an urgent need to build an intelligent planning algorithm system to break through the efficiency bottleneck.
[0006] To address the above problems, this invention proposes a wireless network planning and design method based on AI learning. Summary of the Invention
[0007] To overcome the shortcomings of existing technologies, this invention provides a simple and efficient AI-based wireless network planning and design method.
[0008] This invention is achieved through the following technical solution: A wireless network planning and design method based on AI learning includes the following steps: Step S1: Input Parameter Acquisition and Verification Receive product performance parameters, business area layout information, and network coverage targets as joint input parameters; The input parameters are standardized in format, the integrity and validity of the data are verified, and missing, erroneous and invalid data (such as incorrectly formatted coordinate information and performance parameters that are out of reasonable range) are removed to ensure that the input data is usable. The product performance parameters include coverage capability, capacity, and power consumption; The business area layout information includes drawing data, obstacle distribution, business hot zone coordinates and signal sensitive zone range; The network coverage targets include target coverage, edge rate, capacity requirements, and latency threshold.
[0009] Step S2: AI Adaptation Simulation Algorithm Model The AI big model analyzes scenario characteristics based on business area layout information, including terrain complexity, obstacle density, and business hotspot distribution range, and automatically retrieves the appropriate wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. In step S2, if the AI large model analysis determines that the application scenario is a complex indoor scenario, then the ray tracing model is called first. If the AI large model analysis determines that the application scenario is an open area, then the simplified simulation model should be used first.
[0010] Step S3: Automatically iteratively optimize the point placement scheme Based on the difference between the simulation results and the preset coverage targets, the AI model automatically adjusts the base station location, altitude, antenna downtilt angle and power parameters, and triggers the simulation repeatedly until the solution meets all preset targets without the need for manual intervention. In step S3, the point placement scheme is automatically iterated and optimized, as follows: Step S3.1: The user generates a preliminary base station deployment plan based on the input parameters according to the scenario requirements, including the number of base stations, approximate locations, initial power, and antenna downtilt angle settings; Step S3.2: Simulate network performance using the invoked simulation algorithm model and output key indicator data, including coverage, edge rate, capacity distribution, and latency; Step S3.3: Compare the simulation results of the AI large model with the preset coverage target to determine whether all requirements are met; If the target is not met, the base station location, height, antenna downtilt angle and power parameters will be automatically adjusted to generate a new deployment plan and trigger the simulation algorithm model again. Step S3.4: Repeat the simulation and parameter adjustment steps until the output simulation results fully meet the preset coverage target, then stop the iteration.
[0011] Step S4: Output the optimal solution It directly outputs a planning scheme containing key parameters for actual deployment and implementation; The key parameters include the specific location coordinates of the base station, installation height, antenna downtilt angle, transmission power, and cell division.
[0012] In step S4, a standardized planning scheme document is generated, which includes a scheme description, parameter details and simulation verification report, for planners to use directly for deployment and implementation.
[0013] A wireless network planning and design system based on AI learning, used to implement the above method, includes: The input parameter acquisition and verification module is responsible for receiving product performance parameters, business area layout information, and network coverage targets as joint input parameters; it performs format standardization processing on the input parameters, verifies the integrity and validity of the data, and removes missing, erroneous, and invalid data to ensure that the input data is usable. The simulation algorithm model AI adaptation module is responsible for calling the large AI model, analyzing scene characteristics based on business area layout information, including terrain complexity, obstacle density and business hot zone distribution range, and automatically retrieving the adapted wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. The automatic iteration module is responsible for automatically adjusting the base station location, altitude, antenna downtilt angle, and power parameters based on the difference between the simulation results and the preset coverage targets, and triggering the simulation in a loop until the solution meets all preset targets without the need for manual intervention. The optimal solution output module is responsible for directly outputting a planning scheme containing key parameters, generating standardized planning scheme documents, and directly using them for actual deployment and implementation.
[0014] A computing device for wireless network planning and design based on AI learning, comprising: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.
[0015] A computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by an AI-learning-based wireless network planning and design computing device, cause the AI-learning-based wireless network planning and design computing device to perform any of the methods described above.
[0016] The beneficial effects of this invention are: the AI-based wireless network planning and design method can comprehensively balance multi-dimensional constraints, has higher simulation accuracy, improves the adaptability of indicators, significantly improves planning efficiency, greatly reduces reliance on manual labor and costs, and improves the implementation effect of the solution. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Appendix Figure 1 This is a schematic diagram of the wireless network planning and design method based on AI learning according to the present invention. Detailed Implementation
[0019] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions in the embodiments of this invention will be clearly and completely described below in conjunction with the embodiments of this invention. Obviously, the described embodiments are merely some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.
