WO2024045932A1 - 一种资源调度方法、装置、系统、存储介质及电子系统 - Google Patents

一种资源调度方法、装置、系统、存储介质及电子系统 Download PDF

Info

Publication number
WO2024045932A1
WO2024045932A1 PCT/CN2023/108230 CN2023108230W WO2024045932A1 WO 2024045932 A1 WO2024045932 A1 WO 2024045932A1 CN 2023108230 W CN2023108230 W CN 2023108230W WO 2024045932 A1 WO2024045932 A1 WO 2024045932A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
actual
virtual
scenario
scene
Prior art date
Application number
PCT/CN2023/108230
Other languages
English (en)
French (fr)
Inventor
王欢
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2024045932A1 publication Critical patent/WO2024045932A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising 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
    • H04W72/00—Local resource management
    • H04W72/12—Wireless traffic scheduling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/54—Allocation or scheduling criteria for wireless resources based on quality criteria

Definitions

  • Embodiments of the present disclosure relate to the field of communications, and specifically, to a resource scheduling method, device, system, storage medium, and electronic system.
  • Embodiments of the present disclosure provide a resource scheduling method, device, system, storage medium and electronic system to at least solve the problem of complex scene construction and difficulty in optimizing resource scheduling algorithms through simulation software based on numerical analysis in related technologies and difficult to carry out in real scenarios. Problems where optimization and simulation algorithms are difficult to apply in real environments.
  • a resource scheduling method includes: receiving scene data of multiple physical objects in an actual scene; determining the network quality in the actual scene based on the scene data; and performing network quality management in the virtual simulation scene based on the network quality.
  • the resource scheduling algorithm is adjusted to obtain the adjusted resource scheduling algorithm, in which the virtual simulation scene is constructed based on the scene data; the adjusted resource scheduling algorithm is deployed to the base station in the actual scene.
  • a resource scheduling device includes: a first receiving module for receiving scene data of multiple physical objects in an actual scene; a first determining module for based on the scene data. Determine the actual scenario The network quality in Module for deploying the adjusted resource scheduling algorithm to base stations in actual scenarios.
  • a resource scheduling system including: a data collection instrument, used to collect scene data of various physical objects in actual scenes; a server, wirelessly connected to the data collection instrument, used to perform the above Resource scheduling method in any embodiment.
  • a computer-readable storage medium is also provided.
  • a computer program is stored in the storage medium, wherein the computer program executes any of the above method embodiments when run by a processor. steps in.
  • an electronic system including a memory and a processor, a computer program is stored in the memory, and the processor is configured to run the computer program to perform any of the above. Steps in method embodiments.
  • Figure 1 is a hardware structure block diagram of a mobile terminal of a resource scheduling method according to an embodiment of the present disclosure
  • Figure 2 is a flow chart of a resource scheduling method according to an embodiment of the present disclosure
  • Figure 3 is a block diagram of a digital twin-based resource scheduling algorithm processing system according to this embodiment.
  • Figure 4 is a flow chart of resource scheduling algorithm processing based on digital twins according to this embodiment
  • Figure 5 is a block diagram of a resource scheduling system according to an embodiment of the present disclosure.
  • Figure 6 is a block diagram of a digital twin-based resource scheduling algorithm adjustment device according to this embodiment.
  • Figure 7 is a block diagram of a resource scheduling system according to an embodiment of the present disclosure.
  • FIG. 1 is a hardware structure block diagram of a mobile terminal of the resource scheduling method according to an embodiment of the present disclosure.
  • the mobile terminal may include one or more (only one is shown in Figure 1 ) processor 102 (the processor 102 may include but is not limited to a processing system such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned mobile terminal may also include a processor for communication functions.
  • Transmission device 106 and input and output device 108 may be executed in a mobile terminal, a computer terminal, or a similar computing system.
  • the structure shown in Figure 1 is only illustrative, and it does not limit the structure of the above-mentioned mobile terminal.
  • the mobile terminal may also include more or fewer components than shown in FIG. 1 , or have a different configuration than shown in FIG. 1 .
