WO2021004455A1 - 无线资源管理方法及装置 - Google Patents

无线资源管理方法及装置 Download PDF

Info

Publication number
WO2021004455A1
WO2021004455A1 PCT/CN2020/100661 CN2020100661W WO2021004455A1 WO 2021004455 A1 WO2021004455 A1 WO 2021004455A1 CN 2020100661 W CN2020100661 W CN 2020100661W WO 2021004455 A1 WO2021004455 A1 WO 2021004455A1
Authority
WO
WIPO (PCT)
Prior art keywords
cell
terminal
parameter set
mobility
interval
Prior art date
Application number
PCT/CN2020/100661
Other languages
English (en)
French (fr)
Inventor
叶飞
梁王乐文
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
Priority to EP20837432.2A priority Critical patent/EP3998783A4/en
Publication of WO2021004455A1 publication Critical patent/WO2021004455A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • H04W4/027—Services making use of location information using location based information parameters using movement velocity, acceleration information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/50—Service provisioning or reconfiguring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/51—Allocation or scheduling criteria for wireless resources based on terminal or device properties
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Definitions

  • the embodiments of the present disclosure relate to, but are not limited to, the field of wireless communication technology.
  • the present disclosure provides a wireless resource management method, including: generating a cell characteristic interval of a cell based on a radio frequency fingerprint, and constructing a terminal model in the cell characteristic interval; and hopping according to the terminal model in the cell characteristic interval of the cell Change the situation and determine the mobility feature corresponding to the cell.
  • the present disclosure provides a wireless resource management device, including: a model construction module for generating a cell characteristic interval of a cell based on a radio frequency fingerprint, and constructing a terminal model in the cell characteristic interval; and a management module for The mobility feature corresponding to the cell is determined according to the hopping situation of the terminal model in the cell feature interval of the cell.
  • the present disclosure provides a computer-readable storage medium that stores a computer program that, when executed by a processor, implements the steps of the above-mentioned wireless resource management method.
  • Fig. 1 is a schematic diagram of an implementation environment according to an exemplary embodiment of the present disclosure
  • Fig. 2 is a flowchart of a wireless resource management method according to an embodiment of the present disclosure
  • Fig. 3 is an exemplary diagram of a construction process of a cell characteristic interval according to an embodiment of the present disclosure
  • Fig. 4 is an exemplary diagram of a mobility feature identification process and a parameter issuance process corresponding to a cell according to an embodiment of the present disclosure
  • Figure 5 is an exemplary diagram of a parameter set update process according to an embodiment of the present disclosure.
  • Fig. 6 is a schematic diagram of a radio resource management apparatus according to an embodiment of the present disclosure.
  • the most common way to identify the speed of the user terminal includes: according to the historical information of the terminal, the mobile speed of the terminal is determined by the length of time the terminal resides in the historical cell; in the high-speed rail scene, the Doppler effect Determine the moving speed of the terminal.
  • the Doppler effect Determine the moving speed of the terminal.
  • the embodiments of the present disclosure provide a wireless resource management method and device that use radio frequency fingerprint technology to identify the mobility characteristics corresponding to a cell, which can be applied to different application scenarios and have versatility and universality.
  • the embodiments of the present disclosure can be applied to the intelligent control of wireless resources, so as to support the intelligent and refined control of wireless resources, so that the parameters of the wireless resources can be dynamically adjusted with the changes of the scene, thereby making the parameter configuration more reasonable and extremely reliable. Dadi improves the performance in the area and enhances the user experience.
  • Fig. 1 is a schematic diagram of an implementation environment according to an exemplary embodiment of the present disclosure.
  • the communication system may include: a user terminal 101, a network device 102, and a network management control terminal 103.
  • the network device 102 can communicate with the user terminal 101 and the network management control terminal 103 respectively.
  • FIG. 1 is only an example, and the present disclosure does not limit the number of user terminals 101, network devices 102, and network management control terminals 103.
  • LTE Long Term Evolution
  • TDD Time Division Duplex
  • UMTS Universal Mobile Telecommunication System
  • NR 5G New Radio
  • the network device 102 may be an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, a base station device in a 5G network, or a base station in a future communication system, etc.
  • Evolutional Node B eNB or eNodeB
  • the user terminal 101 may communicate with one or more core networks (Core Network) via a radio access network (Radio Access Network, RAN), and may also be referred to as an access terminal, user equipment (UE), user unit, User station, mobile station, mobile station, remote station, remote terminal, mobile device, terminal device, terminal, wireless communication device, user agent or user device.
  • Core Network Radio Access Network
  • the user terminal 101 may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a wireless local loop (Wireless Local Loop, WLL) station, a personal digital processing (Personal Digital Assistant, PDA), Handheld devices with wireless communication functions, computing devices, or other processing devices connected to wireless modems, in-vehicle devices, wearable devices, or terminal devices in 5G networks, etc.
  • SIP Session Initiation Protocol
  • WLL Wireless Local Loop
  • PDA Personal Digital Assistant
  • the user terminal 101 obtains wireless signal information through measurement, and informs the network device 102 (such as a base station) of the obtained wireless signal information.
  • the network device 102 provides the user terminal 101 with appropriate wireless resources, thereby Ensure the normal service of the user terminal 101 when moving between base stations.
  • the wireless resource allocation is configured through different parameters. It can be seen that the parameter configuration that conforms to the regional characteristics is very important in wireless network communication and directly determines the user experience.
  • the wireless resource management method provided in this embodiment can be executed by the network management control terminal, and the network management control terminal can issue the wireless resource configuration parameters to the network device according to the information reported by the network device, thereby realizing the intelligent and refined wireless resource Parameter management.
  • the network management control terminal can be an independent server or a server cluster. However, this disclosure is not limited to this.
  • Fig. 2 is a flowchart of a wireless resource management method according to an embodiment of the present disclosure. As shown in FIG. 2, the wireless resource management method provided in this embodiment includes the following steps S201 to S202.
  • step S201 based on the radio frequency fingerprint, a cell characteristic interval of the cell is generated, and a terminal model in the cell characteristic interval is constructed;
  • step S202 the mobility feature corresponding to the cell is determined according to the hopping situation of the terminal model in the cell feature interval of the cell.
  • the radio frequency fingerprint is used to characterize the wireless signal strength characteristics of the coverage area of the network device (base station).
  • the cell characteristic interval is used to identify the wireless performance location area of the user terminal. The determination of the cell characteristic interval depends on the radio frequency fingerprint in the network area.
  • any terminal in any cell characteristic interval when the terminal appears in multiple cell characteristic intervals within a timing period, it means that the terminal is in the process of moving, which is called hopping in this embodiment. .
  • the process of the terminal moving from one cell characteristic interval to another cell characteristic interval can be called a jump.
  • the jump index per unit time can be calculated (for example, the jump index per unit time is obtained by dividing the total number of jumps in the timing period by the timing period). The larger the value, the faster the moving speed of the terminal; conversely, when the jump index per unit time is 0 or smaller, it means that the terminal has not moved or the moving speed is slower.
  • the mobility characteristics corresponding to the cell are used to characterize the mobility characteristics (high mobility or non-high mobility) of most terminals in the cell.
  • the speed threshold for example, 90km/h
  • the cell when the number of terminals with high mobility characteristics in a cell is greater than or equal to a threshold, the cell is considered to correspond to high mobility characteristics, that is, the cell is a high-speed cell; when the number of terminals with high mobility characteristics in a cell If it is less than a threshold, it is considered that the cell corresponds to a non-high mobility, that is, the cell is a non-high-speed cell.
  • the speed threshold that distinguishes the terminal's high mobility characteristics and non-high mobility characteristics can be configured, for example, it is configured to an existing network experience value of 80km/h.
  • the signal interval is divided according to the radio frequency fingerprint, the cell characteristic interval of the cell is generated, and the terminal model in the characteristic interval of the cell is constructed, and the corresponding mobility characteristics of the cell are further inferred, thereby accurately identifying the cell as a high-speed cell Or non-high-speed cells to support intelligent and refined control of wireless resources.
  • the wireless resource management method of this embodiment may further include: based on historical data related to radio frequency fingerprints in the network area, through machine learning The radio frequency fingerprint characteristic interval is constructed in a manner, and step S201 may include: superimposing the real-time data in the network area as auxiliary information on the radio frequency fingerprint characteristic interval to generate the cell characteristic interval of the cell.
  • Fig. 3 is an exemplary diagram of a construction process of a cell characteristic interval in an embodiment of the disclosure. As shown in FIG. 3, in this example, the construction process of the cell characteristic interval includes the following steps S301 to S304.
  • step S301 collect historical data related to the radio frequency fingerprint, for example, including but not limited to signal quality, measurement reports (for example, including wireless signal strength, interference, reference signal power indication, signal-to-noise ratio, etc.), terminal information (for example, Including the number of users, location information, etc.), cell information, etc.
  • signal quality for example, including but not limited to signal quality
  • measurement reports for example, including wireless signal strength, interference, reference signal power indication, signal-to-noise ratio, etc.
  • terminal information for example, Including the number of users, location information, etc.
  • cell information for example, including cell information, etc.
  • the cell is divided into multiple intervals according to the signal strength, and the clustering algorithm is used to construct the dynamic radio frequency fingerprint characteristic interval, and the radio frequency fingerprint is constructed according to the number of users, user distribution, and base station cell information in the set statistical period Characteristic interval model.
