An AI-based comprehensive energy efficiency control method for tower base stations

Abstract

The present invention provides an AI-based comprehensive energy efficiency control method for an iron tower base station, which belongs to the field of power supply technology. The method specifically includes: using a signal problem coefficient to determine signal problem users among access users, obtaining historical access and usage data of different signal problem users in the iron tower base station at different time periods, and determining a power optimization period in the time period based on the historical access and usage data of different signal problem users at different time periods and the signal problem coefficient. In the power optimization period, the signal strength of different users using the iron tower base station under different power supply powers of the radio frequency modules is determined, and the power supply strategy of the radio frequency module of the iron tower base station in the power optimization period is determined in combination with the historical access and usage data of different users in the power optimization period, thereby realizing effective control of the energy efficiency of the iron tower base station.

Description

Technical Field

[0001] The present invention belongs to the technical field of communication base stations, and in particular relates to an AI-based comprehensive energy efficiency control method for tower base stations. Background Art

[0002] Tower base stations are the "mother of 5G" and undertake the important tasks of network signal coverage and transmission, providing users with a faster and more stable communication experience. On the other hand, in order to achieve energy efficiency optimization of tower base stations, the invention patent application CN202410136236.1 "Power supply and communication service integrated control module and method for low-carbon emission base stations" reduces the energy consumption of mobile communication base stations, improves energy utilization rate, and reduces carbon emissions of mobile communication base stations through effective linkage between mobile communication base stations and power supply systems. However, there are the following technical problems:

[0003] When performing energy efficiency optimization management, existing technical solutions ignore the differentiated adjustment of the power supply power of the base station's RF module based on the analysis results of the base station's historical communication data. If the same power supply power is used, it will inevitably lead to the energy efficiency of the tower base station being difficult to meet the requirements.

[0004] In response to the above technical problems, the present invention provides an AI-based comprehensive energy efficiency control method for tower base stations. Summary of the Invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0006] According to one aspect of the present invention, an AI-based comprehensive energy efficiency control method for tower base stations is provided.

[0007] An AI-based comprehensive energy efficiency control method for tower base stations, specifically including:

[0008] S1 determines the distribution data of different types of buildings within a preset area with the tower base station as the center, and proceeds to the next step when it is determined based on the distribution data that the tower base station can adjust the power supply of the radio frequency module;

[0009] S2 determines the signal strength of the access user of the tower base station during historical access, and uses the trained AI model to determine the signal problem coefficients of different access users based on the analysis results of the signal strength, and uses the signal problem coefficients to identify users with signal problems among the access users;

[0010] S3: obtaining historical access usage data of different signal problem users in the tower base station at different time periods, and determining a power optimization period in the time period based on the historical access usage data of different signal problem users at different time periods and a signal problem coefficient;

[0011] S4 determines the signal strength of different users of the tower base station under different power supply powers of the RF modules during the power optimization period, and determines the power supply strategy of the RF module of the tower base station during the power optimization period in combination with the historical access usage data of different users during the power optimization period.

[0012] A further technical solution is that the types of buildings include residential areas, commercial offices, hospitals and shopping malls.

[0013] A further technical solution is that the distribution data includes the building area of ​​the building and the distance from the tower base station.

[0014] A further technical solution is that the AI ​​model is built using one or a combination of convolutional neural networks, recurrent neural networks, long short-term memory networks and artificial neural networks.

[0015] A further technical solution is that the historical access usage data includes the historical access times of the signal problem user in different time periods and the historical access durations for different historical access times.

[0016] A further technical solution is that the method for determining the power optimization period is:

[0017] Determining the number of historical accesses of the user with signal problems in the time period based on the historical access usage data of the user with signal problems in the time period, and determining the base station usage frequency coefficient of the user with signal problems in the time period based on the historical access times and durations of the different historical access times of the user with signal problems in the time period;

[0018] Determining the communication demand coefficients of different signal problem users in the said time period by multiplying the base station usage frequency coefficients of different signal problem users in the said time period by the signal problem coefficients;

[0019] The working reliability demand coefficient of the tower base station in the period is determined by summing the weights of the communication demand coefficients of different signal problem users in the period, and the working reliability demand coefficient is used to determine whether the tower base station in the period is a power optimization period.

