A method and device for energy saving control of base station

Abstract

The embodiment of the present invention provides a method and device for energy-saving control of a base station, the method comprising: determining a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship; using an energy-saving start-up threshold determination model based on a genetic algorithm to determine energy-saving start-up threshold data for the network cell group; determining whether each network cell in the network cell group meets the energy-saving start-up conditions according to the energy-saving start-up threshold data, and controlling the base station corresponding to the network cell that meets the energy-saving start-up conditions to enter an energy-saving state. The embodiment of the present application does not require manual setting and adjustment of energy-saving thresholds, can effectively reduce errors caused by manual operations, reduce the error rate, and can automatically determine appropriate energy-saving start-up threshold data for each network cell and update it in a timely manner, has high universality and flexibility, and in addition, does not need to rely on manual ability and experience, and has high accuracy.

Description

Technical Field

[0001] The present invention relates to the field of mobile communication technology, and in particular to a method and device for energy saving control of a base station. Background Art

[0002] The access capacity of a base station is set according to the peak traffic volume of the wireless access point. However, in reality, base stations are not always working at full capacity, and the communication capacity of base stations is often idle. Adjusting the communication capacity that a base station can provide according to the number of communication services helps save energy consumption of the base station. At present, there are three mainstream energy-saving technologies supported by the industry:

[0003] 1. Intelligent channel shutdown: For example, for 2T2R / 4T4R cells with bandwidth above 5MHz, during a fixed network time period, when there is no service or the service volume is low in the cell, some transmission channels are shut down, such as reducing 2T to 1T and 4T to 2T.

[0004] 2. Intelligent carrier frequency shutdown: For cells with the same coverage, when the sum of the carrier frequency load of the capacity cell and the carrier frequency load of the basic cell is small, the users on the carrier frequency of the capacity cell will be switched to the carrier frequency of the basic cell, and the carrier frequency of the capacity cell will be shut down. When the load of the basic cell exceeds the threshold, the carrier frequency of the capacity cell will be turned on.

[0005] 3. Symbol shutdown: For the RF module, turn off the power amplifier on symbols without data to save power consumption.

[0006] No matter which of the above energy-saving technologies is used, a threshold value (or called a threshold) needs to be set in advance, and then the index collected by the base station is compared with the threshold value, and the opening or closing of the energy-saving operation is determined according to the comparison result.

[0007] In the prior art, the threshold value is generally determined manually. The technicians determine the threshold value by observing the indicators of the base station equipment and combining experience. The threshold value set in this way has the problem of poor universality, that is, the threshold value set according to the situation of one base station may not be applicable to another base station, and the energy-saving threshold value will not change for a long time after being set, and cannot be flexibly adjusted according to the business load. In addition, it is heavily dependent on the ability and experience of the technicians. Once the technicians are insufficient in ability and experience, the threshold value set is not good or wrong, which will not only fail to achieve the purpose of energy saving, but also affect the normal operation of the base station.

[0008] In view of the above problems, it is necessary to provide a base station energy-saving solution with stronger universality and higher accuracy. Summary of the invention

[0009] The purpose of the embodiments of the present invention is to provide a method and device for energy saving control of a base station, so as to solve the problems that the energy saving scheme of the base station caused by the existing manual method of determining the energy saving threshold is poor in universality, prone to errors and low in accuracy.

[0010] In order to solve the above technical problems, the embodiment of the present invention is implemented as follows:

[0011] In a first aspect, an embodiment of the present invention provides a method for energy saving control of a base station, the method comprising:

[0012] Determine a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship;

[0013] Using a genetic algorithm-based energy-saving start threshold determination model to determine energy-saving start threshold data for the network cell group;

[0014] According to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell meeting the energy-saving start condition is controlled to enter the energy-saving state.

[0015] In a second aspect, an embodiment of the present invention provides an energy-saving control device for a base station, the device comprising:

[0016] A network cell group determination module, used to determine a network cell group according to multiple layers of network cells having the same coverage relationship;

[0017] An activation threshold determination module, configured to determine energy-saving activation threshold data for the network cell group by adopting an energy-saving activation threshold determination model based on a genetic algorithm;

[0018] The energy-saving control module is used to determine whether each network cell in the network cell group meets the energy-saving start-up conditions according to the energy-saving start-up threshold data, and control the base station corresponding to the network cell that meets the energy-saving start-up conditions to enter the energy-saving state.

[0019] In a third aspect, an embodiment of the present invention provides a computer device, comprising a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through a bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the steps of the energy-saving control method of the base station as described in the first aspect.

[0020] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy-saving control method of the base station as described in the first aspect are implemented.

[0021] The energy-saving control method and device of the base station in the embodiment of the present invention, by determining a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then using an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then according to the energy-saving start threshold data, determine whether each network cell in the network cell group meets the energy-saving start condition, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using an energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, can effectively reduce the errors caused by manual operation, reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, with high universality and flexibility, in addition, it does not need to rely on manual ability and experience, and has high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0023] Figure 1 A schematic diagram of a first flow chart of a base station energy saving control method provided by an embodiment of the present invention;

[0024] Figure 2 A second flow chart of the energy saving control method for a base station provided in an embodiment of the present invention;

[0025] Figure 3 A schematic diagram of decimal to binary conversion provided by an embodiment of the present invention;

[0026] Figure 4 A third flow chart of the energy saving control method of a base station provided in an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of a basic operation flow of a genetic algorithm provided by an embodiment of the present invention;

[0028] Figure 6 A schematic diagram of a crossover operation provided by an embodiment of the present invention;

[0029] Figure 7 A schematic diagram of a variation operation provided by an embodiment of the present invention;

[0030] Figure 8 A schematic diagram of the module composition of the energy-saving control device of the base station provided by an embodiment of the present invention;

[0031] Fig. 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0034] The existing method of manually setting thresholds to achieve base station energy saving has at least the following defects:

[0035] ① Relying on manual activation of base station energy saving wastes manpower and cannot avoid errors caused by tasks; ② The energy saving threshold is set through optimization experience and remains unchanged for a long time, so it cannot be flexibly adjusted according to the business load, nor can the optimal threshold be determined; ③ Network indicators and user perception are not considered: Existing power-saving technologies mainly consider the load of sectors with the same coverage (PRB utilization rate), and do not clearly consider the compensation cell drop rate, switching success rate, number of users, etc., and cannot timely evaluate the impact of energy saving on existing network indicators and user perception.

