WO2024078076A1 - 基站节能方法、设备及存储介质 - Google Patents

基站节能方法、设备及存储介质 Download PDF

Info

Publication number
WO2024078076A1
WO2024078076A1 PCT/CN2023/107310 CN2023107310W WO2024078076A1 WO 2024078076 A1 WO2024078076 A1 WO 2024078076A1 CN 2023107310 W CN2023107310 W CN 2023107310W WO 2024078076 A1 WO2024078076 A1 WO 2024078076A1
Authority
WO
WIPO (PCT)
Prior art keywords
energy
saving
load
cell
base station
Prior art date
Application number
PCT/CN2023/107310
Other languages
English (en)
French (fr)
Inventor
汪海波
龚和平
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2024078076A1 publication Critical patent/WO2024078076A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements

Definitions

  • the embodiments of the present disclosure relate to the field of communication technology, and in particular to a base station energy saving method, device and storage medium.
  • Multi-layer wireless network coverage means more base stations and equipment, which also means more energy consumption and cost. Therefore, under multi-layer network coverage, operators have an urgent need to reasonably save energy on base stations.
  • Energy saving has the following shortcomings: when the energy-saving cell enters energy saving, a fixed load threshold adjustment upper limit is generally adopted. Since the load threshold adjustment upper limit cannot be automatically adjusted as the environment of the energy-saving cell changes, the energy-saving effect of the base station is poor, resulting in a waste of base station resources.
  • the embodiments of the present disclosure provide a base station energy-saving method, device and storage medium, which can adaptively adjust the load threshold adjustment upper limit of the energy-saving cell according to the environment of the energy-saving cell, thereby improving the energy-saving effect of the base station.
  • the disclosed embodiment provides a base station energy saving method, comprising: if an energy-saving cell is in an energy-saving state, collecting base station information of the base station to which the energy-saving cell belongs; selecting a threshold adjustment action based on the base station information and a preset threshold adjustment action set; adjusting the load threshold of the energy-saving cell according to the threshold adjustment action, and obtaining new base station information of the base station after the load threshold adjustment; adjusting the load threshold of the energy-saving cell again according to the new base station information, and iteratively adjusting the load threshold of the energy-saving cell until a preset iteration termination condition is met, to obtain an upper limit of the load threshold adjustment of the energy-saving cell; and using the upper limit of the load threshold adjustment to control the energy-saving state of the energy-saving cell.
  • An embodiment of the present disclosure also provides a base station energy-saving device, which includes 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 steps of any one of the base station energy-saving methods provided in the description of the embodiment of the present disclosure are implemented.
  • An embodiment of the present disclosure also provides 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 steps of any base station energy saving method provided in the description of the embodiment of the present disclosure.
  • FIG1 is a schematic diagram of a flow chart of a base station energy saving method provided by an embodiment of the present disclosure
  • FIG2 is a schematic diagram of an energy-saving framework of a base station energy-saving method provided in an embodiment of the present disclosure
  • FIG3 is a schematic diagram of a first sub-flow diagram of a base station energy saving method provided by an embodiment of the present disclosure
  • FIG4 is a schematic diagram of a second sub-flow of the base station energy saving method provided in an embodiment of the present disclosure
  • FIG5 is a schematic diagram of a third sub-flow of the base station energy saving method provided in an embodiment of the present disclosure.
  • FIG6 is a schematic block diagram of the structure of a base station energy-saving device provided in an embodiment of the present disclosure.
  • the embodiments of the present disclosure provide a base station energy saving method, device and storage medium.
  • the processing method can be applied to a centralized network element of a base station, i.e., a centralized processing module, to generate an energy saving strategy of the base station, and to send the energy saving strategy to the base station via a gateway network element of the base station, to control the energy saving cell to enter energy saving, and to achieve energy saving of the base station.
  • Figure 1 is a schematic diagram of the flow of the base station energy saving method provided by the embodiment of the present disclosure
  • Figure 2 is a schematic diagram of the energy saving framework of the base station energy saving method provided by the embodiment of the present disclosure. As shown in Figures 1 and 2, the method includes the following steps S11-S15:
  • the base station information of the base station to which the energy-saving cell belongs is collected.
  • the base station information can be described in state S, that is, state S is the environmental information of the energy-saving cell.
  • the base station information includes the environmental information of the base station.
  • the environmental information includes the surrounding environment information of the energy-saving cell and the service indicators and configuration information of the base station corresponding to the energy-saving cell, including: 1) the surrounding environment information of the energy-saving cell, including the temperature, humidity and weather information of the environment where the base station is located; 2) date-related, including date information such as holidays and days of the week; 3) the energy-saving cell's own indicators and configuration, including the performance data (Performance Management, PM), configuration management data (Configuration Management, CM) and measurement report (Measurement Report, MR) of the energy-saving cell, wherein MR refers to the measurement report sent by the user to the network in the call state. Since the scenarios of each energy-saving cell are different, it is possible to achieve scenario-based cell energy saving, that is, to achieve energy saving of the cell according to the specific scenario of each energy-saving cell.
  • S12 According to the base station information, based on a preset threshold adjustment action set, select a threshold adjustment action.
  • a threshold adjustment action set is pre-set, i.e., a preset threshold adjustment action set, which includes threshold adjustment actions, and the threshold adjustment actions may be as follows: 1) increase the load threshold by two reference points; 2) increase the load threshold by one reference point; 3) keep the load threshold unchanged; 4) decrease the load threshold by one reference point; 5) decrease the load threshold by two reference points.
  • one reference point of the load threshold can be 1 for the number of users, and can be 1% for the uplink physical resource block (RPB) utilization and the downlink RPB utilization.
  • RPB physical resource block
  • the load threshold of the energy-saving cell is adjusted according to the threshold adjustment action, and the adjusted load threshold is used to control the energy-saving state of the energy-saving cell, thereby generating corresponding base station information, and obtaining new base station information of the base station after the load threshold adjustment.
  • the new base station information includes KPI evaluation indicators, and the new base station information page may include the content of the base station information.
  • the load threshold of the energy-saving cell is adjusted again according to the new base station information, and the reward corresponding to the threshold adjustment action can be determined according to the new base station information, wherein the reward describes the feedback on the threshold adjustment action, and the reward is the feedback of the environment on the threshold adjustment action after the threshold adjustment action is executed.
  • the composition of the reward may include two parts: 1) energy-saving duration and KPI indicator reward and punishment value, wherein the energy-saving duration may be read from the PM counter, for example, a day may be divided into 96 time scales with a time granularity of 15 minutes, and one minute of energy-saving duration is one minute, and the KPI indicator reward and punishment value is the score given by comparing the KPI evaluation indicator with the preset KPI load threshold, and the indicators used for KPI evaluation may include: 1) cell wireless connection rate Acc_ratio; 2) cell wireless drop rate Drop_ratio; 3) handover success rate Handout_ratio; 4) cell average rate dlAvg; 5) cell uplink average rate ulAvg.
  • the score of a single indicator may be shown in Table 1 below, which describes the relationship table between rewards and KPI indicators.
  • each indicator is as follows: 1) When the indicator is degraded and within a1% of the load threshold, it is -b1 points; 2) When the indicator is degraded and within a1%-a2% of the load threshold, it is -b2 points; 3) When the indicator is degraded and exceeds a2% of the load threshold, it is -b3 points; 4) When the indicator is not degraded and within a1% of the load threshold, it is c1 points; 5) When the indicator is not degraded and within a1%-a2% of the load threshold, it is c2 points; 6) When the indicator is not degraded and the difference with the load threshold exceeds a2% of the load threshold, it indicates that the energy-saving cell can fully bear the load, which is c3 points.
  • the sum of the scores of the indicators participating in the evaluation is used as the indicator evaluation score, and the sum of the indicator evaluation score and the energy-saving time score is used as the reward. It should be noted that the above examples are only used to illustrate the implementation of the embodiments of the present disclosure, and are not used to limit the implementation of the embodiments of the present disclosure.
  • a threshold adjustment action is selected again, for example, the threshold adjustment action selected again can be called a second threshold adjustment action.
  • a threshold adjustment action is selected again, that is, a second threshold adjustment action.
  • Qlearning in reinforcement learning
  • the Q function is updated. This step is skipped in the first round of adjustment.
  • the current environmental information state S' and reward R of the energy-saving cell are used to update the Q function.
  • S is the state of the previous round
  • A is the action taken in the previous round
  • ⁇ is the learning rate
  • ⁇ is the discount factor
  • the threshold adjustment action A is selected.
  • the threshold adjustment action can be selected from the preset threshold adjustment action set based on the ⁇ -greedy strategy, that is, the action is randomly selected with a probability of ⁇ , and the action with the largest value calculated by the Q function is selected with a probability of (1- ⁇ ).
  • the initial value of ⁇ can be 0.1.
  • the threshold adjustment action is selected again to adjust the load threshold of the energy-saving cell, and the above steps of adjusting the load threshold of the energy-saving cell according to the base station information are repeated until the preset iteration termination condition is met, and the load threshold adjustment upper limit of the energy-saving cell is obtained, that is, a process similar to that of obtaining the reward corresponding to the threshold adjustment action is adopted, and the reward corresponding to the second threshold adjustment action is determined according to the second threshold adjustment action, and then the action is selected according to the reward, and the corresponding reward is determined according to the action, and the step of iteratively adjusting the load threshold of the energy-saving cell by using the threshold adjustment action is performed, and it can decay at a rate of 1/the number of iterations as the periodic iteration, and the load threshold of the energy-saving cell is adjusted according to the selected threshold adjustment action until the preset
  • the base station information of the base station to which the energy-saving cell belongs is collected, and according to the base station information and based on the preset threshold adjustment action set, the threshold adjustment action is selected, and according to the threshold adjustment action, the load threshold of the energy-saving cell is adjusted, and the new base station information of the base station after the load threshold adjustment is obtained, and according to the new base station information, the load threshold of the energy-saving cell is adjusted again, and the load threshold of the energy-saving cell is iteratively adjusted until the preset iteration termination condition is met, and the load threshold adjustment upper limit of the energy-saving cell is obtained, and the load threshold adjustment upper limit is adopted to control the energy-saving state of the energy-saving cell.
  • the load threshold adjustment upper limit Since the load threshold adjustment upper limit fully considers the more comprehensive factors such as the energy-saving cell's own configuration, surrounding environment, and holiday business characteristics, the load threshold adjustment upper limit is adapted to the specific application environment of each energy-saving cell as much as possible to be the optimal load threshold. Compared with the method of adopting a unified and fixed load threshold upper limit in the traditional technology, the embodiment of the present disclosure can realize one energy-saving cell corresponding to one energy-saving strategy, and can improve the energy-saving effect of energy-saving cells.
  • Figures 2 and 3 is a schematic diagram of the first sub-flow of the base station energy saving method provided in the embodiment of the present disclosure. As shown in Figure 3, in this embodiment, before the energy-saving cell is in the energy-saving state, the following steps S31 to S34 are also included:
  • a wireless coverage area identified by a global cell identifier is called a cell, and one base station can correspond to multiple cells.
  • the cells are pre-configured as energy-saving cells and basic coverage cells.
  • the energy-saving cells describe cells that are configured to perform energy-saving tasks to achieve the energy-saving requirements of base station equipment.
  • the basic coverage cells describe cells that provide basic coverage of wireless networks. Basic coverage cells cannot enter the energy-saving state, are not used to perform energy-saving tasks, and are used to provide a backup service for wireless network communications.
  • the time is divided into different time periods according to the preset time granularity in advance, that is, the preset time period. For example, you can divide a day into 96 time periods according to the 15-minute time granularity, or you can divide it into different time periods of 30 minutes, 60 minutes, 90 minutes, etc.
  • the time granularity divides each day into different time periods.
  • the first predicted load of the energy-saving cell in the preset time period is first obtained.
