CN115086986A

CN115086986A - Policy adjustment method and related device

Info

Publication number: CN115086986A
Application number: CN202110281208.5A
Authority: CN
Inventors: 袁晶晶; 许森; 孙震强; 张乐; 信金灿
Original assignee: China Telecom Corp Ltd
Current assignee: China Telecom Corp Ltd
Priority date: 2021-03-16
Filing date: 2021-03-16
Publication date: 2022-09-20

Abstract

The disclosure provides a strategy adjusting method, a system, a device and a non-transitory computer readable storage medium, and relates to the field of wireless communication. The strategy adjusting method comprises the following steps: the NMS sends data collection command to EMS; EMS initiates a measurement report request to the base station; the base station reports the performance index to the EMS; EMS carries on the energy efficiency calculation according to the performance index that the base station reports, and report performance index and energy efficiency calculation result to NMS; the NMS sends the performance index and the energy efficiency calculation result to an artificial intelligence energy-saving platform; and the artificial intelligent energy-saving platform generates a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and transmits the channel shutdown strategy to the base station through NMS and EMS. The base station energy-saving effect can be effectively improved, and user experience is guaranteed.

Description

Policy adjustment method and related device

Technical Field

The present disclosure relates to the field of wireless communications, and in particular, to a method, a system, an apparatus, and a non-transitory computer-readable storage medium for policy adjustment.

Background

The introduction of new technologies such as multiple antennas in the 5G era will greatly increase the power consumption of the 5G network. The problem of high energy consumption of the base station master equipment is an urgent problem for operators to solve.

Currently, a popular base station energy saving technology is that an AI (Artificial Intelligence) technology is used to predict a load, a radio frequency shutdown strategy of a base station is made in advance, and after the shutdown strategy is issued, related performance indexes need to be monitored, so that the user service quality is ensured and the energy saving purpose is achieved. The channel turn-off strategy is mainly characterized by aiming at the NR carrier waves of multiple channels, so that when users are few in idle time, a part of channels can be turned off, and the power consumption is reduced.

Disclosure of Invention

The technical problem solved by the present disclosure is how to more effectively improve the base station energy saving effect for the channel turn-off strategy, and at the same time, ensure the user experience.

According to an aspect of the present disclosure, there is provided a policy adjustment method, including: a network management system NMS sends a data acquisition instruction to a network element management system EMS; EMS initiates a measurement report request to the base station; the base station reports the performance index to the EMS; EMS carries on the energy efficiency calculation according to the performance index that the base station reports, and report performance index and energy efficiency calculation result to NMS; the NMS sends the performance index and the energy efficiency calculation result to the artificial intelligence energy-saving platform; and the artificial intelligent energy-saving platform generates a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and transmits the channel shutdown strategy to the base station through NMS and EMS.

In some embodiments, the policy adjustment method further comprises: monitoring performance indexes by an artificial intelligent energy-saving platform; and the artificial intelligence energy-saving platform adjusts the channel turn-off strategy according to the monitoring condition of the performance index.

In some embodiments, the generating, by the artificial intelligence energy-saving platform, the channel shutdown policy according to the performance index and the energy efficiency calculation result includes: the artificial intelligence energy-saving platform trains a machine learning model by using the performance index and the energy efficiency calculation result; the artificial intelligence energy-saving platform predicts performance indexes by using a machine learning model; and the artificial intelligent energy-saving platform generates a channel shutdown strategy under the condition that the predicted performance index is lower than a threshold value.

In some embodiments, the performance indicators include: the average wireless resource control RRC connection user number, the uplink RANK average value, the downlink modulation and coding strategy MCS optimal rate, the air interface time delay and the collection starting and stopping time.

In some embodiments, the average number of RRC connected users is: and acquiring the average number of users of the NR cell in the RRC connection state in the starting and stopping time.

In some embodiments, the uplink RANK average is: and in the collection starting and stopping time, dividing the sum of double of the TB number of the RANK1 used for uplink transmission and the TB number of the RANK2 used for uplink transmission by the total number of the TBs transmitted by the MAC layer of the uplink.

In some embodiments, the downlink RANK average is: in the acquisition start-stop time, the number of TBs using RANK1 for downlink transmission, twice the number of TBs using RANK 2for downlink transmission, three times the number of TBs using RANK3 for downlink transmission, and four times the number of TBs using RANK4 for downlink transmission are divided by the total number of TBs transmitted by the downlink MAC layer.

