Method and apparatus for network optimization, electronic device and storage medium

Abstract

The present disclosure provides a network optimization method and device, electronic equipment and storage medium, which model the optimal cell evaluated from a network cell set to obtain an optimal cell model library; screen a target optimal cell with the highest similarity to the wireless environment of the frequency switching cell in the optimal cell model library; modify the switching parameters of the frequency switching cell to be consistent with the switching parameters of the target optimal cell, and detect the performance indicators of the frequency switching cell after modifying the switching parameters; if the performance indicators fail to meet the evaluation indicator requirements, the optimization processing of the frequency switching cell is continued until the performance indicators of the frequency switching cell meet the evaluation indicators of the optimal cell. Compared with the related art, the present disclosure can improve the accuracy of switching through modeling processing, find the most suitable switching parameters for the current wireless environment, thereby optimizing the switching process, and reduce unnecessary network resource consumption and improve network efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method and apparatus for network optimization, electronic equipment, and storage medium. Background Technology

[0002] With the continuous development of wireless mobile network technology, users have increasingly higher requirements for network quality and communication experience. In wireless mobile networks, handover is a crucial means of ensuring communication quality and data service continuity. However, data transmission may be interrupted during handover, thus affecting users' download speeds and communication experience. This phenomenon is particularly pronounced in cases of frequent handovers. Therefore, how to optimize the network environment during frequent cell handovers (frequency switching) and improve data transmission rates and user experience has become an urgent problem to be solved in the field of wireless mobile networks. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for network optimization. Its main objective is to optimize the parameter configuration of frequency-switching cells, thereby improving data transmission rates and user experience.

[0004] According to a first aspect of this disclosure, a method for network optimization is provided, comprising:

[0005] The optimal cells selected from the network cell set are modeled to obtain an optimal cell model library;

[0006] Select the target optimal cell from the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell;

[0007] The handover parameters of the frequency-switching cell are modified to be consistent with the handover parameters of the target preferred cell, and the performance indicators of the frequency-switching cell are detected after the handover parameters are modified.

[0008] Determine whether the performance indicators meet the evaluation criteria for the preferred cell;

[0009] If the desired performance is not achieved, the frequency-switching cell will continue to be optimized to ensure that its performance metrics meet the evaluation criteria for the optimal frequency-switching cell.

[0010] Optionally, the step of modeling the optimal cells evaluated from the network cell set to obtain an optimal cell model library includes:

[0011] The network cells in the network cell set are evaluated and calculated using a preset evaluation algorithm to obtain the preferred cells;

[0012] The optimal cell is modeled to obtain the optimal cell model library.

[0013] Optionally, the step of modeling the preferred cells to obtain the preferred cell model library includes:

[0014] Calculate the information gain of various performance indicators in the optimized cell;

[0015] Based on the random forest algorithm, the information gain results of different optimal cell cuts are modeled and processed to obtain the optimal cell cut model library.

[0016] Optionally, the step of selecting the target optimal cell from the optimal cell model library that has the highest radio environment similarity to the frequency-switching cell includes:

[0017] Based on the preset evaluation algorithm, the set of network cells to be optimized is evaluated to determine the frequency switching cells;

[0018] The performance index data of the frequency-switching cell and the performance index data of the target optimal switching cell are calculated using the orthogonal matching pursuit algorithm to obtain the target optimal switching cell.

[0019] Optionally, the step of further optimizing the frequency-switching cell to make its performance indicators meet the evaluation indicators of the optimal frequency-switching cell includes:

[0020] Based on the orthogonal matching pursuit algorithm, the target preferred cells are re-selected;

[0021] The handover parameters of the frequency-switching cell are modified to be consistent with the handover parameters of the target preferred cell, and the performance indicators of the frequency-switching cell with modified handover parameters are detected.

[0022] Determine whether the performance indicators of the frequency-switching cell can meet the evaluation indicators after modifying the handover parameters;

[0023] If the desired result is not achieved, the above steps are repeated to ensure that the frequency-switching cell meets the evaluation criteria for the optimal switching cell.

[0024] Optionally, the method further includes:

[0025] When the performance indicators of the frequency-switching cell reach the evaluation indicators after the handover parameters are modified, the frequency-switching cell with modified handover parameters will be modeled and the optimal handover cell model library will be updated.