  • the memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the resource scheduling method in the embodiments of the present disclosure.
  • the processor 102 executes various tasks by running the computer programs stored in the memory 104. Function application and resource scheduling, that is, to implement the above method.
  • Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory.
  • the memory 104 may further include a memory located remotely relative to the processor 102 Memory, these remote memories can be connected to mobile terminals through the network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.
  • Transmission system 106 is used to receive or send data via a network.
  • Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the mobile terminal.
  • the transmission system 106 includes a network adapter (Network Interface Controller, NIC for short), which can be connected to other network devices through a base station to communicate with the Internet.
  • the transmission system 106 may be a radio frequency (Radio Frequency, RF for short) module, which is used to communicate with the Internet wirelessly.
  • NIC Network Interface Controller
  • FIG. 2 is a flow chart of the resource scheduling method according to the embodiment of the present disclosure. As shown in Figure 2, the process includes the following steps:
  • Step S202 Receive scene data of multiple physical objects in the actual scene
  • the scene data in this embodiment can be collected using various data collection instruments such as satellites, collection vehicles, and measuring instruments.
  • Step S204 Determine the network quality of the current communication network in the actual scenario based on the scenario data
  • Step S206 Adjust the resource scheduling algorithm in the virtual simulation scenario according to the network quality to obtain the adjusted resource scheduling algorithm, where the virtual simulation scenario is constructed based on the scenario data;
  • the resource scheduling algorithm in this embodiment may specifically be a wireless resource scheduling algorithm used to schedule served terminals.
  • Step S208 Deploy the adjusted resource scheduling algorithm to the base station in the actual scenario.
  • the resource scheduling algorithm is optimized through simulation software based on numerical analysis.
  • the scene construction is complex, it is difficult to optimize for the real scene, and the simulation algorithm is difficult to apply in the real environment.
  • the scene data Diagnose the current communication network to obtain the network quality, construct a virtual simulation scenario based on the scenario data, adjust the resource scheduling algorithm of the virtual simulation scenario based on the network quality, and deploy the adjusted resource scheduling algorithm to the real scenario to achieve Communication network quality optimization.
  • the virtual entities required for the virtual simulation scene are constructed according to the scene data, wherein the scene data includes at least one of the following: longitude and latitude, physical size, material properties, and altitude; the scene data is combined with the constructed Virtual entities are injected into the virtual simulation scene.
  • the virtual entities required to build a virtual simulation scene include but are not limited to public equipment and buildings such as base stations, houses, street lights, fire hydrants, and protective nets.
  • the scene data of various objects mainly includes longitude and latitude, physical dimensions, material properties, and altitude. wait.
  • the above-mentioned virtual entities required to construct the virtual simulation scene based on the scene data may specifically include: simulating a virtual terminal, a virtual base station and a virtual channel respectively; and restoring the actual scene through a combination of the virtual terminal, the virtual base station and the virtual channel.
  • a software-based hardware platform is built based on a general server. The simulation results are obtained through software simulation of different ISA architecture chips.
  • a virtual base station corresponding to the real base station is built on the general server.
  • the virtual base station in the virtual simulation environment is the same as the real base station.
  • Consistent build an equivalent terminal hardware platform corresponding to the actual scenario based on the universal server, and run the communication protocol stack of the real terminal on the equivalent terminal hardware platform to ensure that the software of the virtual terminal is consistent with the real terminal.
  • the running status of the real terminal is restored in the virtual simulation environment; the universal server is used to configure the virtual channel according to actual channel data to restore the channel status in the actual scenario.
  • actual terminal data of a real terminal in the actual scene is received, where the actual terminal data at least includes: actual location information and actual network communication performance data; the actual terminal data is associated and stored with the scene data. Further, the actual location information is injected into the virtual simulation scene; the actual location information is used to perform position synchronization between the virtual terminal and the real terminal in the virtual simulation scene. Inject actual location information into the virtual simulation scene, in Using actual location information in virtual simulation scenarios can not only achieve real-time synchronization of the locations of virtual terminals and real terminals, but can also be used to reproduce communication scenarios in later algorithm iterative optimizations, facilitating the exploration and optimization of intelligent resource scheduling algorithms.