[0020] A further technical solution is that the signal strength of the user is determined based on a monitoring result of the signal strength of the tower base station under different power supply powers of the radio frequency modules.

[0021] The beneficial effects of the present invention are:

[0022] 1. The power optimization period in the period is determined based on the historical access usage data of different signal problem users in different time periods and the signal problem coefficient. This avoids the technical problem of poor communication of signal problem users caused by optimizing the power supply power of the RF module during the period when the usage frequency of signal problem users is too high. On the basis of reducing the interference to the communication use of signal problem users, it also lays the foundation for further reducing the energy consumption of base stations.

[0023] 2. The power supply strategy of the RF module of the tower base station during the power optimization period is determined based on the signal strength of different users under different RF module power supply powers and historical access usage data. This takes into account the different signal strength requirements of different users due to different usage frequencies, as well as the signal strength of different users under different RF module power supply powers. On the basis of reducing the energy consumption of the base station, it also ensures the communication experience of the users.

[0024] Other features and advantages will be described in the following description. The objectives and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0025] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings.

[0027] Figure 1 It is a flow chart of an AI-based comprehensive energy efficiency control method for tower base stations;

[0028] Figure 2 is a flow chart of a method for determining a base station usage demand coefficient within a distance interval;

[0029] Figure 3 is a flow chart of a method for determining a signal problem coefficient of an access user;

[0030] Figure 4 is a flow chart of a method for determining a power optimization period. DETAILED DESCRIPTION

[0031] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this specification without creative work should fall within the scope of protection of this specification.

[0032] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, an AI-based comprehensive energy efficiency control method for tower base stations is provided, which specifically includes:

[0033] S1 determines the distribution data of different types of buildings within a preset area with the tower base station as the center, and proceeds to the next step when it is determined based on the distribution data that the tower base station can adjust the power supply of the radio frequency module;

[0034] Furthermore, the types of buildings include residential areas, commercial offices, hospitals and shopping malls.

[0035] Specifically, the distribution data includes the building area of ​​the building and the distance from the tower base station.

[0036] It should be noted that determining that the tower base station is capable of adjusting the power supply of the radio frequency module specifically includes:

[0037] Based on the building distribution data, determine the buildings within different distance intervals within a preset area range, and determine the base station usage demand coefficients within the different distance intervals based on the building areas of different types of buildings within the different distance intervals and their distances from the tower base station;

[0038] Determining preset weight coefficients corresponding to different distance intervals based on the distance ranges corresponding to the different distance intervals, and determining the comprehensive usage demand coefficient of the tower base station using the weight sum constructed using the preset weight coefficients and the base station usage demand coefficient;

[0039] Based on the comprehensive usage demand coefficient, it is determined whether the tower base station can adjust the power supply of the radio frequency module.

[0040] Specifically, such as Figure 2 As shown, the method for determining the base station usage demand coefficient within the distance interval is:

[0041] Determining demand coefficient assessment values ​​of different types of buildings using a preset mapping function based on the building areas of different types of buildings and their distances from the tower base station;

[0042] The base station usage demand coefficient within the distance interval is determined based on the sum of demand coefficient evaluation values ​​of different types of buildings.

[0043] Furthermore, when the comprehensive usage demand coefficient of the tower base station is within a preset range, it is determined that the tower base station can adjust the power supply power of the radio frequency module.

[0044] It should also be noted that determining that the tower base station is capable of adjusting the power supply of the radio frequency module specifically includes:

[0045] S11 determines, based on the distribution data of the buildings, whether the total building area of ​​the buildings within a preset area range whose distance from the tower base station is greater than the preset distance meets the requirement; if so, proceeds to the next step; if not, determines that the tower base station cannot adjust the power supply of the RF module;

[0046] S12 determines the total building area of ​​the building within the preset area range, and judges whether the total building area of ​​the building is greater than the preset building area. If so, proceed to the next step; if not, proceed to step S15;

[0047] S13 determines whether the average distance between different buildings and the tower base station is greater than a preset distance. If so, it is determined that the tower base station cannot adjust the power supply of the radio frequency module. If not, proceed to the next step.