  • the load carried by the energy-saving cell in the preset time period that is, the first predicted load
  • the first predicted load can be obtained, so as to evaluate whether the energy-saving cell can enter energy saving in the preset time period according to the first predicted load without affecting the user's use of the network, that is, while saving energy, it is guaranteed that the user's experience of using the network will not be deteriorated.
  • the load of the energy-saving cell can be predicted by load prediction modeling.
  • the load prediction modeling can be modeled using a time series prediction method, using the historical load data corresponding to each time period to predict the load corresponding to the future time period, i.e., the first predicted load.
  • the first predicted load includes indicators describing the network carrying capacity, such as the number of users, uplink RPB utilization, and downlink RPB utilization.
  • a second predicted load of the basic coverage cell in a preset time period is obtained.
  • the second predicted load describes the load that the basic coverage cell itself is predicted to bear in the preset time period.
  • the load that the basic coverage cell itself will bear in the preset time period i.e., the second predicted load, can be predicted based on a similar method to the above-mentioned method of predicting the first predicted load of the energy-saving cell in the preset time period.
  • the second predicted load can be obtained.
  • the load of the energy-saving cell can be directly converted into the load of the basic coverage cell. If the basic coverage cell and the energy-saving cell are of different standards, it is necessary to coordinate the load of the energy-saving cell to convert the load of the energy-saving cell into the load of the basic coverage cell. After the load of the energy-saving cell is transferred to the basic coverage cell, it is determined whether the basic coverage cell can carry the first predicted load based on the first predicted load and the second predicted load.
  • judging whether the basic coverage cell can bear the first predicted load according to the first predicted load and the second predicted load includes:
  • the preset load start threshold describes the load threshold that is turned on by the basic coverage cell when carrying the load transferred from the energy-saving cell;
  • performing load conversion on the first predicted load to obtain a first converted load includes:
  • the first predicted load is converted according to a first reference factor and a first uplink and downlink multiplexing factor to obtain a first converted load.
  • the first predicted load can be converted according to the first reference factor and the first uplink and downlink multiplexing factor to obtain a first converted load, wherein the first reference factor describes the factor of the energy-saving cell relative to the reference cell, the reference cell is a preset cell as a reference, and the first uplink and downlink multiplexing factor describes the factor of the uplink PRB resources and the downlink PRB resources of the energy-saving cell when multiplexing.
  • the load that the basic coverage cell itself will bear in a preset time period is predicted, i.e., the second predicted load.
  • the second predicted load can be converted according to the second reference factor and the second uplink and downlink multiplexing factor to obtain a second converted load, wherein the second reference factor describes the factor of the basic coverage cell relative to the reference cell, the reference cell is a preset cell used as a reference, and the second uplink and downlink multiplexing factor describes the factor of the uplink PRB resources and the downlink PRB resources of the basic coverage cell when they are multiplexed.
  • the preset load start threshold of the basic coverage cell is obtained, and the preset load start threshold can be converted into a third converted load according to the second reference factor and the second uplink and downlink multiplexing factor, wherein the preset load start threshold describes the load threshold that is turned on by the basic coverage cell when carrying the load transferred from the energy-saving cell.
  • the following formula (1) can be used for judgment. If the following formula (1) is satisfied, it is determined that the basic coverage cell can carry the first predicted load, and then it is determined that the energy-saving cell can enter energy-saving mode, and the base station controls the energy-saving cell to enter energy-saving mode. Otherwise, it is determined that the basic coverage cell cannot carry the first predicted load, and then it is determined that the energy-saving cell cannot enter energy-saving mode, and the base station does not control the energy-saving cell to enter energy-saving mode.
  • Formula (1) is as follows:
  • preLoad is the first predicted load of the energy-saving cell
  • preBaseLoad is the second predicted load carried by the basic coverage cell itself
  • baseThrd is the load start threshold of the basic coverage cell
  • multiple energy-saving cells can also be included
  • ⁇ is a factor of the cell relative to the reference cell, and the calculation formula is shown in the following formula (2).
  • the calculation is based on the following formula (2);
  • cellBw is the bandwidth of the cell, in RB;
  • scsCell is the scs of the cell, scs, which stands for sub-carrier space, is the subcarrier spacing, in kHz;
  • afla is the uplink and downlink multiplexing factor, and for the number of users, the load value is 1, and for the uplink RPB utilization and downlink PRB utilization load, the value is 1.
  • Formula (1) and formula (2) can be used to convert the first predicted load of the energy-saving cell into the load carried by the basic coverage cell, and determine whether the basic coverage cell can carry the first predicted load. Measure the load and control the energy-saving cell to enter energy saving in a preset time period.
  • the energy-saving methods include carrier energy saving, deep sleep energy saving, channel shutdown energy saving, and discrete transmission (DTX) energy saving.
  • the energy-saving method of each energy-saving cell can be pre-configured on the network management. If the basic coverage cell cannot carry the first predicted load, the energy-saving cell will not be controlled to enter energy saving in the preset time period.
  • the disclosed embodiment obtains the first predicted load of the energy-saving cell in a preset time period and the second predicted load of the basic coverage cell in the preset time period, and judges whether the basic coverage cell can bear the first predicted load according to the first predicted load and the second predicted load. If the basic coverage cell can bear the first predicted load, the energy-saving cell is controlled to enter energy saving in the preset time period. This not only realizes base station energy saving, but also realizes one energy-saving cell corresponding to one energy-saving strategy. Thus, according to the first predicted load under the multi-layer network of the energy-saving cell, the first predicted load is converted into the load of the basic coverage cell, so as to perform coordinated conversion and coordinated evaluation of loads between the energy-saving cell and the basic coverage cell.
  • the load transfer of energy-saving cells and the load bearing of basic coverage cells can ensure that after the energy-saving cells enter energy-saving mode, their original load can be borne by the basic coverage cells, thereby ensuring that the user experience of using the network will not be deteriorated while saving energy, and realizing energy saving at a flexible time according to the load of each energy-saving cell, thereby improving the flexibility of each energy-saving cell automatically entering energy saving and the accuracy of energy saving.
  • the embodiments of the present disclosure can not only realize "one energy-saving cell corresponds to one energy-saving strategy", different energy-saving cells correspond to different energy-saving strategies, but also can realize that an energy-saving cell adopts different energy-saving strategies in different preset time periods, thereby realizing dynamic adjustment of energy-saving strategies and personalized energy-saving strategies of energy-saving cells, and improving the efficiency and effect of base station energy saving.
  • controlling the energy-saving cell to enter energy saving in the preset time period includes:
  • whether the energy-saving cell can enter energy-saving in a preset time period is determined based on whether the basic coverage cell can carry the first predicted load. If the basic coverage cell cannot carry the first predicted load, it is determined that the energy-saving cell cannot enter energy-saving in the preset time period.
  • the basic coverage cell can carry the first predicted load, it is determined that the energy-saving cell can enter energy-saving in the preset time period, that is, the energy-saving cell starts to enter energy-saving at the starting time point of the preset time period, and based on the determination that the basic coverage cell can carry the first predicted load and the correspondence between the first predicted load and the preset time period, a coordinated decision time period corresponding to the energy-saving cell is generated, wherein the coordinated decision time period describes a time period in which a single energy-saving cell can enter energy-saving in a preset time period based on a coordinated evaluation of the energy-saving cell and the basic coverage cell, and the coordinated decision time period can be described using Bitmap1.
  • any four preset time periods are described as ⁇ 0, 1, 1, 0 ⁇ , where 0 describes that the energy-saving cell cannot enter energy-saving mode in the corresponding preset time period, 1 describes that the energy-saving cell can enter energy-saving mode in the corresponding preset time period, ⁇ 0, 1, 1, 0 ⁇ describes that the energy-saving cell cannot enter energy-saving mode in the first preset time period and the fourth preset time period, and can enter energy-saving mode in the second preset time period and the third preset time period.
  • ⁇ 0, 1, 1, 0 ⁇ describes whether the energy-saving cell can enter energy-saving mode in each corresponding preset time period, and ⁇ 0, 1, 1, 0 ⁇ not only describes the preset time period, but also describes whether the corresponding preset time period can enter energy-saving mode. Based on this, according to the determination that the basic coverage cell can carry the first predicted load and the corresponding relationship between the first predicted load and the preset time period, the coordinated decision time period corresponding to the energy-saving cell can be generated.
  • the upper limit of load threshold adjustment which can be the upper limit of load threshold adjustment of the energy-saving cell obtained based on reinforcement learning, and the upper limit of load threshold adjustment is the adaptive upper limit of load threshold obtained based on the base station environment, and generate the corresponding self-load decision time period of the energy-saving cell according to the first predicted load, the coordinated decision time period and the upper limit of load threshold adjustment, wherein the self-load decision time period describes the time period in which the energy-saving cell can enter energy saving in a preset time period based on the first predicted load of the energy-saving cell itself.
  • the energy-saving time period of the energy-saving cell is generated according to the coordinated decision time period and the self-load decision time period, and the energy-saving time period is used to control the energy-saving cell to enter energy saving, so as to realize base station energy saving.
  • the energy-saving time period describes the time history of the energy-saving cell to perform energy-saving tasks, that is, the energy-saving time period describes the time history of the energy-saving cell in energy saving.
  • the coordinated decision time period and the self-load decision time period are bitwise ANDed to generate the energy-saving time period for the energy-saving cell to enter energy-saving, output the energy-saving time period, and use the energy-saving time period to control the energy-saving cell to enter energy-saving.
  • the energy-saving cell can enter energy-saving if the following two conditions are met at the same time: 1) The first predicted load of the energy-saving cell between the multi-layer network meets the coordinated evaluation condition, that is, the basic coverage cell can bear the load transferred from the energy-saving cell; 2) The first predicted load of the energy-saving cell is less than or equal to the target energy-saving load threshold of the energy-saving cell, and the target energy-saving load threshold can be described by Threshold.
  • the energy-saving time period for the energy-saving cell to enter energy-saving can be generated by converting the coordinated decision time period and the self-load decision time period into binary respectively, and then taking the binary bitwise AND, and the energy-saving time period satisfies the above two conditions, wherein the bitwise AND is true only when the two numbers on the same position are both true, and false when one is false, wherein 1 is true and 0 is false, that is, the two numbers on the same position are only 1 when the same position is 1, otherwise 0 is taken, thereby determining that the energy-saving cell enters the energy-saving time period for energy-saving, and using the energy-saving time period to control the energy-saving cell to enter energy-saving.
  • the energy-saving time period is used to control the energy-saving cell to enter energy-saving mode.
  • the energy-saving time period can be sent to the network management database in the network management network element as an energy-saving parameter, the network management database is updated, and then sent to the base station corresponding to the energy-saving cell through the network management database, and the energy-saving parameter is used to control the energy-saving cell to perform energy-saving tasks, thereby saving energy and realizing base station energy saving.
  • the disclosed embodiment generates a collaborative decision time period and a self-load decision time period corresponding to an energy-saving cell, and based on the collaborative decision time period and the self-load decision time period, for example, bitwise ANDing the collaborative decision time period and the self-load decision time period is performed to generate an energy-saving time period for the energy-saving cell to enter energy-saving mode, thereby further achieving that each energy-saving cell saves energy while ensuring that the user experience of using the wireless network will not be deteriorated.
  • FIG5 is a schematic diagram of a third sub-flow of the base station energy saving method provided in an embodiment of the present disclosure.
  • the self-load decision time period corresponding to the energy-saving cell is generated according to the first predicted load, the coordinated decision time period and the load threshold adjustment upper limit, including:
  • the target energy-saving load threshold is a load threshold value that maximizes the energy-saving time of the energy-saving cell and minimizes the load threshold
