Method, electronic device, computer program product for cell adjustment

Abstract

This application discloses a cell adjustment method, electronic device, computer program product, and computer-readable storage medium. The method, applied to a server, includes: receiving radio data from multiple terminals, wherein the number of cells accessed by the multiple terminals is at least two; determining a load score of the cell accessed by the multiple terminals based on the radio data; determining a cell adjustment strategy for at least one terminal based on the load scores of the cell accessed by the multiple terminals; and sending a cell adjustment instruction including the cell adjustment strategy to at least one terminal accessing the cell, so that the terminal receiving the cell adjustment instruction executes the cell adjustment strategy. According to embodiments of this application, the load score of the current cell is determined based on the radio data sent by the terminal, and an adjustment strategy is implemented for the terminals accessing the cell based on the load score, thereby achieving the purpose of balancing cell load.

Description

Technical Field

[0001] This application relates to the field of wireless communication, and more specifically, to a method for cell adjustment, an electronic device, a computer program product, and a computer-readable storage medium. Background Technology

[0002] In wireless communication, signal strength is often used to determine when a terminal reselects and switches cells. In multi-cell coverage scenarios, a single terminal can only measure the signals of neighboring cells and decide whether to switch cells based on the signal strength of its own cell and those of neighboring cells. Often, after a terminal switches to a cell with a better signal, the uplink and downlink data transmission quality actually deteriorates. At the same time, more and more terminals switch to cells with better signals based on signal strength, causing a further decline in cell service capabilities. Summary of the Invention

[0003] This application aims to provide a method for cell adjustment, an electronic device, a computer program product, and a computer-readable storage medium.

[0004] According to one aspect of this application, a cell adjustment method is proposed, the method being applied to a server, the method comprising: receiving radio data transmitted from a plurality of terminals; wherein the plurality of terminals access at least two cells; determining a load score of the accessed cells based on the radio data transmitted by the plurality of terminals; determining a cell adjustment strategy for at least one of the terminals based on the load scores of the accessed cells; and sending a cell adjustment instruction including the cell adjustment strategy to at least one terminal accessing the cell based on the cell adjustment strategy, such that a terminal receiving the cell adjustment instruction executes the cell adjustment strategy.

[0005] According to another aspect of this application, a method for selecting a cell is proposed, the method being applied to a terminal, the method comprising: sending radio data to a server; receiving a cell adjustment instruction including a cell adjustment strategy sent from the server; and determining an adjustment method according to the cell adjustment instruction.

[0006] According to another aspect of this application, an electronic device is provided, comprising: a processor; and a memory storing a computer program that, when executed by the processor, causes the processor to perform the method as described in any of the preceding embodiments.

[0007] According to another aspect of this application, a computer program product is provided, the computer program product including a computer-readable storage medium storing a computer program operable to cause a computer to perform the method as described in any of the preceding embodiments.

[0008] According to another aspect of this application, a computer-readable storage medium is provided that stores computer-readable instructions thereon, which, when executed by a processor, cause the processor to perform the method as described in any of the preceding embodiments.

[0009] According to an embodiment of this application, the load score of the current cell is determined based on the wireless data sent by the terminal, and then a cell adjustment strategy is implemented for the terminals accessing the cell based on the load score, thereby achieving the purpose of balancing the cell load and improving the cell's data service capability for the terminal.

[0010] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. The above and other objectives, features, and advantages of the present invention will become more apparent from the detailed description of exemplary embodiments with reference to the accompanying drawings.

[0012] Figure 1 A schematic diagram of a cell adjustment method according to an example embodiment of this application is shown.

[0013] Figure 2 A schematic diagram of another cell adjustment method according to an example embodiment of this application is shown.

[0014] Figure 3 A schematic diagram of a method for determining a cell load score according to an example embodiment of this application is shown.

[0015] Figure 4 A schematic diagram of another method for determining cell load score according to an example embodiment of this application is shown.

[0016] Figure 5 A schematic diagram of a cell adjustment method according to an example embodiment of this application is shown.

[0017] Figure 6 A schematic diagram of a cell selection device structure according to an example embodiment of this application is shown.

[0018] Figure 7 A schematic diagram of another cell selection device structure according to an example embodiment of this application is shown.

[0019] Figure 8 A schematic diagram of the device structure of a server according to an example embodiment of this application is shown.

[0020] Figure 9 A schematic diagram of the device structure of a terminal according to an example embodiment of this application is shown.

[0021] Figure 10 A schematic diagram of the structure of an electronic device according to an exemplary embodiment of this application is shown. Detailed Implementation

[0022] 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 embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same drawings in the figures show the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0023] 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 full 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 these specific details, or other methods, components, materials, apparatus, or operations may be employed. In these cases, well-known structures, methods, apparatuses, implementations, materials, or operations will not be shown or described in detail.

[0024] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily need 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.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0026] Before describing the embodiments of this application, the terms appearing in this application will first be explained.

[0027] Uplink band: The range of frequency bands used.

[0028] Uplink Physical Resource Block (PRB) Allocation: The number and location of PRBs allocated to users.

[0029] Modulation and coding scheme (MCS): The modulation method and coding rate used in the uplink.

[0030] Uplink Grant: The cell grants uplink resource access permissions to the terminal.

