A base station capacity optimization method and apparatus

Abstract

This invention provides a base station capacity optimization method and apparatus. By constructing a configuration parameter optimization rule model for the base station, a base station capacity optimization task is created based on the configuration parameter optimization rule model. The base station automatically matches the corresponding configuration parameter optimization rule and optimizes the base station configuration parameters according to the configuration parameter optimization rule. In some implementations, batch automatic matching of base stations and configuration parameter optimization rules can be achieved, and base station capacity optimization can be performed efficiently.

Description

Technical Field

[0001] The embodiments of the present invention relate to, but are not limited to, the field of wireless network configuration technology. Specifically, they relate to, but are not limited to, a base station capacity optimization method and apparatus. Background Technology

[0002] With the advent of the 5G era in wireless networks, base station capacity optimization is crucial to achieving optimal capacity. Most related technologies rely on manual, experience-based judgment to adjust base station configuration parameters, such as changing the value of configuration attribute A for a specific cell reselection under a base station from C1 to C2. Optimizing base station capacity through manual parameter modification is complex and uncontrollable. It's impossible to automatically track the entire optimization process or guarantee timely and safe rollback in case of optimization errors. Furthermore, the large number of base stations and their varying parameter adjustments make manual optimization unsuitable for batch processing.

[0003] To address the aforementioned issues, a smart, fast, flexible, and secure operation and maintenance method is needed for optimizing the configuration parameters of base stations. Summary of the Invention

[0004] The base station capacity optimization method and apparatus provided in this invention mainly solve the technical problem that related technologies do not use standard modeling languages ​​to model base station parameter optimization rules, making it impossible to quickly customize base station parameter optimization rules using optimization rules constructed using standard modeling languages, thus making it impossible to implement base station capacity optimization in batches.

[0005] To address the aforementioned technical problems, embodiments of the present invention provide a base station capacity optimization method, comprising:

[0006] Build a configuration parameter optimization rule model for base stations;

[0007] A base station capacity optimization task is created based on the configuration parameter optimization rule model;

[0008] The base station automatically matches the corresponding configuration parameter optimization rules and optimizes the base station configuration parameters according to the configuration parameter optimization rules.

[0009] This invention also provides a base station capacity optimization device, including a modeling module, a task creation module, a matching module, and a processing module;

[0010] The modeling module is used to build a configuration parameter optimization rule model for the base station;

[0011] The task creation module is used to create a base station capacity optimization task based on the configuration parameter optimization rule model;

[0012] The matching module is used for automatically matching the corresponding configuration parameter optimization rules;

[0013] The processing module is used to optimize the base station configuration parameters according to the configuration parameter optimization rules.

[0014] The beneficial effects of this invention are:

[0015] According to the base station capacity optimization method and apparatus provided in the embodiments of the present invention, a configuration parameter optimization rule model is constructed for the base station, and a base station capacity optimization task is created based on the configuration parameter optimization rule model. The base station automatically matches the corresponding configuration parameter optimization rule and optimizes the base station configuration parameters according to the configuration parameter optimization rule. In some implementation processes, batch base stations and configuration parameter optimization rules can be automatically matched to achieve efficient base station capacity optimization.

[0016] Other features and corresponding beneficial effects of the present invention will be described in the latter part of the specification, and it should be understood that at least some of the beneficial effects will become obvious from the description in the specification. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the basic process of the base station capacity optimization method according to Embodiment 1 of the present invention;

[0018] Figure 2 This is a schematic diagram of the construction configuration parameter optimization rule model structure in Embodiment 1 of the present invention;

[0019] Figure 3 This is a schematic diagram of the base station capacity optimization method according to Embodiment 1 of the present invention;

[0020] Figure 4 This is a schematic diagram of the bidirectional automatic matching of base stations and configuration parameter optimization rules in Embodiment 1 of the present invention;

[0021] Figure 5 This is a flowchart illustrating the KPI evaluation method according to Embodiment 1 of the present invention;

[0022] Figure 6 This is a schematic diagram of the KPI evaluation model according to Embodiment 1 of the present invention;