[0026] According to a second aspect of this disclosure, a network optimization apparatus is provided, comprising:

[0027] The modeling unit is used to model the best cells obtained from the evaluation of the network cell set to obtain a best cell model library;

[0028] The filtering unit is used to filter the target optimal cell in the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell;

[0029] The detection unit is used to modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred handover cell, and to detect the performance indicators of the frequency-switching cell after modifying the handover parameters.

[0030] A judgment unit is used to determine whether the performance indicators meet the evaluation indicators of the preferred cell;

[0031] An optimization unit is used to continue optimizing the frequency-switching cell when the performance index does not meet the evaluation index of the optimal switching cell, so that the performance index of the frequency-switching cell meets the evaluation index of the optimal switching cell.

[0032] Optionally, the modeling unit includes:

[0033] The first evaluation module is used to evaluate and calculate the network cells in the network cell set using a preset evaluation algorithm to obtain the preferred cells.

[0034] The modeling module is used to model the preferred cells and obtain the preferred cell model library.

[0035] Optionally, the modeling module is further used for:

[0036] Calculate the information gain of various performance indicators in the optimized cell;

[0037] Based on the random forest algorithm, the information gain results of different optimal cell cuts are modeled and processed to obtain the optimal cell cut model library.

[0038] Optionally, the filtering unit includes:

[0039] The second evaluation module is used to evaluate the set of network cells to be optimized based on the preset evaluation algorithm, and to determine the frequency switching cells.

[0040] The calculation module is used to calculate the similarity between the performance index data of the frequency-switching cell and the performance index data of the target optimal switching cell using the orthogonal matching pursuit algorithm, so as to obtain the target optimal switching cell.

[0041] Optionally, the optimization unit includes:

[0042] The filtering module is used to re-filter the target preferred cells based on the orthogonal matching pursuit algorithm;

[0043] The detection module is used to modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred handover cell, and to detect the performance indicators of the frequency-switching cell with modified handover parameters.

[0044] The judgment module is used to determine whether the performance indicators of the frequency-switching cell can reach the evaluation indicators after the handover parameters are modified;

[0045] The loop module is used to repeatedly perform optimization processing using the screening module, the detection module, and the judgment module when the performance index does not reach the evaluation index of the optimal cell, until the frequency-switching cell reaches the evaluation index of the optimal cell.

[0046] Optionally, the device further includes:

[0047] The update unit is used to model the frequency-switching cells with modified handover parameters and update the optimal handover cell model library when the performance indicators of the frequency-switching cells reach the evaluation indicators after the handover parameters are modified.

[0048] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0049] At least one processor; and

[0050] A memory communicatively connected to the at least one processor; wherein,

[0051] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0052] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0053] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0054] This disclosure provides a method, apparatus, electronic device, and storage medium for network optimization. The method involves modeling optimal cells evaluated from a network cell set to obtain an optimal cell model library; selecting a target optimal cell from the optimal cell model library that has the highest wireless environment similarity to a frequency-switching cell; modifying the handover parameters of the frequency-switching cell to match those of the target optimal cell, and detecting the performance indicators of the frequency-switching cell after modifying the handover parameters; determining whether the performance indicators meet the evaluation criteria for the optimal cell; and if not, continuing to optimize the frequency-switching cell to ensure that its performance indicators meet the evaluation criteria for the optimal cell. Compared with related technologies, this disclosure, through modeling, enables the system to more accurately identify the target optimal cell that best matches the current frequency-switching cell's wireless environment, thereby improving handover accuracy. By standardizing the handover parameters of the frequency-switching cell with those of the target optimal cell and determining the optimal handover parameters through iterative iteration, the system can find the most suitable handover parameters for the current wireless environment, thus optimizing the handover process. Optimized handover parameters and an accurate handover process can reduce unnecessary network resource consumption and improve network efficiency. Furthermore, determining the optimal handover parameters through iterative iteration can reduce abnormal situations caused by handover failures or other reasons, enhancing system stability.

[0055] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0056] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0057] Figure 1 This is a schematic diagram illustrating the usage of the timer and bias parameter P during a switching process.

[0058] Figure 2 This is a schematic diagram illustrating the impact of network switching on transmission rate.

