RRU power adjustment method and device based on C4.5 decision tree, and medium

Abstract

The invention provides an RRU power adjustment method and device based on a C4.5 decision tree, and a medium. The method comprises the following steps: collecting RRU historical state characteristic data; preprocessing the historical state feature data, and dividing the historical state feature data into a training set and a test set; a C4.5 decision tree model is constructed, and training and testing are completed through the training set and the testing set; generating a power adjustment scheme of the current RRU by using the trained C4.5 decision tree model and the state feature data of the current RRU; and performing real-time power adjustment on the RRU according to the generated power adjustment scheme. The power of the RRU can be adjusted in real time according to the current RRU state data, so that the RRU can better adapt to the current network environment and user requirements, and the network performance and the energy-saving effect are improved. Meanwhile, the stability and reliability of the network can be ensured by monitoring and adjusting the state of the RRU in real time.

Description

Technical Field

[0001] The present invention relates to the field of mobile communications, and particularly to a method, device, and medium for adjusting the power of an RRU based on a C4.5 decision tree. Background Art

[0002] In a mobile communication network, the energy consumption of an RRU accounts for the main part of the base station energy consumption. Traditional RRU power adjustment methods mainly rely on manual experience and trial and error, with low efficiency and difficulty in adapting to complex and changing network environments. Therefore, developing an intelligent RRU power adjustment method to improve network performance and energy-saving effects is an urgent problem to be solved currently. Summary of the Invention

[0003] Aiming at the problems existing in the prior art, a method, device, and medium for adjusting the power of an RRU based on a C4.5 decision tree are provided. A C4.5 decision tree model is trained using historical state feature data of the RRU, and then a power adjustment scheme for the current RRU is generated using this model and the current state data of the RRU.

[0004] A first aspect of the present invention proposes a method for adjusting the power of an RRU based on the C4.5 decision tree algorithm, including:

[0005] Collecting historical state feature data of the RRU, where the historical state feature data includes uplink TA, cell radius, IQ data volume per unit bandwidth, number of users per unit bandwidth, attach times, attach success rate, temperature, and power adjustment status;

[0006] Preprocessing the historical state feature data and dividing it into a training set and a test set;

[0007] Constructing a C4.5 decision tree model and completing training and testing through the training set and the test set;

[0008] Using the trained C4.5 decision tree model and the current state feature data of the RRU to generate a power adjustment scheme for the current RRU;

[0009] Performing real-time power adjustment on the RRU according to the generated power adjustment scheme.

[0010] As a preferred solution, the preprocessing includes: eliminating data that deviates from the mean by 3 times the standard deviation based on the 3σ principle.

[0011] As a preferred solution, the preprocessing further includes: filling missing values using time series linear interpolation.

[0012] As a preferred solution, the preprocessing further includes: discretizing continuous values.

[0013] As a preferred solution, the discretization process of continuous values specifically includes: assuming that there are m values for the continuous values, sorting them and taking the average of every two adjacent values, a total of m - 1 dividing points. Calculate the information gain when each of these m - 1 dividing points is used as a binary dividing point, and select the point with the maximum information gain as the binary discrete classification point for this continuous feature.

[0014] As a preferred solution, in the C4.5 decision tree model, the optimal splitting attribute is selected based on the gain ratio.

[0015] As a preferred solution, in the C4.5 decision tree model, first find the attributes with information gain higher than the average level from the candidate splitting attributes, and then select the attribute with the highest gain ratio from them.

[0016] As a preferred solution, the gain ratio calculation method includes:

[0017]

[0018] where D represents the current sample set, a represents a certain attribute among them, v represents the possible value of attribute a, and V represents the maximum value of a.

[0019] In the second aspect of the present invention, an electronic device is proposed, which includes a memory and a processor. A computer program corresponding to the RRU power adjustment method based on the C4.5 decision tree algorithm as described in the first aspect is stored on the memory and can be loaded and executed by the processor.

