A High-Density Wireless Local Area Network Access Optimization Management Method and System

Abstract

The present invention discloses a method and system for optimizing the management of high-density wireless local area network access, which is applicable to high-density device access environments to improve network performance and user experience. First, through real-time network status monitoring, based on data such as channel utilization rate, device access density, interference situation, etc., the channel allocation is dynamically adjusted; combined with a channel switching mechanism based on device priority to ensure the connection stability of critical devices; through adaptive transmit power control and channel linkage optimization, signal overlap and interference are reduced; multi-level load balancing is achieved among multiple access points to optimize network resource allocation; and through intelligent user access optimization, device behavior and movement trajectories are predicted to ensure seamless access. The present invention can reduce channel conflicts and improve network stability and user experience.

Description

Technical Field

[0001] This application belongs to the technical field of digital information transmission, and particularly relates to a method and system for optimizing the management of high-density wireless local area network access. Background Art

[0002] With the development of wireless communication technology, WLAN (Wireless Local Area Network) technology has become an important part of modern communication and is widely used in scenarios such as office buildings, shopping malls, airports, and campuses. Especially in high-density access environments, such as conference centers, large exhibitions, shopping malls, airport terminals, and campuses, WLAN provides high-speed and low-latency wireless access services for tens of thousands of users and devices. However, with the increase in access devices, changes in network load, and the improvement of users' demand for high-quality network experience, WLAN faces many technical challenges in these high-density access environments, mainly including problems such as channel conflict, low spectrum utilization, network congestion, and signal interference.

[0003] The existing WLAN management has the following defects:

[0004] 1. Most current WLAN systems use a static channel allocation scheme during deployment, that is, when an access point is installed, a fixed channel is pre-allocated for each access point. This static channel allocation method is usually based on a preliminary assessment of the physical environment, such as the distance between access points, signal coverage, and interference areas. However, with the dynamic changes in network usage, especially in high-density environments, the access and mobility of devices occur frequently, and static channel allocation often has difficulty coping with these complex dynamic scenarios.

[0005] 2. Load imbalance in the WLAN network is also one of the common problems in high-density access scenarios. With the change in the number of device accesses, some access points may receive excessive connection requests due to their geographical location or environmental characteristics, resulting in network load being concentrated on some access points. While access points in other areas may be relatively idle and unable to fully utilize their channel resources. This uneven load distribution not only affects the user experience in high-load areas but also leads to waste of spectrum resources.

[0006] 3. In high-density environments, the mobility of user devices poses higher requirements for seamless network access. As users move in space, devices need to switch between different access points frequently. However, traditional WLAN management methods lack intelligent analysis of user movement trajectories, and frequent switching of access points may occur during the roaming process, resulting in connection interruption or signal quality degradation. Especially in large-scale open environments such as airports and shopping malls, the high-speed mobility of user devices poses higher challenges to network access. Summary of the Invention

[0007] The embodiments of the present application provide a method and system for optimizing the management of high-density wireless local area network access. By combining intelligent network status monitoring, adaptive learning algorithms, and dynamic power control technologies, through multi-dimensional and multi-level network management, the WLAN network can achieve adaptive optimization in complex high-density environments. This method can not only respond to network load changes in real time but also predict future network trends through historical data, and perform channel and power optimization configurations in advance, thereby effectively improving network performance, reducing channel conflicts, and optimizing the user access experience.

[0008] In a first aspect, the embodiments of the present application provide a method for optimizing the management of high-density wireless local area network access, including the following steps:

[0009] Step S100: Deploy a monitoring module on each access point, and perform multi-level monitoring and prediction in combination with historical data to generate global network status data;

[0010] Step S200: Based on the generated global network status visual data, in combination with a multi-level channel utilization model, establish monitoring at different levels to obtain channel-related data, and determine the channel utilization rates at different current levels;

[0011] Step S300: Based on the channel utilization rates at different current levels, during the dynamic channel allocation process, perform differential processing on the priorities of devices;

[0012] Step S400: Based on the real-time channel configuration results, in combination with changes in the physical environment and device distribution, dynamically adjust the transmission power of each access point to ensure a balance between signal coverage and interference suppression, and achieve the linkage optimization of channels and power;

[0013] Step S500: Based on the transmission power of each access point, through a multi-level load balancing mechanism, monitor at each level to obtain load indicators at different levels.