[0048] S14 determines the signal strength requirement coefficients of different buildings based on the types of different buildings and the distances from the tower base station, and determines whether the total area of ​​the buildings whose signal strength requirement coefficients are greater than a preset requirement threshold meets the requirement. If not, it is determined that the tower base station cannot adjust the power supply of the radio frequency module. If so, proceed to the next step.

[0049] S15 determines the base station usage demand coefficients in different distance intervals based on the building areas of different types of buildings in different distance intervals and their distances from the tower base station, and determines whether the base station usage demand coefficients in the specified distance intervals meet the requirements. If not, it is determined that the tower base station cannot adjust the power supply of the radio frequency module. If so, proceeding to the next step.

[0050] S16 determines the preset weight coefficients corresponding to different distance intervals based on the distance ranges corresponding to different distance intervals, and determines the comprehensive usage demand coefficient of the tower base station using the weights and weights constructed using the preset weight coefficients and the base station usage demand coefficient, and determines whether the tower base station can adjust the power supply power of the RF module based on the comprehensive usage demand coefficient.

[0051] Furthermore, the specified distance interval is a distance interval within a specified distance range.

[0052] S2 determines the signal strength of the access user of the tower base station during historical access, and uses the trained AI model to determine the signal problem coefficients of different access users based on the analysis results of the signal strength, and uses the signal problem coefficients to identify users with signal problems among the access users;

[0053] Specifically, such as Figure 3 As shown, the method for determining the signal problem coefficient of the access user is:

[0054] Determining, based on an analysis result of the signal strength of the access user, a cumulative access duration of the access user in different signal strength intervals;

[0055] Determining a usage frequency coefficient in different signal strength intervals based on a ratio of the cumulative access duration in different signal strength intervals to the total access duration;

[0056] The problem strength interval is determined based on the signal strength range corresponding to different signal strength intervals, and the signal problem coefficient of the access user is determined using the trained AI model based on the usage frequency coefficient of the access user in the problem strength interval.

[0057] Furthermore, the signal problem coefficient of the access user ranges from 0 to 1, and when the signal problem coefficient of the access user is greater than a preset problem threshold, the access user is determined to be a signal problem user.

[0058] It can be understood that the problematic intensity interval is a signal intensity interval within a specified intensity range.

[0059] It should also be noted that the method for determining the signal problem coefficient of the access user is:

[0060] If it is determined based on the analysis result of the signal strength of the access user that the signal strength is greater than the preset signal strength, then it is determined that the access user is not a user with a signal problem;

[0061] When the signal strength is not greater than the preset signal strength for a certain period of time:

[0062] When the access duration during which the signal strength is not greater than the preset signal strength is less than the preset access duration, it is determined that the access user is not a user with a signal problem;

[0063] When the signal strength is not greater than the preset signal strength and the access time is not less than the preset access time,

[0064] obtaining the number of accesses of the access user and the access durations of different accesses, determining an access frequency coefficient of the access user based on the number of accesses of the access user and the access durations of different accesses, and determining that the access user is not a user with a signal problem when the access frequency coefficient of the access user is less than a preset frequency coefficient;

[0065] When the access frequency coefficient of the access user is not less than the preset frequency coefficient:

[0066] Determining, based on the analysis result of the signal strength of the access user, the cumulative access duration of the access user in different signal strength intervals, and determining the frequency of use coefficient in different signal strength intervals in combination with the number of accesses of the access user in different signal strength intervals and the access durations of different access times;

[0067] When the frequency coefficient of use of the user within the specified signal strength range meets the requirement, it is determined that the access user is not a user with signal problems;

[0068] When the frequency of use coefficient of the user within the specified signal strength range does not meet the requirement:

[0069] The problem strength interval is determined based on the signal strength range corresponding to different signal strength intervals, and the signal problem coefficient of the access user is determined using the trained AI model based on the usage frequency coefficient of the access user in the problem strength interval.