[0031] Uplink latency: The time delay for data to be sent from the terminal to the cell.

[0032] Uplink Request (Scheduling Request): A terminal's request for the cell to allocate uplink resources.

[0033] Downlink frequency band: The range of frequency bands used.

[0034] Downlink Physical Resource Block (PRB) Allocation: The number and location of PRBs allocated to users.

[0035] Modulation and coding scheme (MCS): The modulation method and coding rate used in the downlink.

[0036] Downlink latency: The time delay for data to be sent from the cell to the terminal.

[0037] Downlink Multiple-Input Multiple-Output (MIMO) Configuration: Antenna configuration and mode for the downlink.

[0038] Uplink Channel State Information (CSI): Feedback on uplink channel quality.

[0039] Uplink Power Control (TPC): A command that adjusts the terminal's transmit power.

[0040] RSRP (Reference Signal Received Power): The power of the reference signal received by the terminal, representing the downlink signal strength.

[0041] RSRQ (Reference Signal Received Quality): The quality of the reference signal, taking into account interference and noise.

[0042] SNR (Signal to Noise Ratio): The ratio of signal to noise, reflecting channel quality.

[0043] Downlink Channel State Information (CQI): Feedback on downlink channel quality.

[0044] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Figure 1 A schematic diagram of a cell adjustment method according to an example embodiment of this application is shown, such as... Figure 1 The method shown includes steps S101, S103, S105, and S107. The following will use... Figure 1 Taking an example, a method for cell adjustment according to an example embodiment of this application will be described in detail.

[0045] In the embodiments of this application, Figure 1 The method shown is applied to a server. In this embodiment, the adjustment strategy for multiple cells included in the region where the terminal is located is determined, so as to implement the adjustment strategy for terminals accessing cells in the region, thereby achieving the purpose of cell load balancing. It should be noted that this application does not limit the form of the server; the server in this application includes any computer or cloud platform that can be used to compute this embodiment.

[0046] like Figure 1 As shown, in step S101, wireless data is received from multiple terminals.

[0047] In this application, the terms "cell" and "base station" have the same meaning and are not distinguished. The terminal obtains the radio resources allocated by the corresponding access cell by accessing the cell.

[0048] In this embodiment, the number of cells accessed by multiple terminals is at least two.

[0049] In step S103, the load score of the cell accessed by the multiple terminals is determined based on the wireless data transmitted by the multiple terminals.

[0050] In embodiments of this application, wireless data may include wireless physical resource allocation data and channel quality. In step S103, the load factor and anomaly score of multiple terminals accessing the cell are determined based on the channel quality and wireless physical resource allocation data; and the load score is determined based on the load factor and anomaly score.

[0051] In other embodiments, the wireless data may include congestion data. In step S103, the cell congestion rate of the multiple terminals accessing the cell is determined based on the congestion data, and the load score of the multiple terminals accessing the cell is determined based on the cell congestion rate.

[0052] In step S105, based on the load scores of multiple terminals accessing the cell, a cell adjustment strategy for at least one terminal is determined.

[0053] In an embodiment of this application, in step S105, an average load score for the multiple terminals accessing the cells is determined based on their load scores; and an adjustment strategy for at least one cell is determined based on the load scores of the multiple terminals accessing the cells and the average load score. For example, when the load score of the current cell is greater than the calculated average load score, an adjustment strategy is implemented for the terminals in the current cell. Since multiple terminals access at least two cells, the cell adjustment strategy for the at least one terminal can be determined by comparing the average load score of the multiple cells with the load score of the cell accessed by the at least one terminal.

[0054] In some embodiments, the corresponding receiving cell can be a neighboring cell of the current cell, and the load score of the neighboring cell is less than the calculated average load score.

[0055] In step S107, according to the cell adjustment policy, a cell adjustment instruction including the adjustment policy is sent to at least one terminal accessing the cell, so that the terminal receiving the cell adjustment instruction executes the cell adjustment policy.

[0056] According to an embodiment of this application, after sending a cell adjustment instruction to the terminal, the terminal needs to determine the adjustment method according to the cell adjustment instruction and execute the adjustment method so that the terminal meets the adjustment conditions of the adjustment instruction.

[0057] exist Figure 1 In the illustrated embodiment, based on the cell load score, a cell adjustment strategy is implemented for terminals accessing multiple cells within the terminal's area, thereby achieving the goal of balancing cell load and improving the cell's data service capabilities for the terminal.

[0058] Figure 2 This illustration shows a schematic diagram of another cell adjustment method according to an example embodiment of this application, and... Figure 1 compared to, Figure 2 The method shown also includes steps S109, S111, S113, S115, and S117. To avoid redundancy, this embodiment only describes steps related to... Figure 1 The differences will not be elaborated upon here, and the similarities will not be repeated.

[0059] like Figure 2 As shown, in step S109, updated wireless data is received from multiple terminals.

[0060] In this embodiment, equalization control is implemented for multiple cells in the area where the terminal is located using updated wireless data.

[0061] In step S111, the update load score of the cell accessed by the multiple terminals is determined based on the updated radio data sent by the multiple terminals.

[0062] According to an embodiment of this application, after a terminal performs a migration-in or migration-out operation, the load scores of multiple terminal access cells are updated and determined according to the determination method described in step S103, thereby obtaining updated load scores of multiple terminal access cells.