[0014] Step S600: Based on the load indicators at different levels, through a user behavior prediction model, optimize the access point and channel configurations for mobile user devices in advance to ensure seamless access of the devices during movement and improve the user experience.

[0015] Further, step S100 includes the following sub-steps: The monitoring module respectively performs real-time monitoring on a single access point, a group of access points, and all access points in the entire network; it can not only collect real-time data of each access point but also perform special analysis on areas with dense device access and predict the mobility patterns of devices;

[0016] The monitoring module can collect multi-dimensional data, including information such as channel interference, network traffic patterns, and the movement trajectories of user devices. By analyzing historical access data through deep learning algorithms, it predicts possible network load changes during a specific time period. This prediction function is based on time series analysis, movement patterns, and usage characteristics of device types, and performs preventive optimization adjustments on high-load areas in advance to ensure reasonable allocation of channel resources and power adjustment before the load surges.

[0017] A further setting is that step S200 includes the following sub-steps: By establishing a multi-layer channel utilization model, when performing channel allocation, not only the real-time channel utilization rate of each access point is considered, but also the influence of the geographical location and physical environment between access points on channel allocation is analyzed;

[0018] The multi-layer channel utilization model combines the coverage range of each access point, the channel configuration of neighboring access points, and the interference level for cross-analysis to ensure that channel allocation not only maximizes the utilization of channel resources but also effectively reduces interference within the same physical area;

[0019] The multi-layer channel utilization model allocates channel resources with different priorities to devices with different application requirements; by intelligently classifying application requirements, the channel allocation priority is dynamically adjusted to ensure that high-bandwidth devices or latency-sensitive applications are always connected to the access point with the least interference and the longest channel idle time;

[0020] Based on the global network status view data, determine the current access point-level channel utilization rate, the average channel utilization rate within the access point group, and the average channel utilization rate within the sub-network;

[0021] When the access point-level channel utilization rate, the average channel utilization rate within the access point group, and the average channel utilization rate within the sub-network are greater than the utilization rate thresholds at different levels, it is determined that the utilization rate of this access point is too high.

[0022] A further setting is that step S300 includes the following sub-steps: Based on the generated global network status view data, determine the current channel utilization rates at different levels, including: by assigning different priorities to each connected device, implementing a differentiated channel switching strategy for devices with different priorities;

[0023] During the channel switching process, give priority to ensuring the stable channel connection of key devices. By reserving additional channel capacity or delaying channel switching, ensure that the connections of these key devices are not affected during high network load or interference peak periods; Low-priority devices gradually switch channels according to the network load situation. By real-time analyzing the signal strength and network requirements of low-priority devices, give priority to performing channel switching during periods when their applications are not affected.

[0024] A further setting is that step S400 includes the following sub-steps: By means of multi-dimensional signal perception technology, in combination with physical environment changes, dynamically adjust the transmission power; in an indoor scenario, utilize reflection and refraction analysis to optimize the transmission angle and power output of the access point, ensure uniform signal coverage, and adjust the transmission power according to changes in the physical environment to avoid signal dead zones; and in combination with the dynamic changes in device access density and signal strength, intelligently adjust the transmission power; when devices densely access a specific area, automatically reduce the transmission power of the access points in that area to reduce signal overlap and interference; while when the number of device accesses decreases or the distribution is dispersed, increase the power coverage range to ensure the signal quality of more distant devices.

[0025] A further setting is that step S500 includes the following sub-steps: Establish a multi-level load balancing model to perform load analysis at different levels for device access, network traffic distribution, and channel utilization; the levels include: access point level, access point group level, and sub-network level; this model can perform load balancing across multiple levels, and by analyzing the load conditions of each level in real time, dynamically allocate devices between different levels to ensure load balancing at each level.