  • the radio frequency fingerprint characteristic interval model may include: cell information, neighboring cell information, base station information, terminal information, etc. in the corresponding radio frequency fingerprint characteristic interval.
  • the radio frequency fingerprint characteristic interval and the radio frequency fingerprint characteristic interval model can be constructed through machine learning. Signal segmentation according to radio frequency fingerprints, assisting specific base station and terminal information, can construct a unique radio frequency fingerprint characteristic interval model of base stations and terminals.
  • the initial radio frequency fingerprint feature interval can be intelligently divided, and the initial radio frequency fingerprint feature interval model can be constructed, thereby constructing a radio frequency fingerprint information database .
  • step S303 real-time data is collected, for example, including but not limited to the real-time measurement report, geographic location, etc. reported by the terminal, and the collected real-time data is used as auxiliary information of the radio frequency fingerprint characteristic interval for online data overlay.
  • an online real-time update method is adopted to generate a cell characteristic interval and a cell characteristic interval model.
  • online real-time data overlay can be performed to generate the cell feature interval corresponding to the current scene and the cell feature interval model.
  • the cell characteristic interval model may include: cell information, neighboring cell information, base station information, terminal information, etc. of the corresponding cell characteristic interval.
  • real-time data can be collected periodically, and the cell characteristic interval and the cell characteristic interval model can be updated based on the collected real-time data.
  • the radio frequency fingerprint information database is constructed from historical data, and the cell characteristic interval and the cell characteristic interval model corresponding to the real-time scene are generated based on the radio frequency fingerprint information database and the collected real-time data, which can increase the data processing speed and improve the real-time scene
  • the construction efficiency of the cell characteristic interval and the cell characteristic interval model under the following.
  • constructing a terminal model in the cell characteristic interval may include: detecting that the radio frequency fingerprint in the cell characteristic interval is within a first set duration Whether the stability condition is satisfied; and when the stability condition is satisfied, a terminal model in the characteristic interval of the cell is constructed.
  • the radio frequency fingerprint in the cell characteristic interval does not change within the first set time period, or the change is small, that is, if the stability condition is satisfied, the terminal model in the cell characteristic interval can be constructed.
  • the first set duration can be adjusted according to actual needs, which is not limited in the present disclosure.
  • step S202 may include: determining the number of terminal models whose hopping conditions meet the hopping condition within a second set time period; when the number meets the first A condition is determined that the cell corresponds to high mobility (in other words, the cell is a high-speed cell); when the number does not meet the first condition, it is determined that the cell corresponds to a non-high mobility (in other words, the cell is a non-high-speed cell).
  • the second setting duration can be adjusted according to actual needs, which is not limited in the present disclosure.
  • a terminal model is constructed in a cell characteristic interval, and the terminal hopping times can be recorded in the terminal model, which is used to characterize the total hopping times of all terminals in the cell characteristic interval.
  • the terminal model is considered to meet the hopping condition; the number of terminal models that meet the hopping threshold condition in the cell is counted; when the number of statistics is greater than Threshold, the cell is determined to be a high-speed cell, and vice versa (that is, when the number of statistics is less than or equal to the threshold), the cell is determined to be a non-high-speed cell.
  • the present disclosure does not limit the setting of jump thresholds and thresholds.
  • Fig. 4 is an exemplary diagram of a mobility feature identification process and a parameter issuance process corresponding to a cell according to an embodiment of the present disclosure.
  • the identification process and parameter issuance process of the mobility feature corresponding to the cell include the following steps S401 to S407.
  • step S401 it is determined that the cell characteristic interval model is in a steady state.
  • the radio frequency fingerprint characteristic in the cell characteristic interval is still changing within the first set time period.
  • the changing area is stable, it is determined that the cell characteristic interval model is in a steady state.
  • step S402 a terminal model in the characteristic interval of the cell is constructed, and the jump of the terminal model in the characteristic interval of the cell is continuously monitored.
  • a terminal model is constructed in a cell characteristic interval, and the terminal model is used to record the conditions of all terminals in the cell characteristic interval.
  • UEinGridModel F(Time, UEnum/Grid, Hop/UE, UePath);
  • Time represents time
  • UEnum/Grid represents the number of terminals in the cell characteristic interval (grid)
  • Hop/UE represents the number of terminal hopping times in the cell characteristic interval (ie, the total number of hopping times of all terminals in the cell characteristic interval)
  • UePath represents the location information or running track of each terminal in the cell characteristic interval.
  • step S403 it is judged whether the number of terminal models that meet the hopping condition in the cell is greater than a threshold.
  • the terminal model When the number of terminal hopping times is greater than the hopping threshold within the second set time period, the terminal model is considered to meet the hopping condition; the number of terminal models that meet the hopping condition in the cell is counted; when the hopping condition is met in the cell If the number of terminal models is greater than the threshold, then go to step S404; otherwise, go to step S406.
  • step S404 when the number of terminal models meeting the hopping condition in the cell is greater than the threshold, it is determined that the cell is a high-speed cell.
  • step S405 the parameter set corresponding to the high-speed cell is issued to the base station corresponding to the cell, and the mobility characteristics and monitoring indicators corresponding to the cell are updated synchronously.
  • step S406 when the number of terminal models meeting the hopping condition in the cell is less than or equal to the threshold, it is determined that the cell is a non-high-speed cell.
  • step S407 the parameter set corresponding to the non-high-speed cell is issued to the base station corresponding to the cell, and the mobility characteristics and monitoring indicators corresponding to the cell are updated synchronously.
  • the radio frequency fingerprint technology can accurately identify high-speed cells and non-high-speed cells, thereby supporting fine control of wireless resources, so that the wireless parameter configuration can be dynamically adjusted as the scene changes. Moreover, parameter self-configuration can be realized, thereby saving operators' labor costs.
  • the wireless resource management method of this embodiment may further include: generating parameter sets corresponding to different mobility characteristics through a machine learning manner.
  • generating parameter sets corresponding to different mobility characteristics by means of machine learning may include: generating, by means of machine learning, a first parameter set corresponding to a high-speed cell and a second parameter set corresponding to a non-high-speed cell, the first parameter set and The second parameter set includes: cell-level parameters, or cell-level parameters and terminal-level parameters.
  • cell-level parameters or cell-level parameters and terminal-level parameters.
  • the terminal-level parameters can be issued by the base station to the corresponding terminal.
  • the radio resource management method of this embodiment may further include: delivering a parameter set matching the mobility feature corresponding to the cell to the network device corresponding to the cell .
  • the first parameter set corresponding to the high-speed cell can be issued to the base station; when the cell is a non-high-speed cell, the second parameter set corresponding to the non-high-speed cell can be issued to the base station.
  • the base station receives the first parameter set or the second parameter set, it can allocate radio resources adapted to the scenario.
  • the radio resource management method of this embodiment may further include: periodically monitoring whether the mobility feature corresponding to the cell changes; and when the mobility feature corresponding to the cell changes, triggering parameter set Adjustment. For example, when the cell is changed from a high-speed cell to a non-high-speed cell, the second parameter set corresponding to the non-high-speed cell is issued to the base station; when the cell is changed from a non-high-speed cell to a high-speed cell, the first parameter set corresponding to the high-speed cell is issued to the base station. Parameter set.
  • FIG. 5 is an example diagram of the update process of the parameter set in the embodiment of the disclosure. As shown in FIG. 5, the update process of the parameter set of this example includes the following steps S501 to S503.
  • step S501 the mobility feature corresponding to the cell is monitored in real time during the detection period, and the change of the mobility feature corresponding to the cell in the detection period is checked.
  • step S502 it is determined whether the mobility feature corresponding to the cell has been changed, and if there is a change, step S503 is executed; otherwise, step S501 is returned.
  • the change of the mobility feature corresponding to the cell includes: the cell is changed from a high-speed cell to a non-high-speed cell, or from a non-high-speed cell to a high-speed cell.
  • step S501 when the number of terminal models that meet the hopping condition in a high-speed cell is changed, but the cell is still a high-speed cell, return to step S501; or when the number of terminal models that meet the hopping condition in a non-high-speed cell is changed If the number changes, but the cell is still a non-high-speed cell, return to step S501.
  • step S503 according to the updated mobility characteristics, the corresponding parameter set is delivered to the base station, and the cell parameters are automatically configured to take effect at the base station.
  • the wireless parameter configuration can be dynamically adjusted as the scene changes, which can make the parameter configuration more reasonable and improve the overall throughput of the cell, thereby greatly improving the performance in the area and the user experience of the entire network.
  • the process of performing intelligent management of wireless resources when the cell is determined as a high-speed cell based on the radio frequency fingerprint technology includes the following steps S11 to S15.
  • step S11 a cell characteristic interval model and a terminal model in the cell characteristic interval are constructed through machine learning. Model updates can be performed periodically.
  • the cell characteristic interval is not only different in signal strength, but also different in geographic location.
  • a parameter set corresponding to a high-speed cell and a parameter set corresponding to a non-high-speed cell can be generated.
  • a terminal model in the cell characteristic interval is constructed.
