Method, apparatus and related device for deployment of access point of cell-free network

Abstract

The present disclosure provides a cell-free network access point deployment method and device and related equipment, and relates to the technical field of wireless communication. The method comprises the following steps: obtaining historical user information and historical traffic information in a target area within a historical time period; generating a first access point deployment decision in the target area according to the historical user information and the historical traffic information; monitoring real-time user information and real-time traffic information in the target area at a current time; inputting the first access point deployment decision, the real-time user information and the real-time traffic information into a pre-trained reinforcement learning model to output a second access point deployment decision in the target area. The cell-free network access point deployment method can adapt to a dynamically changing network environment.

Description

Technical Field

[0001] This disclosure relates to the field of wireless communication technology, and in particular to a method, apparatus and related equipment for deploying access points in a non-cellular network. Background Technology

[0002] In November 2023, the International Telecommunication Union Radiocommunication Sector (ITU-R) officially released the Sixth Generation (6G) Vision Report, which clarified six major scenarios for the 6G era. The requirements for peak network speed, user experience speed, and system capacity are further enhanced. Traditional cellular networks usually improve system capacity by reducing cell radius and densely deploying base stations. However, the lack of effective cooperation between base stations leads to a sharp increase in inter-cell interference. System capacity has been theoretically proven to be limited by interference. At the same time, due to the existence of cell edge effect, traditional cellular networks cannot provide stable network throughput, making it difficult to guarantee user experience.

[0003] To address the aforementioned issues of cellular networks, the academic community has proposed cell-free technology. Cell-free technology is a novel wireless access architecture concept derived from distributed multiple-input multiple-output (MIMO) technology. It employs distributed MIMO to construct a mobile communication system with dynamically configured resources. Each antenna element / access point (AP) within the user's coverage area can use the same frequency configuration, eliminating interference through joint processing. This is expected to fundamentally change the cell configuration architecture of traditional cellular networks. Theoretical analysis results show that cell-free technology has advantages in ensuring network throughput and improving system spectral efficiency.

[0004] Cellular-free massive MIMO networks provide services to users by deploying a large number of access points (APs), eliminating cell boundaries and achieving high speed, low latency and high reliability. However, traditional deployment methods are often based on static optimization models, which are difficult to adapt to dynamically changing network environments and user needs.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] This disclosure provides a method, apparatus, and related equipment for deploying access points in a non-cellular network, which at least to some extent overcomes the problem that the methods for deploying access points in non-cellular networks in related technologies cannot adapt to dynamically changing network environments.

[0007] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0008] According to one aspect of this disclosure, a method for deploying access points in a non-cellular network is provided, comprising: acquiring historical user information and historical traffic information within a target area over a historical time period; generating a first access point deployment decision within the target area based on the historical user information and the historical traffic information; monitoring real-time user information and real-time traffic information within the target area at the current moment; inputting the first access point deployment decision, the real-time user information, and the real-time traffic information into a pre-trained reinforcement learning model; and outputting a second access point deployment decision within the target area.

[0009] In some exemplary embodiments of this disclosure, after outputting the deployment decision of the second access point within the target area based on the foregoing scheme, the method further includes: inputting historical user information and real-time user information within the target area into a pre-trained time series prediction model, and outputting predicted values ​​of user information within the target area; and optimizing the deployment decision of the second access point based on the predicted values ​​of user information within the target area.

[0010] In some exemplary embodiments of this disclosure, based on the foregoing scheme, generating a first access point deployment decision within the target area according to the historical user information and the historical traffic information includes: determining a densely populated user area within the target area according to the historical user information and the historical traffic information; using the total capacity of the deployed access points satisfying the historical traffic information of the densely populated user area and the number of deployed access points not exceeding a pre-set budget limit as constraints; setting an optimization objective function based on the cost of deploying access points within the target area; and generating a first access point deployment decision within the target area under the constraints, with the minimum value of the optimization objective function as the optimization objective.

[0011] In some exemplary embodiments of this disclosure, based on the foregoing scheme, determining the densely populated user area within the target region according to the historical user information and the historical traffic information includes: dividing the target region into multiple grids based on a pre-set division rule; calculating the grid density product of each grid within a preset time period according to the historical user information and the historical traffic information; and filtering out grids with a grid density product greater than the pre-set grid density product threshold based on the grid density product of each grid and the pre-set grid density product threshold, thereby determining the densely populated user area within the target region.