[0026] During the channel reconfiguration process, by real-time monitoring the access mode and traffic requirements of devices, dynamically adjust the channel resource allocation at each level to ensure the minimum channel overlap across levels, and reduce the overload and interference of local access points through dynamic channel adjustment; through cross-level channel configuration optimization, reduce the high-load situation in a single access point group or sub-network.

[0027] A further setting is that step S500 includes the following sub-steps: Based on the transmission power of each access point, through a multi-level load balancing mechanism, obtain the access point level load index, access point group load index, and sub-network load index.

[0028] When the access point level load index, access point group load index, and sub-network load index are greater than the load thresholds at different levels, it is determined that the load at that level is too heavy.

[0029] A further setting is that step S600 includes the following sub-steps: By constructing a user behavior prediction model, in combination with the user's historical network usage habits, device movement trajectories, and current network load conditions, pre-allocate access points for high-speed moving user devices; by predicting the movement direction and access requirements of user devices, and optimizing the access point and channel configuration in advance, ensure seamless handover of access points for users during movement.

[0030] At the same time, in combination with the network load situation, prioritize the access optimization for user devices with high bandwidth requirements or sensitive to latency; in high-load situations, ensure the signal quality and connection stability by reserving channel resources and access points for these devices in advance, while other devices with low bandwidth requirements connect by delaying access or switching to a sub-optimal access point.

[0031] In a second aspect, an embodiment of the present application further provides a high-density wireless local area network access optimization management system, including a control device, the control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements the method described in the first aspect.

[0032] The beneficial effects of the present invention are as follows:

[0033] 1. The present invention can pre-adjust channels and power based on device mobility patterns and historical trends before the network load surges; this prediction and adjustment mechanism based on dynamic data breaks through the traditional real-time response method, can optimize in advance, and avoid sudden network congestion.

[0034] 2. The present invention introduces a multi-layer channel utilization model, intelligently allocates channels by combining the physical environment and device application scenarios, and provides differentiated channel resource allocation in combination with the priority requirements of devices. This method can optimize channel utilization in complex environments, minimize co-channel interference, and improve network performance.

[0035] 3. The differentiated channel switching mechanism based on device priority of the present invention enables critical task devices to maintain high reliability even in network congestion or interference environments, while low-priority devices complete channel switching at appropriate times through intelligent scheduling. This differentiated channel switching strategy improves the overall utilization rate of channel resources while ensuring the continuity and reliability of critical applications.

[0036] 4. The present invention can flexibly adjust the transmission power of access points according to the dynamic changes of the environment and devices, ensuring the uniformity of signal coverage and minimizing interference. Especially the intelligent perception of physical environment changes enables the network to adapt to external changes in complex environments, improving the overall network performance and coverage.

[0037] 5. By introducing multi-level load balancing, the present invention breaks through the traditional single-level load balancing method and can achieve global optimization in a multi-level network structure; in different levels of access point groups or sub-networks, dynamically adjust device and channel resources to ensure cross-regional and cross-floor load balancing, which is particularly effective in large buildings or complex network environments.

[0038] 6. Through the user behavior prediction model, the present invention can allocate access points and channel resources for the user equipment in motion in advance to ensure the network connection quality of high-speed moving users; this intelligent access optimization based on behavior prediction greatly improves the network experience of users in a dynamic environment, especially in high-speed moving scenarios that require seamless handover. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic block diagram of the principle of the embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0041] As shown in the Figure 1 accompanying drawings;

[0042] This embodiment discloses a method for optimizing the access management of a high-density wireless local area network, including the following steps:

[0043] Step S100: Deploy a monitoring module on each access point, and perform multi-level monitoring and prediction in combination with historical data to generate global network status data;

[0044] Step S200: Based on the global network status view data generated in step S100 and the predicted network load, in combination with a multi-level channel utilization model, establish monitoring at different levels to obtain channel-related data, and calculate the channel utilization rate at the current access point level , the average channel utilization rate within the access point group , the average channel utilization rate within the subnet , where is the channel utilization rate at the current access point level, is the average channel utilization rate within the access point group, is the average channel utilization rate within the subnet;

