Base station energy saving method, base station and storage medium

Abstract

The embodiment of the invention provides a base station energy saving method, a base station and a storage medium, and belongs to the field of communication. The method comprises the following steps: acquiring historical load data of a base station, and determining a target service scene served by the base station according to the historical load data; obtaining a load prediction model corresponding to the target business scene from a preset load prediction model library; operating a load prediction model corresponding to the target service scene, and performing load prediction processing on the historical load data to obtain load prediction data of the base station; and determining an energy-saving time period and a target energy-saving strategy of the base station according to the load prediction data, and executing the target energy-saving strategy in the energy-saving time period. According to the method, the accuracy and efficiency of energy-saving configuration of the base station are improved.

Description

Technical Field

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

[0002] With the rapid development of communication technology, the current wireless communication network has the characteristics of high transmission rate and low latency, which brings many new experiences to users. Operators have gradually launched public network services for individuals (ToC) and private network services for industries (ToB). As an important part of the wireless communication network, the base station needs to run for a long time to ensure the stability and reliability of the wireless communication network. If effective energy-saving measures are not taken, it will have a great impact on energy consumption and environmental pollution, and the high energy consumption costs will also bring considerable economic pressure to operators. Summary of the invention

[0003] The embodiments of the present invention provide a base station energy saving method, a base station and a storage medium, aiming to improve the accuracy and efficiency of the energy saving configuration of the base station.

[0004] In a first aspect, an embodiment of the present invention provides a base station energy saving method, including:

[0005] Acquire historical load data of the base station, and determine a target service scenario served by the base station according to the historical load data;

[0006] Obtaining a load forecasting model corresponding to the target business scenario from a preset load forecasting model library, wherein the load forecasting model library includes different load forecasting models corresponding to different business scenarios;

[0007] Running a load forecasting model corresponding to the target service scenario, performing load forecasting processing on the historical load data, and obtaining load forecasting data of the base station;

[0008] The energy-saving time period and target energy-saving strategy of the base station are determined according to the load forecast data, and the target energy-saving strategy is executed within the energy-saving time period.

[0009] In a second aspect, an embodiment of the present invention further provides a base station, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the base station energy saving method as described in the first aspect is implemented.

[0010] In a third aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the base station energy saving method as described in the first aspect.

[0011] The embodiment of the present invention provides a base station energy-saving method, a base station and a storage medium. The embodiment of the present invention determines the target business scenario served by the base station based on the historical load data of the base station, and obtains the load prediction model corresponding to the target business scenario from a preset load prediction model library, and then runs the load prediction model corresponding to the target business scenario, performs load prediction processing on the historical load data to obtain the load prediction data of the base station, and determines the energy-saving time period and target energy-saving strategy of the base station according to the load prediction data, and executes the target energy-saving strategy within the energy-saving time period. The whole process does not require human participation, and different load prediction models are used for different business scenarios, which greatly improves the accuracy and efficiency of the energy-saving configuration of the base station. In this way, the use of energy-saving configuration with high accuracy can greatly reduce the power consumption of the base station while meeting the business requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0013] Figure 1 is a schematic block diagram of the structure of a base station provided by an embodiment of the present invention;

[0014] Figure 2 It is a flowchart of a base station energy saving method provided by an embodiment of the present invention;

[0015] Figure 3 yes Figure 2 A schematic flow chart of a sub-step of the base station energy saving method;

[0016] Figure 4 is a flow chart of another base station energy saving method provided by an embodiment of the present invention;

[0017] Figure 5 yes Figure 2 A schematic flow chart of another sub-step of the base station energy saving method;

[0018] Figure 6 It is a schematic block diagram of the structure of a base station energy-saving device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0020] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0021] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0022] At present, the main method used for base station energy saving is: manually configure a fixed energy-saving time period. When the base station is in the energy-saving time period, if the current service load of the base station meets the threshold condition of the energy-saving strategy, the energy saving is turned on. However, the above base station energy-saving method has the following problems: 1. Since the configured energy-saving time period is fixed, but the service load of the base station changes in real time, there is a mismatch between the energy-saving time period and the service load of the base station, which will cause the base station to frequently switch between the energy-saving state and the non-energy-saving state, causing the radio resource control (Radio Resource Control, RRC) link to be repeatedly rebuilt, reducing the stability of the network and the user experience. 2. ToB scenarios are complex, the services are diverse, and customer demands are inconsistent. Different energy-saving time periods need to be manually configured for different service scenarios and customer demands, and the configuration efficiency of base station energy saving is low.

[0023] To solve the above problems, an embodiment of the present invention provides a base station energy-saving method, a base station and a storage medium. The method determines the target business scenario served by the base station through the historical load data of the base station, and obtains the load prediction model corresponding to the target business scenario from the preset load prediction model library, and then runs the load prediction model corresponding to the target business scenario, performs load prediction processing on the historical load data, obtains the load prediction data of the base station, and determines the energy-saving time period and target energy-saving strategy of the base station according to the load prediction data, and executes the target energy-saving strategy within the energy-saving time period. The whole process does not require manual participation, and different load prediction models are used for different business scenarios, which greatly improves the accuracy and efficiency of the energy-saving configuration of the base station. In this way, the energy-saving configuration with high accuracy can greatly reduce the power consumption of the base station while meeting the business requirements.