[0023] Figure 7 This is a schematic diagram of the evaluation process using the KPI evaluation model in Embodiment 1 of the present invention;

[0024] Figure 8 This is a schematic diagram of the structure of the KPI data model in Embodiment 1 of the present invention;

[0025] Figure 9 This is a flowchart illustrating the base station capacity optimization method according to Embodiment 2 of the present invention;

[0026] Figure 10 This is a flowchart illustrating the base station capacity optimization method according to Embodiment 3 of the present invention;

[0027] Figure 11 This is a flowchart illustrating the base station capacity optimization method according to Embodiment 4 of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of this invention clearer, the embodiments of this invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0029] Example 1:

[0030] With a large number of base stations and varying configuration parameters across them, this invention provides an intelligent, efficient, and flexible base station capacity optimization method to address the problem that related technologies do not use a standard modeling language to model base station parameter optimization rules, making it impossible to quickly customize base station parameter optimization rules using optimization rules constructed with a standard modeling language, thus hindering the batch implementation of base station capacity optimization.

[0031] See Figure 1 , Figure 1 This is a basic flowchart of the base station capacity optimization method provided in an embodiment of the present invention, which specifically includes the following steps:

[0032] S101. Construct a configuration parameter optimization rule model for the base station.

[0033] In this embodiment of the invention, the configuration parameter optimization rules mainly include verification rules and key parameters. A verification rule is a set of rules that specifies how to check which attributes of which objects. Verification rules need to be used in conjunction with specific key parameters to function. For the modeling methods of verification rules and key parameters, please refer to [link to relevant documentation]. Figure 2 As shown.

[0034] Specifically, the verification rules consist of two parts: the verification target (Target) and the verification rule list (CheckRuleList). The Target defines the objects to be verified and their attributes; for example, it can define verification of the X attribute of the reSelectCell. The CheckRuleList defines the specific verification rules, which can contain multiple checkrules. It's important to note that the name of each checkrule must be unique. Key parameters include, but are not limited to, serving cell frequency, target frequency, parameter name, verification type, calibration value, minimum value within the parameter value range, maximum value within the parameter value range, and verification rules. The purpose of these key parameters is to categorize cell objects based on attributes such as source and target frequencies, and to set different verification standards.

[0035] It should be noted that the verification rules specify how to identify configuration parameters that do not meet the constraints, but they need to be used in conjunction with specific key parameters to be effective. At the same time, the same verification rule can be used in different places. This method of separating rules from parameters can achieve the effect of defining verification rules once and reusing them multiple times.

[0036] In this embodiment of the invention, a standard modeling language is used to construct a configuration parameter optimization rule model for the base station. This allows for the rapid customization of base station parameter optimization rules. Specifically, this embodiment employs a DSL modeling method to construct the configuration parameter optimization rule model. For example, the specific verification rules in the CheckRuleList are described using a specific DSL language.

[0037] S102. Create a base station capacity optimization task based on the configuration parameter optimization rule model.

[0038] In this embodiment of the invention, a predefined configuration parameter optimization rule model is submitted to the intelligent operation and maintenance platform. The intelligent operation and maintenance platform creates a base station capacity optimization task based on the customized configuration parameter optimization rule model and calls the predefined configuration parameter optimization rule model to optimize the base station capacity.

[0039] It should be noted that in order to perform capacity optimization on base stations in batches, after the configuration parameter optimization rules are predetermined, a batch of base stations will be selected to create base station capacity optimization tasks. This batch of base stations can automatically match the configuration parameter optimization rules to optimize the object parameters.

[0040] In this embodiment of the invention, the base station capacity optimization task can be created by selecting network elements. During the network element selection process, multiple network elements can be selected at once, or only one network element can be selected.

[0041] S103. The base station automatically matches the corresponding configuration parameter optimization rules and optimizes the base station configuration parameters according to the configuration parameter optimization rules.

[0042] With numerous base stations, each potentially having different configuration parameter settings, the same configuration parameter optimization rule might require modifications to some base stations while leaving others untouched. Similarly, for the same base station, some verification rules might necessitate changes to certain configuration parameters, while others remain unchanged. Therefore, automatically matching the corresponding configuration parameter optimization rules to the base station configuration parameters based on the base station capacity optimization task is a flexible and efficient approach to achieving base station capacity improvement.