[0020] In the third aspect of the present invention, a computer-readable storage medium is proposed, on which computer program instructions are stored. When the program instructions are executed by the processor, they are used to implement the process corresponding to the RRU power adjustment method based on the C4.5 decision tree algorithm described in the first aspect.

[0021] Compared with the prior art, the beneficial effects of adopting the above technical solutions are as follows: The present invention can adjust the power of the RRU in real time according to the current RRU status data, enabling it to better adapt to the current network environment and user requirements, thereby improving network performance and energy-saving effects. At the same time, by real-time monitoring and adjusting the status of the RRU, the stability and reliability of the network can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flowchart of the RRU power adjustment method based on the C4.5 decision tree algorithm proposed by the present invention.

[0023] Figure 2 It is a flowchart of the intelligent power adjustment based on the C4.5 decision tree proposed by the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0024] To make the objectives, technical solutions and advantages of the present invention more clearly understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part rather than all of the embodiments of the present application.

[0025] All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application. Without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other arbitrarily. And although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0026] The terms "including" and any variations thereof in the specification and claims of the present application and the above-mentioned accompanying drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0027] "Multiple" in the present application may represent at least two, for example, it may be two, three or more, and the embodiments of the present application do not make limitations. In the technical solutions of the present application, the collection, dissemination, use, etc. of data all comply with the requirements of relevant national laws and regulations.

[0028] To solve the problems in the prior art, the embodiments of the present application propose an RRU power adjustment method based on the C4.5 decision tree algorithm, which can intelligently adjust the RRU power. Please refer to Figure 1 , and the specific solution is as follows:

[0029] Step 1: Collect the historical state characteristic data of the RRU.

[0030] In this embodiment, the collected historical state characteristic data of the RRU mainly includes uplink TA, cell radius, IQ data volume per unit bandwidth, number of users per unit bandwidth, attach times, attach success rate, temperature, power adjustment status, etc. These data can be obtained through the operator's network management system or other relevant tools.

[0031] Step 2: Preprocess the historical state characteristic data and divide it into a training set and a test set.

[0032] In this embodiment, the preprocessing mainly includes data cleaning, formatting, removal of outliers and missing values, continuous value processing, missing value preprocessing, etc. Preferably, the 3σ principle is used to eliminate data that deviates from the mean by 3 times the standard deviation, and the time series linear interpolation method is used to fill the missing values and discretize the continuous values.

[0033] In one embodiment, a specific continuous value discretization processing method is also given, including: assuming that the continuous value has m values, sorting them and taking the average value of every two adjacent values for a total of m-1 division points, respectively calculating the information gain when these m-1 division points are used as binary points, and selecting the point with the largest information gain as the binary discrete classification point of the continuous feature.

[0034] The preprocessed data is divided into training set and test set for subsequent model training and performance evaluation.

[0035] Step 3: Build a C4.5 decision tree model and complete training and testing through training sets and test sets.

[0036] In the ID3 decision tree algorithm, if all the data values in an attribute are different, for example, the IQ data volume of the RRU unit bandwidth in each row of the feature data extracted in this embodiment is different, then it is equivalent to generating a specific branch for each row, and the information gain calculated by this type of attribute will be very large. For example, if the ID3 decision tree algorithm is directly used in this embodiment, the information gain calculated by the IQ data volume under unit bandwidth is very large (0.998), which is much higher than other attributes. Such a decision tree obviously does not have the ability to generalize and cannot effectively predict new samples. In fact, the information gain criterion prefers attributes with a large number of possible values, in order to reduce the adverse effects that may be caused by this preference. This embodiment adopts the C4.5 decision tree model, which does not directly use information gain, but uses the gain ratio to select the optimal partition attribute. The specific calculation formula of the gain ratio is as follows:

[0037]

[0038] Among them, D represents the current sample set, a represents a certain attribute among them, v represents the possible values of attribute a, and V represents the maximum value of a. It can be seen from this calculation formula that the more possible values of attribute a (that is, the larger V is), the usually larger the value of IV(a) will be. It should be noted that the gain ratio criterion has a preference for attributes with fewer possible values. Therefore, in this embodiment, instead of directly selecting the candidate splitting attribute with the largest gain ratio, a heuristic method is used: first, find the attributes with information gain higher than the average level from the candidate splitting attributes, and then select the attribute with the highest gain ratio from them. By calculating the gain ratio, the gain ratio of the IQ data volume under the unit bandwidth is no longer significantly too large (that is, no longer significantly higher than other attributes), which is more in line with the actual situation.