[0036] Starting from the demand of "energy saving and emission reduction, cost reduction and efficiency improvement", this application improves the traditional manual energy saving method into an AI intelligent implementation that integrates automatic data collection, intelligent algorithm judgment, automatic implementation of energy saving schemes, and automatic evaluation of effects and impacts, reducing manpower input and improving work efficiency; by combining base station configuration, base station scenario, network indicators, user perception, and alarm information, using genetic algorithms in machine learning technology, automatically generating thresholds for turning on energy-saving operations or thresholds for turning off energy-saving operations, thereby constructing an energy-saving model, and its energy-saving strategy is more suitable for the current network status of coexistence of multiple layers of networks; the traditional energy-saving method is limited in time, and gradually evolved into "all-weather energy saving", "dynamic energy saving" and "smart energy saving" for base stations, with longer energy saving time and more obvious energy saving effects; while saving energy, it ensures that network indicators are stable and user perception is not affected by multiple balances. The following is a more specific explanation in conjunction with the embodiments.

[0037] The embodiment of the present invention provides a method and device for energy-saving control of a base station, by determining a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then using an energy-saving start threshold determination model based on a genetic algorithm to determine energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter an energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using an energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter an energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, with high universality and flexibility, in addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0038] Figure 1 A first flow chart of a method for controlling energy saving of a base station provided in an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method comprises at least the following steps:

[0039] S102, determine a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship.

[0040] In view of the current network situation where multiple layers of networks coexist, the embodiment of the present application determines energy-saving threshold data (including energy-saving on threshold data and / or energy-saving off threshold data) based on network cell groups, wherein multiple layers of network cells with the same coverage relationship can be divided into one group, and these network cells can be network cells of different standards, such as FDD cells, TDD cells, etc.

[0041] S104, using an energy-saving start threshold determination model based on a genetic algorithm to determine energy-saving start threshold data for the above network cell group.

[0042] The energy-saving activation threshold determination model in the embodiment of the present application can be implemented using a genetic algorithm in machine learning technology, and the energy-saving activation threshold determination model is used to determine the energy-saving activation threshold data for the above-mentioned network cell group.

[0043] S106, determining whether each network cell in the network cell group meets the energy-saving start condition according to the energy-saving start threshold data, and controlling the base station corresponding to the network cell meeting the energy-saving start condition to enter the energy-saving state.

[0044] After determining the energy-saving start threshold data, the energy-saving start condition can be determined according to the energy-saving start threshold data, and then it is judged whether each network cell meets the energy-saving start condition. Next, the base station corresponding to the network cell that meets the energy-saving start condition can be controlled to enter the energy-saving state.

[0045] Among them, this step S106 can adopt any one of the energy-saving technologies among the channel intelligent shutdown technology, carrier frequency intelligent shutdown technology and symbol shutdown technology mentioned above in this application to control the base station corresponding to the network cell that meets the energy-saving start-up conditions to enter the energy-saving state. The embodiments of this application are not limited, and they can all achieve the purpose of the embodiments of this application and should be within the protection scope of this application.

[0046] In the embodiment provided by the present invention, by determining a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship, and then using a genetic algorithm-based energy-saving threshold determination model to determine energy-saving threshold data for the network cell group; then, according to the energy-saving threshold data, determine whether each network cell in the network cell group meets the energy-saving conditions, and control the base station corresponding to the network cell that meets the energy-saving conditions to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can use a genetic algorithm-based energy-saving threshold determination model to automatically determine the energy-saving threshold data, and control the base station corresponding to the network cell that meets the energy-saving conditions to enter the energy-saving state after detecting that the network cell meets the energy-saving conditions, without manually setting and adjusting the energy-saving threshold, can effectively reduce the errors caused by manual operation, reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving threshold data for each network cell and update it in time, with high universality and flexibility, in addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0047] Among them, Figure 2 As shown, the above S104, using a genetic algorithm-based energy-saving start threshold determination model to determine the energy-saving start threshold data for the above network cell group, may specifically include the following S1042-S1046:

[0048] S1042, collecting specified training data for the above-mentioned network cell group, wherein the training data includes comprehensive energy-saving index data of the above-mentioned network cell group, configuration feature data of the base station corresponding to the above-mentioned network cell group, scene feature data and expected energy-saving index data.

[0049] S1044, encoding the collected training data in a binary encoding manner to obtain binary-encoded training data;

[0050] S1046: Based on the binary-coded training data, a genetic algorithm-based energy-saving threshold determination model is trained to obtain energy-saving threshold data for the network cell group.

[0051] The comprehensive energy-saving index data may be comprehensively determined based on the energy-saving index data of each network cell in the network cell group. Specifically, the training data includes the comprehensive energy-saving index data of the network cell group. The collected and specified training data may include:

[0052] Collecting energy-saving index data of each network cell in the above-mentioned network cell group, wherein the above-mentioned energy-saving index data is data collected according to a preset period for each energy-saving index, and the above-mentioned energy-saving index includes at least one of physical resource block PRB utilization rate, connection rate, drop rate, switching success rate, number of radio resource control RRC users, and alarm information;

[0053] According to the energy-saving index data of each of the above-mentioned network cells, the comprehensive energy-saving index data of the above-mentioned network cell group is calculated, wherein the above-mentioned comprehensive energy-saving index data includes the comprehensive PRB utilization rate of the network cell group in the current period, the number of RRC users in the network cell group in the current period, the comprehensive PRB utilization rate of the reserved cell, the switching success rate of the reserved cell, the reserved cell disconnection rate and at least one of the alarm information.

[0054] The energy-saving index data include time period, cell PRB utilization rate, connection rate, drop rate, switching success rate, number of users, alarm information, etc.

[0055] The PRB utilization rate is mainly the average utilization rate of PDSCH PRB, which reflects the utilization of wireless resources in the communication system and provides a basis for whether the system needs to be expanded and the system algorithm optimization.

[0056] The connection rate is the ratio between the number of connected calls and the total number of user calls, which reflects the access capacity of the entire network cell group.

[0057] The call drop rate is the ratio between the number of dropped calls and the number of successfully established connections, which reflects the call drop situation of the entire network cell group.

[0058] The handover success rate is the ratio between the number of successful handovers and the total number of handovers, which reflects the handover situation within the entire network cell group.

[0059] The number of RRC users is the average number of access users in a network cell group.

[0060] The alarm information mainly includes: link disconnection alarm information and service shutdown alarm information.

[0061] How to calculate the above energy-saving index data for each network cell is common knowledge to those skilled in the art, and therefore will not be described again here.