  • a load threshold upper limit value is configured in advance for the load threshold of the energy-saving cell, that is, a preset load threshold value, that is, an energy-saving load threshold value, which describes the upper limit of the load threshold when the energy-saving cell enters energy saving.
  • the preset load threshold value can be configured through the network management, and the preset load threshold value is the configured original load threshold value. Then, the preset load threshold value of the energy-saving cell is obtained, so as to determine the range of load threshold adjustment, that is, the load threshold adjustment interval, according to the preset load threshold value configured on the network management and the upper limit of the load threshold adjustment obtained based on reinforcement learning, and find the optimal target load threshold value from the load threshold adjustment interval, that is, load threshold optimization.
  • Threshold cm is the preset load threshold value, that is, the energy-saving load threshold value configured on the network management
  • Threshold max is the load threshold value output by the load threshold based on adaptive reinforcement learning adjustment, that is, the upper limit of the load threshold adjustment.
  • Threshold ul Max(Threshold cm , Threshold max ), formula (4);
  • the energy-saving load threshold adjustment range of the cell that is, the load threshold adjustment interval, can be described as follows: Threshold init ⁇ Threshold ⁇ Threshold ul , formula (5);
  • the initial value of the load threshold adjustment interval is used as the starting point of the search.
  • the step size of the number of users can be 1.
  • the step size of other indicators can be 1%.
  • an iterative search is traversed upward to select the load threshold value that makes the energy-saving time of the energy-saving cell longest and the load threshold value smallest as the final energy-saving load threshold, that is, the target energy-saving load threshold.
  • the target energy-saving load threshold is the load threshold value that makes the energy-saving time of the energy-saving cell longest and the load threshold smallest.
  • the searched target energy-saving load threshold is compared with the first predicted load. If the first predicted load is greater than the target energy-saving load threshold, the preset time period corresponding to the first predicted load is determined, and the energy-saving cell cannot enter energy-saving mode. Otherwise, if the first predicted load is less than or equal to the target energy-saving load threshold, the preset time period corresponding to the first predicted load is determined, and the energy-saving cell can enter energy-saving mode. According to the correspondence between the first predicted load and the preset time period, the corresponding self-load decision time period of the energy-saving cell is generated.
  • the self-load decision time period describes the time period in which the energy-saving cell can enter energy-saving mode in the preset time period based on the first predicted load of the energy-saving cell itself.
  • the self-load decision time period can be described by Bitmap2, in which the load threshold and the load are the same objects, which are indicators such as the number of users, uplink RPB utilization, and downlink RPB utilization. Based on this, the target energy-saving load threshold can be compared with the first predicted load. In which, the self-load decision time period is both It describes the time period and whether the energy-saving cell can enter energy-saving mode during the preset time period.
  • the load threshold adjustment interval is ⁇ 1, 4 ⁇ , and 0 is used to describe that the energy-saving cell cannot enter energy-saving, and 1 is used to describe that the energy-saving cell can enter energy-saving
  • the collaborative decision time period is ⁇ 0, 1, 1, 0 ⁇ , it describes that the energy-saving cell cannot enter energy-saving in the first preset time period, can enter energy-saving in the second or third preset time period, and cannot enter energy-saving in the fourth preset time period, wherein the preset time period can be a time range divided according to a preset time granularity, for example, a time range divided according to a time granularity of 15 minutes.
  • the preset load threshold value that is, the load threshold load value of the gateway performance configuration uses ⁇ 1, 2, 3, 4 ⁇ to describe the upper limit of the load value of the energy-saving cell in each preset time period.
  • the load value of the first preset time period is 1, the load value of the second preset time period is 2, the load value of the third preset time period is 3, and the load value of the fourth preset time period is 4.
  • the step size for the number of users can be 1, and the step size of other load indicators can be 1%.
  • the load threshold adjustment range ⁇ 1, 4 ⁇ according to the first predicted load of the cell, traverse the iterative search upward and search 3 from ⁇ 0, 2, 3, 0 ⁇ .
  • the load threshold value with the longest value and the smallest load threshold value is used as the final energy-saving load threshold, that is, the target energy-saving load threshold.
  • the preset load threshold value uses ⁇ 1, 2, 5, 4 ⁇ to describe the upper limit of the load value of the energy-saving cell in each preset time period.
  • the load value of the first preset time period is 1, the load value of the second preset time period is 2, the load value of the third preset time period is 5, and the load value of the fourth preset time period is 4.
  • the step size for the number of users can be 1, and the step size of other indicators that meet the requirements can be 1%.
  • the load threshold adjustment range ⁇ 1, 4 ⁇ according to the first predicted load of the cell, traverse the iterative search upward and search 2 from ⁇ 0, 2, 5, 0 ⁇ .
  • the load threshold value with the longest value and the smallest load threshold value is used as the final energy-saving load threshold, that is, the target energy-saving load threshold.
  • the target energy-saving load threshold can also be used to control the energy-saving cell to enter energy-saving mode, that is, the target energy-saving load threshold is used as the threshold for the energy-saving cell to enter energy-saving mode, and the energy-saving cell can be controlled to enter energy-saving mode by sending the target energy-saving load threshold as an energy-saving parameter to the base station corresponding to the energy-saving cell, and using the energy-saving parameter to control the energy-saving cell to enter energy-saving mode.
  • the target energy-saving load threshold is obtained by adjusting the upper limit of the load threshold determined based on the preset base station information of the energy-saving cell, the target energy-saving load threshold fully considers the self-configuration, surrounding environment, holiday business characteristics and other comprehensive factors of the energy-saving cell, so that the target energy-saving load threshold is as optimal as possible, which can improve the energy-saving effect of the energy-saving cell.
  • the energy-saving time period and the target energy-saving load threshold can be used as energy-saving parameters to control energy-saving cells to save energy, so as to ensure that the energy-saving time of the energy-saving cells is the longest and the energy-saving load threshold is the smallest.
  • the target energy-saving load threshold can be close to the load of the energy-saving cells when saving energy, so that the energy-saving cells can enter energy-saving in time when the load is low and exit energy-saving in time when the load is high. While maximizing the energy-saving time, they can exit energy-saving in time when the load suddenly increases. This not only ensures that the user experience of using the wireless network will not deteriorate while saving energy, but also further improves the energy-saving effect of the energy-saving cells, thereby improving the efficiency of energy-saving cells.
  • the method further includes:
  • the energy-saving base station information after the energy-saving cell enters energy-saving, and determine whether the energy-saving base station information meets the preset Change conditions, wherein the energy-saving base station information describes the information of the base station when the energy-saving cell is in energy-saving;
  • the energy-saving base station information satisfies the preset change condition, obtaining the energy-saving load threshold adjustment upper limit corresponding to the load threshold of the energy-saving cell based on reinforcement learning according to the energy-saving base station information;
  • the energy-saving load threshold adjustment upper limit corresponding to the load threshold of the energy-saving cell is not obtained.
  • an energy-saving time period is used as an energy-saving parameter to form an energy-saving strategy, and the energy-saving strategy is sent to a base station to control the energy-saving cell to enter energy-saving.
  • the energy-saving time period and the target energy-saving load threshold are used as energy-saving parameters to form an energy-saving strategy to control the energy-saving cell to perform energy saving.
  • energy-saving base station information is obtained.
  • the energy-saving base station information describes the information of the base station when the energy-saving cell is in energy-saving.
  • the information of the base station can be a key performance indicator, i.e., a KPI indicator, and it is determined whether the energy-saving base station information meets a preset change condition.
  • the preset change condition can be a change in the KPI indicator, a change in the surrounding environment information of the energy-saving cell, etc.
  • the preset change condition can also be a comparison of the energy-saving base station information with the historical base station information.
  • the energy-saving base station information is obtained and compared with the historical base station information.
  • Historical base station information base station information is environmental information of the base station, base station information includes energy-saving base station information and historical base station information, energy-saving base station information describes the energy-saving environmental information of the base station, historical base station information describes the historical environmental information of the base station, and compares the energy-saving base station information with the historical base station information, so as to evaluate whether the environmental information of the base station has undergone significant changes.
  • the energy-saving base station information meets the preset change conditions, it is determined that the environment of the base station has undergone significant changes. According to the energy-saving base station information, based on reinforcement learning, the energy-saving load threshold adjustment upper limit corresponding to the load threshold of the energy-saving cell is obtained. If the energy-saving base station information does not meet the preset change conditions, it is determined that the environment of the base station has not undergone significant changes, and there is no need to re-obtain the load threshold adjustment upper limit corresponding to the load threshold of the energy-saving cell.
  • energy-saving base station information is obtained, and whether the environment of the base station has changed significantly is determined based on the energy-saving base station information. If the environment of the base station has changed significantly, the load threshold adjustment upper limit that fits the energy-saving environment of the energy-saving cell, that is, the energy-saving load threshold adjustment upper limit is re-acquired based on the energy-saving base station information, and energy-saving parameters such as the energy-saving time period and the target energy-saving load threshold are re-determined based on the energy-saving load threshold adjustment upper limit, and a new energy-saving strategy is determined to make the energy-saving strategy fit the actual energy-saving situation of the energy-saving cell.
  • the load threshold adjustment upper limit of the energy-saving cell can be dynamically adjusted based on the information of the base station, so that the load threshold adjustment upper limit matches the energy-saving environment of the energy-saving cell as much as possible, and the energy-saving load threshold of the energy-saving cell is adaptively adjusted according to the change of the base station information after the implementation of the energy-saving strategy, so as to avoid the load threshold adjustment interval of the energy-saving load threshold that is previously learned is no longer suitable for the energy-saving cell conditions, thereby affecting the energy-saving effect of the energy-saving cell and even deteriorating the key performance indicators of the wireless network.
  • FIG. 6 is a schematic block diagram of the structure of a base station energy-saving device provided in an embodiment of the present disclosure.
  • the base station energy-saving device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.
  • I2C Inter-integrated Circuit
  • the processor 301 is used to provide computing and control capabilities to support the operation of the entire base station energy-saving device.
  • the processor 301 can be a central processing unit (CPU), and the processor 301 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.
  • the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.
  • ROM read-only memory
  • the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.
  • FIG6 is merely a block diagram of a partial structure related to the embodiment of the present disclosure, and does not constitute a limitation on the base station energy-saving device to which the embodiment of the present disclosure is applied.
  • the specific server may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
  • the processor is used to run a computer program stored in the memory, and implement any one of the base station energy saving methods provided in the embodiments of the present disclosure when executing the computer program.
  • An embodiment of the present disclosure 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 the steps of any base station energy saving method provided in the description of the embodiment of the present disclosure.
  • the storage medium may be an internal storage unit of the base station energy-saving device described in the foregoing embodiment, such as a hard disk or memory of the base station energy-saving device.
  • the storage medium may also be an external storage device of the base station energy-saving device, 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 energy-saving device.
  • a plug-in hard disk such as a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc.
  • 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).
  • a 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.
  • 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.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本公开实施例提供了一种基站节能方法、设备及存储介质，属于通信技术领域。为解决传统技术中负荷门限调整上限不能随着节能小区所处环境的变化而自动调整的问题，方法通过节能小区处于节能状态时，采集节能小区所属基站的基站信息，根据基站信息，基于预设门限调整动作集合，选取门限调整动作，根据门限调整动作，将节能小区的负荷门限进行调整，并获取负荷门限调整后基站的新基站信息，根据新基站信息，再次调整节能小区的负荷门限，并迭代调整节能小区的负荷门限直至满足预设迭代终止条件，得到节能小区的负荷门限调整上限，并采用负荷门限调整上限，控制节能小区的节能状态。