[0024] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0025] See also Figure 1 , Figure 1 It is a schematic block diagram of the structure of a base station provided by an embodiment of the present invention.

[0026] like Figure 1 As shown, the base station 100 includes a processor 101 and a memory 102, and the processor 101 and the memory 102 are connected via a bus 103, such as an I2C (Inter-integrated Circuit) bus.

[0027] Specifically, the processor 101 is used to provide computing and control capabilities to support the operation of the entire base station. The processor 101 can be a central processing unit (CPU), and the processor 101 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0028] Specifically, the memory 102 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0029] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the base station to which the embodiment of the present invention is applied. A specific base station may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0030] The processor 101 is used to run the computer program stored in the memory 102, and implement any one of the base station energy saving methods provided in the embodiments of the present invention when executing the computer program.

[0031] In some embodiments, the processor 101 is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0032] Acquire historical load data of the base station, and determine a target service scenario served by the base station according to the historical load data;

[0033] Obtaining a load forecasting model corresponding to the target business scenario from a preset load forecasting model library, wherein the load forecasting model library includes different load forecasting models corresponding to different business scenarios;

[0034] Running a load forecasting model corresponding to the target service scenario, performing load forecasting processing on the historical load data, and obtaining load forecasting data of the base station;

[0035] The energy-saving time period and target energy-saving strategy of the base station are determined according to the load forecast data, and the target energy-saving strategy is executed within the energy-saving time period.

[0036] In some embodiments, when the processor 101 determines the target service scenario served by the base station according to the historical load data, it is configured to implement:

[0037] Establishing a load change curve of the base station according to the historical load data, wherein the load change curve describes the relationship between the load of the base station and a time period;

[0038] According to the load change curve, the load change trend of the base station is determined, and according to the load change trend, the target service scenario served by the base station is determined.

[0039] In some embodiments, the load prediction data includes a predicted service load of the base station in a future time period, and the processor 101, when determining the energy-saving time period and the target energy-saving strategy of the base station according to the load prediction data, is used to implement:

[0040] When the predicted service load is less than a preset service load threshold, determining the future time period as an energy-saving time period of the base station;

[0041] The target energy-saving strategy of the base station in the energy-saving time period is determined according to the predicted service load of the base station in the energy-saving time period.

[0042] In some embodiments, after determining the energy-saving time period and the target energy-saving strategy of the base station according to the load forecast data and executing the target energy-saving strategy within the energy-saving time period, the processor 101 is further configured to implement:

[0043] Acquire the actual service load of the base station in the energy-saving time period;

[0044] When the actual service load is less than a preset service load threshold, migrating the user equipment connected to the base station to a neighboring base station;

[0045] After all user equipments accessing the base station are migrated to the neighboring base station, the target energy saving strategy of the base station is switched to a deep sleep strategy, and the deep sleep strategy is executed.

[0046] In some embodiments, the base station includes multiple cells, the historical load data includes the historical service load of each of the cells in different time periods, and the processor 101 is used to implement, when determining the energy-saving time period and target energy-saving strategy of the base station according to the load forecast data:

[0047] Determining a historical load change amount of each cell according to the historical service load of each cell in different time periods;

[0048] Determining a cell to be energy-saving from the plurality of cells according to a historical load change of each cell;

[0049] The energy-saving time period and target energy-saving strategy of the cell to be energy-saving are determined according to the load forecast data, and the target energy-saving strategy is executed on the cell to be energy-saving within the energy-saving time period.

[0050] In some embodiments, when the processor 101 determines the cell to be energy-saving from the plurality of cells according to the historical load change amount of each cell, it is configured to implement:

[0051] Obtain at least one of a user retention rate and a user mobility rate of each of the cells;

[0052] A cell to be energy-saving is determined from the plurality of cells according to at least one of a user residence rate and a user mobility rate of each cell and the historical load change amount.

[0053] In some embodiments, after the processor 101 determines the energy-saving time period and the target energy-saving strategy of the cell to be energy-saving according to the load forecast data, and controls the cell to be energy-saving to execute the target energy-saving strategy within the energy-saving time period, it is further used to implement:

[0054] Acquire the actual service load of the cell to be energy-saving during the energy-saving time period;

[0055] When the actual service load is less than a preset service load threshold, migrating the user equipment connected to the cell to be energy-saving to one or more cells other than the cell to be energy-saving among the multiple cells;

[0056] After the migration is completed, obtaining the networking type of the cell to be energy-saving, the radio remote unit to which it belongs, and the application mode of the radio remote unit;

[0057] According to the networking type of the cell to be energy-efficient, the corresponding remote radio unit and the application mode of the remote radio unit, the target energy-efficient strategy of the cell to be energy-efficient is adjusted, and the adjusted target energy-efficient strategy is executed.

