Air conditioner control method and device for wireless communication macro base station
By obtaining the log information and load prediction model of the base station equipment, the target temperature of the air conditioning system is generated, and the problem of high power consumption of the air conditioning system of the 5G macro base station is solved, and the power consumption is reduced without affecting the communication quality, improving the prediction accuracy and convergence speed.
Patent Information
- Application Number
- CN202410230258.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-29
- Publication Date
- 2025-08-29
AI Technical Summary
The prior art is difficult to maintain communication quality while reducing the power consumption of 5G macro base station air conditioning systems, and the existing methods have problems of high cost or low efficiency.
By obtaining the log information of the base station equipment, calculating the load rate, and using the load prediction model to generate the target temperature of the air conditioning system, combining date, working day information and temperature encoding, the operation of the air conditioning system is optimized to reduce the power consumption during load.
It realizes the reduction of power consumption of macro station air conditioning system when the load is small, while not affecting communication quality, and improves the accuracy and convergence speed of load prediction.
Smart Images

Figure CN120568376A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of base station air conditioning control, and in particular to an air conditioning control method and device for a wireless communication macro base station. Background Art
[0002] While 5G networks bring high speeds, wide bandwidth, and low latency, the power consumption of base stations is also increasing. The power consumption of a single 5G station is 2.5 to 3.5 times that of a single 4G station. Since the transmission power of 5G base stations and 4G base stations is almost the same, all this power consumption is eventually converted into heat. Therefore, 5G base stations have higher requirements for heat dissipation.
[0003] Currently, base stations can be divided into macro stations, micro stations, pico stations and flying stations according to their service range and power. Among them, macro stations have the largest service range, generate the most heat, and also have the greatest heat dissipation pressure. In order to keep the macro station in good working condition, the macro station air-conditioning system needs to consume a lot of electricity.
[0004] How to reduce the heat dissipation power expenditure of macro base stations is the pursuit of those skilled in the art. To this end, the existing technology generally achieves this by increasing the target temperature or increasing the heat exchange rate of the air-conditioning system. However, the former is a direct increase in the target temperature, which may cause the communication equipment of the macro base station to not work in the optimal state and affect the communication quality. The latter will increase the installation cost of the air-conditioning system, and the improvement of the heat exchange efficiency of the air-conditioning system is also very limited. The existing technology has encountered a bottleneck. Summary of the Invention
[0005] The purpose of the present invention is to provide an air-conditioning control method and device for a wireless communication macro base station, which generates a corresponding target temperature acting on the air-conditioning system through the load rate of the macro station equipment, so that the target temperature can be lowered when the load is small, thereby reducing the power consumption of the macro station air-conditioning system without affecting the communication quality.
[0006] The purpose of the present invention can be achieved by the following technical solutions:
[0007] A method for controlling air conditioning of a wireless communication macro base station, comprising:
[0008] Obtain log information of each device in the base station and calculate the average load of the past set time interval based on the log information;
[0009] Based on the obtained average load, combined with the current date, weekday information, temperature and time, the average load for the future set time interval is obtained;
[0010] The average load rate is obtained based on the average load of the interval in the future set time and the pre-configured rated load upper limit;
[0011] A target temperature for the air conditioning system is generated based on the average load factor and sent to the air conditioning system.
[0012] The step of obtaining log information of all devices in the base station and calculating the average load of a set time interval in the past based on the log information includes:
[0013] Obtain log information from each device in the base station and extract the time series of uplink data throughput, downlink data throughput, number of users, and number of resource blocks;
[0014] Based on the obtained time series of uplink data throughput, downlink data throughput, number of users and number of resource blocks, the average load is obtained by weighted calculation.
[0015] The obtained average load is combined with the current month, weekday information, temperature, and time to obtain the average load for the next set time interval, including:
[0016] Get the current date and get the month code and day code;
[0017] Get the current working day information and get the working day code;
[0018] Get temperature information and get temperature code;
[0019] Obtaining a time code according to the time information;
[0020] The obtained average load, month code, date code, weekday code, temperature code and time code are concatenated to obtain a feature vector;
[0021] The obtained feature vector is input into the trained load prediction model to obtain the average load in the future set time interval.
[0022] The method of obtaining the current date and obtaining the month code and day code specifically includes:
[0023] Get the current date;
[0024] Get the month code based on the month information of the date;
[0025] The ratio of the day number of the date to the total number of days in the month is used as the date code.