Description

基站节能方法、设备及存储介质
相关申请的交叉引用
本申请基于2022年10月11日提交的发明名称为“基站节能方法、设备及存储介质”的中国专利申请CN202211243047.1，并且要求该专利申请的优先权，通过引用将其所公开的内容全部并入本申请。
技术领域
本公开实施例涉及通信技术领域，尤其涉及一种基站节能方法、设备及存储介质。
背景技术
随着通信技术的发展以及移动用户的急剧增长，运营商在无线网络建设的设备也日趋增多。随着5G等技术的快速发展和部署，无线的多层网络覆盖已经成为了无线网络覆盖的常态，例如2G网络、3G网络、4G网络及5G网络需同时进行覆盖。多层网络的覆盖意味着更多的基站和设备，也意味着更多的能耗和成本。因此，在多层网络覆盖下，合理的对基站进行节能对运营商有迫切的需求。
在运营商网络运营中，无线基站的能耗占了较大的比重，节能存在如下不足之处：节能小区进入节能，一般采用固定的负荷门限调整上限，由于负荷门限调整上限不能随着节能小区所处环境的变化而自动调整，导致基站的节能效果较差，存在基站资源的浪费。
发明内容
本公开实施例提供了一种基站节能方法、设备及存储介质，能够实现根据节能小区的环境自适应调整节能小区的负荷门限调整上限，从而提升基站的节能效果。
本公开实施例提供一种基站节能方法，包括：若节能小区处于节能状态，采集所述节能小区所属基站的基站信息；根据所述基站信息，基于预设门限调整动作集合，选取门限调整动作；根据所述门限调整动作，将所述节能小区的负荷门限进行调整，并获取所述负荷门限调整后所述基站的新基站信息；根据所述新基站信息，再次调整所述节能小区的负荷门限，并迭代调整所述节能小区的负荷门限直至满足预设迭代终止条件，得到所述节能小区的负荷门限调整上限；采用所述负荷门限调整上限，控制所述节能小区的节能状态。
本公开实施例还提供一种基站节能设备，所述基站节能设备包括处理器、存储器、存储在所述存储器上并可被所述处理器执行的计算机程序以及用于实现所述处理器和所述存储器之间的连接通信的数据总线，其中所述计算机程序被所述处理器执行时，实现如本公开实施例的说明书提供的任一项基站节能方法的步骤。
本公开实施例还提供一种存储介质，用于计算机可读存储，其特征在于，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现如本公开实施例的说明书提供的任一项基站节能的方法的步骤。
附图说明
为了更清楚地说明本公开实施例技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本公开实施例提供的基站节能方法的流程示意图；
图2为本公开实施例提供的基站节能方法的节能框架示意图；
图3为本公开实施例提供的基站节能方法的第一个子流程示意图；
图4为本公开实施例提供的基站节能方法的第二个子流程示意图；
图5为本公开实施例提供的基站节能方法的第三个子流程示意图；
图6为本公开实施例提供的一种基站节能设备的结构示意框图。
具体实施方式
下面将结合本公开实施例中的附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本公开实施例的一部分实施例，而不是全部的实施例。基于本公开实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本公开实施例保护的范围。
附图中所示的流程图仅是示例说明，不是必须包括所有的内容和操作/步骤，也不是必须按所描述的顺序执行。例如，有的操作/步骤还可以分解、组合或部分合并，因此实际执行的顺序有可能根据实际情况改变。
应当理解，在此本公开实施例的说明书中所使用的术语仅仅是出于描述特定实施例的目的而并不意在限制本公开实施例。如在本公开实施例的说明书和所附权利要求书中所使用的那样，除非上下文清楚地指明其它情况，否则单数形式的“一”、“一个”及“该”意在包括复数形式。
本公开实施例提供了一种基站节能方法、设备及存储介质。其中，所述处理方法可以应用于基站的集中式网元，即集中处理模块，生成基站的节能策略，并将节能策略经基站的网关网元下发至基站，控制节能小区进入节能，实现基站节能。
下面结合附图，对本公开实施例作详细说明。在不冲突的情况下，下述的实施例及实施例中的特征可以相互组合。
请参阅图1与图2，图1为本公开实施例提供的基站节能方法的流程示意图，图2为本公开实施例提供的基站节能方法的节能框架示意图。如图1与图2所示，该方法包括以下步骤S11-S15：
S11、若节能小区处于节能状态，采集所述节能小区所属基站的基站信息。
在一实施例中，若节能小区处于节能状态，采集节能小区所属基站的基站信息，基站信息可以采用状态S描述，即状态S为节能小区的环境信息，基站信息包括基站的环境信息，环境信息包括节能小区的周围环境信息与节能小区所对应基站的本身业务指标与配置信息，包括：1)节能小区的周围环境信息，包括基站所在环境的温度、湿度与天气等信息；2)日期相关，包括节假日与星期几等日期信息；3)节能小区自身指标与配置，包括节能小区的性能数据(Performance Management，PM)、配置管理数据(Configuration Management，CM)与测量报告(Measurement Report，MR)，其中，MR指用户在通话状态下向网络发送的测 量报告。由于每个节能小区的场景不同，从而能够实现基于场景的小区节能，即根据每个节能小区的具体场景实现对小区的节能。
S12、根据所述基站信息，基于预设门限调整动作集合，选取门限调整动作。
在一实施例中，预先设置门限调整动作集合，即预设门限调整动作集合，预设门限调整动作集合包含门限调整动作，门限调整动作可以为如下内容：1)上调负荷门限两个基准点；2)上调负荷门限一个基准点；3)保持负荷门限不变；4)下调负荷门限一个基准点；5)下调负荷门限两个基准点。其中，负荷门限的一个基准点为对于用户数步长可以为1，对于上行物理资源块(Physical Resource Block，RPB)利用率与下行RPB利用率可以为1％。
S13、根据所述门限调整动作，将所述节能小区的负荷门限进行调整，并获取所述负荷门限调整后所述基站的新基站信息。
在一实施例中，根据门限调整动作，将节能小区的负荷门限进行调整，并采用调整后的负荷门限控制节能小区的节能状态，从而产生对应的基站信息，并获取负荷门限调整后基站的新基站信息，新基站信息包括KPI评估指标，新基站信息页可以包括基站信息的内容。
S14、根据所述新基站信息，再次调整所述节能小区的负荷门限，并迭代调整所述节能小区的负荷门限直至满足预设迭代终止条件，得到所述节能小区的负荷门限调整上限；
S15、采用所述负荷门限调整上限，控制所述节能小区的节能状态。
在一实施例中，根据新基站信息，再次调整节能小区的负荷门限，可以为根据新基站信息，确定门限调整动作所对应的奖励，其中，奖励描述对门限调整动作的反馈，奖励是执行门限调整动作后，环境对门限调整动作的反馈。奖励的组成可以包括两部分：1)节能时长与KPI指标奖惩值，其中，节能时长可以是从PM计数器中读取，例如，可以以15分钟为时间粒度，将一天分为96个时间刻度，节能时长一刻为一分，KPI指标奖惩值，是KPI评估指标与预设值的KPI负荷门限相比较给出的评分，KPI评估使用的指标可以包括：1)小区无线接通率Acc_ratio；2)小区无线掉线率Drop_ratio；3)切换出成功率Handout_ratio；4)小区平均速率dlAvg；5)小区上行平均速率ulAvg。单个指标评分可以如下表格1所示，表格1描述奖励与KPI指标关系表。
表格1
表格1中，各个指标含义如下：1)指标劣化，在负荷门限的a1％以内时，为-b1分；2)指标劣化，在负荷门限的a1％-a2％以内时，为-b2分；3)指标劣化，超负荷门限的a2％时，为-b3分；4)指标未劣化，在负荷门限的a1％以内时，为c1分；5)指标未劣化，在负荷门限的a1％-a2％以内时，为c2分；6)指标未劣化，与负荷门限的差值超过负荷门限的a2％时，表明节能小区能够充分的承载负荷，为c3分。然后将参与评估的指标分数相加之和作为指标评估分，指标评估分数与节能时长分之和作为奖励。需要说明的是，上述示例只是用于说明本公开实施例的实施方式，不用于限定本公开实施例的实施方式。
然后根据所述奖励，基于所述预设门限调整动作集合，再选取门限调整动作，例如再选取的门限调整动作可以称为第二门限调整动作。在一实施例中，根据奖励，基于预设门限调整动作集合，重新选取门限调整动作，即第二门限调整动作。例如，基于强化学习中的Qlearning 算法来进行节能小区的负荷门限的自学习与自调整时，获取到奖励R后，更新Q函数，第一轮调整跳过该步骤，其余轮次，在上一轮次调整周期完成后，使用节能小区当前的环境信息状态S’和奖励R更新Q函数，更新公式如下：
Q(S，A)＝Q(S，A)+α[R+βmaxQ(S’，A)-Q(S，A)]，公式(1)；
其中，S为上一轮状态，A为上一轮采取的动作，α为学习速率、β为折扣因子，然后再选取门限调整动作A，可以基于ε-greedy策略从预设门限调整动作集合中选取门限调整动作，即以ε的概率随机选择动作，以(1-ε)概率选择Q函数计算出值最大的动作，ε的初始值可以为0.1。