[0059] Figure 3 A flowchart illustrating a network optimization method provided in an embodiment of this disclosure;

[0060] Figure 4 A flowchart illustrating another network optimization method provided in this embodiment of the disclosure;

[0061] Figure 5 This is a diagram illustrating a recursive operation.

[0062] Figure 6 This is a schematic diagram of a decision tree;

[0063] Figure 7 A flowchart illustrating a network optimization method;

[0064] Figure 8 A schematic diagram of a network optimization device provided in an embodiment of this disclosure;

[0065] Figure 9 A schematic diagram of another network optimization device provided in an embodiment of this disclosure;

[0066] Figure 10 A schematic block diagram of an example electronic device provided for embodiments of this disclosure. Detailed Implementation

[0067] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0068] In-frequency handover is based on coverage handover and includes the process of measurement control issuance, measurement report submission, target cell decision-handover preparation, handover execution, and handover completion. It is triggered by the A3 event, and its triggering conditions are as follows:

[0069] Mn+ofn+ocn-hys>Ms+ofs+ics+off

[0070] in:

[0071] Mn represents the measurement results of neighboring cells;

[0072] ofn is a frequency-specific offset on the frequency of adjacent cells, which is generally 0;

[0073] 0cn is the cell-specific offset of the neighboring cell. If the neighboring cell is not configured, the value is 0, which is also known as CIO.

[0074] Ms represents the measurement results for the serving cell;

[0075] Mn represents the measurement results of neighboring cells;

[0076] ofs is the frequency-specific offset of the serving cell, which is typically 0;

[0077] Ocs is the cell-specific offset of the serving cell, which is usually 0;

[0078] Hys represents the delay of the event;

[0079] `off` is the bias parameter for this event;

[0080] When the above formula is satisfied, event A3 is ready to enter the handover preparation state. That is, under normal circumstances, handover can occur when the following conditions are met.

[0081] Mn-hys>Ms+off

[0082] Figure 1 This diagram illustrates the usage of the Time-to-Time (TTT) timer and bias parameter P during the handover process. During handover, setting the Time-to-Time (TTT) timer and the handover set p helps avoid unnecessary handovers caused by fluctuations resulting from rapid decay. Setting the value too low will cause frequent handovers, while setting the value too high can easily lead to handover failures.

[0083] 4. According to the 3GPP protocol, 5G networks all adopt the traditional hard handover method. This method will cause data transmission interruption and affect the download speed during the handover process of about 50ms. It has little impact on the service transmission speed, but frequent handover will significantly affect the data transmission speed and user experience. Figure 2 This is a schematic diagram illustrating the impact of switching networks on transmission rates.

[0084] The following description, with reference to the accompanying drawings, outlines a method, apparatus, electronic device, and storage medium for network optimization according to embodiments of the present disclosure.

[0085] Figure 3 This is a schematic flowchart illustrating a network optimization method provided in an embodiment of the present disclosure.

[0086] like Figure 3 As shown, the method includes the following steps:

[0087] Step 101 involves modeling the optimal cells obtained from the network cell set to obtain an optimal cell model library.

[0088] In the embodiments of this disclosure, to improve spectrum utilization, a large service area is typically divided into multiple smaller "cells," each with its unique frequency configuration. The network cell set is the collection of these cells. To optimize different network cells, the network cell set is a dataset of performance data for these cells. The network cell set can be a dataset of data from a specific region or a dataset after filtering; this disclosure does not limit this. By evaluating the network cells in the network cell set, high-quality handover cells are obtained. All obtained high-quality handover cells are then modeled to obtain a high-quality handover cell model library.

[0089] Through modeling, we can more accurately analyze the resource usage of cells, making the allocation of network resources more reasonable and effective, thereby improving the overall network performance. The establishment of the model library can help analyze and predict users' mobility patterns, prepare resources in advance, and reduce users' sense of delay and interruption when switching cells.

[0090] Step 102: Select the target optimal cell from the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell.