[0045] The model algorithm is as follows:

[0046] ,

[0047] where is the current channel utilization rate, is the actually used bandwidth, is the available bandwidth, and i is the number of currently associated devices i;

[0048] Channel utilization rate at the access point group level:

[0049] ,

[0050] where is the average channel utilization rate within the group, G is the total number of connected devices within the group,

[0051] Channel utilization rate at the sub-network level:

[0052] = ,

[0053] where is the average channel utilization rate within the sub-network, N is the total number of devices within the sub-network;

[0054] Then, based on the real-time channel utilization rate information, dynamically allocate and adjust the channel configuration, and set the utilization thresholds at different levels , when > , it is considered that the channel utilization rate of this access point is too high ( is the utilization threshold at the i-th level), optimize the utilization of channel resources, and reduce the channel conflicts and interferences between adjacent access points;

[0055] Step S300: During the dynamic channel allocation process, by differentiating the priorities of devices, ensure the channel stability of critical devices first, minimize the impact of channel switching on high-priority devices, and low-priority devices will gradually adjust the channel when the network load permits;

[0056] Step S400: Based on the real-time channel configuration results in Step S300, combined with the changes in the physical environment and the device distribution, dynamically adjust the transmission power of each access point to ensure the balance between the signal coverage range and interference suppression, and achieve the joint optimization of channels and power;

[0057] Step S500: Through a multi-level load balancing mechanism, monitor at each level to obtain the load metrics at the access point level , the load metric at the access point group level , the load metric at the sub-network level , where Load metric at the access point level, is the load metric at the access point group level, is the load metric at the sub-network level;

[0058] The model algorithm is as follows:

[0059] = (Ratio of traffic to channel utilization rate),

[0060] wherein is the network traffic within a unit time, is the access point load index;

[0061] = ,

[0062] = ,

[0063] = (group traffic evenly distributed to the number of devices),

[0064] wherein is the current number of connected devices, is the total access point traffic within the group, is the total number of device accesses within the group, is the access point group load index;

[0065] = ,

[0066] = ,

[0067] = (sub-network traffic evenly distributed to the number of devices),

[0068] wherein is the total traffic within the current sub-network, is the total number of device accesses within the sub-network, is the sub-network load index;

[0069] According to the real-time load information, set a threshold and adjust the strategy: Set a threshold

[0070] If > , it is considered that the access point load is too heavy,

[0071] If > , the access point group load is too heavy,

[0072] If > , the sub-network load is too heavy;

[0073] Combined with the real-time device access and channel resource allocation situation, perform load balancing processing on the load of access points and access point groups, and perform channel reconfiguration across levels to reduce local overload and channel conflicts; Step S600: Through the user behavior prediction model, combined with the user's historical usage habits and real-time network load situation, optimize the access point and channel configuration for the moving user equipment in advance to ensure seamless access during the movement of the equipment and improve the user experience.

[0074] Specifically, step S100 includes the following sub-steps: The monitoring module monitors the individual access points, access point groups (such as multiple access points on the same floor), and all access points in the entire network in real time; it not only collects the real-time data of each access point, but also can perform special analysis on areas with intensive device access and predict the mobility pattern of the devices.

[0075] The monitoring module can collect multi-dimensional data, including channel interference, network traffic patterns, the movement trajectories of user equipment, etc. By analyzing the historical access data through deep learning algorithms, it predicts the possible network load changes during specific time periods (such as commuting, peak meeting periods); this prediction function is based on the usage characteristics of time series analysis, movement patterns, and device types (such as mobile devices), and performs preventive optimization adjustments on high-load areas in advance to ensure the reasonable allocation of channel resources and power adjustment before the load surges.

[0076] Specifically, step S200 includes the following sub-steps: By establishing a multi-layer channel utilization model, when performing channel allocation, not only consider the real-time channel utilization rate of each access point, but also analyze the influence of the geographical location and physical environment (such as walls, obstacles, etc.) between access points on channel allocation.