[0070] Furthermore, the AI ​​model is built using one or a combination of convolutional neural networks, recurrent neural networks, long short-term memory networks, and artificial neural networks.

[0071] S3: obtaining historical access usage data of different signal problem users in the tower base station at different time periods, and determining a power optimization period in the time period based on the historical access usage data of different signal problem users at different time periods and a signal problem coefficient;

[0072] It should also be noted that the historical access usage data includes the historical access times of the signal problem user in different time periods and the historical access durations for different historical access times.

[0073] Specifically, such as Figure 4 As shown, the method for determining the power optimization period is:

[0074] Determining the number of historical accesses of the user with signal problems in the time period based on the historical access usage data of the user with signal problems in the time period, and determining the base station usage frequency coefficient of the user with signal problems in the time period based on the historical access times and durations of the different historical access times of the user with signal problems in the time period;

[0075] Determining the communication demand coefficients of different signal problem users in the said time period by multiplying the base station usage frequency coefficients of different signal problem users in the said time period by the signal problem coefficients;

[0076] The working reliability demand coefficient of the tower base station in the period is determined by summing the weights of the communication demand coefficients of different signal problem users in the period, and the working reliability demand coefficient is used to determine whether the tower base station in the period is a power optimization period.

[0077] Furthermore, the method for determining the base station usage frequency coefficient of the signal problem user in the time period is:

[0078] Taking the historical access times of the signal problem user in the time period and the historical access duration of the signal problem user with different historical access times in the time period as input values, a prediction model based on BP neural network is used to determine the base station usage frequency coefficient of the signal problem user in the time period.

[0079] Specifically, when the working reliability requirement coefficient is less than a preset threshold, it is determined that the tower base station does not belong to the power optimization period during the period.

[0080] It should be further explained that the method for determining the power optimization period is:

[0081] Determine the historical access times of the user with signal problems in the period based on the historical access usage data of the user with signal problems in the period;

[0082] When the total number of historical access times of the user with signal problems during the period does not meet the requirement:

[0083] Then determining the time period as a power optimization time period;

[0084] When the total number of historical access times of the user with signal problems during the period meets the requirement:

[0085] Determine the total historical access duration of the user with the signal problem in the time period. When the total historical access duration of the user with the signal problem in the time period does not meet the requirement:

[0086] Then determining the time period as a power optimization time period;

[0087] When the total historical access duration of the user with signal problems during the period meets the requirement:

[0088] Determining the number of historical accesses of the user with signal problems in the time period based on the historical access usage data of the user with signal problems in the time period, and determining the base station usage frequency coefficient of the user with signal problems in the time period based on the historical access times and durations of the different historical access times of the user with signal problems in the time period;

[0089] When the base station usage frequency coefficient in the time period is greater than the preset frequency threshold and the number of signal problem users does not meet the requirement:

[0090] Then determining the time period as a power optimization time period;

[0091] When the base station usage frequency coefficient in the time period is greater than the preset frequency threshold and the number of signal problem users meets the requirement:

[0092] Determining the communication demand coefficients of different signal problem users in the said time period by multiplying the base station usage frequency coefficients of different signal problem users in the said time period by the signal problem coefficients;

[0093] The working reliability demand coefficient of the tower base station in the period is determined by summing the weights of the communication demand coefficients of different signal problem users in the period, and the working reliability demand coefficient is used to determine whether the tower base station in the period is a power optimization period.

[0094] S4 determines the signal strength of different users of the tower base station under different power supply powers of the RF modules during the power optimization period, and determines the power supply strategy of the RF module of the tower base station during the power optimization period in combination with the historical access usage data of different users during the power optimization period.

[0095] Furthermore, the signal strength of the user is determined according to a monitoring result of the signal strength of the tower base station under different power supply powers of the radio frequency modules.