[0091] In the embodiments of this disclosure, frequency-switching cells are cells that are frequently handed over. Frequent handovers can significantly impact data transmission rates and user experience. From the optimal handover cell model library, target optimal handover cells with the highest similarity to the frequency-switching cell's wireless environment are selected. The purpose is to identify the optimal handover cells in the optimal handover cell model library that best match the frequency-switching cell's wireless environment. By finding the target optimal handover cell with the highest similarity to the frequency-switching cell's wireless environment, the handover success rate can be improved, and handover failures due to environmental differences can be reduced. Target cells with high similarity have network conditions more closely similar to the frequency-switching cell, which can reduce latency during the handover process and improve the user experience.

[0092] Step 103: Modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred cell, and detect the performance indicators of the frequency-switching cell after modifying the handover parameters.

[0093] In the embodiments of this disclosure, before optimization, handover parameters of the frequency-switching cell and the target superior cell are collected, including but not limited to handover threshold, handover time delay, and handover power. The handover parameters of the frequency-switching cell are then modified to match those of the target superior cell. This requires calculating the handover parameters of the target superior cell using an algorithm and setting them in the frequency-switching cell. After modifying the handover parameters, the performance indicators of the frequency-switching cell are tested, including but not limited to signal quality, handover success rate, and user satisfaction.

[0094] Modifying handover parameters can improve the handover performance of frequency-switching cells, reducing handover failures or delays caused by inappropriate parameters. Optimizing handover parameters can enhance the user experience, reducing discomfort during the handover process. It can also improve network efficiency, reducing network resource waste caused by handover failures or delays. Finally, it can enhance network stability, reducing network instability caused by handover failures or delays.

[0095] Step 104: Determine whether the performance indicators meet the evaluation indicators of the preferred cell.

[0096] In the embodiments of this disclosure, the evaluation metrics for frequency-switching cells in a mobile communication network mainly include, but are not limited to, handover success rate, call drop rate, call quality, and user experience. After modifying the handover parameters, the performance metrics data of the frequency-switching cell are detected to determine whether they meet the evaluation metrics.

[0097] By modifying the handover parameters, the handover performance of the cell can be optimized, the handover success rate can be improved, the call drop rate can be reduced, and the call quality can be improved, thereby meeting the evaluation indicators of the best handover cell.

[0098] Step 105: If the desired result is not achieved, continue to optimize the frequency-switching cell so that its performance indicators reach the evaluation indicators of the optimal frequency-switching cell.

[0099] In the embodiments of this disclosure, the target superior cell with the highest similarity to the frequency-switching cell's wireless environment, as described in the preceding steps, is further selected. The handover parameters of the frequency-switching cell are then modified using the handover parameters of the target superior cell. Through iterative processing of the handover parameters, the network performance of the frequency-switching cell can be further optimized.

[0100] This disclosure provides a network optimization method, which involves modeling optimal switching cells obtained from a set of network cells to obtain an optimal switching cell model library; selecting a target optimal switching cell from the optimal switching cell model library that has the highest radio environment similarity to a frequency-switching cell; modifying the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target optimal switching cell, and detecting the performance index of the frequency-switching cell after modifying the handover parameters; determining whether the performance index meets the evaluation index of the optimal switching cell; if it does not meet the evaluation index, continuing to optimize the frequency-switching cell so that the performance index of the frequency-switching cell meets the evaluation index of the optimal switching cell. Compared with related technologies, this disclosure, through modeling, enables the system to more accurately identify the target optimal cell that best matches the current frequency-switching cell's wireless environment, thereby improving handover accuracy. By standardizing the handover parameters of the frequency-switching cell with those of the target optimal cell and determining the optimal handover parameters through iterative iteration, the system can find the most suitable handover parameters for the current wireless environment, thus optimizing the handover process. Optimized handover parameters and an accurate handover process can reduce unnecessary network resource consumption and improve network efficiency. Furthermore, determining the optimal handover parameters through iterative iteration can reduce abnormal situations caused by handover failures or other reasons, enhancing system stability.

[0101] To clearly illustrate the embodiments of this disclosure, this embodiment provides a flowchart of another network optimization method.

[0102] like Figure 4 As shown, the method includes the following steps:

[0103] Step 201: Use a preset evaluation algorithm to evaluate and calculate the network cells in the set of network cells to obtain the preferred cells.