[0063] In step S113, the total deviation of the load scores of the multiple terminals accessing the cell is determined based on the updated load scores of the multiple terminals accessing the cell.

[0064] In a specific embodiment, the total load score deviation of multiple terminals accessing the cell is determined using formula (1).

[0065] Reward = -∑ i (L i -L avg ) 2 (1)

[0066] Where Reward is the calculated total deviation of the load score, L i For the update load score of the i-th cell, L avg The average load score of the cells in the area where the terminal is located, where i is the i-th cell.

[0067] In step S115, if the total deviation of the load score is greater than the preset deviation threshold, the update cell adjustment strategy of at least one cell is determined based on the update load scores of the multiple terminal access cells.

[0068] It should be noted that the deviation threshold can be set as needed and is not specifically limited here. In a specific embodiment, the deviation threshold can be 0 or any value. If it is 0, it means that the load of each cell in the area is close to the average. If it does not reach the average, the server will continuously output adjustment strategies to the terminal to ensure that the cell load tends to the average.

[0069] In step S117, according to the update cell adjustment policy, an update cell adjustment instruction including the update cell adjustment policy is sent to at least one terminal accessing the cell, so that the terminal receiving the update cell adjustment instruction executes the update cell adjustment policy.

[0070] It should be noted that after each time the terminal executes the update adjustment strategy according to the received update adjustment instruction, steps S109 and S111 can be executed again. Based on the total deviation of the load scores of multiple terminal access cells, it is determined whether the load of the cells in the area where the terminal is located needs to be further adjusted so that the cells in the area can achieve load balancing, thereby improving the data service capability of the cells for the terminal.

[0071] In this embodiment, by calculating the total deviation of the load scores of multiple terminals accessing the cell, it is determined whether the load of the cell in the area where the terminal is located needs to be further adjusted. By dynamically adjusting the number of terminals accessing the cell, the terminal can always select the cell with the best service quality, thereby achieving the goal of balancing the cell load.

[0072] Figure 3 A schematic diagram of a method for determining cell load score according to an example embodiment of this application is shown, such as... Figure 3 The method shown includes steps S301, S303 and S305.

[0073] like Figure 3As shown, in step S301, the load factor of multiple terminals accessing the cell is determined based on the wireless physical resource allocation data.

[0074] In the embodiments of this application, the wireless physical resource allocation data includes actual wireless physical resource allocation data and expected wireless physical resource allocation data. The load factor for multiple terminals accessing the cell is determined based on the ratio of the actual wireless physical resource allocation data to the expected wireless physical resource allocation data, as shown in formula (2). When the load factor is less than 1, especially when the load factor is significantly less than 1, it indicates that the cell may have insufficient wireless physical resource allocation data and is at risk of overload.

[0075]

[0076] In some embodiments, the actual wireless physical resource allocation data is determined based on terminal channel quality data, physical resource data allocated by the cell to the terminal, and / or the terminal's uplink data requirements.

[0077] In specific embodiments, terminal channel quality data includes, but is not limited to, uplink channel state information (CSI), uplink power control (TPC), downlink signal strength (RSRP), downlink signal quality (RSRQ), signal-to-noise ratio (SNR), and / or downlink channel state information (CQI); physical resource data allocated by the cell to the terminal includes, but is not limited to, uplink bandwidth, uplink physical resource block (PRB) allocation, modulation and coding scheme (MCS), uplink grant, uplink delay, downlink bandwidth, downlink physical resource block (PRB) allocation, modulation and coding scheme (MCS), downlink delay, and / or downlink multiple-input multiple-output (MIMO) configuration; terminal uplink data requirements include, but are not limited to, uplink resource requests (SR), used to assist in analyzing the cell's load status.

[0078] According to some embodiments, the actual wireless physical resource allocation data is calculated using formula (3) to calculate each wireless physical resource parameter as a quantitative value of the wireless physical resources allocated to the terminal by a comprehensive evaluation cell. Since the degree of influence of each parameter on the actual wireless physical resource allocation data is different, a weight is assigned to each parameter in the calculation formula shown in formula (3). These weight coefficients are used to calculate a comprehensive "wireless physical resource allocation data" to reflect the cell's load status through weighted summation.

[0079] It should be noted that the weight values ​​shown in formula (3) can be determined based on experimental data or network planning experience, and no specific limitation is made here.

[0080] Wireless physical resource allocation data 实际=w1*UplinkBandwidth+w2*UplinkPRBAllocation+w3*UplinkMCS+w4*UplinkGrant+w5*UplinkDelay+w6*DownlinkBandwidth+w7*DownlinkPRBAllocation+w8*DownlinkMCS+w9*DownlinkDelay+w10*DownlinkMIMOConfiguration (3)

[0082] Where w1, w2, ..., w10 are the weight coefficients corresponding to each wireless physical resource, for example, w1 is 0.1, w2 is 0.2, w3 is 0.05, w4 is 0.1, w5 is 0.05, w6 is 0.1, w7 is 0.2, w8 is 0.05, w9 is 0.05, and w10 is 0.1, used to represent the relative importance of each parameter to the final actual wireless physical resource allocation data. In specific embodiments, the weight value can be determined according to the importance of each parameter, and no specific limitation is made here; UplinkBandwidth is the uplink bandwidth, Uplink... kPRBAllocation is the uplink physical resource block allocation, UplinkMCS is the uplink modulation and coding scheme, UplinkGrant is the uplink grant, UplinkDelay is the uplink delay, DownlinkBandwidth is the downlink bandwidth, DownlinkPRBAllocation is the downlink physical resource block allocation, DownlinkMCS is the downlink modulation and coding scheme, DownlinkDelay is the downlink delay, and DownlinkMIMOConfiguration is the downlink multiple input / output configuration.