[0077] The multi-layer channel utilization model combines the coverage range of each access point, the channel configuration of neighboring access points, and the interference level for cross-analysis to ensure that the channel allocation not only maximizes the utilization of channel resources but also effectively reduces interference within the same physical area.

[0078] The multi-layer channel utilization model allocates channel resources with different priorities to devices with different application requirements; by intelligently classifying application requirements, it dynamically adjusts the channel allocation priority to ensure that high-bandwidth devices or latency-sensitive applications (such as video conferencing) are always connected to the access point with the least interference and the longest channel idle time. For access points with a relatively high channel utilization rate, it can be considered to guide new devices to connect to access points with lighter loads, optimize channel allocation, reduce the load by changing channel parameters (such as frequency, bandwidth, etc.), monitor the channel utilization of the entire access point group, dynamically allocate channels, monitor the channel utilization of the entire access point group, dynamically allocate channels, conduct an overall review of channel resources at the entire sub-network level, dynamically adjust the operating frequency bands of each access point, and optimize channel usage through spectrum management.

[0079] Specifically, step S300 includes the following sub-steps: By assigning different priorities to each connected device (based on device type, application requirements, and network sensitivity), implement a differential channel switching strategy for devices with different priorities;

[0080] During the channel switching process, give priority to ensuring the stable channel connection of critical devices (such as devices used for online meetings or security monitoring devices). By reserving additional channel capacity or delaying channel switching, ensure that the connections of these critical devices are not affected during periods of high network load or peak interference; lower-priority devices gradually switch channels according to the network load situation. By real-time analyzing the signal strength and network requirements of lower-priority devices, prioritize channel switching during periods when their applications are not affected.

[0081] Specifically, step S400 includes the following sub-steps: Through multi-dimensional signal sensing technology, combined with physical environment changes (such as door and window opening and closing, dynamic obstacles, weather changes, etc.), dynamically adjust the transmission power; in an indoor scenario, utilize reflection and refraction analysis to optimize the transmission angle and power output of the access point, ensure uniform signal coverage, and adjust the transmission power according to changes in the physical environment to avoid signal dead zones; and combined with the dynamic changes in device access density and signal strength, intelligently adjust the transmission power; when devices densely access a specific area, automatically reduce the transmission power of the access points in that area to reduce signal overlap and interference; while when the number of device accesses decreases or the distribution is scattered, increase the power coverage range to ensure the signal quality of more distant devices.

[0082] Specifically, step S500 includes the following sub-steps: establishing a multi-level load balancing model to perform load analysis at different levels for device access, network traffic distribution, and channel utilization; the levels include: access point level, access point group level (such as a set of access points on the same floor or in the same area), and sub-network level (such as a building or a specific area); this model can perform load balancing across multiple levels, and by analyzing the load conditions of each level in real time, dynamically allocate devices between different levels to ensure load balancing at each level;

[0083] During the channel reconfiguration process, by monitoring the access mode and traffic requirements of devices in real time, dynamically adjust the channel resource allocation at each level to ensure the minimization of cross-level channel overlap, and reduce the overload and interference of local access points through dynamic channel adjustment; through cross-level channel configuration optimization, reduce the high-load situation in a single access point group or sub-network;

[0084] When an access point is overloaded, reallocate the devices connected to it to access points with lighter loads. Strategies can be adopted to guide newly connected devices to select access points with lighter loads, check the load situation within the group, and dynamically adjust the traffic distribution within the group if necessary, redirecting a part of the traffic to other groups or access points. At the sub-network level, reallocate resources, which may involve adjusting the configuration of access points to ensure uniform global load.

[0085] Specifically, step S600 includes the following sub-steps: by constructing a user behavior prediction model, combining the user's historical network usage habits, device movement trajectories, and current network load conditions, pre-allocate access points for high-speed moving user devices; by predicting the movement direction and access requirements of user devices, and optimizing the access point and channel configuration in advance, ensure seamless handover of access points during the user's movement;

[0086] At the same time, in combination with the network load situation, perform priority access optimization for user devices with high bandwidth requirements or sensitive to latency (such as video conferencing devices or real-time gaming devices); in high-load situations, reserve channel resources and access points for these devices in advance to ensure their signal quality and connection stability, while other devices with low bandwidth requirements connect through delayed access or switch to sub-optimal access points.