进而根据第二门限调整动作，确定第二门限调整动作所对应的奖励，并根据奖励，基于预设门限调整动作集合，再选取门限调整动作，将节能小区的负荷门限进行调整，循环上述根据基站信息，调整节能小区的负荷门限的步骤，直至满足预设迭代终止条件，得到节能小区的负荷门限调整上限，即采用与获取门限调整动作所对应奖励类似的过程，根据第二门限调整动作，确定第二门限调整动作所对应的奖励，再根据奖励去选取动作，并根据动作确定相应的奖励，迭代将节能小区的负荷门限采用门限调整动作进行调整的步骤，且随着周期迭代可以以1/迭代次数的速率衰减，根据选择的门限调整动作对节能小区的负荷门限进行调整，直至满足预设迭代终止条件，迭代结束，输出节能小区的负荷门限所对应的调整上限，即负荷门限调整上限，从而得到节能小区的负荷门限调整上限，并采用负荷门限调整上限，控制节能小区的节能状态。
本申请实施例，通过节能小区处于节能状态时，采集节能小区所属基站的基站信息，根据基站信息，基于预设门限调整动作集合，选取门限调整动作，根据门限调整动作，将节能小区的负荷门限进行调整，并获取负荷门限调整后基站的新基站信息，根据新基站信息，再次调整节能小区的负荷门限，并迭代调整节能小区的负荷门限直至满足预设迭代终止条件，得到节能小区的负荷门限调整上限，并采用负荷门限调整上限，控制节能小区的节能状态，由于负荷门限调整上限充分考虑了节能小区的自身配置、周围环境、节假日业务特征等较为全面的因素，从而使负荷门限调整上限尽可能地适应每个节能小区的具体应用环境而为最佳负荷门限，相比于传统技术中采取统一且固定负荷门限上限的方式，本公开实施例能够实现一个节能小区对应一个节能策略，能够提高节能小区进行节能的节能效果。
在一实施例中，请参阅图2与图3，图3为本公开实施例提供的基站节能方法的第一个子流程示意图。如图3所示，在该实施例中，所述若节能小区处于节能状态之前，还包括如下步骤S31至S34：
S31、获取节能小区在预设时间段的第一预测负荷，其中，所述节能小区描述小区被配置为能够执行节能任务的小区，所述第一预测负荷描述预测的所述节能小区承载的负荷。
在一实施例中，采用全球小区识别码进行标识的无线覆盖区域称为小区，一个基站可以对应多个小区。预先将小区配置为节能小区与基础覆盖小区，节能小区描述小区被配置为能够执行节能任务的小区，以实现基站设备的节能需求，基础覆盖小区描述提供无线网络基础覆盖的小区，基础覆盖小区不能进入节能状态，不用于执行节能任务，用于提供无线网络通信的兜底服务。
预先将时间按照预设时间粒度切分为不同的时间段，即预设时间段。例如，可以按照15分钟时间粒度将每天切分为96个时间段，也可以按照30分钟、60分钟、90分钟等不同的时 间粒度将每天切分为不同的时间段。
进行基站节能时，首先获取节能小区在预设时间段的第一预测负荷，可以通过预测节能小区在预设时间段承载的负荷，即第一预测负荷，进而获取第一预测负荷，以便根据第一预测负荷评估节能小区在预设时间段是否能够进入节能，且不影响用户对网络的使用，即在节能的同时保障用户使用网络的体验不会变差。
请继续参阅图2，预测节能小区在预设时间段的第一预测负荷，可以采取负荷预测建模的方式对节能小区的负荷进行预测，负荷预测建模可以采用时间序列预测方法进行建模，利用每个时间段所对应的历史负荷数据，预测未来时间段所对应的负荷，即第一预测负荷，其中，第一预测负荷包括用户数、上行RPB利用率、下行RPB利用率等描述网络承载量的指标。
S32、获取基础覆盖小区在所述预设时间段的第二预测负荷，其中，所述基础覆盖小区描述提供无线网络基础覆盖的小区，所述第二预测负荷描述预测的所述基础覆盖小区自身将会承载的负荷。
在一实施例中，获取基础覆盖小区在预设时间段的第二预测负荷，第二预测负荷描述预测的基础覆盖小区自身将会在预设时间段承载的负荷，可以基于上述预测节能小区在预设时间段的第一预测负荷的类似方法，预测基础覆盖小区自身将会在预设时间段承担的负荷，即第二预测负荷，便可获取第二预测负荷。
S33、根据所述第一预测负荷与所述第二预测负荷，判断所述基础覆盖小区是否能够承载所述第一预测负荷；
S34、若所述基础覆盖小区能够承载所述第一预测负荷，控制所述节能小区在所述预设时间段进入节能；
S35、若所述基础覆盖小区不能够承载所述第一预测负荷，不控制所述节能小区在所述预设时间段进入节能。
在一实施例中，对于存在2G、3G、4G与5G等多层制式网络的节能小区与基础覆盖小区，若基础覆盖小区与节能小区的制式相同，节能小区的负荷可以直接转换为基础覆盖小区的负荷，若基础覆盖小区与节能小区的制式不相同，需要将节能小区的负荷进行协同转换，以将节能小区的负荷转换为基础覆盖小区的负荷，进而在节能小区的负荷转移到基础覆盖小区后，根据第一预测负荷与第二预测负荷，判断基础覆盖小区是否能够承载所述第一预测负荷。
在一实施例中，所述根据所述第一预测负荷与所述第二预测负荷，判断所述基础覆盖小区是否能够承载所述第一预测负荷，包括：
将所述第一预测负荷进行负荷转换，得到第一转换负荷；
将所述第二预测负荷进行负荷转换，得到第二转换负荷；
获取所述基础覆盖小区的预设负荷开启门限，并将所述预设负荷开启门限进行负荷转换，得到第三转换负荷，其中，所述预设负荷开启门限描述所述基础覆盖小区在承载所述节能小区转移来的负荷时开启的负荷门限；
若所述第一转换负荷与所述第二转换负荷之和小于或者等于所述第三转换负荷，判定所述基础覆盖小区能够承载所述第一预测负荷。
进一步地，将所述第一预测负荷进行负荷转换，得到第一转换负荷，包括：
根据第一基准因子与第一上下行复用因子，将所述第一预测负荷进行负荷转换，得到第一转换负荷。
在一实施例中，可以根据第一基准因子与第一上下行复用因子，将第一预测负荷进行负荷转换，得到第一转换负荷，其中，第一基准因子描述节能小区相对于基准小区的因子，基准小区为预设的作为基准的小区，第一上下行复用因子描述节能小区的上行PRB资源与下行PRB资源在复用时的因子。
预测基础覆盖小区自身将会在预设时间段承担的负荷，即第二预测负荷，并可以根据第二基准因子与第二上下行复用因子，将第二预测负荷进行负荷转换，得到第二转换负荷，其中，第二基准因子描述基础覆盖小区相对于基准小区的因子，基准小区为预设的作为基准的小区，第二上下行复用因子描述基础覆盖小区的上行PRB资源与下行PRB资源在复用时的因子。
获取基础覆盖小区的预设负荷开启门限，并可以根据第二基准因子与第二上下行复用因子，将预设负荷开启门限进行负荷转换，得到第三转换负荷，其中，预设负荷开启门限描述基础覆盖小区在承载节能小区转移来的负荷时开启的负荷门限。
然后计算第一转换负荷与第二转换负荷之和，并将第一转换负荷与第二转换负荷之和与第三转换负荷进行比较，若第一转换负荷与第二转换负荷之和小于或者等于第三转换负荷，判定基础覆盖小区能够承载第一预测负荷，否则，判定基础覆盖小区不能够承载第一预测负荷。
例如，判断基础覆盖小区是否能够承载第一预测负荷，可以采取如下公式(1)进行判断，若满足如下公式(1)，判定基础覆盖小区能够承载第一预测负荷，进而判定节能小区可以进入节能，基站控制节能小区进入节能，否则，判定基础覆盖小区不能够承载第一预测负荷，进而判定节能小区不可以进入节能，基站不控制节能小区进入节能。公式(1)如下：
其中，preLoad为节能小区的第一预测负荷；preBaseLoad为基础覆盖小区自身承载的第二预测负荷；baseThrd为基础覆盖小区的负荷开启门限；m为节能小区的索引，取值为1至M，M为正整数，上式中取值可以为M＝1，描述包含一个节能小区，在其它示例中，也可以包含多个节能小区；n为基础覆盖小区的索引，取值为1至N，N为正整数，上式中取值可以为N＝1，描述包含一个基础覆盖小区，在其它示例中，也可以包含多个基础覆盖小区；γ为小区相对于基准小区的因子，计算公式如下公式(2)所示，对于负荷为用户数时，γ＝1，对于上行RPB利用率、下行PRB利用率因素时，基于如下公式(2)计算；
其中，cellBw为小区的带宽，单位为RB，scsCell为小区的scs，scs，英文为sub-carrier space，为子载波间隔，单位为kHz；afla为上下行复用因子，对于用户数，负荷取值为1，对于上行RPB利用率、下行PRB利用率负荷，取值为1。
采用公式(1)与公式(2)即可以将节能小区的第一预测负荷转换为基础覆盖小区承载的负荷，并判断基础覆盖小区是否能够承载第一预测负荷，若基础覆盖小区能够承载第一预 测负荷，控制节能小区在预设时间段进入节能，其中，节能方式包括载波节能、深度睡眠节能、通道关断节能、非连续发射(Discrete Transmission，DTX)节能，每个节能小区的节能方式可以预先配置在网管上，若基础覆盖小区不能够承载第一预测负荷，不控制节能小区在预设时间段进入节能。
本公开实施例，通过获取节能小区在预设时间段的第一预测负荷及基础覆盖小区在预设时间段的第二预测负荷，并根据第一预测负荷与第二预测负荷，判断基础覆盖小区是否能够承载第一预测负荷，若基础覆盖小区能够承载第一预测负荷，控制节能小区在预设时间段进入节能，不但能够实现基站节能，而且实现了一个节能小区对应一个节能策略，从而根据节能小区的多层网络下的第一预测负荷，并将第一预测负荷转换为基础覆盖小区的负荷，以在节能小区与基础覆盖小区之间进行负荷的协同换算与协同评估，在判断节能小区可以进入节能时，不仅考虑了节能小区自身负荷的大小，而且综合评估了节能小区的负荷转移与基础覆盖小区的负荷承载，可保证节能小区进入节能后，其原有的负荷能够被基础覆盖小区承载，在节能的同时保障用户使用网络的体验不会变差，实现根据每个节能小区的负载在灵活的时间进入节能，提高每个节能小区自动进入节能的灵活性与节能的精确性，相比传统技术中根据全网小区统一配置节能策略，本公开实施例不但能够实现“一个节能小区对应一个节能策略”，不同的节能小区对应不同的节能策略，而且能够实现一个节能小区在不同的预设时间段采取不同的节能策略，从而实现了节能策略的动态调整与节能小区的个性化节能策略，提高了基站节能的效率与效果。