[0083] In the embodiments of this application, it is expected that the wireless physical resource allocation data is determined based on a preset relationship between the terminal channel quality and the amount of wireless physical resources allocated to the cell under normal load conditions and good channel quality. The relationship between the terminal channel quality and the amount of wireless physical resources allocated to the cell under normal load conditions can be trained based on historical data of the relationship between the terminal channel quality and the amount of wireless physical resources allocated to the cell under normal load conditions.

[0084] In a specific embodiment, the desired wireless physical resource allocation data is determined according to formula (4), and the obtained desired wireless physical resource allocation data is a set of multiple factors.

[0085] Wireless physical resource allocation data 期望 =∫(RSRP,RSRQ.SNR,CQI,CSI)(4)

[0086] Where RSRP is downlink signal strength, RSRQ is downlink signal quality, SNR is signal-to-noise ratio, CQI is downlink channel state information, and CSI is uplink channel state information, the ∫ function can be fitted using historical data to represent the standard relationship between terminal channel quality and the amount of radio physical resources allocated to the cell under normal load conditions. Empirical formulas or machine learning-based fitting formulas can be used to map channel quality to expected radio physical resource allocation data.

[0087] In step S303, anomaly scores for multiple terminals accessing the cell are determined based on channel quality and wireless physical resource allocation data.

[0088] The wireless physical resource allocation anomaly score is used to evaluate the degree of deviation between the actual wireless physical resource allocation and the wireless physical resource allocation according to a preset benchmark, under preset channel quality conditions. The wireless physical resources allocated according to the preset benchmark can be the amount of wireless physical resources that can be allocated to a cell in good operating condition under various channel quality intensities.

[0089] In an embodiment of this application, in step S303, a preset neural network is used to calculate the wireless physical resource allocation anomaly score of the cells in the region based on channel quality and wireless physical resource allocation data. The anomaly score is used to characterize the degree of deviation between the actual wireless physical resource allocation and the wireless physical resources allocated according to the preset benchmark under the preset channel quality.

[0090] In a specific embodiment, the preset neural network is a multilayer perceptron (MLP) or convolutional neural network (CNN) structure, used to capture the nonlinear relationship between channel quality and resource allocation when a cell is overloaded. The input features of the neural network model include channel quality, uplink, and downlink radio physical resource allocation data. When training the neural network, a dataset containing both normal and overloaded cell states is used to train the model, enabling it to identify abnormal resource allocation under cell load conditions. A cross-entropy loss function and the Adam optimizer are employed to ensure the neural network model can accurately identify overload conditions. During prediction, if the neural network model finds that the channel quality is good but the radio physical resource allocation is below a preset abnormal radio physical resource allocation score threshold, it outputs an abnormal radio physical resource allocation score for the cells in the area. This score is used to assess the current cell load status.

[0091] In step S305, the load score is determined based on the load factor and the anomaly score.

[0092] In specific embodiments, the cell load needs to be assessed holistically by combining the aforementioned load factor and radio physical resource allocation anomaly score. For example, if the calculated radio physical resource allocation anomaly score is higher than a preset radio physical resource allocation anomaly score threshold and the load factor is lower than a preset load factor threshold, then an overload problem is confirmed in the cell. Alternatively, if only the anomaly score is higher than the preset radio physical resource allocation anomaly score threshold but the load factor is higher than the preset load factor threshold, then it is considered a problem with an individual terminal, rather than a global overload.

[0093] It should be noted that the threshold for abnormal allocation of wireless physical resources and the threshold for load factor can be determined according to the operational needs of cell load, and no specific limitation is made here.

[0094] According to an embodiment of this application, the load score is calculated using formula (5).

[0095]

[0096] Where w1 and w2 are preset weight values ​​used to balance the impact of load factor and anomaly score, N is the number of terminals currently connected to the cell, and LoadFactor... i The load factor is calculated for the i-th terminal corresponding to the cell.

[0097] In specific embodiments, the values ​​of w1 and w2 can be determined based on the importance of the load factor and the anomaly score in the actual application, and are not specifically limited here. For example, when the importance of the load factor is greater than that of the anomaly score, the weight value w1 corresponding to the load factor can be set to 0.6, and the weight value w2 corresponding to the anomaly score can be set to 0.4.

[0098] Figure 4 A schematic diagram of another method for determining cell load score according to an example embodiment of this application is shown, such as... Figure 4 The method shown includes steps S401 and S403.

[0099] like Figure 4 As shown, in step S401, the cell blocking rate of multiple terminals accessing the cell is determined based on the blocking data.

[0100] According to an embodiment of this application, the cell blocking rate is calculated based on the number of terminals experiencing data blocking in each cell and the total number of terminals currently connected to the cell.