[0062] After obtaining the energy-saving index data of each network cell in the group, these energy-saving index data can be used to calculate the comprehensive energy-saving index data of the entire network cell group. The specific example is as follows:

[0063] The comprehensive PRB utilization rate of the network cell group in the current period = the sum of the effective PRB utilization rate numerators in the network cell group / the sum of the effective PRB utilization rate denominators in the network cell group;

[0064] The number of radio resource control (RRC) users in the current period in the network cell group = the sum of the average number of RRC connections of all cells in the network cell group;

[0065] Comprehensive PRB utilization rate of reserved cells = sum of numerators of PRB utilization rates of reserved cells in the network cell group / sum of denominators of PRB utilization rates of reserved cells in the network cell group;

[0066] Reserved cell handover success rate = the sum of the numerators of the number of successful handovers of reserved cells in the network cell group / the sum of the denominators of the number of handover attempts of reserved cells in the network cell group;

[0067] Reserved cell disconnection rate = sum of the numerators of the reserved cell disconnection times in the network cell group / number of reserved cell connection attempts in the network cell group.

[0068] Alarm information = whether there are important alarms in each cell in the network cell group.

[0069] The above energy-saving index data needs to be collected multiple times in different time periods, such as once every 15 minutes. For example, the energy-saving index input can be collected after a period of time as shown in Table 1 below:

[0070] Table 1

[0071] frequency PRB Utilization Connection rate Drop rate Switching success rate Number of users Warning information 1 80％ 92％ 6％ 84％ 32 yes 2 75％ 84％ 3％ 81％ 34 no 3 86％ 76％ 7％ 90％ 55 yes 4 90％ 89％ 4％ 77％ 21 yes 5 55％ 82％ 2％ 94％ 15 no

[0072] In addition, the configuration feature data of the base station corresponding to the above-mentioned network cell group can be encoded according to the configuration information of the base station, and the above-mentioned configuration information includes information such as the base station BBU model, RRU model, MIMO mode, modulation and demodulation mode, and transmission power.

[0073] The above scene feature data can be obtained by encoding according to the scene information corresponding to the network cell group, and the above scene information includes information related to application scenarios such as schools, hospitals, subways, scenic spots, venues, high-speed railways, etc. The scene information can be encoded to obtain scene feature data to represent specific scenes, such as using 001 to represent a school and 002 to represent a hospital.

[0074] The configuration information and scenario information of the above base stations can be used as conditions for machine training. In the subsequent machine training process, there will be different optimal energy-saving thresholds for different scenarios and different base station configurations.

[0075] In addition, the above-mentioned expected energy-saving index data may include at least one of the expected value of energy-saving target, the expected value of user perception index, the expected value of business volume, the expected value of flow rate and the expected value of the number of users. The expected energy-saving index data is a set of optimal parameters for a set of power-saving algorithms (such as energy-saving activation algorithms). It may include the expected value of energy-saving target (i.e., the expected value of energy-saving target), such as the expectation that the base station can save 5 kWh of electricity per hour; it may also include the expected value of the impact on network indicators, such as the expected value of user perception index (i.e., the expected value of user perception index, including the expected value of delay, the expected value of packet loss rate, the expected value of disconnection rate, etc.), and the expected value of business volume (i.e., the expected value of business volume), the expected value of flow rate (i.e., the expected value of flow rate), and the expected value of the number of users (i.e., the expected value of the number of users).

[0076] After the training data is collected, it is necessary to encode the collected training data. For example, all energy-saving index data and expected values ​​(i.e. expected energy-saving index data) are encoded and input. The encoding method affects the efficiency of the program. After encoding, the initial groups are generated, and the individuals in these groups are also expressed in the form of codes.

[0077] Coding is the primary problem to be solved when applying genetic algorithms, and it is also a key step in designing genetic algorithms. In addition to determining the arrangement of individual parameter values, the encoding method also solves the decoding method when individuals transform from genotypes in the search space to phenotypes in the solution space. The encoding method also affects the operation methods of genetic operators such as crossover operators and mutation operators.

[0078] The binary coding method is the most common coding method in genetic algorithms. The coding symbol set it uses is a binary symbol set {0,1} composed of binary symbols 0 and 1. The individual genotype it constitutes is a binary coding symbol string.

[0079] In the embodiment of the present application, each parameter in the training data can be converted into binary code. For example, for a numeric parameter, the corresponding number can be converted from decimal to binary (see Figure 3 To understand, such as Figure 3 As shown, it shows a schematic diagram of decimal to binary conversion provided in an embodiment of the present application, which converts the decimal code "36" into the binary code "00100100"); for text-type parameters (such as alarm information), the corresponding parameters can be represented by specific binary codes, such as using 00 to represent the link break alarm information and 01 to represent the service withdrawal alarm information.

[0080] After the training data is collected and binary-encoded, the energy-saving start-up threshold determination model based on the genetic algorithm can be trained based on the binary-encoded training data to obtain the energy-saving start-up threshold data for the above-mentioned network cell group. In some modified implementations of the embodiments of the present application, please refer to Figure 4 The above S1046, based on the above binary coded training data, trains the energy-saving threshold determination model based on the genetic algorithm to obtain the energy-saving threshold data for the above network cell group, which may specifically include the following S1046-02, S1046-04:

[0081] S1046-02, initializing the energy-saving start threshold determination model to determine the objective function, initial group and energy-saving start algorithm corresponding to the energy-saving start threshold determination model, wherein the initial group includes a plurality of individuals, each of the individuals includes a combination of a plurality of threshold values ​​set for the comprehensive energy-saving index data;

[0082] S1046-04, substitute each of the above individuals in the above initial group and the above training data into the above energy-saving start-up algorithm to train the above energy-saving start-up threshold determination model, and through individual evaluation, determine the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the above objective function as the energy-saving start-up threshold data for the above network cell group.

[0083] Based on the above implementation, in some modified implementations, please continue to refer to Figure 4 The above method may further include the following S1046-06 to S1046-12:

[0084] S1046-06, if after training the initial population, no individual that can achieve the optimal solution of the objective function is obtained, then select excellent individuals from the initial population for replication;

[0085] S1046-08, performing a crossover operation and / or a mutation operation on the copied excellent individuals to generate new individuals;

[0086] S1046-10, determining a new group based on the generated new individuals;

[0087] S1046-12, based on the above-mentioned new group, the above-mentioned energy-saving threshold determination model is trained until the optimal solution of the above-mentioned objective function is reached, and the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the above-mentioned objective function is determined as the energy-saving threshold data for the above-mentioned network cell group.

[0088] The following describes the specific embodiments. In some examples, a genetic algorithm is used to generate a first power-saving model (ie, a power-saving start threshold determination model).

[0089] The mathematical programming model of genetic algorithm is as follows:

[0090]

[0091] Where X is the decision variable, maxf(X) is the objective function, X∈R, is the constraint condition, U is the basic space, and R is a subset of U. A solution X that satisfies the constraint condition is called a feasible solution, and the set R represents the set of all solutions that satisfy the constraint condition, which is called the feasible solution set.