[0104] Specifically, in step 201, frequent handovers directly impact data service perception. By incorporating data service duration, the number of RRC connected users, and the total number of handovers into the evaluation, and instead of calculating frequent handovers for a single terminal at a single moment, a more comprehensive assessment of whether cell handovers are frequent is achieved. Cells with more than m handovers per user per unit time and a handover success rate greater than 98% are selected as high-quality handover cells.

[0105]

[0106] Where P ho The handover success rate metric is defined as i, where i represents frequent cell handovers, and P represents the success rate of handovers. i q represents the cell handover frequency. i y represents the total number of cell handovers. i t represents the number of RRC connected users in the cell. i Indicates the duration of UE user data transmission, when P i A cell is considered to be frequently switching cells if and only if the condition p is greater than 0.4. ho ≥0.98 P i A cell can only be considered a high-quality handover cell if its value is ≤0.4.

[0107] Step 202: Model the preferred cells to obtain the preferred cell model library.

[0108] As a refinement of an embodiment of this disclosure, the step of modeling the preferred cells to obtain the preferred cell model library includes: calculating the information gain of various performance indicators in the preferred cells; and modeling the information gain results of different preferred cells based on the random forest algorithm to obtain the preferred cell model library.

[0109] Specifically, in step 202, the performance indicators of each cell in the entire network within the period are obtained (including performance parameters such as packet loss rate, PRB utilization rate, handover success rate, interference, overlapping coverage rate, and TA (7% proportion).

[0110] Table 1. Cellular Wireless Environment Data Collection (Interference data has been segmented using an algorithm)

[0111]

[0112]

[0113] Calculate the information gain of various indicators:

[0114]

[0115] Where Ent(D) is the information entropy, which is defined as:

[0116]

[0117] Where P k For a single performance metric in P ho When the percentage of cells is ≥0.98, the information entropy of the root node is:

[0118]

[0119] Taking the "interference" attribute as an example to calculate information gain, it can be explained that the interference attribute has three sample classifications (weak, medium, and strong), with subsets D respectively. 1 (Interference = Weak), D 2 (Interference = Medium) and D 3 (Interference = Strong). (Interference = Weak) includes the numbers: {1, 4, 6, 10, 13, 17}, where positive samples account for 3 / 6 and negative samples account for 3 / 6.

[0120]

[0121] Calculate D in sequence 2 (Interference = Medium) and D 3 The information entropy of (interference = strong) is:

[0122]

[0123]

[0124] The information gain of the cell "attribute" interference is:

[0125]

[0126] Similar methods were used to calculate the information gain of other data attributes as follows:

[0127] Gain(D, MR coverage) = 0.143;

[0128] Gain(D, PRB utilization) = 0.141;

[0129] Gain(D, probability of overlapping coverage) = 0.281;

[0130] Gain(D, packet loss rate) = 0.389;

[0131] Gain(D, TA < 7 percentage) = 0.006;

[0132] Clearly, the attribute "packet loss rate" has the greatest information gain, so it is chosen as the dividing attribute, i.e., D.1 Calculate, begin recursive calculation, such as Figure 5 As shown.

[0133] Similarly, calculate the information gain of other indicators under high, medium, and low packet loss rates, that is, use the attribute set [packet loss rate] {interference, MR coverage, PRB utilization, overlap coverage, TA>7 percentage} based on D 1 Calculate the information gain of each attribute:

[0134] Gain(D 1 MR coverage) = 0.043;

[0135] Gain(D 1 PRB utilization rate) = 0.458;

[0136] Gain(D 1 (overlapping probability) = 0.331;

[0137] Gain(D 1 Interference) = 0.498;

[0138] Gain(D 1 (TA < 7 percentage) = 0.456;

[0139] Since the interference attribute has the highest information gain, it is used as the second attribute to recalculate the information gain of the other attributes, and so on, until the lowest information attribute value is calculated. The final decision tree is then obtained as follows: Figure 6 As shown, by calculating the information gain of cell performance data, cell handover is divided by label for data modeling, making it a "digital dictionary" for the OMP algorithm.

[0140] Step 203: Based on the preset evaluation algorithm, evaluate the set of network cells to be optimized to determine the frequency switching cells.

[0141] Specifically, in step 203, the evaluation algorithm shown in step 201 is used to evaluate the set of network cells that need to be optimized in order to determine the frequency-switching cells that need to be optimized.