[0058] In some embodiments, after the processor 101 determines the energy-saving time period and the target energy-saving strategy of the cell to be energy-saving according to the load forecast data, and controls the cell to be energy-saving to execute the target energy-saving strategy within the energy-saving time period, it is further used to implement:

[0059] In the case that there is an idle antenna in the cell to be energy-saving, if the idle antenna is not associated with a cell other than the cell to be energy-saving among the multiple cells, the channel corresponding to the idle antenna is turned off.

[0060] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the base station described above can refer to the corresponding process in the following base station energy saving method embodiment, and will not be repeated here.

[0061] The following will be combined Figure 1 The scenario in the embodiment of the present invention provides a detailed introduction to the base station energy saving method. It should be noted that Figure 1 The scenarios are only used to explain the base station energy saving method provided in the embodiment of the present invention, but do not constitute a limitation on the application scenarios of the base station energy saving method provided in the embodiment of the present invention.

[0062] See also Figure 2 , Figure 2 It is a flowchart of a base station energy saving method provided by an embodiment of the present invention.

[0063] like Figure 2 As shown, the base station energy saving method includes steps S101 to S104.

[0064] Step S101: Acquire historical load data of a base station, and determine a target service scenario served by the base station based on the historical load data.

[0065] In this embodiment, the historical load data includes the historical service load of the base station in different time periods in the past. The time granularity of different time periods can be the same or different. The past period can be the past month, the past half month or the past week. The embodiment of the present invention does not specifically limit this. For example, the historical load data includes the historical service load of the base station every hour in the past month. The historical service load may include the historical physical resource block (PRB) utilization rate, the historical radio resource control (RRC) maximum number of connections, etc. The target business scenarios include any business scenario in power, coal mining, manufacturing, port industry, rail transit, supermarkets, hospitals, and campuses.

[0066] In some embodiments, Figure 3 As shown, step S101 includes: sub-step S1011 to sub-step S1012.

[0067] Sub-step S1011, establishing a load change curve of the base station according to historical load data.

[0068] In this embodiment, the load change curve describes the relationship between the load of the base station and the time period. For example, the historical load data includes the service load of the base station in each of the multiple historical time periods, and the service load in each of the multiple historical time periods and each of the multiple historical time periods can be fitted by the least square method to obtain the load change curve of the base station. For example, the service load of each hour of the base station in the past month and each hour in the past month are fitted by the least square method to obtain the load change curve of the base station.

[0069] Sub-step S1012: determining the load change trend of the base station according to the load change curve, and determining the target service scenario served by the base station according to the load change trend.

[0070] In this embodiment, the load change trend of the base station is used to describe the change of the load of the base station in different time periods. The load change trend of the base station can be determined through the historical load data of the base station. Since the load change trend of the base station in different business scenarios is different, the target business scenario currently served by the base station can be accurately determined through the load change trend of the base station.

[0071] In some embodiments, determining the target service scenario served by the base station according to the load change trend may include: determining the similarity between the load change trend of the base station and each preset load change trend; determining the preset load change trend corresponding to the highest similarity as the target load change trend, and determining the service scenario corresponding to the target load change trend as the target service scenario. The preset load change trends corresponding to different service scenarios may be predetermined.

[0072] For example, the load change trend of the base station is P0, the preset load change trend corresponding to the power business scenario is P1, the preset load change trend corresponding to the coal mine business scenario is P2, the preset load change trend corresponding to the hospital business scenario is P3, and the preset load change trend corresponding to the campus business scenario is P4. Through calculation, we can get the similarity between the load change trend P0 and the load change trend P1, load change trend P2, load change trend P3 and load change trend P4 respectively. Since the similarity between the load change trend P0 and the load change trend P3 is the highest, the hospital business scenario corresponding to the load change trend P3 can be determined as the target business scenario served by the base station.

[0073] Step S102: Obtain a load forecasting model corresponding to a target business scenario from a preset load forecasting model library.

[0074] In this embodiment, the load forecasting model library includes different load forecasting models corresponding to different business scenarios. The load forecasting models corresponding to different business scenarios are obtained by pre-training a neural network model based on a plurality of training samples corresponding to different business scenarios, and the training samples include the first load data and the second load data corresponding to the business scenario. The neural network model includes but is not limited to a long short-term memory network (Long Short-Term Memory, LSTM), a convolutional neural network (Convolutional Neural Networks, CNN) and a recurrent neural network (Recurrent Neural Network, RNN), etc.

[0075] For example, for each business scenario, the load data of the base station in different time periods can be collected in advance to obtain multiple load data; based on the multiple load data of the base station, multiple training samples are generated, and one training sample includes the first load data as the model input and the second load data as the model label; the long short-term memory network is trained according to the multiple training samples to obtain the load prediction model corresponding to the corresponding business scenario. For example, the load data A of the base station in the time period 06:00 to 08:00 and the load data B in the time period 08:00 to 10:00 are combined as the first load data in the training sample, and the load data C of the base station in the time period 10:00 to 12:00 is determined as the second load data. In a similar manner, the load prediction models corresponding to different business scenarios can be obtained.