[0012] In some exemplary embodiments of this disclosure, based on the foregoing scheme, the optimization objective function is obtained by the following formula:

[0013]

[0014] Where N represents the number of locations where access points can be deployed; This is represented as the cost of deploying an access point at the i-th location; The denot represents whether an access point is deployed at the i-th location; i represents the location where an access point can be deployed.

[0015] In some exemplary embodiments of this disclosure, based on the foregoing scheme, the constraints are obtained by the following formula:

[0016]

[0017] in, The channel capacity of the access point at the i-th location is represented by M; M represents the number of grids divided into sections. The traffic information of the user in the j-th grid is represented by ; j represents the j-th grid that has been divided; K represents the maximum number of access points that are preset.

[0018] In some exemplary embodiments of this disclosure, based on the foregoing scheme, the first access point deployment decision is used to determine the number and deployment location of access points to be deployed in the target area, and the second access point deployment decision is used to adjust the action of each access point in the first access point deployment decision, wherein the action of each access point includes at least one of the following: controlling the on / off state of the access point, adjusting the transmission power, and allocating spectrum resources.

[0019] According to another aspect of this disclosure, an access point deployment device without cellular networks is also provided, comprising: a network information acquisition module for acquiring historical user information and historical traffic information within a target area over a historical time period; a first access point deployment decision generation module for generating a first access point deployment decision within the target area based on the historical user information and the historical traffic information; and a second access point deployment decision generation module for monitoring real-time user information and real-time traffic information within the target area at the current moment, inputting the first access point deployment decision, the real-time user information, and the real-time traffic information into a pre-trained reinforcement learning model, and outputting a second access point deployment decision within the target area.

[0020] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform any of the above-described methods for deploying access points without cellular networks by executing the executable instructions.

[0021] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements any of the above-described methods for deploying access points without cellular networks.

[0022] According to another aspect of this disclosure, a computer program product is also provided, comprising: a computer program or instructions that, when executed by a processor, implement the access point deployment method for any of the above-described cellular networks.

[0023] The embodiments of this disclosure provide a method, apparatus, and related equipment for deploying access points in a non-cellular network. The method first generates a first access point deployment decision based on historical user information and historical traffic information of the target area to initially deploy access points in the target area. Then, using a reinforcement learning method, the method inputs the current real-time user information and real-time traffic information, as well as the first access point deployment decision, into a pre-trained reinforcement learning model and outputs a second access point deployment decision within the target area to dynamically adjust the configuration of access points in the target area.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0026] Figure 1 This diagram illustrates an exemplary application system architecture of an access point deployment method for a non-cellular network according to an embodiment of the present disclosure.

[0027] Figure 2 A schematic diagram of an access point deployment method for a non-cellular network according to an embodiment of this disclosure is shown;

[0028] Figure 3 This diagram illustrates a reinforcement learning model training process according to an embodiment of the present disclosure.

[0029] Figure 4 This diagram illustrates a feedback and adjustment mechanism for a reinforcement learning model in an embodiment of this disclosure.

[0030] Figure 5 A schematic diagram of an access point deployment device for a non-cellular network according to an embodiment of the present disclosure is shown;

[0031] Figure 6 This diagram illustrates an electronic device for an access point deployment method using a non-cellular network, as shown in an embodiment of this disclosure. Detailed Implementation

[0032] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0033] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0034] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0035] In some embodiments, the system architecture in this disclosure includes a terminal device, a network, and network-side devices.

[0036] Optionally, the terminal device in this embodiment may also be referred to as UE (User Equipment). In specific implementation, the terminal device may be a mobile phone, a tablet personal computer, a laptop computer, a personal digital assistant (PDA), a mobile internet device (MID), a wearable device, or an in-vehicle device, etc. It should be noted that the specific type of terminal device is not limited in the embodiments of this invention.

[0037] A network is a medium used to provide a communication link between terminal devices and network-side devices; it can be a wired network or a wireless network.

[0038] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to Local Area Networks (LANs), Metropolitan Area Networks (MANs), Wide Area Networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats, including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Networks (VPNs), and Internet Protocol Security (IPSec) can be used to encrypt all or some links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0039] It should be noted that a fiber optic link is a special type of wired link that uses optical fiber as the transmission medium and optical signals to transmit data; a wireless link refers to a data transmission path established between the sending and receiving ends through radio waves or infrared rays. Wireless links are the basic unit of a wireless network and can be used for short-range (such as Bluetooth) or long-range (such as satellite communication) data exchange.