  • the terminal appears in multiple cell characteristic intervals within a certain period of time, it means that the terminal is in the process of moving at this time (referred to as hopping). The greater the number of hops per unit time, the faster the moving speed, and vice versa. The same is true.
  • step S12 monitor the hopping of the terminal model in the cell characteristic interval. If the terminal model frequently changes in multiple cell characteristic intervals per unit time and reaches a certain hopping threshold, it means that the terminal user in the interval is moving at a high speed. When a certain number of terminal models are in frequent changes and reach a certain hopping threshold, it is determined that the cell is a high-speed cell, and the high-speed cell parameter adjustment strategy is triggered at this time.
  • step S13 the parameter set corresponding to the constructed high-speed cell is issued to the base station, and the radio frequency fingerprint characteristics in the network are continuously monitored, the cell characteristic interval is updated in real time, and the parameter set samples corresponding to the high-speed cell are updated iteratively.
  • step S14 the network index after the parameter set update is detected in real time, and according to the change of the network index, roll back or confirm that the modification takes effect.
  • step S15 the hopping situation of the terminal model in the characteristic interval is monitored in real time, and it is judged whether the high-speed cell is changed.
  • a new parameter set is updated and executed synchronously, for example, a parameter set corresponding to a non-high-speed cell.
  • the process of intelligently managing wireless resources when the cell is judged as a non-high-speed cell based on the radio frequency fingerprint technology includes the following steps S21 to S25.
  • step S21 a cell characteristic interval model and a terminal model in the interval are constructed through machine learning. Model updates can be performed periodically.
  • the cell characteristic interval is not only different in signal strength, but also different in geographic location.
  • a parameter set corresponding to a high-speed cell and a parameter set corresponding to a non-high-speed cell can be generated.
  • a terminal model in the cell characteristic interval is constructed.
  • the terminal appears in multiple cell characteristic intervals within a certain period of time, it means that the terminal is in the process of moving at this time (referred to as hopping). The greater the number of hops per unit time, the faster the moving speed, and vice versa. The same is true.
  • step S22 monitor the hopping of the terminal model in the cell characteristic interval. If the terminal model has no change in multiple cell characteristic intervals per unit time or is lower than a certain hopping threshold, it means that the terminal user in the interval is not moving or For non-high-speed movement, when a certain amount of terminal models are unchanged or below a certain hopping threshold, the cell is determined to be a non-high-speed cell, and the non-high-speed cell parameter adjustment strategy is triggered at this time.
  • step S23 the parameter set corresponding to the constructed non-high-speed cell is delivered to the base station, and the radio frequency fingerprint characteristics in the network are continuously monitored, the cell characteristic interval is updated in real time, and the parameter set samples corresponding to the non-high-speed cell are iteratively updated.
  • step S24 the network index after the parameter set update is detected in real time, and according to the change of the network index, roll back or confirm that the modification takes effect.
  • step S25 the hopping situation of the terminal model in the characteristic interval is monitored in real time, and it is judged whether the non-high-speed cell has changed.
  • a new parameter set is updated and executed synchronously, for example, the parameter set corresponding to the high-speed cell.
  • the above exemplary embodiments provide the capabilities of refined cell management, high-speed cell identification, and parameter self-configuration, reduce the difficulty of network optimization, improve the ease of use of functions, effectively ensure the utilization of wireless resources, and greatly save operations Moreover, it is suitable for the intelligent technology of wireless communication network, especially the combination of artificial intelligence technology and wireless communication field, which contributes to the intelligent application of the wireless field and plays a vital role.
  • the wireless resource management method of this embodiment may further include: constructing performance models under different parameter set configurations through machine learning.
  • the radio resource management method of this embodiment may further include: activating the performance index within the third set duration Detect and compare the detected performance indicators with the performance indicators in the performance model corresponding to the issued parameter set; when the comparison result meets the deviation condition, the parameter set rollback is triggered.
  • the third setting duration can be adjusted according to actual needs, which is not limited in the present disclosure.
  • the process of performing wireless resource intelligent management performance guarantee based on radio frequency fingerprint technology includes the following steps S31 to S35.
  • step S31 the cell characteristic interval model and the terminal model in the cell characteristic interval are constructed through machine learning, and the parameter set corresponding to the high-speed cell and the parameter set corresponding to the non-high-speed cell are generated through the machine learning method.
  • step S32 the cell characteristic interval model, the cell parameter set and the performance index are associated, and the performance model under different parameter configurations is constructed through machine learning.
  • step S33 whenever the cell’s high-speed or non-high-speed determination is successful and the parameter set is issued, the performance index detection within a certain period of time (that is, the third set duration) is started to detect whether the current operation performance index is consistent with The performance indicators in the performance model deviate.
  • step S34 if the deviation exceeds a certain deviation threshold, the fallback parameter set is triggered to the previous configuration; for example, if the current cell is a high-speed cell and the previous stage is a non-high-speed cell, fall back to the parameter set corresponding to the non-high-speed cell .
  • step S35 if there is no deviation or the deviation is within the controlled range, the performance model is maintained and the parameter set determined by the current decision is adopted.
  • the performance model is only updated when the cell characteristic interval model or the terminal model or cell parameter set within the interval changes, and other scenarios are in a stable state.
  • the embodiment of the present disclosure constructs a radio frequency fingerprint
  • the information database also intelligently divides the cell characteristic interval, and further through the creation of the cell characteristic interval model and the terminal model in the cell characteristic interval, infer the mobility characteristics corresponding to the current cell, and perform intelligent real-time matching of the mobility characteristics at the base station Parameter self-configuration.
  • Fig. 6 is a schematic diagram of a radio resource management apparatus according to an embodiment of the present disclosure.
  • the wireless resource management device provided in this embodiment includes: a model construction module 601, which is used to generate a cell characteristic interval of a cell based on radio frequency fingerprints, and construct a terminal model in the cell characteristic interval; and a management module 602 , Used to determine the mobility feature corresponding to the cell according to the hopping situation of the terminal model in the cell feature interval of the cell.
  • the model construction module 601 is also used to construct the radio frequency fingerprint characteristic interval through machine learning based on the historical data related to the radio frequency fingerprint in the network area; and to generate the cell characteristic interval of the cell in the following way: The real-time data inside is superimposed on the radio frequency fingerprint characteristic interval as auxiliary information to generate the cell characteristic interval of the cell.
  • the model construction module 601 is configured to construct a terminal model in the cell characteristic interval by detecting whether the radio frequency fingerprint in the cell characteristic interval satisfies the stability condition within a first set time period; when the stability condition is satisfied , Then construct the terminal model in the cell characteristic interval.
  • the management module 602 is configured to determine the mobility feature corresponding to the cell according to the hopping situation of the terminal model in the cell feature interval of the cell in the following manner: determine to hop within a second set time period The situation is the number of terminal models that meet the hopping condition; when the number meets the first condition, it is determined that the cell corresponds to high mobility; when the number does not meet the first condition, it is determined that the cell corresponds to non-high mobility.
  • the radio resource management device may further include: a parameter set configuration module, configured to generate parameter sets corresponding to different mobility characteristics through machine learning, and the parameter sets include parameters corresponding to high-speed cells.
  • the first parameter set and the second parameter set corresponding to the non-high-speed cell, both the first parameter set and the second parameter set include: cell-level parameters, or cell-level parameters and terminal-level parameters.
  • the parameter set configuration module is further configured to: after the management module 602 determines the mobility feature corresponding to the cell, deliver to the network device corresponding to the cell a parameter matching the mobility feature corresponding to the cell set.
  • the management module 602 is further configured to: periodically monitor whether the mobility feature corresponding to the cell changes; and when the mobility feature corresponding to the cell changes, trigger parameter set adjustment.
  • the radio resource management device may further include: an index control module for constructing performance models under different parameter set configurations through machine learning; and the parameter set configuration module corresponds to the cell After the network device of the network device has issued the parameter set matching the mobility feature corresponding to the cell, it starts the performance indicator detection within the third set time period, and compares the detected performance indicator with the performance model corresponding to the issued parameter set. Performance index; when the comparison result meets the deviation condition, the parameter set rollback is triggered.
  • the embodiments of the present disclosure also provide a computer-readable storage medium that stores a computer program that, when executed by a processor, implements the steps of the above-mentioned wireless resource management method, such as the steps shown in FIG. 2.
  • Such software may be distributed on a computer-readable medium
  • the computer-readable medium may include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium).
  • the term computer storage medium includes volatile and non-volatile memory 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 disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage device, or Any other medium used to store desired information and that can be accessed by a computer.
  • communication media usually contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as carrier waves or other transmission mechanisms, and may include any information delivery media .