[0043] It should be noted that the base stations and configuration parameter optimization rules are automatically matched bidirectionally. Based on the configuration parameter optimization rule model, a batch of base stations is selected, allowing them to automatically match these optimization rules. This enables capacity optimization for a batch of base stations. See the diagram for a schematic of base station capacity optimization. Figure 3 As shown. It should be understood that multiple base stations will each hit different configuration parameter optimization rules, and can optimize their own configuration parameters independently without affecting each other. For details on the bidirectional automatic matching of base stations and configuration parameter optimization rules, please refer to [link to relevant documentation]. Figure 4 As shown.

[0044] In this embodiment of the invention, after optimizing the base station configuration parameters, a KPI evaluation needs to be performed. To perform the KPI evaluation, a customized KPI evaluation model for the base station capacity optimization effect needs to be developed. The effect of base station capacity optimization can be reasonably evaluated through the KPI evaluation model.

[0045] It should be understood that the optimization of base station capacity ultimately needs to be reflected in performance indicators. Only when various performance indicators are improved after optimization can it be considered a successful configuration parameter optimization. Therefore, KPI evaluation is also required after configuration parameter optimization. KPI evaluation is the last line of defense for configuration parameter optimization and is indispensable. Its purpose is to promptly detect and roll back parameters in the event of optimization failure.

[0046] Please refer to the flowchart for KPI evaluation methods. Figure 5 As shown, the specific steps include:

[0047] S501. Use the KPI evaluation model to evaluate the optimized base station configuration parameters.

[0048] In this embodiment of the invention, the capacity optimization result of each base station is evaluable; see the KPI evaluation model for details. Figure 6As shown, the KPI evaluation model evaluates each cell under base station management separately. This article uses a single cell as an example to explain the KPI evaluation method in detail. The specific steps are as follows:

[0049] S701. Calculate the first N neighboring cells of the first cell based on the number of neighboring cell handovers of the first cell, where N is a natural number greater than or equal to 1.

[0050] S702. Combine the N neighboring cells to perform aggregation operations to obtain the evaluation index values ​​respectively;

[0051] S703. Evaluate the optimization effect based on the evaluation index values.

[0052] In this embodiment of the invention, during the base station capacity optimization process, the parameters of the cell may be optimized and modified. Aggregation calculations are performed using N neighboring cells to obtain the evaluation index values ​​for each cell. It should be noted that each evaluation index value is the optimized evaluation index value based on the configured parameters. In step S703, evaluating the optimization effect based on the evaluation index values ​​can specifically involve comparing the optimized evaluation index values ​​with the unoptimized evaluation index values, assigning a score to each index based on the fluctuation of the index values, and then weighted summing the scores to obtain the final score for the cell.

[0053] It should be noted that the KPI evaluation model is predefined and is built using a standard modeling language. After creating a base station capacity optimization task, the KPI evaluation model is called at the same time as the configuration parameter optimization rule model, so as to evaluate the effect of base station capacity optimization.

[0054] The KPI evaluation model is an overall evaluation of the base station capacity optimization effect. In this embodiment of the invention, key KPI indicators can also be selected to construct a KPI data model, and the optimized base station performance indicators can be quantitatively evaluated through the KPI data model.

[0055] In this embodiment of the invention, the KPI data model can be customized; see [link / reference]. Figure 8 As shown, users can select different KPI indicators and customize different KPI data models based on the specific situation of each base station. The KPI data model includes the KPI name, fluctuation range, whether it is a red line indicator (isRedLineKpi), and whether it is a positive indicator (isPositiveKpi). It should be noted that Range indicates that fluctuations within this range are reasonable; isRedLineKpi specifies whether the indicator is a red line indicator, which has veto power—if the red line indicator deteriorates, the optimization fails; isPositiveKpi indicates whether the indicator is a positive indicator, with a larger value indicating a better indicator.