[0076] In some embodiments, training a long short-term memory network according to multiple training samples to obtain a load forecasting model corresponding to the corresponding business scenario may include: randomly selecting a training sample from multiple training samples as a target sample; inputting the first load data in the target sample into the long short-term memory network for load forecasting processing to obtain load forecasting data; determining the loss value of the long short-term memory network according to the load forecasting data and the second load data in the target sample; when the loss value is greater than or equal to a preset loss value, updating the parameters of the long short-term memory network, and returning to the step of randomly selecting a training sample from multiple training samples as the target sample, until the loss value of the long short-term memory network is less than the preset loss value or the number of training times reaches the set value.

[0077] In some embodiments, the base station may periodically collect the load data of the base station, and update the load prediction model corresponding to the target service scenario according to the collected load data. This embodiment can improve the accuracy of the load prediction model by updating and optimizing the load prediction model, thereby improving the accuracy of the load prediction data, so that the energy-saving time period and energy-saving strategy of the base station can be more accurately configured using accurate load prediction data.

[0078] Step S103: Run the load prediction model corresponding to the target business scenario, perform load prediction processing on the historical load data, and obtain the load prediction data of the base station.

[0079] In this embodiment, the load prediction data includes the predicted service load of the base station in a future time period. The future time period can be set based on actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the load prediction data includes the predicted service load of the base station in the next 1 hour or 2 hours.

[0080] Step S104: Determine the energy-saving time period and target energy-saving strategy of the base station according to the load forecast data, and execute the target energy-saving strategy within the energy-saving time period.

[0081] In this embodiment, the energy-saving time period and target energy-saving strategy of the base station can be adaptively configured through the load prediction data of the base station. The whole process does not require manual participation, which greatly improves the accuracy and efficiency of the energy-saving configuration of the base station. Among them, the target energy-saving strategy of the base station includes any energy-saving strategy of symbol shutdown, channel shutdown, carrier shutdown and deep sleep. The symbol shutdown includes basic shutdown and enhanced shutdown. The basic shutdown means that when the base station downlink symbol has no data to send, the corresponding power amplifier and other devices are turned off to achieve energy saving. The enhanced shutdown is based on the basic shutdown. When the base station is under load, the symbol aggregation, centralized transmission and other strategies are adopted to achieve energy saving and consumption reduction. Channel shutdown means that when the base station is under load, the corresponding uplink / downlink channels of the base station are turned off with different granularity to achieve energy saving. After the channel is closed, the broadcast and data channels can be compensated to improve coverage. Carrier shutdown means that the capacity layer is turned off on the premise of meeting the coverage requirements of the base station. Generally, the carrier is shut down regularly by setting the time to deal with the tidal effect. The base station can periodically execute the base station energy-saving method provided in the embodiment of the present invention, so that the energy-saving time period and energy-saving strategy of the base station can be periodically updated.

[0082] In some embodiments, the load prediction data includes the predicted service load of the base station in a future time period. According to the load prediction data, determining the energy-saving time period and the target energy-saving strategy of the base station may include: if the predicted service load of the base station in the future time period is less than a preset service load threshold, determining the future time period as the energy-saving time period of the base station; and determining the target energy-saving strategy of the base station in the energy-saving time period according to the predicted service load of the base station in the energy-saving time period. The preset service load threshold may be set based on actual conditions, and the embodiments of the present invention do not specifically limit this.

[0083] Exemplarily, according to the predicted service load of the base station in the energy-saving time period, determining the target energy-saving strategy of the base station in the energy-saving time period may include: determining the target load interval in which the predicted service load of the base station in the energy-saving time period is located; querying the mapping relationship between the pre-stored load interval and the energy-saving strategy to obtain the energy-saving strategy corresponding to the target load interval, and determining the energy-saving strategy corresponding to the target load interval as the target energy-saving strategy of the base station in the energy-saving time period. Among them, the mapping relationship between the pre-stored load interval and the energy-saving strategy can be set based on actual conditions, and the embodiment of the present invention does not specifically limit this.

[0084] In some embodiments, Figure 4 As shown, after step S104, the following steps are also included:

[0085] Step S105: Acquire the actual service load of the base station during the energy-saving period.

[0086] For example, if the energy-saving time period of the base station is from 00:30 to 02:30, then when the current time of the base station is 00:30, the actual service load of the base station in the time period from 00:30 to 02:30 can be obtained. It can be understood that, in the energy-saving time period, the actual service load of the base station in the energy-saving time period can be obtained regularly. For example, after the current time of the base station is 00:30, in the time period from 00:30 to 02:30, the actual service load of the base station in the energy-saving time period is obtained every 15 minutes. Among them, the actual service load includes the actual number of users, the actual PRB utilization rate, the actual maximum number of RRC connections, etc.