Abstract

本公开提供一种无线资源管理方法和装置以及计算机可读存储介质，所述方法包括：基于射频指纹，生成小区的小区特征区间，并构建小区特征区间内的终端模型；以及根据该小区的小区特征区间内的终端模型的跳变情况，确定该小区对应的移动性特征。

Description

无线资源管理方法及装置 技术领域
本公开实施例涉及但不限于无线通信技术领域。
背景技术
随着无线通信网络的迅猛发展，用户规模和业务量随之快速增长，复杂多样的业务类型、庞大的用户群体，对于无线小区的差异化配置和管理都提出了新的挑战。对于不同类型的小区用户特征，采用不同的无线资源管理参数，这些参数随着用户模型的变更动态更新，低成本、智能化、无人化是各大运营商日常运营管理中关注的首要问题之一。
在实际应用中，当一个小区中的用户多数为低移动性特征时，只有配置与之匹配的低移动性属性参数，才可以充分提供单位区域内的系统容量，为用户提供更高的体验感受；当一个小区中的用户多数为高移动性特征时，需要与之匹配的高移动性属性参数，用以减少移动性带来的性能损失。
由此可见，小区的高低速识别、无线资源精细化的参数配置，都为运营商带来很大的困扰和工作量，也增加了巨大的成本，各大运营商迫切需要解决这些问题。
发明内容
本公开提供一种无线资源管理方法，包括：基于射频指纹，生成小区的小区特征区间，并构建所述小区特征区间内的终端模型；以及根据所述小区的小区特征区间内的终端模型的跳变情况，确定所述小区对应的移动性特征。
另一方面，本公开提供一种无线资源管理装置，包括：模型构建模块，用于基于射频指纹，生成小区的小区特征区间，并构建所述小区特征区间内的终端模型；以及管理模块，用于根据所述小区的小区特征区间内的终端模型的跳变情况，确定所述小区对应的移动性特 征。
另一方面，本公开提供一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述无线资源管理方法的步骤。
附图说明
附图用来提供对本公开技术方案的进一步理解，并且构成说明书的一部分，与本公开的实施例一起用于解释本公开的技术方案，并不构成对本公开技术方案的限制。
图1为根据本公开示例性实施例的实施环境示意图；
图2为根据本公开实施例的无线资源管理方法的流程图；
图3为根据本公开实施例的小区特征区间的构建流程的示例图；
图4为根据本公开实施例的小区对应的移动性特征的识别流程和参数下发流程的示例图；
图5为根据本公开实施例的参数集更新流程的示例图；以及
图6为根据本公开实施例的无线资源管理装置的示意图。
具体实施方式
为使本公开的目的、技术方案和优点更加清楚明白，下文中将结合附图对本公开的实施例进行详细说明。需要说明的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互任意组合。
在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行。并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
在传统方式中，用户终端(User Equipment，UE)速度识别最常见的方式包括：根据终端历史信息，通过终端在历史小区驻留的时长来判决终端移动速度；在高铁场景通过多普勒效应来判断终端移动速度。但是，无论采用哪种方式，要么误差大，要么应用场景受限，在实际应用中均无法广泛使用，不具备通用性和普遍性。
针对精细化管理的参数配置，更是需要大量的专家日积月累才 可以形成专家经验库，耗费大量的人力和时间，成本极高。
本公开实施例提供一种无线资源管理方法及装置，利用射频指纹技术识别小区对应的移动性特征，可以适用于不同的应用场景，具备通用性和普遍性。本公开实施例可以应用于无线资源智能化控制中，从而支持对无线资源进行智能化、精细化控制，使得无线资源的参数可以随场景的变化而动态调整，进而使得参数配置更合理，可以极大地提升区域内的性能，提升用户体验。
图1为根据本公开示例性实施例的实施环境示意图。如图1所示，通信系统可以包括：用户终端101、网络设备102以及网络管理控制端103。网络设备102可以分别与用户终端101和网络管理控制端103进行通信。图1仅为一种示例，本公开对于用户终端101、网络设备102以及网络管理控制端103的数目并不限定。
应理解，图1所示的通信系统仅仅是一个示例，本公开实施例不限定于此。本公开实施例的技术方案可以应用于各种通信系统，例如：长期演进(Long Term Evolution，LTE)系统、LTE时分双工(Time Division Duplex，TDD)、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、5G新空口(New Radio，NR)通信系统等。
网络设备102可以是LTE中的演进型基站(Evolutional Node B，eNB或eNodeB)、5G网络中的基站设备、或者未来通信系统中的基站等。
用户终端101可以经无线接入网(Radio Access Network，RAN)与一个或多个核心网(Core Network)进行通信，也可称为接入终端、用户设备(User Equipment，UE)、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、终端设备、终端、无线通信设备、用户代理或用户装置。例如，用户终端101可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字处理(Personal Digital Assistant，PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、 可穿戴设备、或者5G网络中的终端设备等。
在无线网络通信中，用户终端101会通过测量的方式获取无线信号信息，并将获取的无线信号信息告知网络设备102(比如，基站)，网络设备102为用户终端101提供合适的无线资源，从而保证用户终端101在各个基站之间移动时的正常业务。
不同类型的用户终端、不同的用户习惯、以及不同的用户分布，对小区无线资源的需求不同，从而造成无线资源分配具有较大的差异性。尤其在用户终端的高速移动和非高速移动场景下，无线资源分配是否恰当，对用户体验起着至关重要的作用。而无线资源分配是通过不同的参数配置的。由此可见，符合区域特征的参数配置在无线网络通信中是至关重要的，直接决定着用户体验。
本实施例提供的无线资源管理方法可以由网络管理控制端执行，网络管理控制端可以根据网络设备上报的信息，向网络设备下发配置无线资源的参数，从而实现无线资源智能化、精细化的参数管理。网络管理控制端可以为一台独立的服务器，或者服务器集群。然而，本公开对此并不限定。
图2为根据本公开实施例的无线资源管理方法的流程图。如图2所示，本实施例提供的无线资源管理方法包括如下步骤S201至S202。
在步骤S201，基于射频指纹，生成小区的小区特征区间，并构建小区特征区间内的终端模型；
在步骤S202，根据该小区的小区特征区间内的终端模型的跳变情况，确定该小区对应的移动性特征。
本实施例中，射频指纹用于表征网络设备(基站)覆盖区域无线信号强度特征。小区特征区间用于标识用户终端的无线性能位置区域。小区特征区间的确定依赖于网络区域内的射频指纹。
本实施例中，针对任一小区特征区间内的任一终端，当定时周期内该终端出现在多个小区特征区间内，则代表该终端处于移动过程中，在本实施例中称为跳变。终端从一个小区特征区间移动到另一个小区特征区间的过程可以称之为一次跳变。针对一个终端，根据定时周期内该终端的跳变总次数，可以计算出单位时间的跳变指数(比如， 通过定时周期内的跳变总次数除以定时周期得到)，单位时间的跳变指数越大，则代表终端的移动速度越快；反之，当单位时间的跳变指数为0或较小，则代表终端未移动或者移动速度较慢。
本实施例中，小区对应的移动性特征用于表征小区内大部分终端的移动性特征(高移动性或非高移动性)。当一终端的移动速度大于或等于速度阈值(比如，90km/h)，则认为该终端具有高移动性特征；否则，该终端即具有非高移动性特征。比如，当一小区内具有高移动性特征的终端数目大于或等于一阈值，则认为该小区对应高移动性特征，即，该小区为高速小区；当一小区内具有高移动性特征的终端数目小于一阈值，则认为该小区对应非高移动性，即，该小区为非高速小区。需要说明的是，区分终端的高移动性特征和非高移动性特征的速度阈值是可以配置的，比如，配置为现网经验值80km/h。