[0087] This embodiment also discloses a high-density wireless local area network access optimization management system, including a control device, and the control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0088] The following embodiments are based on network test data in real scenarios and detail the application effects of the present invention in different scenarios. All data are measurement values in simulated actual network environments, are reasonable and operable, and fully demonstrate the superiority of the present invention.

[0089] Application Example 1

[0090] There are significant dynamic changes in the access of devices on campus, especially during peak class hours and exam periods. Traditional static channel allocation is difficult to cope with the scenario of a sharp increase in the access volume of these devices, resulting in an increase in network latency in hot spots such as teaching buildings and libraries. The present invention optimizes through multi-level load balancing, dynamic channel allocation and power control to ensure network stability during peak periods.

[0091] During peak hours (such as during class hours), each access point connects 30 devices, and the total device access volume is about 6,000. In particular, the devices in libraries, teaching buildings and dormitories are dense.

[0092] Initial network latency: The network latency during peak hours is 200 ms, and the latency in some areas exceeds 300 ms.

[0093] Initial throughput: The network throughput during peak periods is 5 Gbps, and the network performance is poor.

[0094] After adopting the solution of this embodiment, load distribution can be carried out across floors and regions. It can dynamically adjust the access points and channel resources of devices among different regions such as teaching buildings, dormitories and libraries to ensure that the load in local areas is not too high, and at the same time avoid the decline of network performance caused by channel conflicts. Through an intelligent channel allocation algorithm, combined with the physical environment of the access point (such as building structure, partition walls, etc.), the channel allocation and transmission power are dynamically adjusted to reduce channel overlap and ensure that the network operates efficiently under high load, especially in device-dense areas such as libraries, teaching buildings and dormitories, and the power is automatically adjusted to reduce signal interference. Through the self-learning engine, it can optimize future channel allocation strategies based on historical data, anticipate the device access requirements during peak hours in advance, and adjust power and channel resources before the load increases to ensure that the network continuously maintains the best state.

[0095] The effects are as follows;

[0096] Network latency: The network latency during peak hours is reduced from 200 ms to 90 ms, and the network latency in extreme cases is controlled within 130 ms, and the campus network operates more stably.

[0097] Throughput: The network throughput is increased from 5 Gbps to 7.5 Gbps, with an overall increase of 50%. Especially during peak class hours, network congestion is greatly reduced.

[0098] Application Example 2

[0099] The traditional static management method of shopping malls is difficult to quickly respond to the dynamic access and mobility changes of devices, resulting in network congestion in hot spots of shopping malls. Through user behavior prediction and multi-level load balancing mechanisms, the present invention effectively optimizes channel resource allocation and device access in hot spots and high-load periods, avoiding channel conflicts and network overload.

[0100] Number of device accesses: On average, 30 devices are connected to each access point. During peak periods, 50 devices are connected to each access point in densely populated areas. The total number of device accesses is 10,000, and 80% of the devices are concentrated in the dining area.

[0101] Initial network latency: The average network latency is 250 ms, and the latency in hot spots exceeds 400 ms, seriously affecting the user experience.

[0102] Initial throughput: The network throughput during peak periods is 4 Gbps, but channel conflicts result in an actual throughput far lower than expected.

[0103] After adopting the solution of this embodiment, through the user behavior prediction model, the present invention predicts the usage behavior and traffic demand of devices based on historical access data. Before lunch and dinner peaks, it can allocate channel resources for the dining area in the device-intensive area in advance, ensuring that channel conflicts in high-load areas are minimized. It can perform load balancing of device access points and channel resources across regions (such as shopping areas and rest areas). During high loads, it can adjust the channels in hot spots in real time and transfer part of the load to the access of adjacent regions, avoiding overload of a single access point.

[0104] The effects are as follows;

[0105] Network latency: The network latency is reduced from 250 ms to 100 ms, and the latency in hot spots is reduced to within 150 ms.