In some embodiments, the downlink MCS yield is: and in the acquisition starting and ending time, the sum of the number of RBs with MCS being more than or equal to 17 in the MCS Index Table1 for PDSCH Table of the gNB cell and the number of RBs with MCS being more than or equal to 11 in the MCS Index Table2for PDSCH Table is compared with the total occupied number of downlink PRBs of the cell.

In some embodiments, the performing, by the EMS, energy efficiency calculation according to the performance index reported by the base station includes: calculating an energy consumption value by the CU-CP; calculating an energy consumption value and a service volume by the CU-UP; the DU calculates an energy consumption value and a traffic volume; the AAU calculates the energy consumption value and the traffic volume.

In some embodiments, the energy consumption value is calculated as follows:

P(t)＝u(i)*i(t)

wherein, p (t) is the power value at time t, u (t) is the voltage value at time t, i (t) is the current value at time t, and Tr is the measuring time.

In some embodiments, the CU-UP calculating traffic comprises: adding UP the uplink data amount transmitted from the DU to the CU-UP, the uplink data amount from the external CU-UP to the CU-UP, and the uplink data amount from the external eNB to the CU-UP, calculating an uplink flow; the downlink traffic is calculated by adding the downlink data amount transmitted from CU-UP to DU, the downlink data amount from CU-UP to external CU-UP, and the downlink data amount from CU-UP to external eNB.

In some embodiments, the DU computation traffic includes: taking the uplink data volume from the bottom layer to the DU as uplink flow; the downlink data amount from the DU to the underlay is used as the downlink traffic.

In some embodiments, the AAU calculating the traffic comprises: calculating the PRB utilization rate.

In some embodiments, the energy efficiency calculation method of each network element is as follows:

the energy efficiency value of the CU is the sum of the statistical traffic of the CU-UP divided by the energy consumption value of the CU-CP and the energy consumption value of the CU-UP; the energy efficiency value of the DU is the statistical DU traffic divided by the DU energy consumption value; the energy efficiency value of the AAU is the statistical AAU traffic divided by the AAU energy consumption value.

According to another aspect of the present disclosure, there is provided a policy adjustment system including: the network management system NMS is configured to issue a data acquisition instruction to the element management system EMS; EMS, configured to initiate a measurement report request to the base station; carrying out energy efficiency calculation according to the performance index reported by the base station, and reporting the performance index and the energy efficiency calculation result to NMS; a base station configured to report a performance index to an EMS; the NMS is configured to send the performance index and the energy efficiency calculation result to the artificial intelligence energy-saving platform; and the artificial intelligent energy-saving platform is configured to generate a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and transmit and send the channel shutdown strategy to the base station through EMS and NMS.

In some embodiments, the policy adjustment system is configured to calculate the energy efficiency value of each network element of the base station by: the energy efficiency value of the CU is the sum of the statistical traffic of the CU-UP divided by the energy consumption value of the CU-CP and the energy consumption value of the CU-UP; the energy efficiency value of the DU is the statistical DU traffic divided by the DU energy consumption value; the energy efficiency value of the AAU is the statistical AAU traffic divided by the AAU energy consumption value.

In some embodiments, the artificial intelligence energy-saving platform is configured to: training a machine learning model by using the performance index and the energy efficiency calculation result; predicting performance indexes by using a machine learning model; and generating a channel shutdown strategy under the condition that the predicted performance index is lower than a threshold value.

In some embodiments, the artificial intelligence energy savings platform is further configured to: monitoring performance indexes in real time; and adjusting the channel turn-off strategy according to the degradation change of the performance index.

In some embodiments, the NMS is configured to: and comparing the change of the energy efficiency value of each network element before and after the strategy adjustment to determine an energy-saving result.

According to still another aspect of the present disclosure, there is provided a policy adjustment apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the aforementioned policy adjustment method based on instructions stored in the memory.

According to yet another aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions which, when executed by a processor, implement the aforementioned policy adjustment method.

The base station energy-saving effect can be effectively improved, and user experience is guaranteed.

Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

In order to more clearly illustrate the embodiments of the present disclosure or technical solutions in the related art, the drawings required to be used in the description of the embodiments or the related art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and for those skilled in the art, other drawings may be obtained according to the drawings without inventive exercise.