本公开实施例中，按照射频指纹来划分信号区间段，生成小区的小区特征区间，并构建小区特征区间内的终端模型，进一步推理出小区对应的移动性特征，从而可以精准识别小区为高速小区或非高速小区，以支持对无线资源进行智能化、精细化控制。
基于图2所示的无线资源管理方法，在一示例性实施方式中，在步骤S201之前，本实施例的无线资源管理方法还可以包括：基于网络区域内射频指纹相关的历史数据，通过机器学习方式构建射频指纹特征区间，并且步骤S201可以包括：将网络区域内的实时数据，作为辅助信息叠加到射频指纹特征区间，生成该小区的小区特征区间。
图3为本公开实施例中小区特征区间的构建流程的示例图。如图3所示，在本示例中，小区特征区间的构建过程包括如下步骤S301至S304。
在步骤S301，采集射频指纹相关的历史数据，比如，包括且不限于信号质量、测量报告(比如，包括无线信号强度、干扰、参考信号功率指示、信噪比等信息)、终端信息(比如，包括用户数、位置信息等)、小区信息等。
在步骤S302，按照信号强度将小区划分为多个区间段，并使用聚类算法，构建动态射频指纹特征区间，并根据设定统计周期内的用 户数量、用户分布、基站小区信息，构建射频指纹特征区间模型。射频指纹特征区间模型中可以包括：相应的射频指纹特征区间内的小区信息、邻区信息、基站信息、终端信息等。
在本示例中，可以通过机器学习方式构建射频指纹特征区间和射频指纹特征区间模型。按照射频指纹进行信号分段，辅助特定的基站和终端信息，可以构建出基站和终端特有的射频指纹特征区间模型。
在本示例中，通过获取历史的测量报告、终端信息、小区信息以及位置信息等，可以智能划分出初始的射频指纹特征区间，构建初始的射频指纹特征区间模型，由此构建无线射频指纹信息库。
在步骤S303，采集实时数据，比如，包括且不限于终端上报的实时测量报告、地理位置等，并将采集的实时数据作为射频指纹特征区间的辅助信息进行在线数据叠加。
在步骤S304，采用在线实时更新的方式，生成小区特征区间和小区特征区间模型。基于初始的射频指纹特征区间，进行在线实时数据叠加，可以生成对应当前场景的小区特征区间，以及小区特征区间模型。小区特征区间模型中可以包括：相应的小区特征区间的小区信息、邻区信息、基站信息、终端信息等。
在本示例中，可以周期性采集实时数据，并根据采集的实时数据进行小区特征区间和小区特征区间模型的更新。
在本示例中，通过历史数据构建无线射频指纹信息库，并根据无线射频指纹信息库和采集的实时数据生成对应实时场景的小区特征区间和小区特征区间模型，可以提升数据处理速度，提高实时场景下的小区特征区间和小区特征区间模型的构建效率。
基于图2所示的无线资源管理方法，在一示例性实施方式中，在步骤S201中，构建小区特征区间内的终端模型可以包括：检测小区特征区间内的射频指纹在第一设定时长内是否满足稳定条件；以及当满足稳定条件，则构建该小区特征区间内的终端模型。在一示例中，小区特征区间内的射频指纹在第一设定时长内不发生变化，或者变化较小，即，满足稳定条件，可以构建该小区特征区间内的终端模型。第一设定时长可以根据实际需求进行调整，本公开对此并不限定。
基于图2所示的无线资源管理方法，在一示例性实施方式中，步骤S202可以包括：确定在第二设定时长内跳变情况满足跳变条件的终端模型的数目；当该数目满足第一条件，则确定该小区对应高移动性(换言之，小区为高速小区)；当该数目不满足第一条件，则确定该小区对应非高移动性(换言之，小区为非高速小区)。第二设定时长可以根据实际需求进行调整，本公开对此并不限定。
在一示例中，在一个小区特征区间内构建一个终端模型，该终端模型内可以记录终端跳变次数，用于表征该小区特征区间内全部终端的跳变总次数。当在第二设定时长内终端跳变次数大于跳变门限值，则认为该终端模型满足跳变条件；统计该小区内满足跳变门限条件的终端模型的数目；当该统计的数目大于阈值，则判定该小区为高速小区，反之(即，当该统计的数目小于或等于阈值)，则判定该小区为非高速小区。关于跳变门限值、阈值的设定本公开并不限定。
图4为根据本公开实施例的小区对应的移动性特征的识别流程和参数下发流程的示例图。在一示例中，如图4所示，小区对应的移动性特征的识别流程和参数下发流程包括如下步骤S401至S407。
在步骤S401，判定小区特征区间模型处于稳态。
对于小区中的任一小区特征区间，检测该小区特征区间内的射频指纹特征在第一设定时长内是否还在变化，当变化区域稳定时，则判定小区特征区间模型处于稳态。
在步骤S402，构建小区特征区间内的终端模型，并持续监测小区特征区间内的终端模型的跳变情况。一个小区特征区间内构建一个终端模型，该终端模型用于记录该小区特征区间内的全部终端的情况。
小区特征区间内的终端模型的一种示例可以为：
UEinGridModel＝F(Time,UEnum/Grid,Hop/UE,UePath)；
其中，Time表示时间，UEnum/Grid表示小区特征区间(栅格)内的终端数目，Hop/UE表示小区特征区间内终端跳变次数(即，小区特征区间内的所有终端的跳变总次数)；UePath表示小区特征区间内每个终端的位置信息或运行轨迹。
在步骤S403，判断小区内满足跳变条件的终端模型的数目是否 大于阈值。
当在第二设定时长内终端跳变次数大于跳变门限值，则认为该终端模型满足跳变条件；统计该小区内满足跳变条件的终端模型的数目；当小区内满足跳变条件的终端模型的数目大于阈值，则转至步骤S404；否者，转至步骤S406。
在步骤S404，当小区内满足跳变条件的终端模型的数目大于阈值，则确定该小区为高速小区。
在步骤S405，下发高速小区对应的参数集到该小区对应的基站，并同步更新该小区对应的移动性特征和监测指标。
在步骤S406，当小区内满足跳变条件的终端模型的数目小于或等于阈值，则确定该小区为非高速小区。
在步骤S407，下发非高速小区对应的参数集到该小区对应的基站，并同步更新该小区对应的移动性特征和监测指标。
本示例中，基于射频指纹技术可以准确识别高速小区和非高速小区，从而支持对无线资源进行精细化控制，使得无线参数配置可以随场景的变换而动态调整。而且，可以实现参数自配置，从而节省运营商人力成本。
基于图2所示的无线资源管理方法，在一示例性实施方式中，本实施例的无线资源管理方法还可以包括：通过机器学习方式生成不同的移动性特征对应的参数集。
示例性地，通过机器学习方式生成不同的移动性特征对应的参数集可以包括：通过机器学习方式生成高速小区对应的第一参数集和非高速小区对应的第二参数集，第一参数集和第二参数集均包括：小区级参数，或者小区级参数和终端级参数。在一示例中，通过下发小区级参数和终端级参数，不仅可以实现小区级控制，还可以实现终端级控制。终端级参数可以由基站下发给对应的终端。
在本示例性实施方式中，确定小区对应的移动性特征之后，本实施例的无线资源管理方法还可以包括：向该小区对应的网络设备下发与该小区对应的移动性特征匹配的参数集。比如，当小区为高速小区，则可以向基站下发高速小区对应的第一参数集；当小区为非高速 小区，则可以向基站下发非高速小区对应的第二参数集。基站接收到第一参数集或第二参数集之后，可以进行适应场景的无线资源分配。
在本示例性实施方式中，本实施例的无线资源管理方法还可以包括：周期性监测小区对应的移动性特征是否发生变更；以及当该小区对应的移动性特征发生变更，则触发进行参数集调整。比如，当小区从高速小区变更为非高速小区，则向基站下发非高速小区对应的第二参数集；当小区从非高速小区变更为高速小区，则向基站下发高速小区对应的第一参数集。
图5为本公开实施例中的参数集的更新流程的示例图。如图5所示，本示例的参数集的更新流程包括如下步骤S501至S503。
在步骤S501，在检测周期内实时监测小区对应的移动性特征，查看检测周期内小区对应的移动性特征的变更情况。
在步骤S502，判断小区对应的移动性特征是否发生变更，若发生变更，则执行步骤S503；否则，返回步骤S501。小区对应的移动性特征发生变更包括：小区从高速小区变更为非高速小区，或者从非高速小区变更为高速小区。
需要注意的是，当一高速小区内满足跳变条件的终端模型的数目发生变更，但该小区仍为高速小区，则返回步骤S501；或者当一非高速小区内满足跳变条件的终端模型的数目发生变更，但该小区仍为非高速小区，则返回步骤S501。
在步骤S503，根据更新后的移动性特征，下发对应的参数集到基站，并自动化配置小区参数到基站生效。
在本示例中，可以随着场景的变化动态调整无线参数配置，可以使得参数配置更合理，提升小区整体吞吐量，从而极大地提升区域内的性能，以及整网的用户体验。
在一示例性实施例中，基于射频指纹技术判决小区为高速小区时进行无线资源智能化管理的流程包括如下步骤S11至S15。