[0056] S502. When the evaluation results show optimization, end the base station capacity optimization task.

[0057] S503. When the evaluation results show deterioration, the optimized base station configuration parameters will be rolled back.

[0058] In this embodiment of the invention, the evaluation results of parameter optimization are displayed on a network element basis. That is, under the same network element, all parameter optimizations either all succeed or all fail. When the evaluation result shows optimization, it indicates that the base station performance has improved. Therefore, this optimization task does not need to be rolled back, and the task ends. When the evaluation result shows deterioration, it indicates that the optimization has failed. The optimized base station configuration parameters need to be rolled back. After the rollback is successful, the task ends.

[0059] The base station capacity optimization method provided in this invention constructs a configuration parameter optimization rule model for the base station, creates a base station capacity optimization task based on the configuration parameter optimization rule model, automatically matches the corresponding configuration parameter optimization rule for the base station and optimizes the base station configuration parameters according to the configuration parameter optimization rule, and evaluates the effect of the base station optimization by KPI after the base station capacity optimization. If the optimization fails, the base station configuration parameters that failed to optimize are rolled back. The configuration parameter optimization rule model can be used to realize the automatic matching of batch base stations and configuration parameter optimization rules for efficient base station capacity optimization. The optimization effect can also be evaluated by KPI evaluation model and rolled back in time after the optimization failure is displayed, which ensures the flexibility and security of base station capacity optimization.

[0060] Example 2:

[0061] Based on the above embodiments, a detailed flowchart illustrating the base station capacity optimization process provided in this embodiment of the invention can be found here. Figure 9 As shown, the specific steps include the following:

[0062] S901, Build a configuration parameter optimization rule model and a KPI evaluation model for the base station.

[0063] In this embodiment of the invention, the configuration parameter optimization rule model is constructed to enable batch capacity optimization of base stations, and the KPI evaluation model is constructed to evaluate the effectiveness of base station capacity optimization. Both the configuration parameter optimization rule model and the KPI evaluation model are predefined and will be directly invoked when creating subsequent base station optimization tasks.

[0064] In this embodiment of the invention, a standard modeling language is used to construct a configuration parameter optimization rule model and a KPI evaluation model for the base station.

[0065] S902. Create a base station capacity optimization task based on the configuration parameter optimization rule model.

[0066] In this embodiment of the invention, a predefined configuration parameter optimization rule model is submitted to the intelligent operation and maintenance platform. Based on the customized configuration parameter optimization rule model, a batch of base stations are selected to create base station capacity optimization tasks, and the predefined configuration parameter optimization rule model is called to optimize the base station capacity.

[0067] S903: The base station automatically matches the corresponding configuration parameter optimization rules and optimizes the base station configuration parameters according to the configuration parameter optimization rules.

[0068] With numerous base stations, each potentially having different configuration parameter settings, the same configuration parameter optimization rule might require modifications to some base stations while leaving others untouched. Similarly, for the same base station, some verification rules might necessitate changes to certain configuration parameters, while others remain unchanged. Therefore, automatically matching the corresponding configuration parameter optimization rules to the base station configuration parameters based on the base station capacity optimization task is a flexible and efficient approach to achieving base station capacity improvement.

[0069] It should be noted that the base station and the configuration parameter optimization rules are automatically matched bidirectionally. In this way, based on the configuration parameter optimization rule model, the base station can automatically match these configuration parameter optimization rules.

[0070] S904. Use the KPI evaluation model to evaluate the optimized base station configuration parameters.

[0071] In this embodiment of the invention, the optimization of base station capacity ultimately needs to be reflected through performance indicators. Only when the various performance indicators are improved after optimization can it be considered a successful configuration parameter optimization. Therefore, KPI evaluation is also required after configuration parameter optimization. KPI evaluation is the last line of defense for configuration parameter optimization and is indispensable. Its purpose is to promptly detect and roll back parameters in the event of optimization failure.