[0092] Genetic algorithm is also a search heuristic algorithm used to solve optimization in the field of artificial intelligence in computer science. It is a type of evolutionary algorithm. This heuristic is usually used to generate useful solutions to optimization and search problems. Evolutionary algorithms were originally developed based on some phenomena in evolutionary biology, including inheritance, mutation, natural selection, and hybridization. If the fitness function is not properly selected, the genetic algorithm may converge to a local optimum instead of reaching the global optimum. Please refer to Figure 5 , the basic operation process of genetic algorithm is as follows:

[0093] a) Initialization: Set the evolutionary generation counter t=0, set the maximum evolutionary generation T, and randomly generate M individuals as the initial population P(0).

[0094] b) Individual evaluation: Calculate the fitness of each individual in the population P(t).

[0095] c) Selection operation: Apply the selection operator to the population. The purpose of selection is to directly pass on the optimized individuals to the next generation or to generate new individuals through pairing and crossover and then pass on to the next generation. The selection operation is based on the fitness evaluation of individuals in the population.

[0096] d) Crossover operation: Apply the crossover operator to the population. The crossover operator plays a core role in genetic algorithms.

[0097] e) Mutation operation: Apply the mutation operator to the population. That is, change the gene values ​​at certain loci of the individual strings in the population. After the population P(t) undergoes selection, crossover, and mutation operations, the next generation population P(t+1) is obtained.

[0098] f) Termination condition judgment: If t = T, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the calculation is terminated.

[0099] The genetic algorithm is applied to the method of the embodiment of the present application, and the relevant steps of generating the first power saving model (i.e., the energy saving start threshold determination model) are as follows:

[0100] Step 1), Initialization (this step corresponds to step S1046-02 above):

[0101] Set the evolution generation counter t = 0, and set the maximum number of generations T. The value of T is set according to actual needs.

[0102] Set the initial population P(0). A population includes multiple individuals. In the present invention, an individual is a combination of a series of threshold values. For example, an individual includes the following parameters: PRB low threshold, number of users low threshold, PRB high threshold, number of users high threshold, disconnection low threshold, handover high threshold, alarm information. The specific values of the individual parameters of each individual included in a population will vary.

[0103] When setting the initial population P(0), specific values need to be assigned to the individual parameters of each individual. When assigning values to the individual parameters, random values can be assigned, or values can be assigned according to experience.

[0104] During the initialization process, in addition to setting the initial population, the energy-saving algorithm (such as the energy-saving activation algorithm) also needs to be determined.

[0105] For the application scenario of base station communication, the base station needs to meet 6 conditions simultaneously to turn on the energy-saving mode, which are respectively:

[0106] (1) The comprehensive PRB utilization rate (maximum of upstream and downstream) of the network cell group in the current time period < PRB low threshold;

[0107] (2) The number of RRC users in the network cell group in the current time period < number of users low threshold;

[0108] (3) The maximum value of the comprehensive PRB utilization rate (maximum of upstream and downstream) in the next time period of the current time period within the historical preset number of days < PRB high threshold; where the historical preset number of days is one week, that is, the maximum value of the comprehensive PRB utilization rate in the next time period of the current time period within the historical 7 days < PRB high threshold;

[0109] (4) The maximum value of the number of RRC users in the next time period of the current time period within the historical preset number of days < number of users high threshold; where the historical preset number of days is one week, that is, the maximum value of the number of RRC users in the next time period of the current time period within the historical 7 days < number of users high threshold;

[0110] (5) The reserved cell KPI is good (disconnection rate < disconnection low threshold & handover success rate > handover high threshold) & no important alarms;

[0111] (6) The comprehensive PRB utilization rate (maximum of upstream and downstream) of the reserved cell < PRB high threshold.

[0112] These energy-saving conditions are recorded as the first energy-saving conditions. For these first energy-saving conditions, a corresponding first energy-saving algorithm (i.e., energy-saving activation algorithm) can be generated. The above-mentioned first energy-saving algorithm is based on the relevant judgment steps of the first energy-saving condition, such as judging the size of the comprehensive PRB utilization rate of the network cell group in the current period and the PRB low threshold. If it is less than, the first condition is satisfied; judging whether the number of RRC users in the network cell group in the current period is less than the low threshold of the number of users, if it is less than, the second condition is satisfied; judging whether the maximum value of the comprehensive PRB utilization rate (uplink and downlink maximum) in the next period of the current period within the historical preset days is less than the PRB high threshold, if it is less than, the third condition is satisfied; judging whether the maximum value of the RRC user number in the next period of the current period within the historical preset days is less than the high threshold of the number of users, if it is less than, the fourth condition is satisfied; judging whether the reserved cell KPI is good (drop rate <drop low threshold & switching success rate> switching high threshold) & no important alarm), if it is satisfied, the fifth condition is satisfied; judging whether the comprehensive PRB utilization rate (uplink and downlink maximum) of the reserved cell is less than the PRB high threshold, if it is less than, the sixth condition is satisfied.

[0113] In the first energy-saving algorithm, the judgment process of the above six conditions can be performed sequentially or in parallel.

[0114] Step 2), individual evaluation and selection (this step corresponds to the above step S1046-04):

[0115] The individual evaluation is to substitute the individual parameters contained in the individual into the first energy-saving algorithm, and evaluate the corresponding individual in combination with the actual parameter values ​​obtained by measurement and the objective function.

[0116] For example, the parameters of an individual in the initial group P(0) are substituted into the first energy-saving algorithm, such as a specific PRB low threshold in individual A is substituted into the "determining the size of the comprehensive PRB utilization rate of the network cell group in the current period and the PRB low threshold" of the energy-saving algorithm, and the PRB utilization rate of the network cell group in the current period actually measured is also substituted into the "determining the size of the comprehensive PRB utilization rate of the network cell group in the current period and the PRB low threshold" of the first energy-saving algorithm. After the other parameters in individual A are similarly substituted into the first energy-saving algorithm, the judgment result of whether the base station enters the energy-saving state can be obtained. The base station is operated according to this judgment result, and the operation effect of the base station is measured based on the objective function. If the global optimal value can be reached (the global optimal value is equal to the expected value, or close to the expected value), it is proved that this individual is needed, and the parameters of this individual (i.e., a set of threshold values ​​for the PRB low threshold, the user number low threshold, the PRB high threshold, the user number high threshold, the disconnection low threshold, the switching high threshold, and the alarm information) are output as the result (i.e., the energy-saving start threshold value) of the first power-saving model (i.e., the energy-saving start threshold determination model).