Fig. 1 shows a flow diagram of a policy adjustment method of some embodiments of the present disclosure.

Fig. 2 illustrates a schematic structural diagram of a policy adjustment system according to some embodiments of the present disclosure.

Fig. 3 shows a schematic structural diagram of a policy adjustment apparatus according to some embodiments of the present disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

The traditional energy-saving technical method for channel shutoff through AI prediction has the problems that:

(1) due to the fact that MIMO degradation is caused after a channel is closed, coverage and peak rate of RRU and AAU are affected, the traditional technology lacks targeted performance index collection and monitoring related to the traditional technology, the influence on user performance perception cannot be accurately judged, and especially under the condition that users are few at night, accuracy of model prediction is affected;

(2) performance index measurement statistics of channel turn-off association is lacked in a network management system and in 3GPP28.552, requirements of AI model training and monitoring cannot be met, a relevant performance index measurement statistical method needs to be defined for accurately monitoring the influence of the channel turn-off on relevant performance indexes and optimizing the accuracy of an AI model, and a base station reports an implementation process of the network management system to an AI energy-saving platform;

(3) meanwhile, for a base station separated architecture, in the conventional technology, statistics of Energy consumption values and traffic volumes of network elements of a base station is not performed, accurate calculation of Energy efficiency (Energy efficiency) cannot be performed, and the effect of an Energy-saving strategy and the influence on Energy consumption of different network elements cannot be effectively evaluated.

Aiming at the problem analysis, the invention provides an optimization method facing the energy-saving technology of the intelligent base station, which is used for analyzing the influence of channel turn-off on coverage and rate, defining a performance index with strong relevance and a measurement statistical method for calculating the energy efficiency related index of each network element of the base station, providing an information interaction flow between the base station and a network management framework and an AI energy-saving platform, monitoring the quality of the performance index in real time, realizing the timeliness of data transmission and the accuracy of model prediction, ensuring user experience and optimizing the AI energy-saving technology, and effectively evaluating the influence of an energy-saving strategy on the energy consumption of each network element of the base station.

Some embodiments of the disclosed policy adjustment method are first described in conjunction with fig. 1.

Fig. 1 shows a flow diagram of a policy adjustment method of some embodiments of the present disclosure. As shown in fig. 1, the method includes steps S101 to S106.

In step S101, the NMS issues a data collection command to the EMS.

For example, the northbound network management NMS sends a data acquisition instruction to the EMS through a data control interface between the NMS and the EMS based on a data requirement for channel shutdown by the AI energy saving platform, specifies an ID of a collected base station cell, specifies a collection start-stop time, and specifies a required performance index, with seconds as a collection granularity (which may be specifically configured according to an actual situation). The data acquisition instruction comprises a relevant index acquisition instruction and an EE calculation instruction which are required by calculating the Energy Efficiency (EE) of each network element.

Wherein the performance indicators at least include: the average wireless resource control RRC connection user number, the uplink RANK average value, the downlink modulation and coding strategy MCS optimal rate, the air interface time delay and the collection starting and stopping time.

The average number of RRC connected users is: and acquiring the average number of users of the NR cell in the RRC connection state in the starting and stopping time. For example, with the gNB-CU-PLMN as the statistical granularity, all UEs within 1ms are periodically sampled at a sampling interval of not more than 1s, whether the UEs are in the RRC connection state or not is judged, and the sampling value of the number of RRC connection users at the moment is counted. And taking the average value of all samples in the statistical time period as the average RRC connection user number. Classifying according to NSSAI slice identification and summarizing statistical output.

The average value of the uplink RANK is as follows: and in the collection starting and stopping time, dividing the sum of double of the TB number of the RANK1 used for uplink transmission and the TB number of the RANK2 used for uplink transmission by the total number of the TBs transmitted by the MAC layer of the uplink. For example, the RANK average value used for uplink transmission in the gNB cell takes seconds as an acquisition interval, and the gNB-DU as a statistical granularity, according to the calculation formula: (TB number × 1 of RANK1 for uplink transmission + TB number × 2 of RANK 2for uplink transmission)/total number of uplink MAC layer transmission TBs) × 100%.