[0101] For example, based on the number of terminals currently experiencing data congestion, report the number N of terminals experiencing data congestion. 阻塞 Based on the current number of terminals in the cell, obtain the total number N of terminals accessing the current cell. 总And use formula (6) to calculate the terminal blocking rate S of the cells in the area.

[0102] S = N 阻塞 / N 总 (6)

[0103] In step S403, the load score of the multiple terminals accessing the cell is determined based on the cell blocking rate.

[0104] According to an embodiment of this application, a load score is calculated using a preset relationship between blocking rate and load score; wherein the relationship between the blocking rate and the load score is obtained by training based on historical blocking rates and historical load scores.

[0105] In a specific embodiment, the cell service capability A represents the load score.

[0106] In some embodiments, a nonlinear regression model (such as decision tree regression or random forest regression) is used to fit and establish the relationship between cell service capability A and terminal blocking rate S, as shown in formula (7).

[0107] S=∫(A) (7)

[0108] Here, ∫(A) is a non-linear function, which is trained based on historical blocking rate and historical load score.

[0109] It should be noted that the data blocking defined in this application refers to a terminal sending a request to the network via various protocols such as HTTP, TCP, UDP, RTP, QUIC, etc. If the network does not respond or a certain percentage of requests are not responded to, it is considered blocking. The blocking rate is the ratio of the number of blocked terminals to all terminal data at a certain time point in a certain cell.

[0110] according to Figure 3 or Figure 4 The aforementioned embodiment can establish a load score data matrix of multiple cells within the area where the terminal is located. Simultaneously, based on the information of neighboring cells contained in the system messages of each cell, a load score data matrix of all neighboring cells of each cell is established, as shown in formula (8) as the cell load score data matrix of the M area where the terminal is located. Here, each row represents a cell, and each column represents a time period (or status update cycle).

[0111]

[0112] Among them, L i,j This represents the load score of cell i at time j, where N is the number of cells in the region, and T is the time for calculating the load score of the cell.

[0113] Since there is no clear and unified functional relationship between the number of terminals migrating out of each cell and the number of terminals migrating in each cell, the cell load is closely related to the resource usage of each terminal, and indirectly related to a specific user group and a specific functional division in a certain area. For example, if a group in a certain area uses a large amount of wireless data, the more such terminals migrate in, the heavier the cell load will be. In the embodiments of this application, in step S109, the deep reinforcement learning model is used to issue adjustment strategies to the terminal in real time according to the load score of the cell in the area where the terminal is located, determined by formula (8). And a reward rule is set, and the reward is verified according to the real-time feedback of the cell load score, as shown in formula (1). The reward is to reduce the total deviation between the load score of each cell and the average load score in the area. Or the reward rule is set according to formula (9), and the reward is verified according to the feedback of the cell terminal blocking rate, as shown in formula (9). The reward is to reduce the total deviation between the blocking rate of each cell and the set target blocking rate. In this embodiment, by using a deep reinforcement learning model, the server is given the ability to adjust the strategy according to empirical data, which makes the adjustment gentle and reasonable.

[0114] Reward = -∣S 目标 -S∣ (9)

[0115] In some embodiments, the issued adjustment strategy includes adjusting the current cell or keeping it in the current cell.

[0116] For example, a migration policy is output to some terminals whose load score is lower than the average load score, and a migration-in cell policy is output at the same time. The migration-in cell is selected as a cell with a load score higher than the average value, and the target cell is a neighboring cell of the source cell.

[0117] In some embodiments, the selected terminals may be determined randomly or according to a preset strategy; no specific limitations are made here.

[0118] In other embodiments, the terminal blocking rate S is higher than the blocking rate target S. 目标 Some terminals output migration policies, setting the target cell for migration to a load capacity score of A>A. 目标 The target community is an adjacent community to the community from which the relocation is taking place.

[0119] Based on the preset target blocking rate, the corresponding cell service capacity threshold A is determined using formula (10). 目标 .

[0120] A 目标 =∫ -1 S 目标 (10)

[0121] Formula (10) and formula (7) are inverse functions of each other.

[0122] In some embodiments, the target blocking rate S 目标 Set it to 5%.

[0123] Figure 5 A schematic diagram of a cell adjustment method according to an example embodiment of this application is shown, such as... Figure 5 The method shown includes steps S501, S503 and S505.

[0124] According to the embodiments of this application, Figure 5 The method shown is applied to the terminal.

[0125] like Figure 5 As shown, in step S501, wireless data is sent to the server.

[0126] In some embodiments, the transmitted wireless data may include wireless physical resource allocation data and channel quality.

[0127] In other embodiments, the transmitted wireless data may include blocking data.

[0128] In step S503, an adjustment instruction including a cell adjustment strategy is received from the server.

[0129] In this embodiment, the adjustment instruction includes adjusting the current cell and / or maintaining the current cell.

[0130] In step S505, the adjustment method is determined according to the cell adjustment instruction.

[0131] According to embodiments of this application, a cell adjustment instruction includes server-side instructions and execution operation instructions. The adjustment strategies included in the cell adjustment instruction include adjusting the current cell and / or maintaining it in the current cell.