[0117] Each individual in the initial population P(0) is evaluated according to the above process. If no individual can achieve the optimal solution of the objective function, the parameters of the excellent individuals are selected and copied, and the proportion of these excellent individuals is increased while the proportion of poor individuals is reduced.

[0118] Whether individual parameters are excellent or not can be determined by the objective function.

[0119] For example, an individual contains two individual parameters (disconnection rate and number of users). When the disconnection rate is lower than 0.01, it has little impact on user indicators. When it is higher than 0.01, it will cause poor network perception. In this way, values ​​lower than 0.01 are considered to be excellent individual parameters. These parameters can be selected and copied to increase the sample ratio.

[0120] The objective function can be optimally defined by maximizing the energy-saving effect and user perception index. Maximizing the energy-saving effect means that the capacity layer cell is completely energy-efficient within the set energy-saving time. The energy-saving effect objective function can be represented by P(max)=Pa*Tx; where P(max) is the maximum value of the objective function, Pa is the no-load energy consumption of the device, and Tx is the maximum energy-saving time. The user perception function is represented by Pj=R1+Vs1+Vs2+T1+T2, where Pj represents the user perception comprehensive index function, R1 is the VOLTE wireless connection rate score, Vs1 is the HTTP large packet download rate score, Vs2 is the video service download rate score, T1 is the average delay score for instant messaging services, and T2 is the average delay score for gaming services. Different weights are assigned according to the importance of the indicators. In an example, the scoring method is shown in Table 2 below:

[0121] Table 2

[0122] Indicator Description Minimum Target value Maximum Weight Scoring Weighted score Volte connection rate 1 80 100 20％ A R1 Http large package download rate 1 80 100 25％ B Vs1 Average instant messaging delay 1 80 100 25％ C Vs2 Average latency of gaming services 1 80 100 15％ D T1 Video service download rate 1 80 100 15％ E T2

[0123] Step 3), perform "crossover" and "mutation" operations (this step corresponds to the above steps S1046-06 to S1046-10):

[0124] In the previous step, if no individual that can achieve the global optimal solution is found, in addition to selecting and copying the excellent individual parameters among the existing individuals, in this step, new individuals (offspring) need to be generated through operations such as crossover and mutation to obtain a new population.

[0125] When performing a crossover operation, the crossover operator is used to perform a crossover operation on the selected object to obtain a new individual. Figure 6 , which shows a schematic diagram of a cross operation provided by an embodiment of the present application, such as Figure 6As shown in the figure, after crossover operation of partial codes "3456" and "6921" in individuals parent1 and parent2, new individuals proto-child1 and proto-child2 are obtained. For details, please refer to Figure 6 Please understand and I will not elaborate on it here.

[0126] When performing a mutation operation, a mutation operator is used to perform a mutation operation on the selected object to obtain a new individual.

[0127] The mutation operation is to change the parameter value of a certain individual parameter group with a small probability. It is also a method of generating new individuals. Figure 7 , which shows a schematic diagram of a variation operation provided in an embodiment of the present application, such as Figure 7 As shown in the figure, the basic position mutation method is used to perform mutation operation. The specific operation process is: first determine the gene mutation position of each individual (such as Figure 7 Then, the original gene of the mutation point is inverted according to a certain probability, for example Figure 7 The second bit "0" of the third individual "101001" is inverted and changed to "1", generating a new individual "111001".

[0128] As mentioned above, the individual parameters in an individual are a series of threshold values. Through operations such as crossover and mutation, new threshold values ​​can be generated, thus providing more possibilities.

[0129] Step 4), re-substitute the individual parameters of the newly generated individuals into the energy-saving algorithm, and evaluate the newly generated individuals in combination with the actual parameter values ​​obtained by measurement and the objective function. (This step corresponds to the above step S1046-12)

[0130] The evaluation of the newly generated individuals is not substantially different from the description of step 2) above, and therefore will not be repeated here.

[0131] After the training phase is over, whether the local optimal solution of the objective function or the maximum evolutionary generation T is reached, the first power-saving model (i.e., the energy-saving threshold determination model) will output the energy-saving threshold values ​​for indicators such as PRB utilization, connection rate, drop rate, switching success rate, number of users, and alarms.

[0132] This type of energy-saving threshold value applies to the entire network cell group. In actual use, each cell in the network cell group compares the actually collected indicators with these energy-saving threshold values. If all the conditions for energy-saving activation are met, the base station will enter the energy-saving state. Correspondingly, the above step S106, based on the above energy-saving threshold data, determines whether each network cell in the above network cell group meets the energy-saving activation conditions, and controls the base station corresponding to the network cell that meets the energy-saving activation conditions to enter the energy-saving state, which may include:

[0133] Determine the energy-saving activation condition of each network cell in the network cell group according to the energy-saving activation threshold data;

[0134] Collecting real-time energy-saving index data of each of the above network cells;

[0135] Determine whether each of the above network cells meets the above energy-saving activation conditions according to the above real-time energy-saving index data;

[0136] Control the base stations corresponding to the network cells that meet the energy-saving start conditions to enter the energy-saving state.

[0137] The above is a relatively detailed description of the implementation method of controlling the base station corresponding to the network cell to enter the energy-saving state. In addition, when and under what circumstances to exit the energy-saving state is also provided by the embodiment of the present application. On the basis of any of the foregoing implementation methods, in some modified implementation methods, the above method further includes:

[0138] Using a genetic algorithm-based energy-saving shutdown threshold determination model to determine energy-saving shutdown threshold data for the above network cell group;

[0139] According to the energy-saving shutdown threshold data, it is determined whether each network cell in the network cell group meets the energy-saving shutdown conditions, and the base stations corresponding to the network cells meeting the energy-saving shutdown conditions are controlled to exit the energy-saving state.

[0140] Specifically, in order to avoid the "ping-pong" phenomenon, in the embodiment of the present application, once the corresponding indicator value in the base station does not meet the energy-saving start threshold value, the base station does not immediately exit the energy-saving state. Instead, the second power-saving model (i.e., energy-saving shutdown threshold determination model) is trained by collecting indicators such as PRB utilization, connection rate, drop rate, switching success rate, number of users, and alarms of each cell in the group, and combining the configuration information and scenario information of the base station itself.

[0141] After the training is completed, the second power saving model (ie, the energy saving shutdown threshold determination model) will output energy saving shutdown threshold values ​​for indicators such as PRB utilization, connection rate, drop rate, switching success rate, number of users, and alarms.

[0142] This type of energy-saving shutdown threshold value is applicable to the entire network cell group. In actual use, each cell in the network cell group compares the actually collected indicators with these energy-saving shutdown threshold values. If any of the energy-saving shutdown conditions is met, the base station will exit the energy-saving state.