在步骤S11，通过机器学习方式构建小区特征区间模型和小区特征区间内的终端模型。可以周期性进行模型更新。小区特征区间不仅在信号强度上不同，在地理位置上也不同。
通过采集现网指标和无线资源配置信息，基于机器学习方式可以生成高速小区对应的参数集和非高速小区对应的参数集。
对于小区中的任一小区特征区间，检测该小区特征区间内的射频指纹特征在第一设定时长内是否还在变化，当变化区域稳定时，构建该小区特征区间内的终端模型。当终端在一定时长内，出现在多个小区特征区间内，则代表终端此时处于移动过程中(称之为跳变)，当单位时间跳变次数越大，则代表移动速度越快，反之亦然。
在步骤S12，监测小区特征区间内终端模型的跳变情况，如果终端模型在单位时间内的多个小区特征区间频繁变动且达到一定跳变门限，则说明区间内的终端用户此时正在高速移动，当一定数量的终端模型均处于频繁变动且达到一定跳变门限时，则判定该小区为高速小区，此时触发高速小区参数调整策略。
在步骤S13，下发构建好的高速小区对应的参数集到基站，并持续监测网络中的射频指纹特征，实时更新小区特征区间，迭代更新高速小区对应的参数集样本。
在步骤S14，实时检测参数集更新后的网络指标，并根据网络指标的变化情况，回退或者确认本次修改生效。
在步骤S15，实时监测特征区间内的终端模型的跳变情况，判决高速小区是否发生变更，当发生变更时，则同步更新和执行新的参数集，比如，非高速小区对应的参数集。
在一示例性实施方式中，基于射频指纹技术判决小区为非高速小区时进行无线资源智能化管理的流程包括如下步骤S21至S25。
在步骤S21，通过机器学习方式构建小区特征区间模型和区间内的终端模型。可以周期性进行模型更新。小区特征区间不仅在信号强度上不同，在地理位置上也不同。
通过采集现网指标和无线资源配置信息，基于机器学习方式可以生成高速小区对应的参数集和非高速小区对应的参数集。
对于小区中的任一小区特征区间，检测该小区特征区间内的射频指纹特征在第一设定时长内是否还在变化，当变化区域稳定时，构建该小区特征区间内的终端模型。当终端在一定时长内，出现在多个 小区特征区间内，则代表终端此时处于移动过程中(称之为跳变)，当单位时间跳变次数越大，则代表移动速度越快，反之亦然。
在步骤S22，监测小区特征区间内终端模型的跳变情况，如果终端模型在单位时间内的多个小区特征区间无变动或低于一定跳变门限，说明区间内的终端用户此时未移动或非高速移动，当一定量的终端模型均处于无变动或低于一定跳变门限，则判定该小区为非高速小区，此时触发非高速小区参数调整策略。
在步骤S23，下发构建好的非高速小区对应的参数集到基站，并持续监测网络中的射频指纹特征，实时更新小区特征区间，迭代更新非高速小区对应的参数集样本。
在步骤S24，实时检测参数集更新后的网络指标，并根据网络指标的变化情况，回退或者确认本次修改生效。
在步骤S25，实时监测特征区间内的终端模型的跳变情况，判决非高速小区是否发生变更，当发生变更时，则同步更新和执行新的参数集，比如，高速小区对应的参数集。
上述示例性实施例提供了精细化小区管理、高速小区识别、参数自配置的能力，降低了网络优化的难度，提升了功能易用性，有效地保证了无线资源利用率，极大地节约了运营商成本等；而且，适用于无线通信网络智能化技术，尤其是将人工智能技术和无线通信领域相结合，为无线领域的智能化应用贡献力量，发挥了至关重要的作用。
基于图2所示的无线资源管理方法，在一示例性实施方式中，本实施例的无线资源管理方法还可以包括：通过机器学习方式构建不同参数集配置下的性能模型。
在本示例中，向小区对应的网络设备下发与该小区对应的移动性特征匹配的参数集之后，本实施例的无线资源管理方法还可以包括：启动在第三设定时长内的性能指标检测，比较检测到的性能指标与下发的参数集对应的性能模型中的性能指标；当比较结果满足偏离条件，则触发参数集回退。第三设定时长可以根据实际需求进行调整，本公开对此并不限定。
在本示例性实施例中，基于射频指纹技术进行无线资源智能化 管理性能保障的流程包括如下步骤S31至S35。
在步骤S31，通过机器学习方式构建小区特征区间模型和小区特征区间内的终端模型，通过机器学习方式生成高速小区对应的参数集和非高速小区对应的参数集。
在步骤S32，将小区特征区间模型、小区参数集和性能指标进行关联，通过机器学习构建出不同参数配置下的性能模型。
在步骤S33，每当小区的高速或非高速判决成功并进行参数集下发后，启动在一定时间段(即，第三设定时长)内的性能指标检测，检测本次操作性能指标是否和性能模型中的性能指标偏离。
在步骤S34，若偏离且超过一定偏离门限，则触发回退参数集至前一配置；比如，当前小区为高速小区，前一阶段为非高速小区，则回退至非高速小区对应的参数集。
在步骤S35，若未发生偏离或偏离在受控范围内，则维持性能模型，采用当前判决确定的参数集。
需要说明的是，性能模型仅在小区特征区间模型或区间内终端模型或小区参数集发生变更时进行更新，其他场景均处于稳定状态。
针对无线通信系统中基站小区在不同场景下，尤其是具有高低速差异特征的情况下，无线资源的移动性参数无法随场景的变化而实时动态变更的问题；本公开实施例通过构建无线射频指纹信息库并智能划分出小区特征区间，进一步地通过创建小区特征区间模型、小区特征区间内的终端模型，推理出当前小区对应的移动性特征，并在基站智能化实时执行与移动性特征匹配的参数自配置。如此，可以实现场景的自识别，为站点规划提供参考；实现参数自配置，节省运营商人力成本；无线资源分配更加合理，提升小区整体吞吐量；采用人工智能技术，使得网络更加智能化。
图6为根据本公开实施例的无线资源管理装置的示意图。如图6所示，本实施例提供的无线资源管理装置，包括：模型构建模块601，用于基于射频指纹，生成小区的小区特征区间，并构建小区特征区间内的终端模型；以及管理模块602，用于根据该小区的小区特征区间内的终端模型的跳变情况，确定该小区对应的移动性特征。
在一示例性实施方式中，模型构建模块601还用于基于网络区域内射频指纹相关的历史数据，通过机器学习方式构建射频指纹特征区间；以及通过以下方式生成小区的小区特征区间：将网络区域内的实时数据，作为辅助信息叠加到射频指纹特征区间，生成小区的小区特征区间。
在一示例性实施方式中，模型构建模块601用于通过以下方式构建小区特征区间内的终端模型：检测小区特征区间内的射频指纹在第一设定时长内是否满足稳定条件；当满足稳定条件，则构建小区特征区间内的终端模型。
在一示例性实施方式中，管理模块602用于通过以下方式根据小区的小区特征区间内的终端模型的跳变情况，确定该小区对应的移动性特征：确定在第二设定时长内跳变情况满足跳变条件的终端模型的数目；当所述数目满足第一条件，则确定小区对应高移动性；当所述数目不满足第一条件，则确定小区对应非高移动性。
在一示例性实施方式中，本实施例提供的无线资源管理装置还可以包括：参数集配置模块，用于通过机器学习方式生成不同的移动性特征对应的参数集，参数集包括高速小区对应的第一参数集和非高速小区对应的第二参数集，第一参数集和第二参数集均包括：小区级参数，或者小区级参数和终端级参数。
在一示例性实施方式中，参数集配置模块，还用于：在管理模块602确定小区对应的移动性特征之后，向该小区对应的网络设备下发与该小区对应的移动性特征匹配的参数集。
在一示例性实施方式中，管理模块602还用于：周期性监测小区对应的移动性特征是否发生变更；以及当该小区对应的移动性特征发生变更，则触发进行参数集调整。
在一示例性实施方式中，本实施例提供的无线资源管理装置还可以包括：指标控制模块，用于通过机器学习方式构建不同参数集配置下的性能模型；以及在参数集配置模块向小区对应的网络设备下发与该小区对应的移动性特征匹配的参数集之后，启动在第三设定时长内的性能指标检测，比较检测到的性能指标与下发的参数集对应的性 能模型中的性能指标；当比较结果满足偏离条件，则触发参数集回退。
关于本实施例提供的无线资源管理装置的相关说明可以参照上述方法实施例的描述，故于此不再赘述。
此外，本公开实施例还提供一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时实现上述的无线资源管理方法的步骤，比如图2所示的步骤。
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。在硬件实施方式中，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。某些组件或所有组件可以被实施为由处理器，如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。