[0020] This AI-based wireless network planning and design method includes the following steps: Step S1: Input Parameter Acquisition and Verification Receive product performance parameters, business area layout information, and network coverage targets as joint input parameters; The input parameters are standardized in format, the integrity and validity of the data are verified, and missing, erroneous and invalid data (such as incorrectly formatted coordinate information and performance parameters that are out of reasonable range) are removed to ensure that the input data is usable. The product performance parameters include coverage capability, capacity, and power consumption; The business area layout information includes drawing data, obstacle distribution, business hot zone coordinates and signal sensitive zone range; The network coverage targets include target coverage, edge rate, capacity requirements, and latency threshold.
[0021] Step S2: AI Adaptation Simulation Algorithm Model The AI big model analyzes scenario characteristics based on business area layout information, including terrain complexity, obstacle density, and business hotspot distribution range, and automatically retrieves the appropriate wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. In step S2, if the AI large model analysis determines that the application scenario is a complex indoor scenario, then the ray tracing model is called first. If the AI large model analysis determines that the application scenario is an open area, then the simplified simulation model should be used first.
[0022] Step S3: Automatically iteratively optimize the point placement scheme Based on the difference between the simulation results and the preset coverage targets, the AI model automatically adjusts the base station location, altitude, antenna downtilt angle and power parameters, and triggers the simulation repeatedly until the solution meets all preset targets without the need for manual intervention. In step S3, the point placement scheme is automatically iterated and optimized, as follows: Step S3.1: The user generates a preliminary base station deployment plan based on the input parameters according to the scenario requirements, including the number of base stations, approximate locations, initial power, and antenna downtilt angle settings; Step S3.2: Simulate network performance using the invoked simulation algorithm model and output key indicator data, including coverage, edge rate, capacity distribution, and latency; Step S3.3: Compare the simulation results of the AI large model with the preset coverage target to determine whether all requirements are met; If the target is not met, the base station location, height, antenna downtilt angle and power parameters will be automatically adjusted to generate a new deployment plan and trigger the simulation algorithm model again. Step S3.4: Repeat the simulation and parameter adjustment steps until the output simulation results fully meet the preset coverage target, then stop the iteration.
[0023] Step S4: Output the optimal solution It directly outputs a planning scheme containing key parameters for actual deployment and implementation; The key parameters include the specific location coordinates of the base station, installation height, antenna downtilt angle, transmission power, and cell division.
[0024] In step S4, a standardized planning scheme document is generated, which includes a scheme description, parameter details and simulation verification report, for planners to use directly for deployment and implementation.
[0025] This AI-based wireless network planning and design system, used to implement the above methods, includes: The input parameter acquisition and verification module is responsible for receiving product performance parameters, business area layout information, and network coverage targets as joint input parameters; it performs format standardization processing on the input parameters, verifies the integrity and validity of the data, and removes missing, erroneous, and invalid data to ensure that the input data is usable. The simulation algorithm model AI adaptation module is responsible for calling the large AI model, analyzing scene characteristics based on business area layout information, including terrain complexity, obstacle density and business hot zone distribution range, and automatically retrieving the adapted wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. The automatic iteration module is responsible for automatically adjusting the base station location, altitude, antenna downtilt angle, and power parameters based on the difference between the simulation results and the preset coverage targets, and triggering the simulation in a loop until the solution meets all preset targets without the need for manual intervention. The optimal solution output module is responsible for directly outputting a planning scheme containing key parameters, generating standardized planning scheme documents, and directly using them for actual deployment and implementation.
[0026] This AI-based wireless network planning and design computing device includes: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for performing any of the methods described above.
[0027] The computer-readable storage medium stores one or more programs, the one or more programs including instructions that, when executed by an AI-based wireless network planning and design computing device, cause the AI-based wireless network planning and design computing device to perform any of the methods described above.
[0028] This AI-based wireless network planning and design method, through deep integration of large AI models and wireless simulation algorithms, constructs an intelligent planning closed loop encompassing "intelligent integration of input parameters + adaptive invocation of simulation models + automatic iteration of solutions + optimal parameter output." Compared with existing technologies, its main features are as follows: 1) Significantly improved planning efficiency: Traditional manual planning processes take several days to several weeks, while this method can shorten the planning cycle by more than 80%, and can output the optimal solution within hours even in complex scenarios.
[0029] 2) Significantly improved solution quality: The AI model can comprehensively balance multi-dimensional constraints, and the number of iterations and optimizations far exceeds the limits of human intervention. The adaptability of the solution in terms of coverage, capacity, latency and other indicators is improved by more than 30%.