The average value of the uplink RANK is as follows: in the acquisition start-stop time, dividing the total number of TBs transmitted by a downlink MAC layer by the number of TBs using RANK1 for downlink transmission, twice the number of TBs using RANK 2for downlink transmission, three times the number of TBs using RANK3 for downlink transmission and four times the number of TBs using RANK4 for downlink transmission. For example, the RANK average value used for downlink transmission in the gNB cell takes seconds as an acquisition interval, and the gNB-DU as a statistical granularity, according to the calculation formula: (number of TBs of RANK1 for downlink transmission × 1+ number of TBs of RANK 2for downlink transmission × 2+ number of TBs of RANK3 for downlink transmission × 3+ number of TBs of RANK4 for downlink transmission) × 100%.

The downlink MCS excellent rate is: and in the acquisition starting and ending time, the sum of the number of RBs with MCS being more than or equal to 17 in the MCS Index Table1 for PDSCH Table of the gNB cell and the number of RBs with MCS being more than or equal to 11 in the MCS Index Table2for PDSCH Table is compared with the total occupied number of downlink PRBs of the cell. For example, take seconds as the acquisition interval and gNB-DU as the statistical granularity; the sum of the number of RBs with MCS being more than or equal to 17 in the MCS Index Table1 for PDSCH Table of the gNB cell and the number of RBs with MCS being more than or equal to 11 in the MCS Index Table2for PDSCH Table is proportional to the total number of occupied downlink PRBs of the cell; according to the calculation formula: (the number of RBs with MCS not less than 17 in the MCS Index Table1 for PDSCH Table + the number of RBs with MCS not less than 11 in the MCS Index Table2for PDSCH Table)/the total number of PRBs in the downlink of the cell.

According to the calculation method of Energy Efficiency (EE), the energy consumption value and the traffic required by the EE need to be measured and calculated. And reporting the type including all network elements and optional part of network elements according to the request of the network manager. For CP/UP separation structure, measurement report is carried out according to the following statistical scheme, and report types including all network elements and optional part of network elements are requested according to the network management. Specifically, the CU-CP calculates the energy consumption value, the CU-UP calculates the energy consumption value and the traffic volume, the DU calculates the energy consumption value and the traffic volume, and the AAU calculates the energy consumption value and the traffic volume. The energy consumption value is obtained by multiplying instantaneous voltage and current of a specific network element and then obtaining an energy consumption measured value by means of product in a measuring period, and the energy consumption value is calculated in the following mode, wherein P (t) is a power value at the time t, u (t) is a voltage value at the time t, i (t) is a current value at the time t, and Tr is measuring time.

P(t)＝u(i)*i(t)

CU-UP calculation traffic includes: adding UP uplink data volume (number of PDCP SDU bits, F1-U interface) transmitted from DU to CU-UP, uplink data volume (number of PDCP SDU bits, Xn-U interface) from external CU-UP to CU-UP, uplink data volume (number of PDCP SDU bits, X2-U interface) from external eNB to CU-UP, calculating uplink traffic; the downlink data amount (number of PDCP SDU bits, F1-U interface) transferred from the CU-UP to the DU, the downlink data amount (number of PDCP SDU bits, Xn-U interface) transferred from the CU-UP to the external CU-UP, and the downlink data amount (number of PDCP SDU bits, X2-U interface) transferred from the CU-UP to the external eNB are added to calculate the downlink traffic.

The DU calculation traffic includes: the uplink data volume from the bottom layer to the DU (the RLC SDU bit number of DRB and SRB) is used as the uplink traffic; the downlink data amount (the number of RLC SDU bits of DRB and SRB) from DU to the lower layer is used as the downlink traffic.

The AAU calculates traffic including: PRB utilization (percentage of PRB utilization on each AAU) is calculated.

In step S102, the EMS initiates a measurement report request to the base station.

After receiving the data acquisition instruction of the NMS, the EMS issues a measurement acquisition instruction to the gNB base station cell through a control interface between the EMS and the gNB, and measures the related performance index according to the performance index measurement method defined in S101.

In step S103, the base station reports the performance index to the EMS.