[0072] In this embodiment of the invention, there are two specific ways to use the KPI evaluation model for evaluation. One way is to evaluate the overall effect of parameter optimization by evaluating each cell managed by the base station. For each cell, the top N neighboring cells of the cell are calculated based on the number of neighboring cell handovers. The values ​​of each evaluation index are obtained by combining the top N neighboring cells and performing aggregation operations. Each index is scored based on the fluctuation of the index before and after optimization, and the weighted sum is the final score of the cell. The other way is to select key KPI indicators to construct a KPI data model and use the KPI data model to quantitatively evaluate the performance indicators of the optimized base station.

[0073] S905. When the evaluation results show optimization, the base station capacity optimization task ends.

[0074] S906. When the evaluation results show deterioration, the base station capacity optimization task will be rolled back.

[0075] In this embodiment of the invention, the evaluation results of parameter optimization are displayed on a network element basis. That is, under the same network element, all parameter optimizations either all succeed or all fail. When the evaluation result shows optimization, it indicates that the base station performance has improved. Therefore, this optimization task does not need to be rolled back, and the task ends. When the evaluation result shows deterioration, it indicates that the optimization has failed. The optimized base station configuration parameters need to be rolled back. After the rollback is successful, the task ends.

[0076] The base station capacity optimization method provided in this invention constructs a configuration parameter optimization rule model and a KPI evaluation model for the base station. Based on the configuration parameter optimization rule model, a base station capacity optimization task is created. The base station automatically matches the corresponding configuration parameter optimization rules and optimizes its configuration parameters according to these rules. After base station capacity optimization, the KPI evaluation model is used to evaluate the optimization effect. If optimization fails, the failed base station configuration parameters are rolled back. This approach allows for efficient base station capacity optimization by automatically matching a batch of base stations with the configuration parameter optimization rules using the configuration parameter optimization rule model, while also enabling optimization effect evaluation through the KPI evaluation model and timely rollback after optimization failure, ensuring both flexibility and security in base station capacity optimization.

[0077] Example 3:

[0078] Based on the above embodiments, this invention provides a detailed description of the process of creating a base station capacity optimization task, using a configuration parameter optimization model and a KPI data model to optimize configuration parameters, and achieving successful optimization.

[0079] See Figure 10 As shown, Figure 10 This is a schematic diagram of the base station capacity optimization process provided in an embodiment of the present invention. The specific process includes the following steps:

[0080] S1001. Construct a configuration parameter optimization rule model and a KPI evaluation model for the base station.

[0081] In this embodiment of the invention, the configuration parameter optimization rule model is constructed to enable batch capacity optimization of base stations, and the KPI evaluation model is constructed to evaluate the effectiveness of base station capacity optimization. Both the configuration parameter optimization rule model and the KPI evaluation model are predefined and will be directly invoked when creating subsequent base station optimization tasks.

[0082] In this embodiment of the invention, a standard modeling language is used to construct a configuration parameter optimization rule model and a KPI evaluation model for the base station.

[0083] S1002. Select the network element to create a base station capacity optimization task and call the configuration parameter optimization rule model.

[0084] Base station capacity optimization tasks can be created by selecting network elements. During the network element selection process, multiple network elements can be selected at once, or only one network element can be selected. In this embodiment of the invention, a network element is selected to create the base station capacity optimization task, and the specific form of the network element list is ["subnet number = a, network element number = b"].

[0085] S1003. The base station automatically matches the corresponding configuration parameter optimization rules and optimizes the base station configuration parameters according to the configuration parameter optimization rules.

[0086] In this embodiment of the invention, the base station and the configuration parameter optimization rules are automatically matched bidirectionally. Thus, based on the configuration parameter optimization rule model, the base station can automatically match these configuration parameter optimization rules to optimize the configuration parameters.

[0087] In this embodiment of the invention, the configuration parameter optimization rules mainly include verification rules and key parameters; the verification rule is a set of rules that specifies how to verify which attributes of which objects, and the verification rule needs to be used in conjunction with specific key parameters to be effective.