[0030] 3) Reduced reliance on manual labor and costs: No need for long-term intervention by professional planners; ordinary technicians can operate it, which greatly reduces labor costs and experience threshold.
[0031] 4) Higher simulation accuracy: Based on scene characteristics, the simulation algorithm model is adaptively called, and the deviation between the simulation results and the actual deployment scenario is reduced to within 5%, which improves the implementation effect of the solution.
[0032] The embodiments described above are merely one specific implementation of the present invention. Ordinary changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention should be included within the protection scope of the present invention.
Claims
1. A wireless network planning and design method based on AI learning, characterized in that: Includes the following steps: Step S1: Input Parameter Acquisition and Verification Receive product performance parameters, business area layout information, and network coverage targets as joint input parameters; The input parameters are standardized in format, the integrity and validity of the data are verified, and missing, erroneous and invalid data are removed to ensure that the input data is usable. Step S2: AI Adaptation Simulation Algorithm Model The AI big model analyzes scenario characteristics based on business area layout information, including terrain complexity, obstacle density, and business hotspot distribution range, and automatically retrieves the appropriate wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. Step S3: Automatically iteratively optimize the point placement scheme Based on the difference between the simulation results and the preset coverage targets, the AI model automatically adjusts the base station location, altitude, antenna downtilt angle and power parameters, and triggers the simulation repeatedly until the solution meets all preset targets without the need for manual intervention. Step S4: Output the optimal solution It directly outputs a planning scheme containing key parameters for actual deployment and implementation; The key parameters include the specific location coordinates of the base station, installation height, antenna downtilt angle, transmission power, and cell division.
2. The wireless network planning and design method based on AI learning according to claim 1, characterized in that: The product performance parameters include coverage capability, capacity, and power consumption; The business area layout information includes drawing data, obstacle distribution, business hot zone coordinates and signal sensitive zone range; The network coverage targets include target coverage, edge rate, capacity requirements, and latency threshold.
3. The wireless network planning and design method based on AI learning according to claim 1, characterized in that: In step S2, if the AI large model analysis determines that the application scenario is a complex indoor scenario, then the ray tracing model is called first. If the AI large model analysis determines that the application scenario is an open area, then the simplified simulation model should be used first.
4. The wireless network planning and design method based on AI learning according to claim 1, characterized in that: In step S3, the point placement scheme is automatically iterated and optimized, as follows: Step S3.1: The user generates a preliminary base station deployment plan based on the input parameters according to the scenario requirements, including the number of base stations, approximate locations, initial power, and antenna downtilt angle settings; Step S3.2: Simulate network performance using the invoked simulation algorithm model and output key indicator data, including coverage, edge rate, capacity distribution, and latency; Step S3.3: Compare the simulation results of the AI large model with the preset coverage target to determine whether all requirements are met; If the target is not met, the base station location, height, antenna downtilt angle and power parameters will be automatically adjusted to generate a new deployment plan and trigger the simulation algorithm model again. Step S3.4: Repeat the simulation and parameter adjustment steps until the output simulation results fully meet the preset coverage target, then stop the iteration.
5. The wireless network planning and design method based on AI learning according to claim 1, characterized in that: In step S4, a standardized planning scheme document is generated, which includes a scheme description, parameter details and simulation verification report, for planners to use directly for deployment and implementation.
6. A wireless network planning and design system based on AI learning, characterized in that: To implement the method according to any one of claims 1 to 5, comprising: The input parameter acquisition and verification module is responsible for receiving product performance parameters, business area layout information, and network coverage targets as joint input parameters; it performs format standardization processing on the input parameters, verifies the integrity and validity of the data, and removes missing, erroneous, and invalid data to ensure that the input data is usable. The simulation algorithm model AI adaptation module is responsible for calling the large AI model, analyzing scene characteristics based on business area layout information, including terrain complexity, obstacle density and business hot zone distribution range, and automatically retrieving the adapted wireless signal simulation algorithm model to ensure the accuracy and efficiency of the simulation. The automatic iteration module is responsible for automatically adjusting the base station location, altitude, antenna downtilt angle, and power parameters based on the difference between the simulation results and the preset coverage targets, and triggering the simulation in a loop until the solution meets all preset targets without the need for manual intervention. The optimal solution output module is responsible for directly outputting a planning scheme containing key parameters, generating standardized planning scheme documents, and directly using them for actual deployment and implementation.
7. A wireless network planning and design computing device based on AI learning, characterized in that: include: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs including instructions for performing the method according to any one of claims 1 to 5.
8. A computer-readable storage medium for storing one or more programs, characterized in that: The one or more programs include instructions that, when executed by an AI-based wireless network planning and design computing device, cause the AI-based wireless network planning and design computing device to perform the method according to any one of claims 1 to 5.