在一实施例中，请参阅图2与图4，图4为本公开实施例提供的基站节能方法的第二个子流程示意图。如图4所示，在该实施例中，所述控制所述节能小区在所述预设时间段进入节能，包括：
S41、根据所述基础覆盖小区能够承载所述第一预测负荷的判定及所述第一预测负荷与所述预设时间段之间的对应关系，生成所述节能小区所对应的协同判决时间段，其中，所述协同判决时间段描述基于对所述节能小区与所述基础覆盖小区的协同评估而确定的所述节能小区能够进入节能的预设时间段；
S42、获取负荷门限调整上限，并根据所述第一预测负荷、所述协同判决时间段与所述负荷门限调整上限，生成所述节能小区所对应的自身负荷判决时间段，其中，所述自身负荷判决时间段描述基于所述第一预测负荷判决所述节能小区能够进入节能的预设时间段；
S43、根据所述协同判决时间段与所述自身负荷判决时间段，生成所述节能小区的节能时间段，并采用所述节能时间段控制所述节能小区进入节能，其中，所述节能时间段描述所述节能小区执行节能任务的时间历程。
在一实施例中，根据基础覆盖小区是否能够承载第一预测负荷，来判定节能小区是否能够在预设时间段进入节能，若基础覆盖小区不能够承载第一预测负荷，判定节能小区不能够在预设时间段进入节能，若基础覆盖小区能够承载第一预测负荷，判定节能小区能够在预设时间段进入节能小区，即节能小区在预设时间段的起始时间点开始进入节能，并根据基础覆盖小区能够承载第一预测负荷的判定及第一预测负荷与预设时间段之间的对应关系，生成节能小区所对应的协同判决时间段，其中，协同判决时间段描述基于对节能小区与基础覆盖小区的协同评估来确定单个的节能小区在预设时间段能够进入节能的时间段，协同判决时间段可以采用Bitmap1描述。例如，若以15分钟为时间粒度，将一天划分为96个预设时间段， 若其中任意4个预设时间段的描述为{0，1，1，0}，其中，0描述对应的预设时间段节能小区不能进入节能，1描述对应的预设时间段节能小区可以进入节能，{0，1，1，0}描述第一个预设时间段与第四个预设时间段，节能小区不能进入节能，第二个预设时间段与第三个预设时间段，节能小区可以进入节能。{0，1，1，0}描述了节能小区在对应的每个预设时间段是否能够进入节能，{0，1，1，0}不仅描述了预设时间段，而且描述了对应的预设时间段是否能够进入节能，基于此，根据基础覆盖小区能够承载第一预测负荷的判定及第一预测负荷与预设时间段之间的对应关系，能够生成节能小区所对应的协同判决时间段。
获取负荷门限调整上限，负荷门限调整上限可以为基于强化学习得到的节能小区的负荷门限上限，负荷门限调整上限为基于基站环境得到的自适应的负荷门限上限，并根据第一预测负荷、协同判决时间段与负荷门限调整上限，生成节能小区所对应的自身负荷判决时间段，其中，自身负荷判决时间段描述基于节能小区自身的第一预测负荷判决节能小区在预设时间段能够进入节能的时间段。主要为根据第一预测负荷及第一预测负荷可被基础覆盖小区承载的协同判决时间段，为节能小区寻找低于基于强化学习的负荷门限调整上限的负荷门限，并能使节能小区在协同判决时间段尽可能进入节能的最优负荷门限，作为目标节能负荷门限，且使用目标节能负荷门限再生成基于第一预测负荷判决的时间段，即自身负荷判决时间段。
根据协同判决时间段与自身负荷判决时间段，生成节能小区的节能时间段，并采用节能时间段控制节能小区进入节能，实现基站节能，其中，节能时间段描述节能小区执行节能任务的时间历程，即节能时间段描述节能小区处于节能的时间历程。
在一示例中，将协同判决时间段与自身负荷判决时间段按位取与，生成节能小区进入节能的节能时间段，输出节能时间段，并采用节能时间段控制节能小区进入节能。其中，节能小区能够进入节能，需同时满足以下两个条件：1)多层网络间的节能小区的第一预测负荷满足协同评估条件，即基础覆盖小区能够承载节能小区转移来的负荷；2)节能小区的第一预测负荷小于或者等于节能小区的目标节能负荷门限，目标节能负荷门限可以采用Threshold描述。可以通过将协同判决时间段与自身负荷判决时间段分别换算成二进制，再将二进制按位取与，生成节能小区进入节能的节能时间段，节能时间段即满足以上所述的两个条件，其中，按位取与为同位上的两个数只有同为真时则真，一假则假，其中1为真，0为假，即同位上的两个数只有同位为1时才取1，否则取0，从而确定节能小区进入节能的节能时间段，并采用节能时间段控制节能小区进入节能。
请继续参阅图2，采用节能时间段控制节能小区进入节能，可以为将节能时间段作为节能参数下发至网管网元中的网管数据库，将网管数据库进行更新，再通过网管数据库下发至节能小区所对应的基站，并采用节能参数控制节能小区执行节能任务，进行节能，从而实现基站节能。
本公开实施例，通过生成节能小区所对应的协同判决时间段与自身负荷判决时间段，并根据协同判决时间段与自身负荷判决时间段，例如将协同判决时间段与自身负荷判决时间段按位取与，生成节能小区进入节能的节能时间段，进一步实现了每个节能小区在节能的同时保障用户使用无线网络的体验不会变差。
在一实施例中，请参阅图5，图5为本公开实施例提供的基站节能方法的第三个子流程示意图。如图5所示，在该实施例中，所述根据所述第一预测负荷、所述协同判决时间段与所述负荷门限调整上限，生成所述节能小区所对应的自身负荷判决时间段，包括：
S51、获取所述节能小区的预设负荷门限值，并根据所述预设负荷门限值与所述负荷门限调整上限，获取所述负荷门限调整的负荷门限调整区间；
S52、基于所述协同判决时间段，根据所述第一预测负荷，遍历所述负荷门限调整区间，获取目标节能负荷门限，其中，所述目标节能负荷门限为使所述节能小区的节能时间最长且负荷门限最小的负荷门限值；
S53、将所述第一预测负荷与所述目标节能负荷门限进行比较；
S54、若所述第一预测负荷小于或者等于所述目标节能负荷门限，根据所述第一预测负荷与所述预设时间段之间的对应关系，生成所述节能小区所对应的自身负荷判决时间段；
S55、若所述第一预测负荷大于所述目标节能负荷门限，不生成所述节能小区所对应的自身负荷判决时间段。
在一实施例中，预先为节能小区的负荷门限配置负荷门限上限值，即预设负荷门限值，亦即节能负荷门限值，描述节能小区进入节能时的负荷门限的上限大小，可以通过网管配置预设负荷门限值，预设负荷门限值为配置的原始负荷门限值。进而获取节能小区的预设负荷门限值，以便根据网管上配置的预设负荷门限值与基于强化学习得到的负荷门限调整上限，确定负荷门限调整的范围，即负荷门限调整区间，并从负荷门限调整区间中寻找到最优的目标负荷门限值，即负荷门限寻优，目标节能负荷门限为使节能小区的节能时间最长且负荷门限最小的负荷门限值。若负荷门限寻优的初始值采用Thresholdinit描述，Thresholdinit可以采用下述公式描述：
Thresholdinit＝Min(Thresholdcm，Thresholdmax)，公式(3)；
其中，Thresholdcm为预设负荷门限值，即网管上配置的节能负荷门限值，Thresholdmax为负荷门限基于自适应的强化学习调整输出的负荷门限值，即负荷门限调整上限。
若负荷门限寻优的上限采用Thresholdul，Thresholdul可以采用如下公式描述：
Thresholdul＝Max(Thresholdcm，Thresholdmax)，公式(4)；
小区的节能负荷门限Threshold调整范围，即负荷门限调整区间，可以描述如下：
Thresholdinit≤Threshold≤Thresholdul，公式(5)；
进行负荷门限寻优时，在协同判决输出的允许节能时间段BitMap1上，即协同判决时间段上，以负荷门限调整区间的初始值为搜索的起点，若第一预测负荷为用户数，用户数的步长可以为1，若第一预测负荷为其它指标，其它指标的步长可以为1％，在负荷门限调整区间上，根据第一预测负荷，向上遍历迭代搜索，选取满足使节能小区的节能时间最长且负荷门限值最小的负荷门限值作为最终的节能负荷门限，即目标节能负荷门限，目标节能负荷门限为使节能小区的节能时间最长且负荷门限最小的负荷门限值。
使用搜索到的目标节能负荷门限与第一预测负荷相比较，若第一预测负荷大于目标节能负荷门限，判定第一预测负荷所对应的预设时间段，节能小区不能进入节能，否则，若第一预测负荷小于或者等于目标节能负荷门限，判定第一预测负荷所对应的预设时间段，节能小区可以进入节能，并根据第一预测负荷与预设时间段之间的对应关系，生成节能小区所对应的自身负荷判决时间段，自身负荷判决时间段描述基于节能小区自身的第一预测负荷判决节能小区在预设时间段能够进入节能的时间段，自身负荷判决时间段可以采用Bitmap2描述，其中，负荷门限与负荷为相同对象，均为用户数、上行RPB利用率、下行RPB利用率等指标，基于此，目标节能负荷门限与第一预测负荷能够相比较。其中，自身负荷判决时间段既 描述了时间段，又描述了在预设时间段节能小区是否能够进入节能。