[0039] During the training process of the C4.5 decision tree model, by selecting appropriate features, setting decision tree parameters, and performing cross-validation and other operations, the performance and generalization ability of the model are optimized. After training, a C4.5 decision tree model that can predict the RRU power adjustment is obtained. The training method is a conventional model training method, which will not be elaborated here.

[0040] To further explain the process of the C4.5 decision tree generation model, the following is combined with Figure 2 for illustration:

[0041] Decision branch 1: Through the C4.5 decision tree algorithm and the discrete processing of continuous variable values, calculate the attribute with the largest information gain ratio. In this embodiment, the calculated largest information gain ratio is the temperature attribute. Therefore, the temperature attribute is used as the first decision branch, as Figure 2 shown:

[0042] For temperature >= 86.5 degrees Celsius, the decision tree model tends to reduce the transmission power. For the opposite situation, it tends to increase the transmission power; uniformly, the left branch represents reducing the transmission power, and the right branch represents increasing the transmission power.

[0043] gini = 0.488 refers to the quality of the split and is always a number between 0.0 and 0.5, where 0.0 means that all samples get the same result, and 0.5 means that the split is exactly in the middle.

[0044] Decision branch 2: After decision branch 1 is determined, continue to calculate the largest information gain ratio while excluding the attribute of branch 1 (temperature). At this time, the calculated largest information gain ratio is the IQ data volume of the unit bandwidth, that is, the second branch on the left. At this time:

[0045] For the left samples = 120 samples, the IQ data volume of the unit bandwidth <= 283.6, it tends to reduce the transmission power, and for the opposite situation, it tends to increase the transmission power:

[0046] The principle of analyzing other decision tree branches in the example is similar and will not be elaborated here.

[0047] Using the generated decision tree model, we can predict faults in the current operating state of the RRU. For example, for the following RRU status data [120, 800, 421, 16, 42, 99.9%, 47], and the uplink TA (Time Advance) of 120 Ts, cell radius of 800 meters, IQ quantity per unit bandwidth of 421 Mbps, number of users per unit bandwidth of 16, attach times of 42, attach success rate of 99.9%, and temperature of 47 degrees Celsius for the RRU, inputting this data into the model indicates that the RRU tends to reduce its transmission power.

[0048] Step 4: Use the trained C4.5 decision tree model and the status feature data of the current RRU to generate a power adjustment plan for the current RRU. That is, input the status data of the current RRU into the model, and according to the output result of the model, the corresponding power adjustment suggestions can be obtained.

[0049] Step 5: Perform real-time power adjustment on the RRU according to the generated power adjustment plan. The adjusted RRU can better adapt to the current network environment and user requirements, thereby improving network performance and energy-saving effects. At the same time, by real-time monitoring and adjusting the status of the RRU, the stability and reliability of the network can be ensured.

[0050] The following introduces an embodiment of the electronic device of the present application, which can be used to execute the high-precision frequency offset estimation method in the above embodiments of the present application. For details not disclosed in the embodiment of the electronic device, please refer to the embodiments of the above method of the present application.

[0051] An electronic device according to an embodiment of the present application includes a memory and a processor, and a computer program corresponding to the RRU power adjustment method based on the C4.5 decision tree algorithm described in the first aspect is stored on the memory and can be loaded and executed by the processor.

[0052] This embodiment also proposes a computer system suitable for implementing the electronic device of the embodiment of the present application. The computer system includes a Central Processing Unit (CPU), which can perform various appropriate actions and processes according to the program stored in the Read-Only Memory (ROM) or the program loaded from the storage section into the Random Access Memory (RAM), such as executing the method described in the above embodiment. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM, and RAM are connected to each other via a bus. The Input / Output (I / O) interface is also connected to the bus.