[0026] The working day codes are as follows:
[0027] When it is a statutory working day and a natural working day, the working day code is 01;
[0028] When it is a statutory working day and a natural rest day, the working day code is 02;
[0029] When it is a statutory rest day, the working day code is 03;
[0030] When it is a statutory holiday, the working day code is 04.
[0031] The step of obtaining temperature information and obtaining a temperature code includes:
[0032] Get temperature information and calculate the average temperature and effective temperature difference:
[0033] T eff =min(|T-24|,|T-12|)
[0034] Where: T is the average temperature in degrees Celsius, T eff is the effective temperature difference value;
[0035] The effective temperature difference value is used as the temperature code.
[0036] The load prediction model is a neural network classification model.
[0037] Generating the target temperature of the air-conditioning system based on the average load rate specifically includes: obtaining the target temperature of the air-conditioning system by looking up a table based on the average load rate.
[0038] An air conditioning control device for a wireless communication macro base station includes a memory, a processor, and a program stored in the memory, wherein the processor implements the above-mentioned method when executing the program.
[0039] A storage medium stores a program thereon, wherein the program implements the above method when executed.
[0040] Compared with the prior art, the present invention has the following beneficial effects:
[0041] 1. Generate the corresponding target temperature for the air conditioning system based on the load rate of the macro station equipment, so that the target temperature can be lowered when the load is light, thereby reducing the power consumption of the macro station air conditioning system without affecting communication quality.
[0042] 2. The load is determined based on uplink data throughput, downlink data throughput, number of users, and number of resource blocks. This can more accurately reflect the load situation and improve the convergence speed under small samples.
[0043] 3. The ratio of the date's ordinal number to the total number of days in the month is used as the date code to effectively solve the problem of inconsistent number of dates in each month. It can also mine information at the beginning and end of the month, thereby improving the prediction accuracy of the model.
[0044] 4. The workday coding takes into account the situations of adjusted holidays and non-adjusted holidays, so as to fully explore the network data differences between the two and improve the prediction accuracy of the model.
[0045] 5. Using the average temperature and the absolute value with a smaller difference between 24 and 12 as the temperature encoding can improve the correlation between temperature and flow, thereby improving the prediction accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 Schematic diagram of the main steps of the method of the present invention. DETAILED DESCRIPTION
[0047] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.
[0048] A method for controlling air conditioning in a wireless communication macro base station generates a corresponding target temperature for the air conditioning system based on the load rate of the macro station's equipment. This method can lower the target temperature when the load is light, thereby reducing the power consumption of the macro station's air conditioning system without affecting communication quality.
[0049] like Figure 1 As shown, including:
[0050] (1) Obtaining log information of each device in the base station and calculating the average load of the past set time interval based on the log information;
[0051] An air conditioning system is generally arranged in a macro base station. The air conditioning system is an air conditioning system with a temperature control function, so that the ambient temperature in the macro base station can be adjusted to a suitable value.
[0052] The process of obtaining the average load of the previously set time interval specifically includes:
[0053] Obtain log information from each device in the base station and extract the time series of uplink data throughput, downlink data throughput, number of users, and number of resource blocks;
[0054] Specifically, the above uplink data throughput, downlink data throughput, number of users and number of resource blocks are the external connection data of the entire macro base station.
[0055] Based on the obtained time series of uplink data throughput, downlink data throughput, number of users and number of resource blocks, the average load is obtained by weighted calculation.
[0056] The load is determined based on uplink data throughput, downlink data throughput, number of users, and number of resource blocks. It can more accurately reflect the load situation and improve the convergence speed under small samples.
[0057] (2) Based on the obtained average load, combined with the current date, weekday information, temperature, and time, the average load for the future set time interval is obtained, including:
[0058] Get the current date and get the month code and day code;
[0059] Get the current working day information and get the working day code;
[0060] Get temperature information and get temperature code;
[0061] Obtaining a time code according to the time information;
[0062] The obtained average load, month code, date code, weekday code, temperature code and time code are concatenated to obtain a feature vector;
[0063] The obtained feature vector is input into the trained load prediction model to obtain the average load in the future set time interval.
[0064] Specifically, for the month code and day code, obtaining the current date and obtaining the month code and day code specifically includes:
[0065] Get the current date;
[0066] Get the month code based on the month information of the date;
[0067] The ratio of the day number of the date to the total number of days in the month is used as the date code.
[0068] Using the ratio of the date's ordinal number to the total number of days in the month as the date code effectively solves the problem of inconsistent number of dates in each month. It can also mine information at the beginning and end of the month, thereby improving the model's prediction accuracy and reducing overfitting problems.