例如，若负荷门限调整区间为{1，4}，并采用0描述节能小区不能进入节能，1描述节能小区能够进入节能，若协同判决时间段为{0，1，1，0}，描述在第一个预设时间段不能进入节能，第2或者3个预设时间段能够进入节能，第4个预设时间段不能够进入节能，其中，预设时间段可以为根据预设时间粒度划分的时间范围，例如，根据15分钟的时间粒度划分的时间范围。
在一示例中，预设负荷门限值，即网关性能配置的负荷门限负荷值采用{1，2，3，4}描述节能小区在每个预设时间段的负荷值上限，第一个预设时间段的负荷值为1，第二预设时间段的负荷值为2，第三个预设时间段的负荷值为3，第四个预设时间段的负荷值为4。
将{0，1，1，0}与{1，2，3，4}对应位相乘，得{0，2，3，0}，描述每个预设时间段能否进入节能及负荷门限的上限，可以以数组描述。
以{1，4}中的1为搜索的起点，以对于用户数步长可以为1，负荷的其它指标可以以步长1％，在负荷门限的调整范围{1，4}内，根据小区的第一预测负荷，向上遍历迭代搜索，从{0，2，3，0}中搜索到3，作为最长且负荷门限值最小的负荷门限值作为最终的节能负荷门限，即目标节能负荷门限。
在另一示例中，预设负荷门限值采用{1，2，5，4}描述节能小区在每个预设时间段的负荷值上限，第一个预设时间段的负荷值为1，第二预设时间段的负荷值为2，第三个预设时间段的负荷值为5，第四个预设时间段的负荷值为4。
将{0，1，1，0}与{1，2，5，4}对应位相乘，得{0，2，5，0}，描述每个预设时间段能否进入节能及负荷门限的上限，可以以数组描述。
以{1，4}中的1为搜索的起点，以对于用户数步长可以为1，符合的其它指标可以以步长1％，在负荷门限的调整范围{1，4}内，根据小区的第一预测负荷，向上遍历迭代搜索，从{0，2，5，0}中搜索到2，作为最长且负荷门限值最小的负荷门限值作为最终的节能负荷门限，即目标节能负荷门限。
进一步地，还可以采用所述目标节能负荷门限控制所述节能小区进入节能，即将目标节能负荷门限作为节能小区进入节能的门限，控制节能小区进入节能，可以为将目标节能负荷门限作为节能参数下发至节能小区所对应的基站，并采用节能参数控制节能小区进入节能。由于目标节能负荷门限为基于节能小区的预设基站信息确定的负荷门限调整上限而获取的，目标节能负荷门限充分考虑了节能小区的自身配置、周围环境、节假日业务特征等较为全面的因素，从而使目标节能负荷门限尽可能地为最佳负荷门限，能够提高节能小区进行节能的节能效果。
更进一步地，还可以同时将节能时间段与目标节能负荷门限同时作为节能参数控制节能小区进行节能，可以实现满足使节能小区的节能时间最长且节能的负荷门限值最小，能够使目标节能负荷门限与节能小区节能时的负荷贴近，从而使节能小区在低负荷时及时进入节能，在高负荷时及时退出节能，在最大化节能时间的同时，在负荷突然增加的情况下及时退出节能，不但能够在节能的同时保障用户使用无线网络的体验不会变差，而且进一步提高了节能小区进行节能的节能效果，从而提升了节能小区进行节能的效率。
在一实施例中，所述采用所述节能时间段控制所述节能小区进入节能之后，还包括：
获取所述节能小区进入节能后的节能基站信息，并判断所述节能基站信息是否满足预设 变化条件，其中，所述节能基站信息描述节能小区处于节能时基站的信息；
若所述节能基站信息满足所述预设变化条件，根据所述节能基站信息，基于强化学习，获取所述节能小区的负荷门限所对应的节能负荷门限调整上限；
若所述节能基站信息不满足所述预设变化条件，不获取所述节能小区的负荷门限所对应的节能负荷门限调整上限。
在一实施例中，采用节能时间段作为节能参数形成节能策略，并将节能策略下发至基站，控制节能小区进入节能，尤其将节能时间段与目标节能负荷门限作为节能参数形成节能策略控制节能小区进行节能，基站实施节能策略后，获取节能基站信息，节能基站信息描述节能小区处于节能时基站的信息，基站的信息可以为关键性能指标，即KPI指标，并判断节能基站信息是否满足预设变化条件，预设变化条件可以为KPI指标的变化、节能小区的周围环境信息的变化等，预设变化条件还可以为节能基站信息与历史基站信息的比较，此时，获取节能基站信息与历史基站信息，基站信息为基站的环境信息，基站信息包括节能基站信息与历史基站信息，节能基站信息描述基站的节能环境信息，历史基站信息描述基站的历史环境信息，并将节能基站信息与历史基站信息的比较，从而评估基站的环境信息是否发生了较大变化，若节能基站信息满足预设变化条件，判定基站的环境发生了较大变化，根据节能基站信息，基于强化学习，获取节能小区的负荷门限所对应的节能负荷门限调整上限，若节能基站信息未满足预设变化条件，判定基站的环境未发生较大变化，无需重新获取节能小区的负荷门限所对应的负荷门限调整上限。
本公开实施例，通过在节能小区进行节能后，获取节能基站信息，并根据节能基站信息，判定基站的环境是否发生较大变化，若基站的环境发生较大变化，根据节能基站信息，重新获取贴合节能小区节能环境的负荷门限调整上限，即节能负荷门限调整上限，并再根据节能负荷门限调整上限，重新确定节能时间段及目标节能负荷门限等节能参数，确定新的节能策略，使节能策略贴合节能小区的节能实际情况，若基站的环境未发生较大变化，无需重新获取节能小区的负荷门限调整上限，从而可以根据基站的信息动态调整节能小区的负荷门限调整上限，使负荷门限调整上限尽可能与节能小区的节能环境匹配，实现根据节能策略实施后基站信息的变化自适应调整节能小区的节能负荷门限，避免之前学习到的节能负荷门限的负荷门限调整区间已不适合节能的小区条件，从而影响节能小区的节能效果甚至无线网络的关键性能指标变差。
请参阅图6，图6为本公开实施例提供的一种基站节能设备的结构示意性框图。如图6所示，基站节能设备300包括处理器301和存储器302，处理器301和存储器302通过总线303连接，该总线比如为I2C(Inter-integrated Circuit)总线。
在一实施例中，处理器301用于提供计算和控制能力，支撑整个基站节能设备的运行。处理器301可以是中央处理单元(Central Processing Unit，CPU)，该处理器301还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。其中，通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
在一实施例中，存储器302可以是Flash芯片、只读存储器(Read-Only Memory，ROM)磁盘、光盘、U盘或移动硬盘等。
本领域技术人员可以理解，图6中示出的结构，仅仅是与本公开实施例方案相关的部分结构的框图，并不构成对本公开实施例方案所应用于其上的基站节能设备的限定，具体的服务器可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
其中，所述处理器用于运行存储在存储器中的计算机程序，并在执行所述计算机程序时实现本公开实施例提供的任意一种所述的基站节能方法。
需要说明的是，所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的基站节能设备的具体工作过程，可以参考前述基站节能方法实施例中的对应过程，在此不再赘述。
本公开实施例还提供一种存储介质，用于计算机可读存储，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现如本公开实施例说明书提供的任一项基站节能的方法的步骤。
其中，所述存储介质可以是前述实施例所述的基站节能设备的内部存储单元，例如所述基站节能设备的硬盘或内存。所述存储介质也可以是所述基站节能设备的外部存储设备，例如所述基站节能设备上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统、装置中的功能模块/单元可以被实施为软件、固件、硬件及其适当的组合。在硬件实施例中，在以上描述中提及的功能模块/单元之间的划分不一定对应于物理组件的划分；例如，一个物理组件可以具有多个功能，或者一个功能或步骤可以由若干物理组件合作执行。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包含计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。
应当理解，在本公开实施例的说明书和所附权利要求书中使用的术语“和/或”是指相关联列出的项中的一个或多个的任何组合以及所有可能组合，并且包括这些组合。需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个......”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本公开实施例序号仅仅为了描述，不代表实施例的优劣。以上所述，仅为本公开实施例的具体实施例，但本公开实施例的保护范围并不局限于此，任何熟悉本技术领域的技术 人员在本公开实施例揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本公开实施例的保护范围之内。因此，本公开实施例的保护范围应以权利要求的保护范围为准。