Claims (11)

  1. 一种无线资源管理方法，包括：
    基于射频指纹，生成小区的小区特征区间；
    构建所述小区特征区间内的终端模型；以及
    根据所述小区的小区特征区间内的终端模型的跳变情况，确定所述小区对应的移动性特征。
  2. 根据权利要求1所述的方法，还包括：
    基于网络区域内的射频指纹相关的历史数据，通过机器学习方式构建所述射频指纹特征区间；
    并且基于射频指纹，生成小区的小区特征区间的步骤包括：
    将所述网络区域内的实时数据，作为辅助信息叠加到所述射频指纹特征区间，生成所述小区的小区特征区间。
  3. 根据权利要求1所述的方法，其中，构建所述小区特征区间内的终端模型的步骤包括：
    检测所述小区特征区间内的射频指纹在第一设定时长内是否满足稳定条件；以及
    响应于满足稳定条件，构建所述小区特征区间内的终端模型。
  4. 根据权利要求1所述的方法，其中，根据所述小区的小区特征区间内的终端模型的跳变情况，确定所述小区对应的移动性特征的步骤包括：
    确定在第二设定时长内跳变情况满足跳变条件的终端模型的数目；
    响应于所述数目满足第一条件，确定所述小区对应高移动性；
    响应于所述数目不满足第一条件，确定所述小区对应非高移动性。
  5. 根据权利要求1至4中任一项所述的方法，还包括：
    通过机器学习方式生成不同的移动性特征对应的参数集。
  6. 根据权利要求5所述的方法，其中，通过机器学习方式生成不同的移动性特征对应的参数集的步骤包括：
    通过机器学习方式生成高速小区对应的第一参数集和非高速小区对应的第二参数集，
    其中，所述第一参数集和所述第二参数集均包括：小区级参数或者小区级参数和终端级参数。
  7. 根据权利要求5所述的方法，其中，在确定所述小区对应的移动性特征的步骤之后，所述方法还包括：
    向所述小区对应的网络设备下发与所述小区对应的移动性特征匹配的参数集。
  8. 根据权利要求7所述的方法，还包括：
    周期性监测所述小区对应的移动性特征是否发生变更；以及
    响应于所述小区对应的移动性特征发生变更，触发进行参数集调整。
  9. 根据权利要求7所述的方法，还包括：
    通过机器学习方式构建不同参数集配置下的性能模型；
    并且向所述小区对应的网络设备下发与所述小区对应的移动性特征匹配的参数集的步骤之后，所述方法还包括：
    启动在第三设定时长内的性能指标检测，比较检测到的性能指标与下发的参数集对应的性能模型中的性能指标；以及
    响应于比较结果满足偏离条件，触发参数集回退。
  10. 一种无线资源管理装置，包括：
    模型构建模块，用于基于射频指纹，生成小区的小区特征区间， 并构建所述小区特征区间内的终端模型；以及
    管理模块，用于根据所述小区的小区特征区间内的终端模型的跳变情况，确定所述小区对应的移动性特征。
  11. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时，使得所述处理器实现如权利要求1至9中任一项所述的无线资源管理方法。
PCT/CN2020/100661 2019-07-11 2020-07-07 无线资源管理方法及装置 WO2021004455A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP20837432.2A EP3998783A4 (en) 2019-07-11 2020-07-07 METHOD AND DEVICE FOR MANAGEMENT OF WIRELESS RESOURCES