[0096] It should be noted that the method for determining the power supply strategy of the radio frequency module of the tower base station during the power optimization period is:

[0097] Determining access durations of different users in the power optimization period based on historical access usage data of different users in the power optimization period, and determining user usage demand values ​​of different users in the power optimization period based on the access durations;

[0098] determining signal usage impact coefficients of different users at different power supplies of the radio frequency modules based on signal strengths of different users at different power supplies of the radio frequency modules, and determining signal impact values ​​of different users by multiplying the signal usage impact coefficients by the user usage demand values;

[0099] By weighting the signal impact values ​​of different users under the power supply power of different RF modules and determining the signal usage stability coefficient under the power supply power of different RF modules, the power consumption of the tower base station under the power supply power of different RF modules is determined, and the time period matching coefficient under the power supply power of different RF modules is determined based on the ratio of the signal usage stability coefficient to the power consumption, and the power supply power of the RF module of the tower base station in the power optimization period is determined based on the time period matching coefficient.

[0100] Furthermore, the power supply power of the radio frequency module corresponding to the maximum time period matching coefficient is used as the power supply power of the radio frequency module of the tower base station in the power optimization period.

[0101] It should also be noted that the method for determining the power supply strategy of the radio frequency module of the tower base station during the power optimization period is:

[0102] determining, based on the signal strengths of different users under different power supplies of the radio frequency modules, signal usage impact coefficients of different users under different power supplies of the radio frequency modules, and determining whether a proportion of users whose signal usage impact coefficients under the power supplies of the radio frequency modules do not meet the requirements is within a preset proportion range; if so, proceeding to the next step; if not, determining that the power supplies of the radio frequency modules cannot be used during the time period;

[0103] Determining access durations of different users in the power optimization period based on historical access usage data of different users in the power optimization period, and determining user usage demand values ​​of different users in the power optimization period based on the access durations, and determining whether a sum of user usage demand values ​​of users whose signal usage impact coefficients do not meet the requirements meets the requirements; if so, proceeding to the next step; if not, determining that the power supply power of the radio frequency module cannot be used in the period;

[0104] determining signal impact values ​​of different users by multiplying the signal usage impact coefficient by the user usage demand value, and determining whether the number of users whose signal impact values ​​do not meet the requirement meets the requirement; if so, proceeding to the next step; if not, determining that the power supply of the RF module cannot be used during the time period;

[0105] By weighting the signal impact values ​​of different users under the power supply power of different RF modules and determining the signal usage stability coefficient under the power supply power of different RF modules, the power consumption of the tower base station under the power supply power of different RF modules is determined, and the time period matching coefficient under the power supply power of different RF modules is determined based on the ratio of the signal usage stability coefficient to the power consumption, and the power supply power of the RF module of the tower base station in the power optimization period is determined based on the time period matching coefficient.

[0106] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, apparatus, and non-volatile computer storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant details, refer to the descriptions of the method embodiments.

[0107] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The foregoing description is merely one or more embodiments of this specification and is not intended to limit this specification. It will be apparent to those skilled in the art that various modifications and variations may be made to one or more embodiments of this specification. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of one or more embodiments of this specification are intended to be within the scope of the claims of this specification.