[0142] Step 204: Use the orthogonal matching pursuit algorithm to calculate the similarity between the performance index data of the frequency-switching cell and the performance index data of the target optimal switching cell to obtain the target optimal switching cell.

[0143] Specifically, in step 204, the OMP algorithm is used to perform an inner product operation on the frequency-switching cell performance and the performance data model of the best matching position of the high-quality handover cell in the "digital dictionary" (optimal handover cell model library). The result is used as the optimal solution for the current loop. The algorithm formula is as follows:

[0144] β=(D tT D t ) -1 D t y

[0145] Where y is a simple sparse algorithm for gaining information on frequency-switching cell performance data, and D is a “digital dictionary”.

[0146] y = Das.t. ||a|| < σ

[0147] The OMP algorithm is implemented by using the least squares method when calculating the residual in each iteration. First, the least squares solution is obtained by using the least squares formula to find the least squares solution of the information gain y of the original performance data under the current support set.

[0148] Then, use the least squares solution β to calculate the residual y.

[0149] γ k =yD t β

[0150] The OMP algorithm only searches for the current optimal solution each time.

[0151] Step 205: Modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred cell, and detect the performance indicators of the frequency-switching cell after modifying the handover parameters.

[0152] Step 206: Determine whether the performance indicators meet the evaluation indicators of the preferred cell.

[0153] For details in steps 205 to 206, please refer to... Figure 7 , Figure 7 This is a flowchart illustrating a network optimization method. The handover parameters of the frequency-switching cell are modified to match the handover parameters of the target superior cell. The performance indicators of the frequency-switching cell after the handover parameters are modified are then checked to determine whether they meet the evaluation indicators of the superior cell. If they do not meet the requirements, step 207 is executed; if they do meet the requirements, step 208 is executed.

[0154] Step 207: Continue to optimize the frequency-switching cell so that the performance indicators of the frequency-switching cell reach the evaluation indicators of the optimal switching cell.

[0155] As a refinement of this embodiment, the further optimization of the frequency-switching cell to make its performance indicators reach the evaluation indicators of the optimal switching cell includes: re-selecting the target optimal switching cell based on the orthogonal matching pursuit algorithm; modifying the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target optimal switching cell, and detecting the performance indicators of the frequency-switching cell with modified handover parameters; determining whether the performance indicators of the frequency-switching cell can reach the evaluation indicators after modifying the handover parameters; if not, repeating the above steps to make the frequency-switching cell reach the evaluation indicators of the optimal switching cell.

[0156] For details, please refer to step 207. Figure 7 The handover parameters of the frequency switching cell are further optimized using the methods in steps 204 to 206.

[0157] If, after a predetermined number of optimization processes, the performance metrics of a frequency-switching cell still fail to meet the evaluation criteria for a superior frequency-switching cell, the frequency-switching cell will be entered into a problem database for specialized optimization analysis.

[0158] Step 208: Model the frequency-switching cells with modified handover parameters and update the optimal handover cell model library.

[0159] For details, please refer to step 208. Figure 7 If the handover index of the problematic cell rises to an excellent value after the data is modified, the OMP algorithm process is closed, the performance data of the cell is entered into the "digital dictionary", the handover cell template is enriched, and the observation basis is provided for subsequent processing of other frequency handover cells. If the problem is still not resolved after N times of modifying the matching parameters, the cell is included in the difficult case library for special analysis. After the problem is resolved, the RF algorithm is looped again to enrich the digital model of the "digital dictionary".

[0160] It should be noted that the embodiments of this disclosure may include multiple steps. For ease of description, these steps are numbered, but these numbers are not a limitation on the execution time slots or execution order between the steps; these steps can be implemented in any order, and the embodiments of this disclosure do not limit this.

[0161] Corresponding to the network optimization method described above, this invention also proposes a network optimization apparatus. Since the apparatus embodiments of this invention correspond to the method embodiments described above, details not disclosed in the apparatus embodiments can be referred to in the method embodiments described above, and will not be repeated here.

[0162] Figure 8 This is a schematic diagram of the structure of a network optimization device provided in an embodiment of the present disclosure, as shown below. Figure 8 As shown, it includes:

[0163] Modeling unit 31 is used to model the best cells obtained from the network cell set to obtain a best cell model library.