[0088] The verification rules consist of two parts: the verification target (Target) and the verification rule list (CheckRuleList). The target defines the objects to be verified and their attributes; for example, it can define verification of the X attribute of a reSelectCell. The checkRuleList defines the specific verification rules, which can contain multiple checkrules. It's important to note that checkrule names must be unique, and the body of each verification rule is described using a DSL language. Key parameters include, but are not limited to, serving cell frequency, target frequency, parameter name, verification type, calibration value, minimum value within the parameter value range, maximum value within the parameter value range, and verification rules. The purpose of these key parameters is to categorize cell objects based on attributes such as source and target frequencies, and to set different verification standards.

[0089] In this embodiment of the invention, the verification rule is to check the reselection cells whose source frequency point is the same as the frequency point of the reselection cell under the current network element in the key parameters, find the corresponding reselection cell, and perform key attribute verification to determine whether the attribute value is within the configured range. The specific verification process is as follows:

[0090]

[0091]

[0092]

[0093] The target for verification is the 10 attributes of the reselected cell: attr_A, attr_B, attr_C, attr_D, attr_E, attr_F, attr_G, attr_H, attr_I, and attr_J; the checkrule name is 0100. The verification rule needs to be used in conjunction with specific key parameters to function. Please refer to the key parameter table shown in Table 1. The key parameter table defines the verification rules for attributes at different frequency points. For example, attribute attr_A uses verification rule 0100 at frequency point 2585. Combined with verification rule 0100, the attributes of the reselected cell corresponding to the serving cell at frequency point 2585 will be verified. If the attribute value is no longer between -140 and -120, it will be optimized to a calibration value of -124.

[0094] Table 1

[0095]

[0096] In this embodiment of the invention, three parameters in the parameter verification results need to be optimized, as shown in Table 2. It is recommended that users change the parameters of the objects in the table from their original values ​​to new values.

[0097] Table 2

[0098] Net Element residential area parameter Original value New value Subnet number = a, Network element number = b reSelectCell1 attr_C 22 30 Subnet number = a, Network element number = b reSelectCell2 attr_D 4 20 Subnet number = a, Network element number = b reSelectCell2 attr_J 22 30

[0099] The results of parameter optimization are displayed on a per-network-element basis. That is, within the same network element, all parameters either succeed or fail completely. In this embodiment of the invention, parameter optimization was successful, and the results are shown in Table 3.

[0100] Table 3

[0101] ne code message Subnet number = a, Network element number = b 0

[0102] S1004. Use the KPI evaluation model to evaluate the optimized base station configuration parameters.

[0103] In this embodiment of the invention, key KPI indicators are selected to construct a KPI data model, and the optimized base station performance indicators are quantitatively evaluated through the customized KPI data model.

[0104] In this embodiment of the invention, the selected key KPI indicators include: Range, which indicates that the fluctuation of the indicator within this range is reasonable; isRedLineKpi, which indicates whether the indicator is a red line indicator; and isPositiveKpi, which indicates whether the indicator is a positive indicator.

[0105] It should be noted that the red line indicator has veto power, meaning that if the red line indicator deteriorates, it means that the optimization has failed.

[0106] This invention uses three metrics—Range, isRedLineKpi, and isPositiveKpi—as the KPI data model. The specific KPI evaluation process is as follows:

[0107]

[0108]

[0109] Table 4

[0110] KPI score Evaluation Indicator A Evaluation Indicator B Evaluation Indicator C Community 1 0.33 1 0 0 Community 2 0.33 0 1 0

[0111] After optimization, all cells under the network element need to be selected for indicator evaluation. The results of indicator evaluation in this embodiment are shown in Table 4. No indicators of either cell under the network element showed deterioration, and the comprehensive scores of both cells 1 and 2 were greater than 0, indicating that the optimization effect was significant.

[0112] S1005. Evaluation results show optimization; base station capacity optimization task terminated.

[0113] In this embodiment of the invention, if the evaluation results show optimization and the base station performance is improved, then the optimization task does not need to be rolled back and the task ends.