  • the communication status information of the current communication network is obtained from actual terminal data, where the communication status information includes at least one of the following: average delay, sector throughput, user packet loss; according to the communication status
  • the information determines the network quality, and network analysis data including the network quality is obtained.
  • the scene data, actual terminal data and network analysis data are sent to the display interface so that the display interface displays the operating status of the current communication network; the resource scheduling algorithm of the virtual base station in the virtual simulation scene is synchronized to the actual base station in the actual scene. The resource scheduling algorithm used.
  • the virtual network communication performance data of the virtual terminal in the virtual simulation scenario is obtained; the virtual network communication performance data is compared with the actual network communication performance data; if the difference between the virtual network communication performance data and the actual network communication performance data is If the value does not meet the preset condition, the communication simulation algorithm of the virtual simulation scenario is adjusted so that the difference between the virtual network communication performance data and the actual network communication performance data meets the preset condition.
  • the network communication performance data in this embodiment mainly includes: uplink rate, downlink rate, received power, signal-to-noise ratio, signal to interference plus noise ratio, user throughput, etc.
  • the communication simulation algorithm of the virtual simulation scene is optimized according to the scene data, actual network communication performance data and the communication simulation algorithm in the actual scene to obtain an optimized communication simulation algorithm; the optimized communication simulation algorithm is Deployed to base stations in actual scenarios. Ensure that the algorithm is completed within the specified time. When the terminal performance meets the performance requirements, the algorithm can be considered to have converged. At this time, the difference between the virtual network communication performance data and the actual network communication performance data meets the preset conditions, and the resource scheduling algorithm optimization process ends.
  • This embodiment can also perform visual monitoring of the virtual simulation scene and the actual scene. Specifically, the status of the actual scene and the virtual simulation scene during the entire process can be displayed in a graphical interface in real time.
  • Figure 3 is a block diagram of a resource scheduling algorithm processing system based on digital twins according to this embodiment. As shown in Figure 3, it includes a data collection system 31, a communication network monitoring system 32, a digital twin server 33, and a graphical display system 34, where , the environment collection system 31 interacts with the digital twin server 33, the communication network monitoring system 32 interacts with the digital twin server 33, and the graphical display system 34 interacts with the communication network monitoring system 32.
  • data interaction between the data collection system 31 and the digital twin server 33 can use either wireless communication circuits or wired communication circuits; the communication network monitoring system 32 needs to ensure that the data Real-time validity, therefore data interaction with the digital twin server 33 must use wired communication circuits; similarly, the graphical display system 34 needs to use wired communication circuits to connect to the communication network monitoring system 32 to ensure data validity in real-time display mode.
  • Figure 4 is a flow chart of the resource scheduling algorithm processing based on digital twins according to this embodiment. As shown in Figure 4, it includes:
  • Step S401 receive scene data and construct a virtual simulation scene based on the scene data
  • the virtual entities required to build virtual simulation scenes include but are not limited to base stations, houses, street lights, fire hydrants, and protective nets. and other public equipment and buildings, the scene data of various objects mainly includes longitude and latitude, physical size, material properties, altitude, etc.; the scene data obtained above is uploaded to the digital twin server 33 through a wireless communication circuit or a limited communication circuit, and the digital The twin server 33 then classifies the collected data according to different scenarios and labels, and digitally stores the data in the server's database. At the same time, all static data is injected into the digital twin simulation system, and the subsequent graphical display system 34 Build an actual scene representation from this static data.
  • Step S402 Perform resource scheduling algorithm scheduling (specifically, it may be a wireless resource scheduling algorithm);
  • the base station When a terminal accesses the cell in the actual scenario, the base station starts to use the preset resource scheduling algorithm to allocate the resources served by the current base station. All terminals are scheduled. At the same time, the base station uploads parameters related to the resource scheduling algorithm to the digital twin server 33.
  • the parameters mainly include: working frequency, working bandwidth, transmit power, longitude and latitude, altitude, antenna configuration, etc.