[0106] Throughput: The network throughput is increased from 4 Gbps to 6.5 Gbps, an increase of 62.5%, and the network performance is more stable during peak periods.

[0107] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A high-density wireless local area network access optimization management method, characterized in that: The following steps are included: Deploy monitoring modules on each access point and combine historical data for multi-level monitoring and prediction to generate global network status data; Based on the generated global network status data, combined with the multi-layer channel utilization model, monitoring is established at different levels to obtain channel-related data and determine the current channel utilization at different levels; Based on the current channel utilization rates of different levels, in the dynamic channel allocation process, the priorities of devices are differentiated to give priority to ensuring the channel stability of key devices, ensuring that the impact of channel switching on high-priority devices is minimal, and low-priority devices are gradually adjusted when the network load allows; Based on the real-time channel configuration results, combined with the changes in the physical environment and the distribution of devices, the transmit power of each access point is dynamically adjusted to ensure a balance between signal coverage and interference suppression, and to achieve linkage optimization of channels and power. Based on the transmission power of each access point, a multi-level load balancing mechanism is used to monitor each level, thereby obtaining the access point level load index. , access point group load indicator and subnetwork load indicators ; The model algorithm is as follows: = ， in is the network traffic per unit time; = ， = ， = ， in is the number of currently connected devices, is the total traffic of access points in the group, The total number of connected devices in the group; = ， = ， = ， in is the total flow in the current sub-network, The total number of devices connected to the sub-network; Set thresholds and adjust policies based on real-time load information: Set a threshold like > , the access point is considered to be overloaded. like > , then the access point group is overloaded, like > , then the subnetwork is overloaded; Combined with the real-time device access and channel resource allocation, the load of the access point and the access point group is balanced, and the channel is reconfigured across layers to reduce local overload and channel conflict; Step S600: Through the user behavior prediction model, combined with the user's historical usage habits and real-time network load conditions, the access point and channel configuration are optimized in advance for the mobile user device to ensure seamless access of the device during movement and improve the user experience; Based on the load indicators at different levels, the access point and channel configuration are optimized in advance for the mobile user equipment through the user behavior prediction model to ensure seamless access of the device during movement and improve the user experience.

2. A high-density wireless local area network access optimization management method as claimed in claim 1, characterized in that: The monitoring module is deployed on each access point, and multi-level monitoring and prediction are performed in combination with historical data to generate global network status data, including: The monitoring module monitors a single access point, a group of access points, and all access points in the entire network in real time. It not only collects real-time data for each access point, but also performs special analysis on areas with dense device access and predicts device mobility patterns. The monitoring module can collect multi-dimensional data, including channel interference, network traffic patterns, movement trajectories of user devices and other information. It analyzes historical access data through deep learning algorithms and predicts possible changes in network load in a specific time period. This prediction function is based on time series analysis, mobile patterns and usage characteristics of device types, and makes preventive optimization adjustments to high-load areas in advance to ensure reasonable allocation of channel resources and power adjustment before the load surges.

3. A high-density wireless local area network access optimization management method as claimed in claim 2, characterized in that: The generated global network status data is combined with a multi-layer channel utilization model to establish monitoring at different levels to obtain channel-related data, including: by establishing a multi-layer channel utilization model, when performing channel allocation, not only the real-time channel utilization of each access point is considered, but also the influence of the geographical location and physical environment between the access points on the channel allocation is analyzed; The multi-layer channel utilization model combines the coverage of each access point, the channel configuration of adjacent access points, and the interference level to perform cross-analysis to ensure that channel allocation can not only maximize the utilization of channel resources, but also effectively reduce interference within the same physical area; The multi-layer channel utilization model allocates channel resources of different priorities to devices with different application requirements. Through intelligent classification of application requirements, the channel allocation priority is dynamically adjusted to ensure that high-bandwidth devices or delay-sensitive applications are always connected to the access point with the least interference and the longest channel idle time.