[0087] Step S106: When the actual service load is less than a preset service load threshold, the user equipment connected to the base station is migrated to a neighboring base station.

[0088] In this embodiment, the neighboring base station is a base station adjacent to the current base station. The preset service load threshold can be set based on actual conditions, and the embodiment of the present invention does not specifically limit this. For example, if the preset service load threshold is 100, and the actual service load of base station A in the energy-saving time period from 00:30 to 02:30 is 80, which is less than 100, then all 80 user devices connected to base station A can be migrated to base station B adjacent to base station A.

[0089] In some embodiments, when the actual service load is less than a preset service load threshold, migrating the user equipment accessing the base station to the neighboring base station may include: when the actual service load is less than the preset service load threshold, obtaining the target number of user equipment allowed to access each neighboring base station; when the maximum target number is greater than the actual number of users of the base station, migrating all the user equipment accessing the base station to the neighboring base station corresponding to the maximum target number. By migrating all the user equipment accessing the base station to the neighboring base station with the largest number of user equipment allowed to access, the stability and reliability of the service can be guaranteed.

[0090] Step S107: After all user equipments connected to the base station are migrated to the neighboring base station, the target energy saving strategy of the base station is switched to the deep sleep strategy, and the deep sleep strategy is executed.

[0091] In this embodiment, when the actual service load of the base station is less than the preset service load threshold, the user equipment connected to the base station is migrated to a neighboring base station, and after the migration is completed, the target energy saving strategy of the base station is switched to deep sleep, so that the power consumption of the base station can be further reduced.

[0092] In some embodiments, executing the deep sleep strategy may include: performing deep sleep on a remote radio unit (RRU) or an active antenna unit (AAU) in a base station. Performing deep sleep on an RRU or AUU in a base station means that only a power module and a preset communication interface of the RRU or AUU are retained, and other functional modules are turned off. The preset communication interface may be an enhanced common public radio interface (eCPRI) or a common public radio interface (CPRI).

[0093] In some embodiments, Figure 5 As shown, step S104 includes sub-steps S1041 to S1043.

[0094] Sub-step S1041: Determine the historical load change of each cell according to the historical service load of each cell in different time periods.

[0095] In this embodiment, the base station may include multiple cells, and the historical load data of the base station includes the historical service load of each cell in different time periods. The historical load change of each cell can be accurately determined by the historical service load of each cell in different time periods. Exemplarily, the maximum historical service load and the minimum historical service load of the cell in different time periods are determined, and the absolute difference between the maximum historical service load and the minimum historical service load is determined as the historical load change of the cell.

[0096] Sub-step S1042: determining a cell to be energy-saving from multiple cells according to the historical load change of each cell.

[0097] In this embodiment, the cell corresponding to the historical load change amount greater than the preset load change amount threshold can be determined as the cell to be energy-saving. The preset load change amount threshold can be set based on actual conditions, and the embodiment of the present invention does not specifically limit this. For example, the preset load change amount threshold is 500.

[0098] In some embodiments, determining the cell to be energy-saving from multiple cells according to the historical load change of each cell may include: obtaining at least one of the user residence rate and the user mobility rate of each cell; and determining the cell to be energy-saving from multiple cells according to at least one of the user residence rate and the user mobility rate of each cell and the historical load change. In this embodiment, the cell to be energy-saving can be accurately determined by at least one of the user residence rate and the user mobility rate of each cell and the historical load change.

[0099] The user retention rate of a cell is used to describe the ratio of the number of user devices that reside in the cell to the total number of users over a period of time, and the user mobility rate of a cell is used to describe the change of users in the cell over a period of time. For example, at time t1, the total number of users in the cell is N1, and at time t2, the total number of users in the cell is N2, and during the time period from time t1 to time t2, there are N3 user devices that always reside in the cell, then the user retention rate of the cell is N3 / N1, and the user mobility rate of the cell is |N2-N1| / N1.

[0100] In some embodiments, according to at least one of the user residence rate and the user mobility rate of each cell and the historical load change, determining the cell to be energy-saving from multiple cells may include: determining the cell corresponding to the historical load change greater than a preset load change threshold and the user residence rate less than the preset user residence rate threshold as the cell to be energy-saving. Or determining the cell corresponding to the historical load change greater than the preset load change threshold and the user mobility greater than the preset user mobility threshold as the cell to be energy-saving. The preset user residence rate threshold and the user mobility rate threshold may be set based on actual conditions, and the embodiments of the present invention do not specifically limit this.

[0101] Sub-step S1043: determining the energy-saving time period and target energy-saving strategy of the cell to be energy-saving according to the load forecast data, and executing the target energy-saving strategy for the cell to be energy-saving within the energy-saving time period.