Claims (10)

  1. 一种基站节能方法，包括：
    若节能小区处于节能状态，采集所述节能小区所属基站的基站信息；
    根据所述基站信息，基于预设门限调整动作集合，选取门限调整动作；
    根据所述门限调整动作，将所述节能小区的负荷门限进行调整，并获取所述负荷门限调整后所述基站的新基站信息；
    根据所述新基站信息，再次调整所述节能小区的负荷门限，并迭代调整所述节能小区的负荷门限直至满足预设迭代终止条件，得到所述节能小区的负荷门限调整上限；
    采用所述负荷门限调整上限，控制所述节能小区的节能状态。
  2. 根据权利要求1所述的基站节能方法，其中，所述若节能小区处于节能状态之前，还包括：
    获取所述节能小区在预设时间段的第一预测负荷；
    获取基础覆盖小区在所述预设时间段的第二预测负荷；
    根据所述第一预测负荷与所述第二预测负荷，判断所述基础覆盖小区是否能够承载所述第一预测负荷；
    若所述基础覆盖小区能够承载所述第一预测负荷，控制所述节能小区在所述预设时间段进入节能。
  3. 根据权利要求2所述的基站节能方法，其中，所述控制所述节能小区在所述预设时间段进入节能，包括：
    根据所述基础覆盖小区能够承载所述第一预测负荷的判定及所述第一预测负荷与所述预设时间段之间的对应关系，生成所述节能小区所对应的协同判决时间段；
    获取负荷门限调整上限，并根据所述第一预测负荷、所述协同判决时间段与所述负荷门限调整上限，生成所述节能小区所对应的自身负荷判决时间段；
    根据所述协同判决时间段与所述自身负荷判决时间段，生成所述节能小区的节能时间段，并采用所述节能时间段控制所述节能小区进入节能。
  4. 根据权利要求3所述的基站节能方法，其中，所述根据所述第一预测负荷、所述协同判决时间段与所述负荷门限调整上限，生成所述节能小区所对应的自身负荷判决时间段，包括：
    获取所述节能小区的预设负荷门限值，并根据所述预设负荷门限值与所述负荷门限调整上限，获取所述负荷门限调整的负荷门限调整区间；
    基于所述协同判决时间段，根据所述第一预测负荷，遍历所述负荷门限调整区间，获取目标节能负荷门限，其中，所述目标节能负荷门限为使所述节能小区的节能时间最长且负荷门限最小的负荷门限值；
    将所述第一预测负荷与所述目标节能负荷门限进行比较；
    若所述第一预测负荷小于或者等于所述目标节能负荷门限，根据所述第一预测负荷与所述预设时间段之间的对应关系，生成所述节能小区所对应的自身负荷判决时间段。
  5. 根据权利要求4所述的基站节能方法，其中，所述获取目标节能负荷门限之后，还包括：
    采用所述目标节能负荷门限控制所述节能小区进入节能。
  6. 根据权利要求3-5任一项所述的基站节能方法，其中，所述采用所述节能时间段控制所述节能小区进入节能之后，还包括：
    获取所述节能小区进入节能后的节能基站信息，并判断所述节能基站信息是否满足预设变化条件，其中，所述节能基站信息描述节能小区处于节能时基站的信息；
    若所述节能基站信息满足所述预设变化条件，根据所述节能基站信息，基于强化学习，获取所述节能小区的负荷门限所对应的节能负荷门限调整上限。
  7. 根据权利要求2所述的基站节能方法，其中，所述根据所述第一预测负荷与所述第二预测负荷，判断所述基础覆盖小区是否能够承载所述第一预测负荷，包括：
    将所述第一预测负荷进行负荷转换，得到第一转换负荷；
    将所述第二预测负荷进行负荷转换，得到第二转换负荷；
    获取所述基础覆盖小区的预设负荷开启门限，并将所述预设负荷开启门限进行负荷转换，得到第三转换负荷；
    若所述第一转换负荷与所述第二转换负荷之和小于或者等于所述第三转换负荷，判定所述基础覆盖小区能够承载所述第一预测负荷。
  8. 根据权利要求7所述的基站节能方法，其中，所述将所述第一预测负荷进行负荷转换，得到第一转换负荷，包括：
    根据第一基准因子与第一上下行复用因子，将所述第一预测负荷进行负荷转换，得到第一转换负荷。
  9. 一种基站节能设备，所述基站节能设备包括处理器、存储器、存储在所述存储器上并可被所述处理器执行的计算机程序以及用于实现所述处理器和所述存储器之间的连接通信的数据总线，其中所述计算机程序被所述处理器执行时，实现如权利要求1至8中任一项所述的基站节能方法的步骤。
  10. 一种存储介质，用于计算机可读存储，所述存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现权利要求1至8中任一项所述的基站节能的方法的步骤。
PCT/CN2023/107310 2022-10-11 2023-07-13 基站节能方法、设备及存储介质 WO2024078076A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211243047.1 2022-10-11
CN202211243047.1A CN117939586A (zh) 2022-10-11 2022-10-11 基站节能方法、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024078076A1 true WO2024078076A1 (zh) 2024-04-18

Family

ID=90668728

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/107310 WO2024078076A1 (zh) 2022-10-11 2023-07-13 基站节能方法、设备及存储介质

Country Status (2)

Country Link
CN (1) CN117939586A (zh)
WO (1) WO2024078076A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102083149A (zh) * 2010-09-20 2011-06-01 大唐移动通信设备有限公司 一种调整节能参数值的方法、系统和设备
WO2015023130A1 (ko) * 2013-08-13 2015-02-19 삼성전자 주식회사 통신 시스템에서의 에너지 절감 방법 및 그 장치
JP2015192252A (ja) * 2014-03-28 2015-11-02 日本電気株式会社 移動通信システム、通信制御装置、省電力制御方法およびプログラム
CN111010700A (zh) * 2018-10-08 2020-04-14 上海华为技术有限公司 确定负载门限的方法和装置
CN112566226A (zh) * 2020-12-16 2021-03-26 北京电信规划设计院有限公司 5g基站智能化节能方法
CN115087080A (zh) * 2021-03-15 2022-09-20 中国电信股份有限公司 移动通信网络的节能控制方法、装置、电子设备及介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102083149A (zh) * 2010-09-20 2011-06-01 大唐移动通信设备有限公司 一种调整节能参数值的方法、系统和设备
WO2015023130A1 (ko) * 2013-08-13 2015-02-19 삼성전자 주식회사 통신 시스템에서의 에너지 절감 방법 및 그 장치
JP2015192252A (ja) * 2014-03-28 2015-11-02 日本電気株式会社 移動通信システム、通信制御装置、省電力制御方法およびプログラム
CN111010700A (zh) * 2018-10-08 2020-04-14 上海华为技术有限公司 确定负载门限的方法和装置
CN112566226A (zh) * 2020-12-16 2021-03-26 北京电信规划设计院有限公司 5g基站智能化节能方法
CN115087080A (zh) * 2021-03-15 2022-09-20 中国电信股份有限公司 移动通信网络的节能控制方法、装置、电子设备及介质

Also Published As

Publication number Publication date
CN117939586A (zh) 2024-04-26

Similar Documents

Publication Publication Date Title
US8005654B2 (en) Method, apparatus and computer program product for intelligent workload control of distributed storage
CN108770017B (zh) 一种无线资源动态均衡方法及系统
CN111132190A (zh) 基站负荷预警方法、装置
CN113543284A (zh) 节能方法、基站、控制单元及存储介质
CN101142789A (zh) 区分服务的无线网络中的QoS测量和监视
CN111385800A (zh) 一种lte容量均衡的载波调度方法和装置
EP4307634A1 (en) Feature engineering programming method and apparatus
Ren et al. Efficient resource provisioning and rate selection for stream mining in a community cloud
CN104093197A (zh) 一种移动互联网中的设备节能方法及系统
CN114007225A (zh) Bwp的分配方法、装置、电子设备及计算机可读存储介质
CN113826078B (zh) 资源调度与信息预测方法、设备、系统及存储介质
CN114786268A (zh) 数据传输带宽调整方法、装置、电子设备及存储介质
US20140119254A1 (en) Cell size optimization for energy savings in cellular networks with hybrid energy supplies
US20220407914A1 (en) Method, system and device for cdn scheduling, and storage medium
US8683479B1 (en) Shifting information technology workload demands
CN116192960A (zh) 基于约束条件的算力网络集群动态构建方法及系统
Yao et al. Data-driven resource allocation with traffic load prediction
CN108521657B (zh) 多业务数字分布系统上行底噪优化方法、装置和系统
CN112434885B (zh) 节能小区的业务预测方法和装置
WO2024078076A1 (zh) 基站节能方法、设备及存储介质
CN113747450A (zh) 一种移动网络中业务部署方法、装置及电子设备
WO2015035927A1 (zh) 一种信道配置方法及系统、接入控制器
CN116017570A (zh) 一种基于区块链的边缘计算系统资源管理方法
CN115955479A (zh) 一种云边端协作系统中的任务快速调度与资源管理方法
CN115835242A (zh) 面向群智感知的通感算联合优化方法、设备及储存介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23876284

Country of ref document: EP

Kind code of ref document: A1