[0040] Wired networks (including fiber optic links) and wireless networks (based on wireless links) each have their advantages, and they are often used in combination to compensate for each other's shortcomings. For example, within an enterprise, a wired network may be used to ensure the efficient and stable operation of critical business operations, while a wireless network may be deployed to provide employees with flexible mobile work conditions. Whether wired or wireless, some form of link is ultimately needed to carry data flow. In addition, the choice of which type of network to use depends on the specific application requirements. For example, fiber optic links may be preferred in data centers to support high-speed exchange of large amounts of data, while wireless networks are more suitable for deploying in outdoor public areas so that the public can access the Internet anytime and anywhere.

[0041] Network-side equipment can be base stations, relays, or access points (APs). Base stations can be 5G and later versions of base stations (e.g., 5G NR NB), or base stations in other communication systems (e.g., eNB base stations). It should be noted that the specific type of network-side equipment is not limited in the embodiments disclosed herein.

[0042] like Figure 1 As shown, in a wireless communication environment, a UE (e.g., a smartphone) establishes a connection with an AP (e.g., a remote antenna unit in a mobile communication system's radio access network) via wireless signals to access the Internet or other network services. Data packets sent by the UE first arrive at the AP, and are then forwarded by the AP to the CPU and the wider network. In a non-cellular network, signals sent by the UE can be received by multiple APs and jointly processed by the CPU. Conversely, data from the network also first arrives at the CPU and is transmitted to the AP before being passed to the UE. The AP itself also has processing capabilities for managing and controlling its operation. For example, the AP needs to handle concurrent connection requests from multiple UEs and adjust signal transmission power.

[0043] Those skilled in the art will understand that the number of terminals, networks, and network-side devices in the embodiments of this disclosure is merely illustrative, and any number of terminals, networks, and network-side devices can be included according to actual needs. This disclosure does not limit this number.

[0044] Under the above system architecture, this disclosure provides a method for deploying access points without cellular networks, which can be executed by any electronic device with computing power.

[0045] In some embodiments, the access point deployment method for a non-cellular network provided in this disclosure can be executed by a terminal device in the above-described system architecture; in other embodiments, the access point deployment method for a non-cellular network provided in this disclosure can be executed by a server in the above-described system architecture; in still other embodiments, the access point deployment method for a non-cellular network provided in this disclosure can be implemented by the terminal device and the server in the above-described system architecture through interaction.

[0046] To better describe the embodiments of this disclosure, the following technical terms are explained:

[0047] Multiple-input multiple-output (MIMO) systems are a type of wireless communication technology. In MIMO systems, both the transmitting and receiving ends use multiple antennas to transmit multiple data streams simultaneously through spatial multiplexing, thereby improving the capacity and spectral efficiency of the wireless communication system.

[0048] Access Point (AP): A device that provides wireless access for terminals.

[0049] Central Processing Unit (CPU): A device responsible for functions such as signal processing.

[0050] Figure 2 This diagram illustrates a method for deploying access points in a cellular-free network according to an embodiment of the present disclosure. The method includes the following steps:

[0051] S202, Obtain historical user information and historical traffic information within the target area during a historical time period.

[0052] It should be noted that the target area in this embodiment of the disclosure is any area covered by the wireless communication network. The target area can refer to a specific geographical range or location, such as a city, a cell, or any other well-defined space. Generally speaking, the target area is defined by base stations (such as eNodeB in 4G LTE or 5G). The coverage capability of the gNodeB (in NR) and its antennas is determined by the number of base stations. For example, in densely populated urban areas, there are more base stations, resulting in a smaller but more refined coverage area; while in remote areas, there are fewer base stations, and the coverage area of ​​a single base station is larger. The historical time period in this embodiment can be a period of time in the past, such as several hours, days, months, or even years. For example, the historical time period can refer to the past month (February 1, 2025 to March 1, 2025). Historical user information can be detailed information about all users active in the target area during the historical time period, including user location information, user behavior data, user device information, etc. For example, user A was in a shopping mall between 14:00 and 15:00 on February 15, 2025, and used social media applications. Historical traffic information is detailed information about network traffic occurring in the target area within a specified historical time period, including traffic type, traffic distribution, traffic source and destination, etc. For example, during February 2025, the total data traffic in an office building area was 10TB, of which video conferencing applications accounted for 60% of the traffic.

[0053] More specifically, the historical user information in this embodiment may include the number of users covering different time periods (such as hours, days, weeks, months) and the location distribution data of users in different time periods, including latitude and longitude information; the historical traffic information may be the uplink and downlink traffic data of users in different time periods.

[0054] S204, based on historical user information and historical traffic information, generates the first access point deployment decision within the target area.