[0164] The filtering unit 32 is used to filter the target optimal cell in the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell;

[0165] The detection unit 33 is used to modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred handover cell, and to detect the performance indicators of the frequency-switching cell after modifying the handover parameters.

[0166] The judgment unit 34 is used to judge whether the performance index meets the evaluation index of the preferred cell;

[0167] The optimization unit 35 is used to continue optimizing the frequency-switching cell when the performance index does not reach the evaluation index of the optimal switching cell, so as to make the performance index of the frequency-switching cell reach the evaluation index of the optimal switching cell.

[0168] This disclosure provides a network optimization apparatus that performs modeling processing on optimal switching cells evaluated from a network cell set to obtain an optimal switching cell model library; filters the optimal switching cell in the optimal switching cell model library that has the highest wireless environment similarity to the frequency switching cell; modifies the handover parameters of the frequency switching cell to be consistent with the handover parameters of the target optimal switching cell, and detects the performance index of the frequency switching cell after modifying the handover parameters; determines whether the performance index meets the evaluation index of the optimal switching cell; if it does not meet the evaluation index, continues to optimize the frequency switching cell so that the performance index of the frequency switching cell meets the evaluation index of the optimal switching cell. Compared with related technologies, this disclosure, through modeling, enables the system to more accurately identify the target optimal cell that best matches the current frequency-switching cell's wireless environment, thereby improving handover accuracy. By standardizing the handover parameters of the frequency-switching cell with those of the target optimal cell and determining the optimal handover parameters through iterative iteration, the system can find the most suitable handover parameters for the current wireless environment, thus optimizing the handover process. Optimized handover parameters and an accurate handover process can reduce unnecessary network resource consumption and improve network efficiency. Furthermore, determining the optimal handover parameters through iterative iteration can reduce abnormal situations caused by handover failures or other reasons, enhancing system stability.

[0169] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the modeling unit 31 includes:

[0170] The first evaluation module 311 is used to evaluate and calculate the network cells in the network cell set using a preset evaluation algorithm to obtain the preferred cell.

[0171] The modeling module 312 is used to perform modeling processing on the preferred cell to obtain the preferred cell model library.

[0172] Furthermore, in one possible implementation of this embodiment, the modeling module 312 is also used for:

[0173] Calculate the information gain of various performance indicators in the optimized cell;

[0174] Based on the random forest algorithm, the information gain results of different optimal cell cuts are modeled and processed to obtain the optimal cell cut model library.

[0175] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the filtering unit 32 includes:

[0176] The second evaluation module 321 is used to evaluate the set of network cells to be optimized based on the preset evaluation algorithm, and determine the frequency switching cells.

[0177] The calculation module 322 is used to calculate the similarity between the performance index data of the frequency-switching cell and the performance index data of the target optimal switching cell using the orthogonal matching pursuit algorithm, so as to obtain the target optimal switching cell.

[0178] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the optimization unit 35 includes:

[0179] The filtering module 351 is used to re-filter the target preferred cells based on the orthogonal matching pursuit algorithm;

[0180] The detection module 352 is used to modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred handover cell, and to detect the performance indicators of the frequency-switching cell with modified handover parameters.

[0181] The judgment module 353 is used to determine whether the performance indicators of the frequency-switching cell can reach the evaluation indicators after the handover parameters are modified;

[0182] The loop module 354 is used to repeatedly perform optimization processing using the screening module, the detection module and the judgment module when the performance index does not reach the evaluation index of the optimal cell, until the frequency-switching cell reaches the evaluation index of the optimal cell.

[0183] Furthermore, in one possible implementation of this embodiment, such as Figure 9 As shown, the device further includes:

[0184] The update unit 36 ​​is used to model the frequency-switching cell with modified handover parameters and update the optimal handover cell model library when the performance index of the frequency-switching cell reaches the evaluation index after the handover parameters are modified.

[0185] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of this embodiment, and the principle is the same, so it is not limited in this embodiment.

[0186] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0187] Figure 10 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0188] like Figure 10 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0189] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0190] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as network optimization methods. For example, in some embodiments, the network optimization methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, computing unit 401 may be configured to perform the aforementioned network optimization method by any other suitable means (e.g., by means of firmware).