[0132] In a specific embodiment, when the cell adjustment strategy is to adjust the current cell, for example, when the terminal does not need to reselect or switch to another cell according to the received cell configuration information, but the server requires the terminal to reselect or switch to a target cell, the corresponding adjustment methods that the terminal can take include: reducing the downlink signal measurement value of the current cell; increasing the downlink signal measurement value of neighboring cells; accelerating the measurement of neighboring cells; and / or accelerating the reporting of measurement reports of neighboring cells, so that the terminal meets the reselection criteria or handover criteria for switching to the target neighboring cell as defined by the network, thereby achieving the effect of reselecting or switching to the specified target cell.

[0133] In other embodiments, when the cell adjustment strategy is to remain in the current cell—for example, when the terminal needs to reselect or switch to another cell according to the received cell configuration information, but the server does not decide to let the terminal switch to another cell based on the received cell load information, and the terminal's optimal strategy is to remain in the current cell—the corresponding adjustment methods that the terminal can take include: adopting or increasing the downlink signal measurement value of the current cell; stopping the measurement of neighboring cells; and / or stopping the reporting of measurement reports for neighboring cells.

[0134] It should be noted that although this application uses wireless physical resource allocation data and the number of terminal congestion in the cell to score the cell load, other schemes that use parameters that are linearly related to the cell load to score the cell load are also within the scope of this application.

[0135] The above description primarily focuses on the methodological aspects of the embodiments of this application. Those skilled in the art should readily recognize that, based on the operations or steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Those skilled in the art can implement the described functionality in different ways for each specific operation or method, and such implementations should not be considered beyond the scope of this application.

[0136] The apparatus embodiments of this application are described below. For details not described in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0137] Figure 6 A schematic diagram of a cell selection device structure according to an example embodiment of this application is shown, such as... Figure 6 The illustrated apparatus includes a wireless data receiving unit 601, a load scoring determination unit 603, an adjustment strategy determination unit 605, and an adjustment strategy sending unit 607. The wireless data receiving unit 601 receives wireless data from multiple terminals, wherein the number of cells accessed by the multiple terminals is at least two. The load scoring determination unit 603 determines the load score of the cell accessed by the multiple terminals based on the wireless data transmitted by the multiple terminals. The adjustment strategy determination unit 605 determines a cell adjustment strategy for at least one of the terminals based on the load scores of the cell accessed by the multiple terminals. The adjustment strategy sending unit 607 sends a cell adjustment instruction including the cell adjustment strategy to at least one terminal accessing the cell, so that the terminal receiving the cell adjustment instruction executes the cell adjustment strategy.

[0138] Figure 7 A schematic diagram of another cell selection device structure according to an example embodiment of this application is shown, such as... Figure 7The apparatus shown includes a wireless data transmission unit 701, an adjustment instruction receiving unit 703, and an adjustment unit 705. The wireless data transmission unit 701 is used to transmit wireless data to a server; the adjustment instruction receiving unit 703 is used to receive adjustment instructions, including cell adjustment strategies, sent from the server; and the adjustment unit 705 is used to determine the adjustment method based on the cell adjustment instructions.

[0139] Figure 8 A schematic diagram of a server device structure according to an example embodiment of this application is shown, such as... Figure 8 The device shown includes a data collection module 801, a cell load calculation module 803, a dynamic load balancing module 805, and a policy distribution module 807.

[0140] According to embodiments of this application, the data collection module 801 collects information reported by each terminal, organizes, classifies, and cleans the data, and deletes invalid data; the cell load calculation module 803 groups and classifies congested cell information and cell resource information according to location and time, analyzes the data using a preset model, calculates and predicts the resource allocation of cells in each area, and generates a digital map of cell load; the dynamic load balancing module 805 analyzes the load status of cells at each location and the data needs of terminals based on the data summary, generates a cell selection reward and punishment strategy, controls the terminal to choose to stay or leave according to the cell load, and achieves dynamic adjustment of cell load balancing effect; the strategy distribution module 807 distributes the cell reward and punishment strategy for each terminal to the terminal. The cell reward and punishment strategy includes the target neighboring cell for migration or migration, or staying in the current cell.

[0141] The amount of wireless physical resources allocated to a terminal by a cell is usually linearly related to the uplink and downlink channel quality of the terminal. The higher the channel quality of the terminal, the more wireless physical resources it receives. However, when the cell is overloaded and its service capacity declines, it cannot provide the terminal with the corresponding wireless physical resources based on the channel quality, and the linear relationship is broken.

[0142] In this application, based on the above characteristics of the data, the preset model in the cell load calculation module 803 includes a linear benchmark model, a nonlinear neural network model, and a load detection module.

[0143] In some embodiments, a linear benchmark model is used to establish a normal linear relationship between channel quality and resource allocation, as shown in Equation (3).

[0144] A nonlinear neural network model is used to detect abnormal resource allocation. As described in step S303, a preset neural network is used to calculate the abnormal wireless physical resource allocation score of the cells in the area based on channel quality and wireless physical resource allocation data.

[0145] The load detection module is used to determine the load status of the cell. As mentioned above, the server pushes cell reward and punishment policies to the terminal based on the cell load status.

[0146] Figure 9 A schematic diagram of the device structure of a terminal according to an example embodiment of this application is shown, such as... Figure 9 The device shown includes a cell resource detection module 901, a user demand prediction module 903, a terminal information reporting module 905, and a policy execution module 907.