[0055] It should be noted that the first access point deployment decision in this embodiment is used to determine the number and location of access points to be deployed in the target area. More specifically, this embodiment generates the first access point deployment decision under cost-system capacity constraints to deploy access points, thereby meeting the service needs of the peak number of users in the target area.

[0056] In some embodiments of this disclosure, the cost-system capacity constraint mainly involves two aspects: cost and system capacity. Cost includes all expenses for deploying access points; system capacity refers to the maximum workload or data volume that the system can handle; for wireless communication networks, system capacity can refer to the total capacity of deployed access points, etc. Therefore, the cost-system capacity constraint in this disclosure means that the number of deployed access points does not exceed the budget limit, and the total capacity of deployed access points must meet the sum of downlink and uplink traffic in the target area.

[0057] S206, monitor the real-time user information and real-time traffic information within the target area at the current moment, input the first access point deployment decision, real-time user information, and real-time traffic information into the pre-trained reinforcement learning model, and output the second access point deployment decision within the target area.

[0058] It should be noted that the reinforcement learning model in this embodiment can be a model that is pre-trained by machine learning on various artificial intelligence algorithm models or combinations thereof. The model can learn strategies through interaction with the environment, which determine the best action that the agent should take in a given state. The input data of the model are the first access point deployment decision, real-time user information and real-time traffic information, and the output data is the second access point deployment decision used to adjust the actions of each access point in the first access point deployment decision.

[0059] In some embodiments, such as Figure 3 As shown, in this embodiment of the present disclosure, before using reinforcement learning to obtain the second access point deployment decision, the preprocessing of the model includes:

[0060] S302, Model Selection: In this embodiment of the disclosure, a Deep Q-Network (DQN) model is selected as the base model, taking advantage of its strengths in handling discrete action spaces and high-dimensional state spaces.

[0061] S304, State Definition: In this embodiment of the disclosure, the number of users in the user information can be defined as: the number of users in the current target area; the traffic information can be defined as: the traffic demand of users at the current moment, including uplink traffic and downlink traffic; the user location in the user information can be defined as: the geographical distribution of users; the access point status can be defined as: the on / off status, power, and coverage of the access point; and the network performance in the target area can be defined as: signal strength, signal-to-interference-plus-noise ratio, latency, and throughput.

[0062] S306, Action Definition: In this embodiment of the disclosure, the access point switch can be defined as: controlling the switching state of the access point. The action space is {0, 1}; power adjustment is defined as: adjusting the transmit power of the access point. The action space is [0, Resource allocation is defined as: allocating bandwidth. Time slot Resources, action space is [0, ] and [0, ].

[0063] S308, Reward Function. In this embodiment of the disclosure, rewards or penalties can be given based on a comprehensive consideration of the user's service quality indicators (such as latency and throughput), the energy consumption level of the access point, and the deployment cost of the access point. Specifically, the user's service quality indicators can be obtained through formula (1). :

[0064]

[0065] Where D represents the latency of network performance within the target area; The latency threshold is set in advance; T represents the network throughput within the target area. The throughput threshold is set in advance.

[0066] The energy consumption of the access point can be obtained through formula (2) in this embodiment. level:

[0067]

[0068] Where N is the number of locations where access points can be deployed; i is the location of the access point that can be deployed. Energy consumption for deploying an access point at position i.

[0069] The deployment cost of the access point can be obtained through formula (3) in this embodiment. :

[0070]

[0071] in, The cost of deploying an access point at location i.

[0072] The embodiments of this disclosure can obtain the total reward R, which comprehensively considers the user's service quality index, the access point's energy consumption level, and the access point's deployment cost, through formula (4):

[0073]

[0074] in, The first weighting coefficient is set in advance; The second weighting coefficient is set in advance; The third weighting coefficient is set in advance.

[0075] It should be noted that the embodiments of this disclosure ensure that the user's service quality meets predetermined standards through user service quality indicators, such as latency. Throughput Under the premise of meeting the service quality indicators, the system energy consumption is reduced by adjusting the switching status and power level of the access point. Furthermore, the embodiments of this disclosure also dynamically allocate resources such as bandwidth and time slots according to the user's traffic demand to improve resource utilization.

[0076] S310, Model Training: This includes training data collection, model initialization, and the model training process. Training data collection involves gathering historical and real-time monitoring data, including user numbers, traffic demands, user locations, access point status, and network performance. Model initialization initializes the parameters of the DQN model, setting hyperparameters such as the learning rate and discount factor. The model training process includes setting the current state... Input model; output Q( a) Select action ; Perform actions Observe the new state and rewards Use the new state and rewards Update model parameters; training terminates after the predetermined number of training epochs or model performance metrics are reached.