[0114] The base station capacity optimization method provided in this invention constructs a configuration parameter optimization rule model and a KPI evaluation model for the base station, creates a base station capacity optimization task, and calls the configuration parameter optimization rule model. The base station automatically matches the corresponding configuration parameter optimization rule and optimizes the base station configuration parameters according to the configuration parameter optimization rule. After the base station capacity optimization, the KPI evaluation model is used to evaluate the effect of the base station optimization. The task ends directly after the optimization is successful. By utilizing the configuration parameter optimization rule model, batch base stations and configuration parameter optimization rules are automatically matched, and base station capacity optimization is performed intelligently and efficiently.

[0115] Example 4:

[0116] Based on the above embodiments, this invention provides a detailed explanation of the process of creating a base station capacity optimization task, optimizing configuration parameters using a configuration parameter optimization model and a KPI data model, and rolling back the current optimization task if the optimization fails.

[0117] See Figure 11 As shown, Figure 11 This is a schematic diagram of the base station capacity optimization process provided in an embodiment of the present invention. The specific process includes the following steps:

[0118] S1101. Construct a configuration parameter optimization rule model and a KPI evaluation model for the base station;

[0119] S1102. Select a network element to create a base station capacity optimization task and call the configuration parameter optimization rule model;

[0120] S1103. The base station automatically matches the corresponding configuration parameter optimization rules and optimizes the base station configuration parameters according to the configuration parameter optimization rules.

[0121] S1104. Use the KPI evaluation model to evaluate the optimized base station configuration parameters;

[0122] S1105. The evaluation results show a deterioration, so the base station capacity optimization task will be rolled back.

[0123] It should be noted that the difference between this embodiment and Embodiment 3 is that when performing KPI evaluation, the evaluation results show that the optimized indicators have deteriorated. The other processes are roughly the same as those in Embodiment 3, and will not be repeated here. This embodiment only provides a detailed description of the differences.

[0124] The evaluation results of the indicators in this embodiment are shown in Table 5. The average scores of the three indicators for the two cells under the network element are -0.33 and -1, respectively. According to the rules, an average score less than 0 indicates that the optimization has failed and the parameters need to be rolled back.

[0125] Table 5

[0126] KPI score Evaluation Indicator A Evaluation Indicator B Evaluation Indicator C Community 1 -0.33 0 -1 0 Community 2 -1 0 0 -1

[0127] In this embodiment of the invention, rolling back the parameters will send a success message, as shown in Table 6, and the task will end.

[0128] Table 6

[0129] ne code message Subnet number = a, Network element number = b 0 success

[0130] The base station capacity optimization method provided in this embodiment of the invention constructs a configuration parameter optimization rule model and a KPI evaluation model for the base station, creates a base station capacity optimization task and calls the configuration parameter optimization rule model. The base station automatically matches the corresponding configuration parameter optimization rule and optimizes the base station configuration parameters according to the configuration parameter optimization rule. After the base station capacity optimization, the KPI evaluation model is used to evaluate the effect of the base station optimization. If the optimization fails, the optimization task is rolled back in a timely manner, thus ensuring the flexibility and security of base station capacity optimization.

[0131] Example 5:

[0132] This invention also provides a base station capacity optimization device, which is used to implement the steps of the above method embodiments. The essence is the same as the above embodiments, so it will not be described again here.

[0133] The base station capacity optimization device includes a modeling module, a task creation module, a matching module, and a processing module;

[0134] The modeling module is used to build a configuration parameter optimization rule model for the base station;

[0135] The task creation module is used to create base station capacity optimization tasks based on the configuration parameter optimization rule model;

[0136] The matching module is used to automatically match the corresponding configuration parameter optimization rules;

[0137] The processing module is used to optimize the base station configuration parameters according to the configuration parameter optimization rules.

[0138] In this embodiment of the invention, the modeling module is also used to build a KPI evaluation model for the cells managed by the base station.

[0139] In this embodiment of the invention, the base station capacity optimization device further includes an evaluation module, which is used to evaluate the optimized base station configuration parameters using a KPI evaluation model; and a processing module, which is used to terminate the base station capacity optimization task when the evaluation result shows optimization, and to roll back the base station capacity optimization task when the evaluation result shows deterioration.