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910626455.7A CN112218231B (zh) 2019-07-11 2019-07-11 一种无线资源管理方法及装置
CN201910626455.7 2019-07-11

Publications (1)

Publication Number Publication Date
WO2021004455A1 true WO2021004455A1 (zh) 2021-01-14

Family

ID=74047272

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/100661 WO2021004455A1 (zh) 2019-07-11 2020-07-07 无线资源管理方法及装置

Country Status (3)

Country Link
EP (1) EP3998783A4 (zh)
CN (1) CN112218231B (zh)
WO (1) WO2021004455A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070213061A1 (en) * 2006-03-02 2007-09-13 Samsung Electronics Co., Ltd. Method and apparatus for cell selection in a mobile communication system
CN103179658A (zh) * 2011-12-22 2013-06-26 华为技术有限公司 利用无线信号来定位的方法和定位服务器
CN106304172A (zh) * 2015-05-18 2017-01-04 中国移动通信集团公司 一种确定终端移动速度的方法和装置
CN108199989A (zh) * 2018-01-16 2018-06-22 南方科技大学 调度方法及装置、大规模多天线系统和存储介质
CN108243451A (zh) * 2016-12-27 2018-07-03 中国移动通信集团辽宁有限公司 一种基于mr数据在td-lte栅格中定位的方法和系统
CN108391292A (zh) * 2017-02-03 2018-08-10 电信科学技术研究院 一种小区选择的方法、基站和用户终端
CN110248366A (zh) * 2019-04-26 2019-09-17 中通服咨询设计研究院有限公司 一种基于终端移动速度的lte网络动态频率复用方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101755778B1 (ko) * 2010-04-02 2017-07-07 인터디지탈 패튼 홀딩스, 인크 저 이동 상태들 및 프로시저들
CN102572989A (zh) * 2012-01-13 2012-07-11 中兴通讯股份有限公司 一种根据终端的移动速度调整参数的方法及系统
US20140301224A1 (en) * 2013-04-03 2014-10-09 Innovative Sonic Corporation Method and apparatus for improving small cell measurement in a wireless communication system
EP2986068B1 (en) * 2013-05-08 2020-04-22 Huawei Technologies Co., Ltd. Wireless network information management methods and network devices
CN105636056B (zh) * 2014-11-14 2021-04-02 中兴通讯股份有限公司 一种频谱资源自优化的节能方法、装置和系统
EP3310096B1 (en) * 2015-07-31 2019-09-11 Huawei Technologies Co., Ltd. Method and apparatus for dynamically combining cells
KR102257786B1 (ko) * 2016-04-20 2021-05-28 콘비다 와이어리스, 엘엘씨 이동성 시그널링 로드 감소
CN106879011B (zh) * 2017-04-19 2020-01-24 北京佰才邦技术有限公司 一种小区组网的方法和装置
WO2019095186A1 (zh) * 2017-11-16 2019-05-23 北京小米移动软件有限公司 小区接入方法和小区接入装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070213061A1 (en) * 2006-03-02 2007-09-13 Samsung Electronics Co., Ltd. Method and apparatus for cell selection in a mobile communication system
CN103179658A (zh) * 2011-12-22 2013-06-26 华为技术有限公司 利用无线信号来定位的方法和定位服务器
CN106304172A (zh) * 2015-05-18 2017-01-04 中国移动通信集团公司 一种确定终端移动速度的方法和装置
CN108243451A (zh) * 2016-12-27 2018-07-03 中国移动通信集团辽宁有限公司 一种基于mr数据在td-lte栅格中定位的方法和系统
CN108391292A (zh) * 2017-02-03 2018-08-10 电信科学技术研究院 一种小区选择的方法、基站和用户终端
CN108199989A (zh) * 2018-01-16 2018-06-22 南方科技大学 调度方法及装置、大规模多天线系统和存储介质
CN110248366A (zh) * 2019-04-26 2019-09-17 中通服咨询设计研究院有限公司 一种基于终端移动速度的lte网络动态频率复用方法

Also Published As

Publication number Publication date
EP3998783A4 (en) 2023-06-14
CN112218231B (zh) 2023-10-10
CN112218231A (zh) 2021-01-12
EP3998783A1 (en) 2022-05-18

Similar Documents

Publication Publication Date Title
CN107426764B (zh) 小区测量方法及装置
RU2411671C2 (ru) Измерение и мониторинг qos в беспроводных сетях с разграничением обслуживания
WO2019206196A1 (zh) 一种模型更新方法、装置及系统
US9814048B2 (en) Apparatus and method in wireless communication system
CN103313301A (zh) 用于实现报告测量以及报告测量结果的方法和装置
US20170171811A1 (en) Access controller, station, access point, and control method
US11606725B2 (en) Wireless band priority metrics analysis and response
CN115552933A (zh) 电信通信系统中的联邦学习
EP3962171A1 (en) User equipment centric wide area optimization method and system thereof
CN105491569A (zh) 频谱资源分配、获取方法及装置
CN102857306A (zh) 一种信道可用度的检测方法、频谱管理方法及系统
CN104954978A (zh) 无线网络测距方法及装置
WO2021004455A1 (zh) 无线资源管理方法及装置
CN104038360A (zh) 基于新无线接入控制器架构的网管实现系统及实现方法
US8223701B2 (en) Communication apparatus, communication system, and method and program for judging reservation acceptance
US11350290B2 (en) Downlink interference detection and identification of aggressor cells
US20230292229A1 (en) Terminal scanning method, system, and apparatus, electronic device, and storage medium
EP3337241A1 (en) Method and apparatus for searching for route of device-to-device wireless mesh network
KR20220018582A (ko) 네트워크 최적화 방법, 장치 및 저장 매체
CN112105046A (zh) 模型训练方法及系统、异频测量估计方法及系统
CN106961694B (zh) 一种评估ptn接入环传输带宽的方法及装置
WO2016070606A1 (zh) 系统容量的预测方法及装置
CN103442406A (zh) 一种接入控制方法及装置
CN117729567B (zh) 无线自组网的优化方法及系统
CN114554551B (zh) 基于prb利用率的基站负载均衡方法、装置及设备

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: 20837432

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020837432

Country of ref document: EP

Effective date: 20220209