[0077] It should be noted that, in this embodiment of the disclosure, the input data state of the DQN model refers to all relevant information that can describe the current state of the environment, including the number of users and user locations in user information, traffic demand in traffic information, the status of each access point in the first access point deployment decision, and the network performance at the current moment, etc.; the output data Q( , a), indicates that in state Under the following circumstances, when taking action a, the expected cumulative reward Q that can be obtained is selected in this embodiment of the disclosure as Q( a) Action corresponding to the maximum value Furthermore, in the embodiments of this disclosure... This is the total reward for the nth time.

[0078] In some embodiments, this disclosure assesses the current network status based on real-time user information and real-time traffic information within the monitoring target area at the current moment, and executes corresponding actions based on the second access point deployment decision output by the reinforcement learning model, such as adjusting the on / off status and power level of the access point, and then assesses the network performance after the actions are executed to ensure that the user service quality meets the requirements.

[0079] In some embodiments, such as Figure 4 As shown, the reinforcement learning model in this embodiment of the disclosure will also perform feedback and adjustments, including:

[0080] S402, Performance Feedback: Feedback the network performance after the action is performed to the reinforcement learning model.

[0081] S404, Model Update: Update model parameters based on network performance feedback to optimize the decision output of the reinforcement learning model.

[0082] S406, Continuous Optimization: Through continuous feedback and adjustments, network configuration is constantly optimized to improve system performance.

[0083] The access point deployment method for non-cellular networks provided in the embodiments of this disclosure first acquires historical user information and historical traffic information within a target area over a historical time period; then, based on the historical user information and historical traffic information, a first access point deployment decision is generated for the target area; finally, real-time user information and real-time traffic information within the target area are monitored at the current moment, and the first access point deployment decision, real-time user information, and real-time traffic information are input into a pre-trained reinforcement learning model to output a second access point deployment decision for the target area. Compared to access point deployment methods in related technologies, which are often based on static optimization models and are difficult to adapt to dynamically changing network environments and user needs, the embodiments of this disclosure first generate a first access point deployment decision based on the historical user information and historical traffic information of the target area to perform preliminary access point deployment in the target area. Then, using a reinforcement learning method, the real-time user information and real-time traffic information at the current moment, as well as the first access point deployment decision, are input into a pre-trained reinforcement learning model to output a second access point deployment decision for the target area, thereby dynamically adjusting the configuration of access points in the target area.

[0084] In some embodiments, after outputting the deployment decision of the second access point within the target area, the access point deployment method for non-cellular networks in this disclosure further includes: inputting historical user information and real-time user information within the target area into a pre-trained time series prediction model, and outputting predicted user information values ​​within the target area; and optimizing the deployment decision of the second access point based on the predicted user information values ​​within the target area. Specifically, by predicting user information within the target area for a future period of time to optimize the deployment decision of the second access point, this disclosure can dynamically adjust the number and configuration of access points throughout the entire area, allocate resources more accurately, avoid resource waste or insufficiency, significantly improve resource utilization efficiency, reduce costs, and improve service quality. Furthermore, it can also determine whether the existing number and deployment of access points can meet future user service requirements based on changes in user information and guide the deployment of new access points.

[0085] More specifically, the optimization of the second access point deployment decision in this disclosure includes: prediction of user information, dynamic adjustment of the number and configuration of access points, and deployment of new access points. User information prediction involves using a time series prediction model, such as a Long Short-Term Memory network or an autoregressive moving average model, inputting historical and real-time user information as input values ​​into a pre-trained time series prediction model, and outputting predicted user information values ​​for a future period. Dynamic adjustment of the number and configuration of access points is based on the predicted user information values. When the number of users in the user information increases, the number of activated access points is increased; when the number of users in the user information decreases, some access points are shut down. The predicted user information values ​​can also be input into a pre-trained reinforcement learning model to optimize the access point configuration. Deployment of new access points involves determining whether to deploy new access points based on changes in the number of users in the user information and the performance of existing deployed access points. The CPU can guide the deployment location and number of new access points to ensure that new access points can effectively improve system performance.