[0102] In this embodiment, the load prediction data of the base station includes the predicted service load of each cell of the base station in a future time period. When the predicted service load of the cell to be energy-saving in the future time period is less than a preset service load threshold, the future time period is determined as the energy-saving time period of the cell to be energy-saving, and the target energy-saving strategy of the cell to be energy-saving is determined based on the predicted service load of the cell to be energy-saving in the energy-saving time period.

[0103] For example, the base station includes cell A, cell B, cell C and cell D. The historical load changes of cell A and cell C are greater than the preset load change threshold, and the historical load changes of cell B and cell D are less than the preset load change threshold. Therefore, cell A and cell C can be determined as cells to be energy-saving. The load prediction data of the base station includes the predicted service loads of cell A, cell B, cell C and cell D in the next 2 hours. The predicted service load of cell A in the next 2 hours is less than the preset service load threshold, and the predicted service load of cell C in the next 2 hours is greater than the preset service load threshold. Then, cell A needs to configure the energy-saving time period. The energy-saving time period of cell A is the next 2 hours. The base station controls cell A to execute the target energy-saving strategy in the next 2 hours, and cell C does not need to configure the energy-saving time period.

[0104] In some embodiments, after controlling the cell to be energy-saving to execute the target energy-saving strategy during the energy-saving period, the base station obtains the actual service load of the cell to be energy-saving during the energy-saving period; when the actual service load is less than the preset service load threshold, the user equipment accessing the cell to be energy-saving is migrated to one or more cells other than the cell to be energy-saving among multiple cells; after the migration is completed, the networking type of the cell to be energy-saving, the radio frequency remote unit to which it belongs, and the application mode of the radio frequency remote unit are obtained; according to the networking type of the cell to be energy-saving, the radio frequency remote unit to which it belongs, and the application mode of the radio frequency remote unit, the target energy-saving strategy of the cell to be energy-saving is adjusted, and the adjusted target energy-saving strategy is executed. In this embodiment, when the number of user equipment accessing the cell to be energy-saving is small, the user equipment accessing the cell to be energy-saving can be migrated to other cells, and a target energy-saving strategy with better energy-saving effect is adopted, which can further reduce the power consumption of the base station.

[0105] In some embodiments, adjusting the target energy saving strategy of the cell to be energy-saving according to the networking type of the cell to be energy-saving, the RF remote unit to which it belongs, and the application mode of the RF remote unit may include: querying the mapping relationship table between the networking type, the RF remote unit to which it belongs, the application mode of the RF remote unit, and the energy saving strategy according to the networking type of the cell to be energy-saving, the RF remote unit to which it belongs, and the application mode of the RF remote unit, to obtain the energy saving strategy corresponding to the networking type of the cell to be energy-saving, the RF remote unit to which it belongs, and the application mode of the RF remote unit; and adjusting the target energy saving strategy of the cell to be energy-saving to the queried energy saving strategy. Wherein, the networking type of the cell to be energy-saving includes a ring networking or a chain networking, etc., the application mode of the RF remote unit includes a normal mode, a merge mode, or a split mode, and when the application mode of the RF remote unit is the normal mode, in the case of a single carrier, one RF remote unit corresponds to one cell, and in the case of multiple carriers, one RF remote unit may also correspond to multiple cells. When the application mode of the RF remote unit is the merge mode, in the case of a single carrier, multiple RF remote units correspond to one cell, and in the case of multiple carriers, multiple RF remote units may also correspond to multiple cells. When the application mode of the radio remote unit is the split mode, one radio remote unit corresponds to multiple cells.

[0106] For example, the target energy-saving strategy of the cell to be energy-saving is carrier shutdown. Through the networking type of the cell to be energy-saving, the RF remote unit to which it belongs, and the application mode of the RF remote unit, the mapping relationship table between the networking type, the RF remote unit to which it belongs, the application mode of the RF remote unit and the energy-saving strategy is queried, and the energy-saving strategy with better energy-saving effect is deep sleep. The energy-saving strategy of the cell to be energy-saving is adjusted from carrier shutdown to deep sleep, and the RF remote unit corresponding to the cell to be energy-saving is put into deep sleep to reduce the power consumption of the base station.

[0107] In some embodiments, migrating user equipment accessing a cell to be energy-efficient to one or more cells among multiple cells other than the cell to be energy-efficient may include: obtaining a target number of user equipment allowed to access each candidate cell, the candidate cell being a cell other than the cell to be energy-efficient among multiple cells included in the base station; migrating user equipment accessing the cell to be energy-efficient to any candidate cell corresponding to a target number greater than the actual number of users of the cell to be energy-efficient; or when it is determined that the target number of each candidate cell is less than the actual number of users of the cell to be energy-efficient, accumulating the number of user accesses supported by each candidate cell to obtain the total number of user accesses; when the total number of user accesses is greater than the actual number of users of the cell to be energy-efficient, migrating user equipment accessing the cell to be energy-efficient to multiple candidate cells.