[0143] Among them, the training process of the second power-saving model (i.e., the energy-saving closing threshold determination model) is generally similar to the training process of the first power-saving model (i.e., the energy-saving opening threshold determination model). For related content, please refer to the aforementioned exemplary description of the energy-saving opening threshold determination model for understanding, and some content will not be repeated. The main differences are:

[0144] 1. The energy-saving algorithms are different.

[0145] When training the second node model, the second energy-saving condition (i.e., energy-saving shutdown condition) is:

[0146] (1) The comprehensive PRB utilization rate of the network cell group in the current period (maximum of uplink and downlink) is greater than the PRB high threshold;

[0147] (2) The number of RRC users in the network cell group in the current period is greater than the upper threshold of the number of users;

[0148] (3) The cell KPI deteriorates (dropped calls > dropped calls upper threshold || handover success rate < handover lower threshold) || major alarm occurs).

[0149] These energy-saving conditions are recorded as second energy-saving conditions (ie, energy-saving shutdown conditions). According to these second energy-saving conditions (ie, energy-saving shutdown conditions), corresponding second energy-saving algorithms (ie, energy-saving shutdown algorithms) can be generated.

[0150] The above-mentioned second energy-saving algorithm is based on the relevant judgment steps of the second energy-saving condition (i.e., the energy-saving shutdown condition), such as judging the size of the comprehensive PRB utilization rate of the network cell group in the current period and the PRB high threshold. If it is greater, the first condition is met; judging whether the number of RRC users in the network cell group in the current period is greater than the high threshold of the number of users. If it is greater, the second condition is met; judging whether the reserved cell KPI has deteriorated (disconnected line>disconnected line high threshold||switching success rate<switching low threshold)||important alarm occurs), if it has deteriorated, the third condition is met.

[0151] In the second energy-saving algorithm, the judgment process of the above three conditions can be performed sequentially or in parallel.

[0152] 2. Individual parameters are different among individuals

[0153] Since the meanings of the relevant thresholds involved in the second energy-saving condition (ie, the energy-saving shut-off condition) are different, the meanings of the individual parameters in the individual are also different.

[0154] For example, when training the second node model, the individual parameters of the individual no longer represent the PRB low threshold, the user number low threshold, the disconnection low threshold, the switching high threshold, and the alarm information, but represent the PRB high threshold, the user number high threshold, the disconnection high threshold, the switching low threshold, the alarm and other information.

[0155] The energy-saving control method of the base station in the embodiment of the present invention determines a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then uses an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using the energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, which has high universality and flexibility. In addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0156] Based on any of the above implementations, in some modified implementations, energy-saving control of the base station may be implemented by the following steps:

[0157] First, the first power-saving model (i.e., energy-saving threshold determination model) is trained by collecting indicators such as the physical resource block (PRB) utilization rate, connection rate, drop rate, switching success rate, number of users, and alarms of each cell in the group, and combining the base station's own configuration information and scenario information.

[0158] After the training is completed, the first power saving model (ie, the energy saving threshold determination model) will output energy saving threshold values ​​for indicators such as PRB utilization, connection rate, drop rate, switching success rate, number of users, and alarms.

[0159] This type of energy-saving threshold applies to the entire network cell group. In actual use, each cell in the network cell group compares the actually collected indicators with these energy-saving thresholds. If all the conditions for energy-saving are met, the base station will enter the energy-saving state.

[0160] Similarly, by collecting the PRB utilization rate, connection rate, drop rate, handover success rate, number of users, alarms and other indicators of each cell in the group, and combining the configuration information and scenario information of the base station itself, the second power saving model (i.e., energy saving shutdown threshold determination model) is trained.

[0161] After the training is completed, the second power saving model (ie, the energy saving shutdown threshold determination model) will output energy saving shutdown threshold values ​​for indicators such as PRB utilization, connection rate, drop rate, switching success rate, number of users, and alarms.

[0162] This type of energy-saving shutdown threshold value is applicable to the entire network cell group. In actual use, each cell in the network cell group compares the actually collected indicators with these energy-saving shutdown threshold values. If all energy-saving shutdown conditions are met, the base station will exit the energy-saving state.

[0163] The energy saving control method of the base station provided by the embodiment of the present invention can also achieve at least the following beneficial effects:

[0164] The present invention makes up for the defects of traditional energy-saving methods such as small application scope, many restrictive factors, and incomplete consideration, and has the following advantages in achieving energy saving:

[0165] (1) Wider application scope: Energy saving can be implemented for base stations covering multiple layers of networks;

[0166] (2) Based on the machine learning algorithm, the energy-saving strategy is dynamically allocated, and the parameters such as the cell network indicators and user perception are comprehensively evaluated. In combination with the application scenario, through the continuous iteration of the genetic algorithm, a threshold close to the expected value is finally obtained, which is more excellent in energy-saving effect. At the same time, it also avoids factors such as low stability caused by human operation.

[0167] The energy-saving control method of the base station provided in the embodiment of the present invention determines a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then uses an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using the energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, which has high universality and flexibility. In addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0168] Corresponding to the energy-saving control method of the base station provided in the above embodiment, based on the same technical concept, the embodiment of the present invention also provides an energy-saving control device of the base station, Figure 8 A schematic diagram of the module composition of the energy-saving control device of the base station provided in an embodiment of the present invention, wherein the energy-saving control device of the base station is used to execute Figure 1 The energy saving control method of the base station described in FIG. 7 is as follows: Figure 8 As shown, the energy-saving control device of the base station includes:

[0169] A network cell group determination module 802, configured to determine a network cell group according to multiple layers of network cells having the same coverage relationship;

[0170] The activation threshold determination module 804 is used to determine the energy-saving activation threshold data for the above network cell group by using the energy-saving activation threshold determination model based on the genetic algorithm;

[0171] The energy-saving control module 806 is used to determine whether each network cell in the network cell group meets the energy-saving start condition according to the energy-saving start threshold data, and control the base station corresponding to the network cell meeting the energy-saving start condition to enter the energy-saving state.