[0086] In some embodiments, this disclosure generates a first access point deployment decision within a target area based on historical user information and historical traffic information, including: determining densely populated user areas within the target area based on historical user information and historical traffic information; using the total capacity of deployed access points satisfying the historical traffic information of densely populated user areas and the number of deployed access points not exceeding a pre-set budget limit as constraints; setting an optimization objective function based on the cost of deploying access points within the target area; and generating a first access point deployment decision within the target area by minimizing the value of the optimization objective function under the constraints. Specifically, the constraints in this disclosure are cost-system capacity constraints. The first access point deployment decision formulated under cost-system capacity constraints aims to balance system performance with the cost required to achieve that performance, ensuring that system efficiency and service quality are maximized within budget limits. More specifically, the first access point deployment decision generated by this disclosure through cost-system capacity constraints not only helps optimize resource allocation and reduce costs but also significantly improves system performance and service levels.

[0087] In some embodiments of this disclosure, the objective function for optimization is obtained through formula (5):

[0088]

[0089] Where N represents the number of locations where access points can be deployed; This is represented as the cost of deploying an access point at the i-th location; The denot represents whether an access point is deployed at the i-th location; i represents the location where an access point can be deployed.

[0090] In some embodiments of this disclosure, the constraints are obtained through formulas (6) to (7):

[0091]

[0092]

[0093] in, The channel capacity of the access point at the i-th location is represented by M; M represents the number of grids divided into sections. The traffic information of the user in the j-th grid is represented by j, where j represents the j-th grid and K represents the maximum number of access points set in advance.

[0094] In some embodiments, this disclosure describes a method for determining densely populated user areas within a target region based on historical user information and historical traffic information. This includes: dividing the target region into multiple grids based on pre-set partitioning rules; calculating the grid density product of each grid within a preset time period based on historical user information and historical traffic information; and filtering out grids with a density product greater than a pre-set threshold based on the grid density product of each grid, thereby determining densely populated user areas within the target region. Specifically, this disclosure divides the target region into different grids per unit area, sets a time period length t, and calculates the grid user density a, grid downlink traffic density b, and grid uplink traffic density c for each time period within time T based on collected user information and traffic information. The grid user density is equal to the ratio of the number of users in the grid to the grid area within time t; the grid downlink traffic density is equal to the ratio of the downlink traffic of all users in the grid to the grid area within time t; and the grid uplink traffic density is equal to the ratio of the uplink traffic of all users in the grid to the grid area within time t. The grid density product s (s=abc) within time t is then calculated.

[0095] It should be noted that the mesh density product threshold is preset in the embodiments of this disclosure. If a grid is randomly selected, and the grid density product of that grid exceeds a certain threshold for a given time period, i.e., s≥ Then, taking this grid as the central grid, if the grid density product of adjacent grids exceeds a certain value for a certain period of time... Then, the grid and the central grid are merged into a new central grid, until the grid density product of the adjacent grids of the central grid is less than a certain value in any time period. The above method is used to divide the grid into areas where the density product is higher than the threshold. The area is called the user-dense area. The planned coverage area may contain multiple user-dense areas. In the remaining grids, a grid is randomly selected, and with that grid as the center, the grids within a radius L that do not belong to the dense area are divided into a region. This process is repeated for all grids until all grids have a region to belong to.

[0096] In some embodiments, this disclosure uses real-time monitoring and reinforcement learning techniques to dynamically adjust the configuration of access points to adapt to changes in user needs and network environment; it utilizes reinforcement learning models to automatically learn the optimal configuration strategy, reducing manual intervention; it obtains predicted user information values ​​by predicting user information, and can pre-adjust the configuration of access points based on these predicted values, improving system response speed and flexibility; furthermore, this disclosure optimizes the deployment and configuration of access points while meeting the user information and service quality requirements of the target area, reducing deployment costs and reducing system energy consumption through dynamic configuration.

[0097] Based on the same inventive concept, this disclosure also provides an access point deployment device without a cellular network, as shown in the following embodiment. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiment, the implementation of this device embodiment can refer to the implementation of the above-described method embodiment, and repeated details will not be described again.

[0098] Figure 5 This diagram illustrates a cellular-free access point deployment apparatus according to an embodiment of the present disclosure. The apparatus includes:

[0099] The network information acquisition module 501 is used to acquire historical user information and historical traffic information within a target area during a historical time period.

[0100] The first access point deployment decision generation module 502 is used to generate a first access point deployment decision within the target area based on historical user information and historical traffic information.

[0101] The second access point deployment decision generation module 503 is used to monitor the real-time user information and real-time traffic information in the target area at the current moment, input the first access point deployment decision, real-time user information and real-time traffic information into the pre-trained reinforcement learning model, and output the second access point deployment decision in the target area.