4. A high-density wireless local area network access optimization management method as claimed in claim 3, characterized in that: Based on the generated global network status data, current channel utilization rates at different levels are determined, including: Based on the global network status data, determine the current access point level channel utilization, the average channel utilization within the access point group, and the average channel utilization within the sub-network; If the access point level channel utilization, the average channel utilization within the access point group, and the average channel utilization within the subnet are greater than utilization thresholds at different levels, it is determined that the access point utilization is too high.

5. A high-density wireless local area network access optimization management method as claimed in claim 4, characterized in that: Based on the generated global network status data, determining current channel utilization rates at different levels, including: performing differentiated channel switching strategies for devices of different priorities by assigning different priorities to each connected device; During the channel switching process, priority is given to ensuring the stability of the channel connection of key devices. By reserving additional channel capacity or delaying channel switching, the connection of these key devices is not affected during periods of high network load or interference peaks. Low-priority devices gradually switch channels according to network load conditions. By real-time analysis of the signal strength and network requirements of low-priority devices, channel switching is prioritized during periods that do not affect the operation of their applications.

6. A high-density wireless local area network access optimization management method as claimed in claim 5, characterized in that: Based on the real-time channel configuration results, combined with the changes in the physical environment and the distribution of devices, the transmission power of each access point is dynamically adjusted, including: through multi-dimensional signal perception technology, combined with changes in the physical environment, the transmission power is dynamically adjusted; in indoor scenarios, reflection and refraction analysis is used to optimize the transmission angle and power output of the access point to ensure uniform signal coverage, and the transmission power is adjusted according to changes in the physical environment to avoid signal dead spots; and the transmission power is intelligently adjusted in combination with the dynamic changes in device access density and signal strength; when devices are densely accessed in a specific area, the transmission power of the access points in the area is automatically reduced to reduce signal overlap and interference; and when the number of device accesses decreases or the distribution is dispersed, the power coverage range is increased to ensure the signal quality of farther devices.

7. A high-density wireless local area network access optimization management method as claimed in claim 6, characterized in that: Based on the transmission power of each access point, monitoring is implemented at each level through a multi-level load balancing mechanism to obtain load indicators at different levels, including: establishing a multi-level load balancing model to perform load analysis at different levels on device access, network traffic distribution and channel utilization; the levels include: access point level, access point group level, and sub-network level; the model can perform load balancing across multiple levels, dynamically allocate devices between different levels by analyzing the load status of each level in real time, and ensure load balancing at each level; During the channel reconfiguration process, the channel resource allocation of each level is dynamically adjusted by real-time monitoring of the device's access mode and traffic demand to ensure that cross-level channel overlap is minimized, and the overload and interference of local access points are reduced through dynamic channel adjustment; through cross-level channel configuration optimization, high load conditions in a single access point group or subnetwork are reduced.

8. A high-density wireless local area network access optimization management method as claimed in claim 7, characterized in that: Based on the transmission power of each access point, obtaining access point level load indicators, access point group load indicators, and sub-network load indicators through a multi-level load balancing mechanism; When the access point level load indicator, the access point group load indicator, and the sub-network load indicator are greater than load thresholds of different levels, it is determined that the level is overloaded.

9. A high-density wireless local area network access optimization management method as claimed in claim 8, characterized in that: Based on the load indicators at different levels, the access point and channel configuration are optimized in advance for the mobile user equipment through the user behavior prediction model to ensure seamless access of the device during movement and improve the user experience, including: pre-allocating access points for high-speed mobile user equipment by building a user behavior prediction model, combining the user's historical network usage habits, device movement trajectory and current network load status; by predicting the movement direction and access needs of the user equipment, and optimizing the access point and channel configuration in advance, ensuring that the user can seamlessly switch access points during movement; At the same time, taking into account the network load situation, priority access optimization is performed for user devices with high bandwidth requirements or delay sensitivity. Under high load conditions, channel resources and access points are reserved for these devices in advance to ensure their signal quality and connection stability, while other devices with low bandwidth requirements are connected by delaying access or switching to suboptimal access points.

10. A high-density wireless local area network access optimization management system, applied to a high-density wireless local area network access optimization management method according to any one of claims 1 to 9, characterized in that: The method comprises a control device, wherein the control device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

Images