[0140] In this embodiment of the invention, the processing module includes a search module and an optimization module; the search module is used to find the target parameter in the key parameters using the verification rules, and is also used to verify the parameter value of the cell corresponding to the target parameter; the optimization module is used to optimize the parameter value of the corresponding cell according to the parameter value of the target parameter.

[0141] In this embodiment of the invention, the evaluation module includes a calculation module and an evaluation sub-module; the calculation module is used to calculate the top N neighboring cells of the first cell based on the number of neighboring cell handovers of the first cell, where N is a natural number greater than or equal to 1; and to perform aggregation operations on the N neighboring cells to obtain evaluation index values ​​respectively; the evaluation sub-module is used to evaluate the optimization effect based on the evaluation index values.

[0142] In this embodiment of the invention, the evaluation module is also used to select key KPI indicators to evaluate the optimized base station configuration parameters.

[0143] The above description, in conjunction with specific implementation methods, provides a further detailed explanation of the embodiments of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A base station capacity optimization method, comprising: Obtain the configuration parameter optimization rule model built for the base station; Based on the configuration parameter optimization rule model, a base station capacity optimization task is created so that the base station can automatically match the corresponding verification rules and key parameters according to the base station capacity optimization task, use the verification rules to find the target parameter in the key parameters, verify the parameter value of the cell corresponding to the target parameter, and optimize the parameter value of the corresponding cell according to the parameter value of the target parameter.

2. The base station capacity optimization method as described in claim 1, characterized in that, Before creating the base station capacity optimization task based on the configuration parameter optimization rule model, the following steps are also included: A KPI evaluation model is constructed for the cells managed by the base station.

3. The base station capacity optimization method as described in claim 2, characterized in that, The method further includes: The optimized base station configuration parameters are evaluated using a KPI evaluation model. When the evaluation results show optimization, the base station capacity optimization task ends. If the assessment results show a deterioration, the base station capacity optimization task will be rolled back.

4. The base station capacity optimization method as described in claim 3, characterized in that, The evaluation of the optimized base station configuration parameters using the KPI evaluation model includes: The first N neighboring cells of the first cell are calculated based on the number of neighbor cell handovers of the first cell, where N is a natural number greater than or equal to 1; The evaluation index values ​​are obtained by performing aggregation operations on the N neighboring regions; The optimization effect is evaluated based on the evaluation index values.

5. The base station capacity optimization method as described in claim 3, characterized in that, The evaluation of the optimized base station configuration parameters using the KPI evaluation model also includes: Key performance indicators (KPIs) were selected to evaluate the optimized base station configuration parameters.

6. A base station capacity optimization device, comprising a modeling module and a task creation module; The modeling module is used to obtain the configuration parameter optimization rule model constructed for the base station; The task creation module is used to create a base station capacity optimization task based on the configuration parameter optimization rule model, so that the base station automatically matches the corresponding verification rules and key parameters according to the base station capacity optimization task, uses the verification rules to find the target parameter in the key parameters, verifies the parameter value of the cell corresponding to the target parameter, and optimizes the parameter value of the corresponding cell according to the parameter value of the target parameter.

7. The base station capacity optimization device as described in claim 6, characterized in that, The modeling module is also used to build a KPI evaluation model for the cells managed by the base station.

8. The base station capacity optimization device as described in claim 7, characterized in that, The device also includes an evaluation module and a processing module; The evaluation module is used to evaluate the optimized base station configuration parameters using a KPI evaluation model. The processing module is also used to terminate the base station capacity optimization task when the evaluation result shows improvement, and to roll back the base station capacity optimization task when the evaluation result shows deterioration.

9. The base station capacity optimization device as described in claim 8, characterized in that, The evaluation module includes a calculation module and an evaluation sub-module; The calculation module is used to calculate the top N neighboring cells of the first cell based on the number of neighboring cell handovers of the first cell, where N is a natural number greater than or equal to 1; and to perform aggregation calculations on the N neighboring cells to obtain evaluation index values ​​respectively. The evaluation submodule is used to evaluate the optimization effect based on the evaluation index value.

10. The base station capacity optimization device as described in claim 8, characterized in that, The evaluation module is also used to select key KPIs to evaluate the optimized base station configuration parameters.

Images