Claims

1. An AI-based comprehensive energy efficiency control method for tower base stations, characterized in that: Specifically include: Determine the distribution data of different types of buildings within a preset area with the tower base station as the center, and proceed to the next step when it is determined based on the distribution data that the tower base station can adjust the power supply of the radio frequency module; Determine the signal strength of the access user of the tower base station during historical access, and determine the signal problem coefficients of different access users using the trained AI model based on the analysis results of the signal strength, and use the signal problem coefficients to identify users with signal problems among the access users; Obtaining historical access usage data of different signal problem users in the tower base station at different time periods, and determining a power optimization period in the time period based on the historical access usage data of different signal problem users at different time periods and a signal problem coefficient; During the power optimization period, determining the signal strength of the radio frequency module of the tower base station under different power supply powers for different users, and determining the power supply strategy of the radio frequency module of the tower base station during the power optimization period in combination with historical access usage data of different users during the power optimization period; Determining the total building area of ​​the buildings within the preset area range, and when it is determined that the total building area of ​​the buildings is greater than the preset building area, and when it is determined that the average distance between different buildings and the tower base station is greater than the preset distance, determining that the tower base station cannot adjust the power supply of the radio frequency module; The method for determining the signal problem coefficient of the access user is: Determining, based on an analysis result of the signal strength of the access user, a cumulative access duration of the access user in different signal strength intervals; Determining a usage frequency coefficient in different signal strength intervals based on a ratio of the cumulative access duration in different signal strength intervals to the total access duration; Determine the problem strength interval using signal strength ranges corresponding to different signal strength intervals, and determine the signal problem coefficient of the access user using the trained AI model based on the access user's usage frequency coefficient in the problem strength interval; The signal problem coefficient of the access user ranges from 0 to 1, wherein when the signal problem coefficient of the access user is greater than a preset problem threshold, the access user is determined to be a signal problem user; The problem strength interval is a signal strength interval within a specified strength range; The AI ​​model is built using one or a combination of convolutional neural networks, recurrent neural networks, long short-term memory networks, and artificial neural networks.

2. The AI-based tower base station comprehensive energy efficiency control method according to claim 1, characterized in that: The types of buildings include residential areas, commercial offices, hospitals and shopping malls.

3. The AI-based tower base station comprehensive energy efficiency control method according to claim 1, characterized in that: The distribution data includes the building area of ​​the building and the distance from the tower base station.

4. The AI-based tower base station comprehensive energy efficiency control method according to claim 1, characterized in that: Determining that the tower base station is capable of adjusting the power supply of the radio frequency module specifically includes: Based on the building distribution data, determine the buildings within different distance intervals within a preset area range, and determine the base station usage demand coefficients within the different distance intervals based on the building areas of different types of buildings within the different distance intervals and their distances from the tower base station; Determining preset weight coefficients corresponding to different distance intervals based on the distance ranges corresponding to the different distance intervals, and determining the comprehensive usage demand coefficient of the tower base station using the weight sum constructed using the preset weight coefficients and the base station usage demand coefficient; Based on the comprehensive usage demand coefficient, it is determined whether the tower base station can adjust the power supply of the radio frequency module.

5. The AI-based tower base station comprehensive energy efficiency control method according to claim 4, characterized in that: The method for determining the base station usage demand coefficient within the distance interval is: Determining demand coefficient assessment values ​​of different types of buildings using a preset mapping function based on the building areas of different types of buildings and their distances from the tower base station; The base station usage demand coefficient within the distance interval is determined based on the sum of demand coefficient evaluation values ​​of different types of buildings.

6. The AI-based tower base station comprehensive energy efficiency control method according to claim 1, characterized in that: The historical access usage data includes the historical access times of the signal problem user in different time periods and the historical access durations for different historical access times.

7. The AI-based tower base station comprehensive energy efficiency control method according to claim 1, characterized in that: The method for determining the power supply strategy of the radio frequency module of the tower base station during the power optimization period is as follows: Determining access durations of different users in the power optimization period based on historical access usage data of different users in the power optimization period, and determining user usage demand values ​​of different users in the power optimization period based on the access durations; determining signal usage impact coefficients of different users at different power supplies of the radio frequency modules based on signal strengths of different users at different power supplies of the radio frequency modules, and determining signal impact values ​​of different users by multiplying the signal usage impact coefficients by the user usage demand values; By weighting the signal impact values ​​of different users under the power supply power of different RF modules and determining the signal usage stability coefficient under the power supply power of different RF modules, the power consumption of the tower base station under the power supply power of different RF modules is determined, and the time period matching coefficient under the power supply power of different RF modules is determined based on the ratio of the signal usage stability coefficient to the power consumption, and the power supply power of the RF module of the tower base station in the power optimization period is determined based on the time period matching coefficient.

Images