According to the network management request, the gNB base station cell reports related performance index data including all network elements and optional part of network elements to the EMS through a data reporting interface, and follows the requirement of acquisition granularity. EMS stores all measured performance index data in a structured mode according to the collection granularity and period and completes the calculation of the Energy Efficiency (EE) of each network element of the base station; the EE calculation method of each network element of the base station comprises the following steps: the energy efficiency EE of the CU is the traffic of the CU-UP defined and counted in the step 1 divided by the sum of the energy consumption value of the CU-CP and the energy consumption value of the CU-UP; the energy efficiency EE of the DU is the traffic of the DU defined and counted in the step 1 divided by the energy consumption value; the energy efficiency EE of the AAU is the AAU traffic divided by the energy consumption value defined as a statistic in step 1.

In step S104, the EMS performs energy efficiency calculation according to the performance index reported by the base station, and reports the performance index and the energy efficiency calculation result to the NMS.

EMS reports the related performance collection data according to the collection granularity and the statistical period through a data reporting interface between EMS and NMS, and NMS receives the data and completes the storage and the convergence.

In step S105, the NMS sends the performance index and the energy efficiency calculation result to the artificial intelligence energy saving platform.

For example, the NMS transmits the data to the data lake and performance monitoring module of the AI energy saving platform in time according to the real-time requirement of the AI energy saving platform for data acquisition.

In step S106, the artificial intelligence energy saving platform generates a channel shutdown policy according to the performance index and the energy efficiency calculation result, and transparently transmits the channel shutdown policy to the base station through the NMS and the EMS.

The artificial intelligence energy-saving platform trains a machine learning model by using the performance index and the energy efficiency calculation result. And then, the artificial intelligence energy-saving platform predicts the performance index by using a machine learning model. And finally, generating a channel turn-off strategy by the artificial intelligence energy-saving platform under the condition that the predicted performance index is lower than a threshold value. For example, the AI energy saving platform completes the acquisition of the acquired performance index data, data processing and model training, predicts the average number of RRC connection users in the next week, and performs a threshold generation channel shutdown strategy when the average number of RRC connection users is set to be less than or equal to the threshold one. And the channel turn-off strategy is issued to the gNB base station cell to take effect.

According to the embodiment, the index quantity and the measurement acquisition method which can evaluate the perception influence on the user performance after the channel is shut down are defined according to the analysis of the influence of the channel shut down on the coverage, and the effective evaluation of the technical effect of the channel shut down is realized. Aiming at the base station separated architecture, each network element at the base station side completes the statistics of respective energy consumption index and the statistics of corresponding throughput, and reports the index result to a corresponding network manager or gathers the index result to a base station control surface entity, and the base station control surface entity sends the index result to the corresponding network manager, and the network manager side completes the calculation and reporting of the energy efficiency of each network element. By defining a performance index acquisition flow between the base station and the network manager, the AI energy-saving platform can monitor the performance index in real time, ensure the accuracy and timeliness of data transmission, optimize the generation of the turn-off of the adjustment channel, and optimize the AI energy-saving technology while ensuring the user experience.

Meanwhile, the embodiment provides an important data technology for the channel shutdown strategy generation method based on AI, improves timeliness and accuracy of data and models, can effectively evaluate the energy-saving effect of the energy-saving strategy, can effectively guarantee user service quality under channel shutdown, and reduces user complaints.

In addition, the embodiment enhances the existing protocol, does not introduce a new protocol process, has low implementation difficulty, does not need to improve a terminal, is convenient and simple, and has good backward compatibility and deployment feasibility.

In some embodiments, the policy adjustment method further includes step S107 to step S108.

In step S107, the artificial intelligence energy saving platform monitors the performance index.

In step S108, the artificial intelligence energy saving platform adjusts the channel shutdown strategy according to the monitoring condition of the performance index.

For example, a performance monitoring module in the AI energy saving platform can monitor the quality change of the performance index, and cancel the channel shutdown when one or a group of indexes is lower than a threshold value two; and simultaneously checking the energy consumption value and the energy efficiency value of each network element in the statistical time period. In addition, through long-time acquisition, training and strategy generation of performance indexes, the optimal threshold value of the average RRC user number for channel shutoff can be found, the accuracy of the model is improved, the user service experience is guaranteed, and the AI model accuracy rate and the energy-saving technology are improved.