[0191] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0192] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0193] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0194] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0195] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0196] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0197] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0198] The various numerical designations such as "first," "second," etc., used in this disclosure are merely for ease of description and are not intended to limit the scope of the embodiments of this disclosure, nor do they indicate a sequential order.

[0199] At least one of the features described in this disclosure can also be described as one or more, and multiple features can be two, three, four or more, and this disclosure does not impose any limitations. In the embodiments of this disclosure, for a technical feature, the technical features in that technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no sequential order or size order among the technical features described by "first", "second", "third", "A", "B", "C" and "D".

[0200] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0201] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for network optimization, characterized in that, include: The optimal handover cells evaluated from the network cell set are modeled to obtain an optimal handover cell model library; wherein, the optimal handover cells are high-quality handover cells; Select the target optimal cell from the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell; wherein, the frequency-switching cell is a cell that is frequently handed over. The handover parameters of the frequency-switching cell are modified to be consistent with the handover parameters of the target preferred cell, and the performance indicators of the frequency-switching cell are detected after the handover parameters are modified. Determine whether the performance indicators meet the evaluation criteria for the preferred cell; If the desired performance is not achieved, the frequency-switching cell will continue to be optimized to ensure that its performance metrics meet the evaluation criteria for the optimal frequency-switching cell.

2. The method according to claim 1, characterized in that, The process of modeling the optimal cells selected from the network cell set to obtain an optimal cell model library includes: The network cells in the network cell set are evaluated and calculated using a preset evaluation algorithm to obtain the preferred cells; The optimal cell is modeled to obtain the optimal cell model library.

3. The method according to claim 2, characterized in that, The process of modeling the preferred cells to obtain the preferred cell model library includes: Calculate the information gain of various performance indicators in the optimized cell; Based on the random forest algorithm, the information gain results of different optimal cell cuts are modeled and processed to obtain the optimal cell cut model library.

4. The method according to claim 2, characterized in that, The process of selecting the target optimal cell from the optimal cell model library that has the highest radio environment similarity to the frequency-switching cell includes: Based on the preset evaluation algorithm, the set of network cells to be optimized is evaluated to determine the frequency switching cells; The performance index data of the frequency-switching cell and the performance index data of the target optimal switching cell are calculated using the orthogonal matching pursuit algorithm to obtain the target optimal switching cell.

5. The method according to claim 4, characterized in that, The step of further optimizing the frequency-switching cell to make its performance indicators meet the evaluation indicators of the optimal frequency-switching cell includes the following steps: Based on the orthogonal matching pursuit algorithm, the target preferred cells are re-selected; The handover parameters of the frequency-switching cell are modified to be consistent with the handover parameters of the target preferred cell, and the performance indicators of the frequency-switching cell with modified handover parameters are detected. Determine whether the performance indicators of the frequency-switching cell can meet the evaluation indicators after modifying the handover parameters; If the desired result is not achieved, the above steps are repeated to ensure that the frequency-switching cell meets the evaluation criteria for the optimal switching cell.

6. The method according to claim 1, characterized in that, The method further includes: When the performance indicators of the frequency-switching cell reach the evaluation indicators after the handover parameters are modified, the frequency-switching cell with modified handover parameters will be modeled and the optimal handover cell model library will be updated.

7. A network optimization apparatus, characterized in that, include: A modeling unit is used to model the high-quality handover cells obtained from the network cell set to obtain a high-quality handover cell model library; wherein, the high-quality handover cells are high-quality handover cells. The filtering unit is used to filter the target optimal cell in the optimal cell model library that has the highest wireless environment similarity to the frequency-switching cell; wherein, the frequency-switching cell is a frequently switched cell; The detection unit is used to modify the handover parameters of the frequency-switching cell to be consistent with the handover parameters of the target preferred handover cell, and to detect the performance indicators of the frequency-switching cell after modifying the handover parameters. A judgment unit is used to determine whether the performance indicators meet the evaluation indicators of the preferred cell; An optimization unit is used to continue optimizing the frequency-switching cell when the performance index does not meet the evaluation index of the optimal switching cell, so that the performance index of the frequency-switching cell meets the evaluation index of the optimal switching cell.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images