[0108] In some embodiments, after the cell to be energy-saving is controlled to execute the target energy-saving strategy during the energy-saving period, if there is an idle antenna in the cell to be energy-saving, if the idle antenna is not associated with a cell other than the cell to be energy-saving among multiple cells, the channel corresponding to the idle antenna is turned off. This embodiment can further reduce the power consumption of the base station and improve the energy-saving effect by further turning off the channel corresponding to the idle antenna that is not associated with the remaining cells after executing the target energy-saving strategy.

[0109] In some embodiments, the base station obtains the actual service load of each cell at preset intervals; if the actual service load of a cell exceeds a preset service load upper threshold, the cell in the energy-saving state is controlled to exit the energy-saving state, and the cell exiting the energy-saving state is used for load sharing. The preset time and service load upper threshold can be set based on actual conditions, and the embodiments of the present invention do not specifically limit this. This embodiment realizes dynamic switching of the cell entering and exiting energy-saving by monitoring the actual service load of each cell of the base station, thereby improving service stability.

[0110] See also Figure 6 , Figure 6 It is a schematic block diagram of the structure of a base station energy-saving device provided by an embodiment of the present invention.

[0111] like Figure 6 As shown, the base station energy saving device 200 includes:

[0112] A load acquisition module 210, configured to acquire historical load data of the base station;

[0113] A scenario determination module 220, configured to determine a target service scenario served by the base station according to the historical load data;

[0114] A model acquisition module 230 is used to acquire a load forecasting model corresponding to the target business scenario from a preset load forecasting model library, wherein the load forecasting model library includes different load forecasting models corresponding to different business scenarios;

[0115] The load prediction module 240 is used to run the load prediction model corresponding to the target service scenario, perform load prediction processing on the historical load data, and obtain the load prediction data of the base station;

[0116] The energy-saving configuration module 250 is used to determine the energy-saving time period and target energy-saving strategy of the base station according to the load forecast data, and execute the target energy-saving strategy within the energy-saving time period.

[0117] In some embodiments, the scene determination module 220 is further configured to:

[0118] Establishing a load change curve of the base station according to the historical load data, wherein the load change curve describes the relationship between the load of the base station and a time period;

[0119] According to the load change curve, the load change trend of the base station is determined, and according to the load change trend, the target service scenario served by the base station is determined.

[0120] In some embodiments, the load prediction data includes the predicted service load of the base station in a future time period, and the energy-saving configuration module 250 is further used to:

[0121] When the predicted service load is less than a preset service load threshold, determining the future time period as an energy-saving time period of the base station;

[0122] The target energy-saving strategy of the base station in the energy-saving time period is determined according to the predicted service load of the base station in the energy-saving time period.

[0123] In some embodiments, the base station energy saving device 200 further includes:

[0124] The load acquisition module 210 is further used to obtain the actual service load of the base station in the energy-saving time period;

[0125] A user migration module, configured to migrate user equipment connected to the base station to a neighboring base station when the actual service load is less than a preset service load threshold;

[0126] The sleep module is used to switch the target energy-saving strategy of the base station to a deep sleep strategy and execute the deep sleep strategy after all user equipments accessing the base station are migrated to the neighboring base station.

[0127] In some embodiments, the base station includes a plurality of cells, the historical load data includes the historical service load of each of the cells in different time periods, and the energy saving configuration module 250 is further used to:

[0128] Determining a historical load change amount of each cell according to the historical service load of each cell in different time periods;

[0129] Determining a cell to be energy-saving from the plurality of cells according to a historical load change of each cell;

[0130] The energy-saving time period and target energy-saving strategy of the cell to be energy-saving are determined according to the load forecast data, and the target energy-saving strategy is executed on the cell to be energy-saving within the energy-saving time period.

[0131] In some embodiments, the energy saving configuration module 250 is further used to:

[0132] Obtain at least one of a user retention rate and a user mobility rate of each of the cells;

[0133] A cell to be energy-saving is determined from the plurality of cells according to at least one of a user residence rate and a user mobility rate of each cell and the historical load change amount.

[0134] In some embodiments, the base station energy saving device 200 further includes:

[0135] The load acquisition module 210 is further used to obtain the actual service load of the cell to be energy-saving during the energy-saving period;

[0136] When the actual service load is less than a preset service load threshold, migrating the user equipment connected to the cell to be energy-saving to one or more cells other than the cell to be energy-saving among the multiple cells;

[0137] A user migration module, configured to obtain, after the migration is completed, the networking type of the cell to be energy-saving, the corresponding radio remote unit and the application mode of the radio remote unit;

[0138] The energy-saving adjustment module is used to adjust the target energy-saving strategy of the cell to be energy-saving according to the networking type of the cell to be energy-saving, the radio remote unit to which it belongs and the application mode of the radio remote unit, and execute the adjusted target energy-saving strategy.

[0139] In some embodiments, the base station energy saving device 200 further includes:

[0140] The channel shutoff module is used for shutting down the channel corresponding to the idle antenna if there is an idle antenna in the cell to be energy-saving and if the idle antenna is not associated with a cell other than the cell to be energy-saving among the multiple cells.