The embodiment is applied to a scene of saving energy of a base station based on AI, and combines with other radio frequency shutdown technologies related to base station energy saving, the method has certain expansibility, and can divide association indexes aiming at different radio frequency shutdown strategies respectively, so that effect monitoring is performed on different radio frequency shutdown strategies in a targeted manner, and the service quality of users with different requirements is guaranteed.

Some embodiments of the disclosed policy adjustment system are described below in conjunction with fig. 2.

Fig. 2 illustrates a schematic structural diagram of a policy adjustment system according to some embodiments of the present disclosure. As shown in fig. 2, the policy adjustment system includes: the network management system NMS is configured to issue a data acquisition instruction to the element management system EMS; EMS, configured to initiate a measurement report request to the base station; carrying out energy efficiency calculation according to the performance index reported by the base station, and reporting the performance index and the energy efficiency calculation result to NMS; a base station configured to report a performance index to an EMS; the NMS is configured to send the performance index and the energy efficiency calculation result to the artificial intelligence energy-saving platform; and the artificial intelligence energy-saving platform is configured to generate a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and issue the channel shutdown strategy to the base station.

In some embodiments, the artificial intelligence energy savings platform is further configured to: monitoring performance indexes; and adjusting the channel turn-off strategy according to the performance index.

In some embodiments, the artificial intelligence energy savings platform is configured to: training a machine learning model by using the performance index and the energy efficiency calculation result; predicting performance indexes by using a machine learning model; and generating a channel shutdown strategy under the condition that the predicted performance index is lower than a threshold value.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or may not be executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

Some embodiments of the disclosed policy adjustment apparatus are described below in conjunction with fig. 3.

Fig. 3 shows a schematic structural diagram of a policy adjustment apparatus according to some embodiments of the present disclosure. As shown in fig. 3, the policy adjustment device 30 includes: a memory 310 and a processor 320 coupled to the memory 310, the processor 320 configured to perform the policy adjustment method of any of the foregoing embodiments based on instructions stored in the memory 310.

Memory 310 may include, for example, a system memory, a fixed non-volatile storage medium, and so on. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs.

The policy adjustment device 30 may further include an input output interface 330, a network interface 340, a storage interface 350, and the like. These

interfaces

330, 340, 350 and the memory 310 and the processor 320 may be connected, for example, by a bus 360. The input/output interface 330 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 340 provides a connection interface for various networking devices. The storage interface 950 provides a connection interface for external storage devices such as an SD card and a usb disk.

The present disclosure also includes a non-transitory computer readable storage medium having stored thereon computer instructions that, when executed by a processor, implement the policy adjustment method in any of the foregoing embodiments.

The aforementioned integrated units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.

The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, so that any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.

Claims

1. A policy adjustment method, comprising:

a network management system NMS sends a data acquisition instruction to a network element management system EMS;

EMS initiates a measurement report request to the base station;

the base station reports the performance index to the EMS;

EMS carries on the energy efficiency calculation according to the performance index that the base station reports, and report performance index and energy efficiency calculation result to NMS;

the NMS sends the performance index and the energy efficiency calculation result to the artificial intelligence energy-saving platform;

and the artificial intelligent energy-saving platform generates a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and transmits the channel shutdown strategy to the base station through NMS and EMS.

2. The policy adjustment method according to claim 1, further comprising:

monitoring performance indexes by an artificial intelligent energy-saving platform;

and the artificial intelligence energy-saving platform adjusts the channel turn-off strategy according to the monitoring condition of the performance index.

3. The policy adjustment method according to claim 1, wherein the generating of the channel shutdown policy by the artificial intelligence energy-saving platform according to the performance index and the energy efficiency calculation result comprises:

the artificial intelligence energy-saving platform trains a machine learning model by using the performance index and the energy efficiency calculation result;

the artificial intelligence energy-saving platform predicts performance indexes by using a machine learning model;

and the artificial intelligent energy-saving platform generates a channel shutdown strategy under the condition that the predicted performance index is lower than a threshold value.

4. The policy adjustment method according to claim 1, wherein the performance indicators comprise: the average wireless resource control RRC connection user number, the uplink RANK average value, the downlink modulation and coding strategy MCS optimal rate, the air interface time delay and the collection starting and stopping time.

5. The policy adjustment method according to claim 4, wherein the average number of RRC connected users is: and acquiring the average number of users of the NR cell in the RRC connection state in the starting and stopping time.