[0172] In an embodiment of the present invention, by determining a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship, and then using a genetic algorithm-based energy-saving threshold determination model to determine energy-saving threshold data for the network cell group; then, according to the energy-saving threshold data, determine whether each network cell in the network cell group meets the energy-saving conditions, and control the base station corresponding to the network cell that meets the energy-saving conditions to enter an energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can use a genetic algorithm-based energy-saving threshold determination model to automatically determine the energy-saving threshold data, and control the base station corresponding to the network cell that meets the energy-saving conditions to enter an energy-saving state after detecting that the network cell meets the energy-saving conditions, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving threshold data for each network cell and update it in time, with high universality and flexibility, in addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0173] Optionally, the above-mentioned opening threshold determination module 804 is specifically used to:

[0174] For the above network cell group, collecting specified training data, wherein the above training data includes comprehensive energy-saving index data of the above network cell group, configuration feature data of the base station corresponding to the above network cell group, scene feature data and expected energy-saving index data;

[0175] Encoding the collected training data in a binary encoding manner to obtain binary-encoded training data;

[0176] Based on the above binary-coded training data, the energy-saving start-up threshold determination model based on the genetic algorithm is trained to obtain the energy-saving start-up threshold data for the above network cell group.

[0177] Optionally, the above-mentioned opening threshold determination module is specifically used to:

[0178] Collecting energy-saving index data of each network cell in the above-mentioned network cell group, wherein the above-mentioned energy-saving index data is data collected according to a preset period for each energy-saving index, and the above-mentioned energy-saving index includes at least one of physical resource block PRB utilization rate, connection rate, drop rate, switching success rate, number of radio resource control RRC users, and alarm information;

[0179] According to the energy-saving index data of each of the above-mentioned network cells, the comprehensive energy-saving index data of the above-mentioned network cell group is calculated, wherein the above-mentioned comprehensive energy-saving index data includes the comprehensive PRB utilization rate of the network cell group in the current period, the number of RRC users in the network cell group in the current period, the comprehensive PRB utilization rate of the reserved cell, the switching success rate of the reserved cell, the reserved cell disconnection rate and at least one of the alarm information.

[0180] Optionally, the above-mentioned opening threshold determination module is specifically used to:

[0181] Initializing the energy-saving start threshold determination model to determine the objective function, initial group and energy-saving start algorithm corresponding to the energy-saving start threshold determination model, wherein the initial group includes a plurality of individuals, and each of the individuals includes a combination of a plurality of threshold values ​​set for the comprehensive energy-saving index data;

[0182] Substitute each of the above-mentioned individuals in the above-mentioned initial group and the above-mentioned training data into the above-mentioned energy-saving start-up algorithm to train the above-mentioned energy-saving start-up threshold determination model, and through individual evaluation, determine the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the above-mentioned objective function as the energy-saving start-up threshold data for the above-mentioned network cell group.

[0183] Optionally, the above-mentioned opening threshold determination module is further used for:

[0184] If no individual that can achieve the optimal solution of the objective function is obtained after training based on the initial population, then excellent individuals are selected from the initial population for replication;

[0185] After performing a crossover operation and / or a mutation operation on the copied excellent individuals, a new individual is generated;

[0186] Determine a new group based on the generated new individuals;

[0187] The energy-saving threshold determination model is trained based on the new group until the optimal solution of the objective function is reached, and the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the objective function is determined as the energy-saving threshold data for the network cell group.

[0188] Optionally, the energy-saving control module 806 is enabled, and is further used to:

[0189] Determine the energy-saving activation condition of each network cell in the network cell group according to the energy-saving activation threshold data;

[0190] Collecting real-time energy-saving index data of each of the above network cells;

[0191] Determine whether each of the above network cells meets the above energy-saving activation conditions according to the above real-time energy-saving index data;

[0192] Control the base stations corresponding to the network cells that meet the energy-saving start conditions to enter the energy-saving state.

[0193] Optionally, the above device further includes:

[0194] A shutdown threshold determination module, used to determine the energy-saving shutdown threshold data for the above network cell group using an energy-saving shutdown threshold determination model based on a genetic algorithm;

[0195] The energy-saving control module is used to determine whether each network cell in the above network cell group meets the energy-saving shutdown conditions according to the above energy-saving shutdown threshold data, and control the base stations corresponding to the network cells that meet the energy-saving shutdown conditions to exit the energy-saving state.

[0196] The energy-saving control device of the base station in the embodiment of the present invention determines a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then uses an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using the energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, which has high universality and flexibility. In addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0197] The energy-saving control device for a base station provided in an embodiment of the present invention can implement each process in the embodiment corresponding to the energy-saving control method for the above-mentioned base station, and will not be described again here to avoid repetition.

[0198] It should be noted that the energy-saving control device of the base station provided in the embodiment of the present invention and the energy-saving control method of the base station provided in the embodiment of the present invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned energy-saving control method of the base station, and the repeated parts will not be repeated.

[0199] Corresponding to the energy-saving control method of the base station provided in the above embodiment, based on the same technical concept, an embodiment of the present invention further provides a computer device, which is used to execute the energy-saving control method of the base station. Fig. 9 A schematic diagram of a computer device for implementing various embodiments of the present invention is shown in FIG. Fig. 9 As shown. The computer device may have relatively large differences due to different configurations or performances, and may include one or more processors 901 and memory 902, and the memory 902 may store one or more storage applications or data. Among them, the memory 902 can be a short-term storage or a persistent storage. The application stored in the memory 902 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the computer device. Furthermore, the processor 901 can be configured to communicate with the memory 902 to execute a series of computer executable instructions in the memory 902 on the computer device. The computer device may also include one or more power supplies 903, one or more wired or wireless network interfaces 904, one or more input and output interfaces 905, and one or more keyboards 906.

[0200] Specifically in this embodiment, the computer device includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the following method steps:

[0201] Determine a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship;

[0202] Using a genetic algorithm-based energy-saving start threshold determination model to determine energy-saving start threshold data for the above network cell group;

[0203] According to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell meeting the energy-saving start condition is controlled to enter the energy-saving state.

[0204] The computer device in the embodiment of the present invention determines a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then uses an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter the energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using the energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, which has high universality and flexibility, and in addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0205] The computer device provided in the embodiment of the present invention can implement each process in the embodiment corresponding to the energy-saving control method of the above-mentioned base station, and will not be described again here to avoid repetition.

[0206] It should be noted that the computer device provided in the embodiment of the present invention and the energy-saving control method of the base station provided in the embodiment of the present invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the energy-saving control method of the aforementioned base station, and the repeated parts will not be repeated.

[0207] Corresponding to the energy-saving control method of the base station provided in the above embodiment, based on the same technical concept, the embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the following method steps are implemented:

[0208] Determine a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship;

[0209] Using a genetic algorithm-based energy-saving start threshold determination model to determine energy-saving start threshold data for the above network cell group;

[0210] According to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell meeting the energy-saving start condition is controlled to enter the energy-saving state.