[0102] This disclosure provides an access point deployment device for a non-cellular network. It acquires historical user information and historical traffic information within a target area over a historical time period using a network information acquisition module. A first access point deployment decision generation module generates a first access point deployment decision for the target area based on the historical user information and historical traffic information. A second access point deployment decision generation module monitors real-time user information and real-time traffic information within the target area at the current moment, inputs the first access point deployment decision, real-time user information, and real-time traffic information into a pre-trained reinforcement learning model, and outputs a second access point deployment decision for the target area. Compared to related technologies where access point deployment methods are often based on static optimization models and are difficult to adapt to dynamically changing network environments and user needs, this disclosure first generates a first access point deployment decision based on the historical user information and historical traffic information of the target area to perform initial access point deployment in the target area. Then, using a reinforcement learning method, it inputs the real-time user information and real-time traffic information, along with the first access point deployment decision, into a pre-trained reinforcement learning model and outputs a second access point deployment decision for the target area to dynamically adjust the access point configuration in the target area.

[0103] In some embodiments, the access point deployment apparatus for non-cellular networks in this disclosure further includes: a user information prediction value output module, used to output a second access point deployment decision in the target area, input historical user information and real-time user information in the target area into a pre-trained time series prediction model, and output a user information prediction value in the target area; and a second access point deployment decision optimization module, used to optimize the second access point deployment decision based on the user information prediction value in the target area.

[0104] In some embodiments of this disclosure, the first access point deployment decision generation module is further configured to determine a densely populated user area within the target area based on historical user information and historical traffic information; constrained by the total capacity of the deployed access points meeting the historical traffic information of the densely populated user area and the number of deployed access points not exceeding a pre-set budget limit; set an optimization objective function based on the cost of deploying access points within the target area; and under the constraints, generate a first access point deployment decision within the target area with the minimum value of the optimization objective function as the optimization objective.

[0105] In some embodiments of this disclosure, the first access point deployment decision generation module is further configured to divide the target area into multiple grids based on a pre-set division rule; calculate the grid density product of each grid within a preset time period based on historical user information and historical traffic information; and filter out grids with a density product greater than the pre-set grid density product threshold based on the grid density product of each grid and the pre-set grid density product threshold to determine the dense user area within the target area.

[0106] In some embodiments, the objective function of this disclosure is obtained by formula (5).

[0107] In some embodiments, the constraints are obtained by formulas (6) to (7).

[0108] In some embodiments of this disclosure, a first access point deployment decision is used to determine the number and location of access points to be deployed within a target area, and a second access point deployment decision is used to adjust the action of each access point in the first access point deployment decision, wherein the action of each access point includes at least one of the following: controlling the on / off state of the access point, adjusting the transmission power, and allocating spectrum resources.

[0109] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0110] Based on the same inventive concept, this disclosure also provides an electronic device, which includes: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the access point deployment method for any of the above-described methods via executing the executable instructions. Since the principle by which this electronic device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this electronic device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be described again.

[0111] The following reference Figure 6 To describe an electronic device 600 according to such an embodiment of the present disclosure. Figure 6 The electronic device 600 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0112] like Figure 6 As shown, the electronic device 600 is manifested in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 601, at least one storage unit 602, and a bus 603 connecting different system components (including storage unit 602 and processing unit 601).

[0113] The storage unit stores program code, which can be executed by the processing unit 601, causing the processing unit 601 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0114] In some embodiments, when an electronic device is used to control, for example, the cellular network-free access point deployment method described in this disclosure, the processing unit 601 may execute the following steps of the method embodiments described above:

[0115] Acquire historical user information and historical traffic information within the target area over a historical time period; generate a first access point deployment decision within the target area based on the historical user information and historical traffic information; monitor real-time user information and real-time traffic information within the target area at the current moment, input the first access point deployment decision, real-time user information, and real-time traffic information into a pre-trained reinforcement learning model, and output a second access point deployment decision within the target area.

[0116] Storage unit 602 may include readable media in the form of volatile storage units, such as random access memory (RAM) 6021 and / or cache memory 6022, and may further include read-only memory (ROM) 6023.

[0117] Storage unit 602 may also include a program / utility 6024 having a set (at least one) program module 6025, such program module 6025 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0118] Bus 603 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0119] Electronic device 600 can also communicate with one or more external devices 604 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 605. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 606. As shown, network adapter 606 communicates with other modules of electronic device 600 via bus 603. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0120] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0121] Based on the same inventive concept, this disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the access point deployment method for any of the above-described methods. Since the principle by which this computer-readable storage medium embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this computer-readable storage medium embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0122] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0123] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0124] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0125] In practice, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0126] Based on the same inventive concept, this disclosure also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the access point deployment method for a non-cellular network according to any one of the above method embodiments. Since the principle by which this computer program product embodiment solves the problem is similar to that of the above method embodiments, the implementation of this computer program product embodiment can refer to the implementation of the above method embodiments, and repeated details will not be elaborated further.