6. The policy adjustment method according to claim 4, wherein the uplink RANK average value is:

and in the collection starting and stopping time, dividing the sum of double of the TB number of the RANK1 used for uplink transmission and the TB number of the RANK2 used for uplink transmission by the total number of the TBs transmitted by the MAC layer of the uplink.

7. The policy adjustment method according to claim 4, wherein the downlink RANK average value is:

in the acquisition start-stop time, the number of TBs using RANK1 for downlink transmission, twice the number of TBs using RANK 2for downlink transmission, three times the number of TBs using RANK3 for downlink transmission, and four times the number of TBs using RANK4 for downlink transmission are divided by the total number of TBs transmitted by the downlink MAC layer.

8. The policy adjustment method according to claim 4, wherein the downlink MCS goodness rate is:

and in the acquisition starting and ending time, the sum of the number of RBs with MCS being more than or equal to 17 in the MCS Index Table1 for PDSCH Table of the gNB cell and the number of RBs with MCS being more than or equal to 11 in the MCS Index Table2for PDSCH Table is compared with the total occupied number of downlink PRBs of the cell.

9. The policy adjustment method according to claim 1, wherein the EMS performing energy efficiency calculation according to the performance index reported by the base station includes:

calculating an energy consumption value by the CU-CP;

the CU-UP calculates an energy consumption value and a traffic volume;

the DU calculates an energy consumption value and a traffic volume;

the AAU calculates the energy consumption value and the traffic volume.

10. The policy adjustment method according to claim 9, wherein the energy consumption value is calculated as follows:

P(t)＝u(i)*i(t)

11. The policy adjustment method according to claim 9, wherein the CU-UP calculating traffic comprises:

adding UP the uplink data amount transmitted from the DU to the CU-UP, the uplink data amount from the external CU-UP to the CU-UP, and the uplink data amount from the external eNB to the CU-UP, calculating an uplink flow;

the downlink traffic is calculated by adding the downlink data amount transmitted from CU-UP to DU, the downlink data amount from CU-UP to external CU-UP, and the downlink data amount from CU-UP to external eNB.

12. The policy adjustment method according to claim 9, wherein the DU calculating the traffic volume comprises:

taking the uplink data volume from the bottom layer to the DU as uplink flow;

the downlink data amount from the DU to the underlay is used as the downlink traffic.

13. The policy adjustment method according to claim 9, wherein the AAU calculating the traffic comprises: calculating the PRB utilization rate.

14. The policy adjustment method according to claim 9, wherein the energy efficiency calculation method of each network element is as follows:

15. A policy adjustment system comprising:

the network management system NMS is configured to issue a data acquisition instruction to the element management system EMS;

EMS, configured to initiate a measurement report request to the base station; carrying out energy efficiency calculation according to the performance index reported by the base station, and reporting the performance index and the energy efficiency calculation result to NMS;

a base station configured to report a performance index to an EMS;

the NMS is configured to send the performance index and the energy efficiency calculation result to the artificial intelligence energy-saving platform;

and the artificial intelligent energy-saving platform is configured to generate a channel shutdown strategy according to the performance index and the energy efficiency calculation result, and transmit the channel shutdown strategy to the base station through the NMS and the EMS.

16. The policy adjustment system according to claim 15, wherein the policy adjustment system is configured to calculate the energy efficiency value of each network element of the base station by:

17. The policy adjustment system according to claim 15 wherein the artificial intelligence energy saving platform is configured to:

training a machine learning model by using the performance index and the energy efficiency calculation result;

predicting performance indexes by using a machine learning model;

and generating a channel shutdown strategy under the condition that the predicted performance index is lower than a threshold value.

18. The policy adjustment system according to claim 15, wherein the artificial intelligence energy savings platform is further configured to:

monitoring performance indexes in real time;

and adjusting the channel turn-off strategy according to the degradation change of the performance index.

19. The policy adjustment system according to claim 15, wherein the NMS is configured to: and comparing the change of the energy efficiency value of each network element before and after the strategy adjustment to determine an energy-saving result.

20. A policy adjustment apparatus comprising:

a memory; and

a processor coupled to the memory, the processor configured to perform the policy adjustment method of any one of claims 1-14 based on instructions stored in the memory.

21. A non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer instructions that, when executed by a processor, implement the policy adjustment method of any one of claims 1 to 14.