[0147] The cell resource detection module 901 is used to collect indicators of the amount of radio physical resources allocated to the terminal by the cell and the uplink and downlink channel quality parameters of the terminal. Specifically, it includes indicators characterizing the amount of radio physical resources allocated to the terminal by the cell, including uplink resource parameters, downlink signal quality, and channel quality parameters. Uplink resource parameters include uplink bandwidth, uplink physical resource block (PRB) allocation, modulation and coding scheme (MCS), uplink grant, uplink delay, and uplink scheduling request; downlink resource parameters include downlink bandwidth, downlink physical resource block (PRB) allocation, modulation and coding scheme (MCS), downlink delay, and downlink multiple-input multiple-output (MIMO) configuration; the terminal's channel quality parameters include uplink signal quality and downlink signal quality, for example, uplink channel state information (CSI) and uplink power control (TPC) characterizing uplink signal quality, and uplink channel state information (CSI), uplink power control (TPC), and signal-to-noise ratio (SNR) characterizing downlink signal quality.

[0148] The user demand prediction module 903 is used to predict future traffic and bandwidth demands based on user behavior and application needs, and then send the predictions to the terminal information reporting module 905.

[0149] The terminal information reporting module 905 reports the terminal's wireless physical resource quantity indicators and channel quality parameters in real time. It also needs to report the PCI (Physical Cell ID) information, frequency points, and terminal GPS coordinates of the current cell and neighboring cells.

[0150] The policy execution module 907 executes the policy issued by the server. In order to implement the corresponding policy, it can move the blocked cell or low service capacity cell specified by the server into the terminal penalty list. For cells that are added to the penalty list, the terminal's measurement signal value for that cell is weighted lower to avoid reselection or switching to that cell.

[0151] According to embodiments of this application, in order to facilitate users' understanding of network status and adjustment of strategies, Figure 9The device also includes a real-time network monitoring module. This module displays information about the currently connected cell, signal strength, data transmission rate, and whether there is any congestion. Simultaneously, when the server issues a new operation command, the real-time network monitoring module can prompt the user and display recommended cell information. The user can also choose whether to accept the operation command on the interface to manually fine-tune the cell selection.

[0152] Figure 10 A schematic diagram of the structure of an electronic device according to an exemplary embodiment of this application is shown below. Figure 10 To describe an electronic device 200 according to this embodiment of the present application. Figure 10 The electronic device 200 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0153] like Figure 10 As shown, the electronic device 200 is presented in the form of a general-purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one storage unit 220, a bus 230 connecting different system components (including storage unit 220 and processing unit 210), a display unit 240, etc.

[0154] The storage unit stores program code, which can be executed by the processing unit 210 to perform the methods described in this specification according to various exemplary embodiments of this application. For example, the processing unit 210 can perform, for example... Figure 1 The method shown.

[0155] Storage unit 220 may include readable media in the form of volatile storage units, such as random access memory (RAM) 2201 and / or cache memory 2202, and may further include read-only memory (ROM) 2203.

[0156] Storage unit 220 may also include a program / utility 2204 having a set (at least one) program module 2205, such program module 2205 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.

[0157] Bus 230 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.

[0158] Electronic device 200 can also communicate with one or more external devices 300 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 200, and / or with any device that enables electronic device 200 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 250. Furthermore, electronic device 200 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 260. Network adapter 260 can communicate with other modules of electronic device 200 via bus 230. 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 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0159] Through 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. The technical solutions according to the embodiments of this application 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, or network device, etc.) to execute the methods described above according to the embodiments of this application.

[0160] Software products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example,, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections with one or more wires, portable 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 thereof.

[0161] Computer-readable storage media may include data signals 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 storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the 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.

[0162] Program code for performing the operations of this application 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).

[0163] The aforementioned computer-readable medium carries one or more programs, which, when executed by a device, cause the computer-readable medium to perform the aforementioned functions.

[0164] Those skilled in the art will understand that the above modules can be distributed in the device as described in the embodiments, or they can be modified accordingly and placed in one or more devices that are unique to this embodiment. The modules in the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0165] According to an embodiment of this application, a computer program product is proposed, including a computer program or instructions that, when executed by a processor, can perform the methods described above.

[0166] This application significantly improves the accuracy and dynamic response capability of network load management through the collaborative work of terminals and servers. Compared with existing technologies, this application no longer relies on terminals to make independent cell selection decisions. Instead, the server integrates data from multiple terminals, generates optimal strategies in real time, and pre-pushes them to terminals about to enter the relevant areas. This approach avoids decision-making conflicts between terminals, reduces the frequency of data congestion, and achieves dynamic balancing of cell load, making network resource allocation more intelligent. Furthermore, terminal devices can significantly reduce poor network experience caused by data congestion, improving user satisfaction. Simultaneously, intelligent allocation of network load effectively reduces network infrastructure overload; the more terminals using the network, the greater the benefits.

[0167] The embodiments of the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, any changes or modifications made by those skilled in the art based on the ideas of the present invention, its specific implementation methods, and its application scope, are all within the scope of protection of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method of cell adjustment, characterized by, The method is applied to a server, and the method includes: Receive wireless data from multiple terminals, wherein the number of cells accessed by the multiple terminals is at least two; Based on the wireless data transmitted by the multiple terminals, determine the load score of the cell accessed by the multiple terminals; Based on the load scores of the multiple terminals accessing the cells, a cell adjustment strategy for at least one of the terminals is determined; and According to the cell adjustment policy, a cell adjustment instruction including the cell adjustment policy is sent to at least one terminal accessing the cell, so that the terminal receiving the cell adjustment instruction executes the cell adjustment policy.