[0127] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0128] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0129] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0130] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A method for deploying access points in a non-cellular network, characterized in that, include: Obtain historical user information and historical traffic information within the target area during a historical time period; Based on the historical user information and the historical traffic information, a deployment decision for the first access point within the target area is generated; Monitor real-time user information and real-time traffic information within the target area at the current moment, input the first access point deployment decision, the real-time user information, and the real-time traffic information into a pre-trained reinforcement learning model, and output the second access point deployment decision within the target area; After outputting the deployment decision of the second access point within the target area, the method further includes: inputting historical user information and real-time user information within the target area into a pre-trained time series prediction model, and outputting predicted user information values ​​within the target area; optimizing the deployment decision of the second access point based on the predicted user information values ​​within the target area, wherein the optimization of the deployment decision of the second access point includes: predicting user information, dynamically adjusting the number and configuration of access points, and deploying new access points.

2. The method for deploying access points in a non-cellular network according to claim 1, characterized in that, Based on the historical user information and the historical traffic information, a deployment decision for the first access point within the target area is generated, including: Based on the historical user information and the historical traffic information, determine the densely populated user areas within the target area; The constraints are that the total capacity of the deployed access points meets the historical traffic information of the densely populated user area, and the number of deployed access points does not exceed the pre-set budget limit. Based on the cost of deploying access points within the target area, an optimization objective function is set. Under the constraints, the first access point deployment decision within the target area is generated with the minimum value of the optimization objective function as the optimization objective.

3. The method for deploying access points in a non-cellular network according to claim 2, characterized in that, Based on the historical user information and the historical traffic information, the densely populated user areas within the target area are determined, including: The target area is divided into multiple grids based on pre-set division rules; Calculate the grid density product of each grid within a preset time period based on the historical user information and the historical traffic information; Based on the grid density product of each grid and a pre-set grid density product threshold, grids with a density product greater than the grid density product threshold are filtered out to determine the dense user areas within the target area.

4. The method for deploying access points in a non-cellular network according to claim 3, characterized in that, The optimization objective function is obtained through the following formula: ； Where N represents the number of locations where access points can be deployed; This is represented as the cost of deploying an access point at the i-th location; The denot represents whether an access point is deployed at the i-th location; i represents the location where an access point can be deployed.

5. The method for deploying access points in a non-cellular network according to claim 4, characterized in that, The constraint conditions are obtained using the following formula: ； ； in, The channel capacity of the access point at the i-th location is represented by M; M represents the number of grids divided into sections. The traffic information of the user in the j-th grid is represented by ; j represents the j-th grid that has been divided; K represents the maximum number of access points that are preset.

6. The method for deploying access points in a non-cellular network according to claim 1, characterized in that, The first access point deployment decision is used to determine the number and location of access points to be deployed within the target area. The second access point deployment decision is used to adjust the action of each access point in the first access point deployment decision. The action of each access point includes at least one of the following: controlling the on / off state of the access point, adjusting the transmission power, and allocating spectrum resources.

7. A cellular network-free access point deployment device, characterized in that, include: The network information acquisition module is used to acquire historical user information and historical traffic information within a target area during a historical time period. The first access point deployment decision generation module is used to generate a first access point deployment decision within the target area based on the historical user information and the historical traffic information. The second access point deployment decision generation module is used to monitor the real-time user information and real-time traffic information in the target area at the current time, input the first access point deployment decision, the real-time user information and the real-time traffic information into the pre-trained reinforcement learning model, and output the second access point deployment decision in the target area. The device further includes: a user information prediction value output module, used to output the second access point deployment decision within the target area, input historical user information and real-time user information within the target area into a pre-trained time series prediction model, and output the user information prediction value within the target area; and a second access point deployment decision optimization module, used to optimize the second access point deployment decision based on the user information prediction value within the target area, wherein the optimization of the second access point deployment decision includes: prediction of user information, dynamic adjustment of the number and configuration of access points, and deployment of new access points.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the access point deployment method for a non-cellular network according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the access point deployment method for a non-cellular network as described in any one of claims 1 to 6.

10. A computer program product, comprising: A computer program or instruction, characterized in that, when executed by a processor, the computer program or instruction implements the access point deployment method for a non-cellular network as described in any one of claims 1 to 6.

Images