[0211] The computer-readable storage medium in the embodiment of the present invention determines a network cell group, wherein the network cell group includes multiple layers of network cells with the same coverage relationship, and then uses an energy-saving start threshold determination model based on a genetic algorithm to determine the energy-saving start threshold data for the network cell group; then, according to the energy-saving start threshold data, it is determined whether each network cell in the network cell group meets the energy-saving start condition, and the base station corresponding to the network cell that meets the energy-saving start condition is controlled to enter an energy-saving state. Compared with the traditional manual base station energy-saving threshold method, the present application scheme can automatically determine the energy-saving start threshold data using an energy-saving start threshold determination model based on a genetic algorithm, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter an energy-saving state after detecting that the network cell meets the energy-saving start condition, without manually setting and adjusting the energy-saving threshold, which can effectively reduce the errors caused by manual operation and reduce the error rate, and this automated control method can automatically determine the appropriate energy-saving start threshold data for each network cell and update it in time, which has high universality and flexibility, and in addition, it does not need to rely on manual ability and experience, and has high accuracy.

[0212] The computer-readable storage medium provided in the embodiment of the present invention can implement each process in the embodiment corresponding to the energy-saving control method of the above-mentioned base station, and will not be described again here to avoid repetition.

[0213] It should be noted that the computer-readable storage medium provided in the embodiment of the present invention and the energy-saving control method of the base station provided in the embodiment of the present invention are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned energy-saving control method of the base station, and the repeated parts will not be repeated.

[0214] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0215] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0216] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0217] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0218] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0219] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0220] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0221] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0222] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0223] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for energy saving control of a base station, characterized in that: The method comprises: Determine a network cell group, wherein the network cell group includes multiple layers of network cells having the same coverage relationship; Using a genetic algorithm-based energy-saving start threshold determination model to determine energy-saving start threshold data for the network cell group; Determine, according to the energy-saving start threshold data, whether each network cell in the network cell group meets the energy-saving start condition, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state; The adopting of the energy-saving start threshold determination model based on the genetic algorithm to determine the energy-saving start threshold data for the network cell group includes: For the network cell group, collecting specified training data, wherein the training data includes comprehensive energy-saving index data of the network cell group, configuration feature data of the base station corresponding to the network cell group, scene feature data and expected energy-saving index data; Encoding the collected training data in a binary encoding manner to obtain binary-encoded training data; Initializing the energy-saving start threshold determination model to determine the objective function, initial group and energy-saving start algorithm corresponding to the energy-saving start threshold determination model, wherein the initial group includes a plurality of individuals, each of which includes a combination of a plurality of threshold values ​​set for the comprehensive energy-saving index data; Substitute each of the individuals in the initial group and the binary-coded training data into the energy-saving start-up algorithm to train the energy-saving start-up threshold determination model, and through individual evaluation, determine the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the objective function as the energy-saving start-up threshold data for the network cell group.

2. The method according to claim 1, characterized in that The training data includes comprehensive energy-saving index data of the network cell group; The collecting of specified training data for the network cell group includes: For the network cell group, collecting energy-saving index data of each network cell in the network cell group, wherein the energy-saving index data is data collected according to a preset period for each energy-saving index, and the energy-saving index includes at least one of a physical resource block PRB utilization rate, a connection rate, a drop rate, a switching success rate, a number of radio resource control RRC users, and alarm information; According to the energy-saving index data of each network cell, the comprehensive energy-saving index data of the network cell group is calculated, wherein the comprehensive energy-saving index data includes the comprehensive PRB utilization rate of the network cell group in the current period, the number of RRC users in the network cell group in the current period, the comprehensive PRB utilization rate of the reserved cell, the switching success rate of the reserved cell, the disconnection rate of the reserved cell and at least one of the alarm information.

3. The method according to claim 1, characterized in that The method further comprises: If no individual that can achieve the optimal solution of the objective function is obtained after training according to the initial population, then selecting excellent individuals from the initial population for replication; After performing a crossover operation and / or a mutation operation on the copied excellent individuals, a new individual is generated; Determine a new group based on the generated new individuals; The energy-saving threshold determination model is trained based on the new group until the optimal solution of the objective function is reached, and the combination of multiple threshold values ​​corresponding to individuals that can achieve the optimal solution of the objective function is determined as the energy-saving threshold data for the network cell group.

4. The method according to claim 1, characterized in that: The determining, according to the energy-saving start threshold data, whether each network cell in the network cell group meets the energy-saving start condition, and controlling the base station corresponding to the network cell meeting the energy-saving start condition to enter the energy-saving state includes: Determining the energy-saving activation condition of each network cell in the network cell group according to the energy-saving activation threshold data; Collecting real-time energy-saving index data of each of the network cells; Determining whether each of the network cells meets the energy-saving activation condition according to the real-time energy-saving indicator data; Control the base stations corresponding to the network cells that meet the energy-saving start conditions to enter the energy-saving state.

5. The method according to claim 1, characterized in that The method further comprises: Using a genetic algorithm-based energy-saving shutdown threshold determination model to determine energy-saving shutdown threshold data for the network cell group; According to the energy-saving shutdown threshold data, it is determined whether each network cell in the network cell group meets the energy-saving shutdown condition, and the base station corresponding to the network cell meeting the energy-saving shutdown condition is controlled to exit the energy-saving state.

6. A base station energy-saving control device, characterized in that: The device comprises: A network cell group determination module, used to determine a network cell group according to multiple layers of network cells having the same coverage relationship; An activation threshold determination module, configured to determine energy-saving activation threshold data for the network cell group by adopting an energy-saving activation threshold determination model based on a genetic algorithm; An energy-saving control module is used to determine whether each network cell in the network cell group meets the energy-saving start condition according to the energy-saving start threshold data, and control the base station corresponding to the network cell that meets the energy-saving start condition to enter the energy-saving state; The opening threshold determination module is specifically used for: For the network cell group, collecting specified training data, wherein the training data includes comprehensive energy-saving index data of the network cell group, configuration feature data of the base station corresponding to the network cell group, scene feature data and expected energy-saving index data; Encoding the collected training data in a binary encoding manner to obtain binary-encoded training data; Initializing the energy-saving start threshold determination model to determine the objective function, initial group and energy-saving start algorithm corresponding to the energy-saving start threshold determination model, wherein the initial group includes a plurality of individuals, each of which includes a combination of a plurality of threshold values ​​set for the comprehensive energy-saving index data; Substitute each of the individuals in the initial group and the binary-coded training data into the energy-saving start-up algorithm to train the energy-saving start-up threshold determination model, and through individual evaluation, determine the combination of multiple threshold values ​​corresponding to the individuals that can achieve the optimal solution of the objective function as the energy-saving start-up threshold data for the network cell group.

7. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored in the memory to implement the energy-saving control method of the base station as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the energy-saving control method for a base station according to any one of claims 1 to 5 is implemented.

Images