[0069] For weekday codes, they are:
[0070] When it is a statutory working day and a natural working day, the working day code is 01;
[0071] When it is a statutory working day and a natural rest day, the working day code is 02;
[0072] When it is a statutory rest day, the working day code is 03;
[0073] When it is a statutory holiday, the working day code is 04.
[0074] The weekday coding takes into account the situations of adjusted holidays and non-adjusted holidays, so that the network data differences between the two can be fully exploited, thereby improving the prediction accuracy of the model.
[0075] For temperature encoding, obtain temperature information and obtain temperature encoding, including:
[0076] Get temperature information and calculate the average temperature and effective temperature difference:
[0077] T eff =min(|T-24|,|T-12|)
[0078] Where: T is the average temperature in degrees Celsius, T eff is the effective temperature difference value;
[0079] The effective temperature difference value is used as the temperature code.
[0080] Using the average temperature and the smaller absolute value of the difference between 24 and 12 as the temperature encoding can improve the correlation between temperature and flow, thereby improving the prediction accuracy of the model.
[0081] Generally, the load prediction model is a neural network classification model.
[0082] (3) obtaining an average load rate based on the obtained average load of the interval at the future set time and the preconfigured rated load upper limit;
[0083] (4) Generate a target temperature for the air conditioning system based on the average load rate and send it to the air conditioning system.
[0084] In some embodiments, the target temperature of the air-conditioning system is generated based on the average load rate, specifically by looking up a table based on the average load rate to obtain the target temperature of the air-conditioning system.
[0085] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
Claims
1. A method for controlling air conditioning of a wireless communication macro base station, characterized in that: include: Obtain log information of each device in the base station and calculate the average load of the past set time interval based on the log information; Based on the obtained average load, combined with the current date, weekday information, temperature and time, the average load for the future set time interval is obtained; The average load rate is obtained based on the average load of the interval in the future set time and the pre-configured rated load upper limit; A target temperature for the air conditioning system is generated based on the average load factor and sent to the air conditioning system.
2. The air conditioning control method of a wireless communication macro base station according to claim 1, characterized in that: The step of obtaining log information of all devices in the base station and calculating the average load of a set time interval in the past based on the log information includes: Obtain log information from each device in the base station and extract the time series of uplink data throughput, downlink data throughput, number of users, and number of resource blocks; Based on the obtained time series of uplink data throughput, downlink data throughput, number of users and number of resource blocks, the average load is obtained by weighted calculation.
3. The air conditioning control method of a wireless communication macro base station according to claim 2, characterized in that: The obtained average load is combined with the current month, weekday information, temperature, and time to obtain the average load for the next set time interval, including: Get the current date and get the month code and day code; Get the current working day information and get the working day code; Get temperature information and get temperature code; Obtaining a time code according to the time information; The obtained average load, month code, date code, weekday code, temperature code and time code are concatenated to obtain a feature vector; The obtained feature vector is input into the trained load prediction model to obtain the average load in the future set time interval.
4. The air conditioning control method of a wireless communication macro base station according to claim 3, characterized in that: The method of obtaining the current date and obtaining the month code and day code specifically includes: Get the current date; Get the month code based on the month information of the date; The ratio of the day number of the date to the total number of days in the month is used as the date code.
5. The air conditioning control method of a wireless communication macro base station according to claim 3, characterized in that: The working day codes are as follows: When it is a statutory working day and a natural working day, the working day code is 01; When it is a statutory working day and a natural rest day, the working day code is 02; When it is a statutory rest day, the working day code is 03; When it is a statutory holiday, the working day code is 04.
6. The air conditioning control method of a wireless communication macro base station according to claim 3, characterized in that: The step of obtaining temperature information and obtaining a temperature code includes: Get temperature information and calculate the average temperature and effective temperature difference: T eff =min(|T-24|,|T-12|) Where: T is the average temperature in degrees Celsius, T eff is the effective temperature difference value; The effective temperature difference value is used as the temperature code.
7. The air conditioning control method of a wireless communication macro base station according to claim 3, characterized in that: The load prediction model is a neural network classification model.
8. The air conditioning control method of a wireless communication macro base station according to claim 1, characterized in that: Generating the target temperature of the air-conditioning system based on the average load rate specifically includes: obtaining the target temperature of the air-conditioning system by looking up a table based on the average load rate.
9. An air conditioning control device for a wireless communication macro base station, comprising a memory, a processor, and a program stored in the memory, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.
10. A storage medium having a program stored thereon, characterized in that: When the program is executed, the method according to any one of claims 1 to 8 is implemented.