[0053] The following components are connected to the I / O interface: an input section including a keyboard, a mouse, etc.; an output section including, for example, a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc. and a speaker; a storage section including a hard disk, etc.; and a communication section including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as required. A removable storage medium, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive as required so that the computer program read from it can be installed into the storage section as required.

[0054] Specifically, according to the embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section and / or installed from the removable storage medium. When the computer program is executed by the Central Processing Unit (CPU), various functions defined in the system of the present application are executed.

[0055] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0056] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in a flowchart or block diagram can represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0057] The units involved in the embodiments described in this application can be implemented in software or in hardware, and the described units can also be provided in a processor. In some cases, the names of these units do not constitute a limitation on the units themselves.

[0058] As another aspect, the present application also provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the RRU power adjustment method based on the C4.5 decision tree algorithm described in the above embodiments.

[0059] As another aspect, the present application also provides a computer-readable medium. The computer-readable medium can be included in the electronic device described in the above embodiments; it can also exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device implements the RRU power adjustment method based on the C4.5 decision tree algorithm described in the above embodiments.

[0060] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0061] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented in software or in a manner of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0062] For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to specific circumstances; the accompanying drawings in the embodiments are used to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0063] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

[0064] The foregoing is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. RRU power adjustment method based on C4.5 decision tree, characterized in that, Including: Collecting historical status feature data of the RRU, where the historical status feature data includes uplink TA, cell radius, IQ data volume per unit bandwidth, number of users per unit bandwidth, attach times, attach success rate, temperature, and power adjustment status; Preprocessing the historical status feature data and dividing it into a training set and a test set; Constructing a C4.5 decision tree model and completing training and testing through the training set and the test set; Generating a power adjustment scheme for the current RRU by using the trained C4.5 decision tree model and the status feature data of the current RRU; Performing real-time power adjustment on the RRU according to the generated power adjustment scheme.

2. The RRU power adjustment method based on the C4.5 decision tree according to claim 1, wherein The preprocessing includes: eliminating data that deviates from the mean by 3 times the standard deviation based on the 3σ principle.

3. The method for adjusting the RRU power based on the C4.5 decision tree according to claim 1 or 2, characterized in that The preprocessing further includes: filling missing values by using the time series linear interpolation method.

4. The RRU power adjustment method based on the C4.5 decision tree according to claim 1 or 2, characterized in that The preprocessing further includes: discretizing continuous values.

5. The method for adjusting the RRU power based on the C4.5 decision tree according to claim 4, characterized in that, The discretization processing of continuous values specifically includes: assuming that the continuous value has m values, sorting them and taking the average of every two adjacent values to obtain a total of m - 1 division points, calculating the information gain when each of these m - 1 division points is used as a binary division point, and selecting the point with the maximum information gain as the binary discrete classification point of this continuous feature.

6. The RRU power adjustment method based on the C4.5 decision tree according to claim 1, wherein In the C4.5 decision tree model, the optimal division attribute is selected based on the gain ratio.

7. The RRU power adjustment method based on the C4.5 decision tree according to claim 6, characterized in that In the C4.5 decision tree model, first find the attributes whose information gain is higher than the average level from the candidate division attributes, and then select the attribute with the highest gain ratio from them.

8. The RRU power adjustment method based on the C4.5 decision tree according to claim 6 or 7, characterized in that, The gain ratio calculation method includes: where D represents the current sample set, a represents a certain attribute among them, v represents the possible values of attribute a, and V represents the maximum value of a.

9. An electronic device, characterized in that, Including a memory and a processor, and a computer program capable of being loaded and executed by the processor is stored on the memory, corresponding to the RRU power adjustment method based on the C4.5 decision tree algorithm according to any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, they are used to implement the process corresponding to the RRU power adjustment method based on the C4.5 decision tree algorithm according to any one of claims 1 to 8.

Images