2. The method according to claim 1, characterized in that, According to the cell adjustment policy, the method further includes sending a cell adjustment instruction including the cell adjustment policy to at least one terminal accessing the cell, so that the terminal receiving the cell adjustment instruction executes the cell adjustment policy. Receive updated wireless data from multiple terminals; Based on the updated radio data sent by the multiple terminals, determine the update load score of the cell accessed by the multiple terminals; Based on the updated load scores of the multiple terminals accessing the cells, the total deviation of the load scores of the multiple terminals accessing the cells is determined; If the total deviation of the load score exceeds a preset deviation threshold, an update cell adjustment strategy for at least one cell is determined based on the updated load scores of the multiple terminal access cells; and According to the updated cell adjustment policy, an updated cell adjustment instruction including the updated cell adjustment policy is sent to at least one terminal accessing the cell, so that the terminal receiving the updated cell adjustment instruction executes the updated cell adjustment policy.

3. The method according to claim 1, characterized in that, The wireless data includes wireless physical resource allocation data and channel quality. Based on the wireless data transmitted by the multiple terminals, the load score of the cell accessed by the multiple terminals is determined, including: The load factor and anomaly score of the multiple terminal access cells are determined based on the wireless physical resource allocation data and the channel quality. The load score is determined based on the load factor and the anomaly score.

4. The method according to claim 3, characterized in that, The load factor and anomaly score of the multiple terminal access cells are determined based on the wireless physical resource allocation data and the channel quality, including: The load factor of the multiple terminal access cells is determined based on the wireless physical resource allocation data; Anomaly scores for the multiple terminals accessing the cell are determined based on the channel quality and the wireless physical resource allocation data.

5. The method according to claim 4, characterized in that, The wireless physical resource allocation data includes actual wireless physical resource allocation data and expected wireless physical resource allocation data. The load factor of the multiple terminal access cells is determined based on the wireless physical resource allocation data, including: The load factor for the multiple terminals accessing the cell is determined based on the ratio of the actual wireless physical resource allocation data to the expected wireless physical resource allocation data of the cell.

6. The method according to claim 3, characterized in that, Based on the channel quality and the wireless physical resource allocation data, anomaly scores for the multiple terminals accessing the cell are determined, including: Based on the preset neural network, the channel quality, and the wireless physical resource allocation data, anomaly scores are determined for the access cells of the multiple terminals. The anomaly scores are used to characterize the degree of deviation between the actual wireless physical resource allocation data and the ideal wireless physical resource allocation data.

7. The method according to claim 1, characterized in that, Based on the load scores of the multiple terminals accessing the cell, a cell adjustment strategy is determined for at least one of the terminals, including: Based on the load scores of the multiple terminals accessing the cells, the average load score of the multiple terminals accessing the cells is determined; A cell adjustment strategy for at least one of the terminals is determined based on the load score and the average load score.

8. The method according to claim 1, characterized in that, The wireless data includes congestion data. Based on the wireless data transmitted by the multiple terminals, a load score for the cell accessed by the multiple terminals is determined, including: Based on the blocking data, the cell blocking rate of the multiple terminals accessing the cell is determined; The load score of the multiple terminals accessing the cell is determined based on the cell blocking rate.

9. The method according to claim 8, characterized in that, The load score for the multiple terminals accessing the cell is determined based on the cell blocking rate, including: The load score is determined based on the relationship between the preset blocking rate and the load score; wherein the relationship between the preset blocking rate and the load score is obtained by model training based on historical blocking rates and historical load scores.

10. A method for adjusting a residential community, characterized in that, The method is applied to a terminal, and the method includes: Send wireless data to the server; Receive cell adjustment instructions, including cell adjustment strategies, sent from the server; The adjustment method is determined based on the community adjustment instruction.

11. The method according to claim 10, characterized in that, The cell adjustment strategy includes adjusting the current cell and / or maintaining the current cell.

12. The method according to claim 11, characterized in that, When the cell adjustment strategy is to adjust the current cell, the adjustment method includes: Reduce the current downlink signal measurement value of the cell; Increase downlink signal measurement values ​​of adjacent cells; Accelerate measurements in neighboring cells; and / or Expedite the submission of measurement reports for neighboring cells.

13. The method according to claim 11, characterized in that, When the cell adjustment strategy is to remain in the current cell, the adjustment method includes: Adopt or increase the downlink signal measurement value of the current cell; Stop measurements in adjacent cells; and / or Stop submitting measurement reports for adjacent cells.

14. An electronic device, comprising: processor; as well as A memory storing a computer program that, when executed by the processor, causes the processor to perform the method as claimed in any one of claims 1-9 or 10-13.

15. A computer program product, characterized in that, The computer program product includes a computer-readable storage medium storing a computer program operable to cause a computer to perform the method as described in 1-9 or any one of claims 10-13.

16. A computer-readable storage medium having stored thereon computer-readable instructions that, when executed by a processor, cause the processor to perform the method as claimed in any one of claims 1-9 or 10-13.

Images