[0141] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the base station energy-saving device described above can refer to the corresponding process in the aforementioned base station energy-saving method embodiment, and will not be repeated here.

[0142] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any base station energy saving method provided in the description of the embodiment of the present invention.

[0143] The storage medium may be an internal storage unit of the base station described in the foregoing embodiment, such as a hard disk or memory of the base station. The storage medium may also be an external storage device of the base station, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the base station.

[0144] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0145] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0146] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A base station energy saving method, characterized in that: include: Acquire historical load data of the base station, and determine a target service scenario served by the base station according to the historical load data; Obtaining a load forecasting model corresponding to the target business scenario from a preset load forecasting model library, wherein the load forecasting model library includes different load forecasting models corresponding to different business scenarios; Running a load forecasting model corresponding to the target service scenario, performing load forecasting processing on the historical load data, and obtaining load forecasting data of the base station; The energy-saving time period and target energy-saving strategy of the base station are determined according to the load forecast data, and the target energy-saving strategy is executed within the energy-saving time period.

2. The base station energy saving method according to claim 1, characterized in that: The determining, according to the historical load data, a target service scenario served by the base station includes: Establishing a load change curve of the base station according to the historical load data, wherein the load change curve describes the relationship between the load of the base station and a time period; According to the load change curve, the load change trend of the base station is determined, and according to the load change trend, the target service scenario served by the base station is determined.

3. The base station energy saving method according to claim 1, characterized in that: The load prediction data includes a predicted service load of the base station in a future time period, and determining the energy-saving time period and target energy-saving strategy of the base station according to the load prediction data includes: In a case where the predicted service load is less than a preset service load threshold, determining the future time period as the energy-saving time period; The target energy-saving strategy of the base station in the energy-saving time period is determined according to the predicted service load of the base station in the energy-saving time period.

4. The base station energy saving method according to claim 1, characterized in that: The step of determining the energy-saving time period and the target energy-saving strategy of the base station according to the load forecast data, and executing the target energy-saving strategy within the energy-saving time period, further comprises: Acquire the actual service load of the base station in the energy-saving time period; When the actual service load is less than a preset service load threshold, migrating the user equipment connected to the base station to a neighboring base station; After all user equipments accessing the base station are migrated to the neighboring base station, the target energy saving strategy of the base station is switched to a deep sleep strategy, and the deep sleep strategy is executed.

5. The base station energy saving method according to any one of claims 1 to 3, characterized in that: The base station includes a plurality of cells, the historical load data includes the historical service load of each of the cells in different time periods, and determining the energy-saving time period and target energy-saving strategy of the base station according to the load prediction data includes: Determining a historical load change amount of each cell according to the historical service load of each cell in different time periods; Determining a cell to be energy-efficient from the plurality of cells according to a historical load change of each cell; The energy-saving time period and target energy-saving strategy of the cell to be energy-saving are determined according to the load forecast data, and the target energy-saving strategy is executed on the cell to be energy-saving within the energy-saving time period.

6. The base station energy saving method according to claim 5, characterized in that: The step of determining a cell to be energy-saving from a plurality of cells according to a historical load change amount of each cell includes: Obtain at least one of a user retention rate and a user mobility rate of each of the cells; A cell to be energy-saving is determined from the plurality of cells according to at least one of a user residence rate and a user mobility rate of each cell and the historical load change amount.

7. The base station energy saving method according to claim 5, characterized in that: After determining the energy-saving time period and the target energy-saving strategy of the cell to be energy-saving according to the load forecast data, and controlling the cell to be energy-saving to execute the target energy-saving strategy within the energy-saving time period, the method further includes: Acquire the actual service load of the cell to be energy-saving during the energy-saving time period; When the actual service load is less than a preset service load threshold, migrating the user equipment connected to the cell to be energy-saving to one or more cells other than the cell to be energy-saving among the multiple cells; After the migration is completed, obtaining the networking type of the cell to be energy-saving, the radio remote unit to which it belongs, and the application mode of the radio remote unit; According to the networking type of the cell to be energy-efficient, the corresponding remote radio unit and the application mode of the remote radio unit, the target energy-efficient strategy of the cell to be energy-efficient is adjusted, and the adjusted target energy-efficient strategy is executed.

8. The base station energy saving method according to claim 5, characterized in that: After determining the energy-saving time period and the target energy-saving strategy of the cell to be energy-saving according to the load forecast data, and controlling the cell to be energy-saving to execute the target energy-saving strategy within the energy-saving time period, the method further includes: In the case that there is an idle antenna in the cell to be energy-saving, if the idle antenna is not associated with a cell other than the cell to be energy-saving among the multiple cells, the channel corresponding to the idle antenna is turned off.

9. A base station, characterized in that: The base station includes a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection communication between the processor and the memory, wherein when the computer program is executed by the processor, the base station energy saving method according to any one of claims 1 to 8 is implemented.

10. A storage medium for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the base station energy saving method according to any one of claims 1 to 8.

Images