  • the digital twin server 33 will Base station data is associated with corresponding scenarios and then stored in categories;
  • Step S403 Receive actual terminal data of the actual scene collected in real time, where the actual terminal data specifically includes word actual location information and actual network communication performance data;
  • the simulation system Before using various types of real environment data collected, the simulation system first needs to simulate virtual terminals, virtual base stations, and virtual channels respectively. Through the close integration of the three, the main components of the real communication network can be restored 1:1. Since the actual base station is composed of ARM+DSP heterogeneous chips, and it is difficult to directly simulate the chip hardware behavior in the digital twin model, it is considered to implement a software-based hardware platform based on a general x86 server and conduct software simulation of different ISA architecture chips. Realize the construction of equivalent real base station model on x86 server.
  • the virtual base station has the same hardware processing capabilities as the real base station, which can ensure that the optimization algorithm obtained in the simulation environment can adapt to the instruction, memory, and IO processing capabilities of the real chip; on the other hand, it can directly run the driver, BSP, OS and APP and other software programs can completely restore the real base station operating status.
  • the actual terminal is composed of an ARM main control chip and multiple accelerator IPs.
  • an equivalent terminal hardware platform is also built based on the x86 server.
  • the complete communication protocol stack of the real terminal is run on this platform to ensure that the virtual terminal and real terminal software Consistency, restore the real terminal running state in the simulation environment.
  • the virtual channel uses the x86 server to configure accordingly according to the actual channel data, restoring the complex channel status in the real scenario to cope with various application scenarios.
  • Step S404 inject actual location information into the virtual simulation environment
  • Step S405 Optimize the resource scheduling algorithm to obtain an optimized resource scheduling algorithm
  • the communication network status database constructed by the digital twin server 33 on the one hand, inject all terminal location information stored in the digital twin server 33 into the virtual simulation environment, and use the terminal location information in the simulation environment to realize both virtual terminals and real terminals Real-time position synchronization can also be used to reproduce communication scenarios in later algorithm iterative optimization, facilitating the exploration and optimization of intelligent resource scheduling algorithms.
  • the digital twin server 33 uploads all terminal status information to the communication network monitoring system 32 through wired communication circuits.
  • the communication network monitoring system 32 is responsible for statistics and mining of all network communication performance data obtained, and uses these data to obtain the current Communication status information such as the fairness of each user in the communication network, the overall average delay, sector throughput, and user packet loss. Furthermore, known theories on communication networks are used to further diagnose and analyze these data to diagnose the current communication network congestion. situation and communication quality.
  • the communication network monitoring system 32 Immediately after the communication network monitoring system 32 completes the analysis of the communication network, the communication network monitoring system 32 sends the scene data and analysis data to the graphical display system 34, and the graphical display system 34 displays the current network operating status in real time based on these data; After the graphical display system 34 can display the actual scene communication network status in real time, consider further synchronizing the digital twin simulation platform with the actual test environment: synchronize the base station resource scheduling algorithm in the digital twin simulation platform to the resource scheduling algorithm used by the actual base station. , to ensure the consistency between the simulation environment and the actual environment.
  • the simulation system performs a numerical analysis on the status of each terminal in the simulation system based on the injected actual resource scheduling algorithm and communication simulation algorithm, and obtains the virtual network communication performance data of each virtual terminal, which mainly includes: uplink rate, downlink rate, etc. Line rate, received power, signal-to-noise ratio, signal to interference plus noise ratio, user throughput, etc.;
  • the virtual network communication performance data of the terminal in the simulation system is uploaded to the communication network monitoring system 32.
  • the communication network monitoring system 32 processes the simulation data similar to the actual network communication performance data to complete classified storage, data mining and After system diagnosis, all data are uploaded to the graphical display system 34.
  • the graphical display system 34 displays the simulated environment network status in real time based on the data, coupled with the existing real-scenario communication network status display. In this way, the communication network The operation and maintenance personnel can monitor the real scene and the simulation scene at the same time; at the same time, the communication network monitoring system 32 compares the simulation data of the terminal with the actual data. If the error is large, the communication simulation algorithm in the virtual platform ( Specifically, it can be adjusted (wireless communication simulation algorithm), modify the communication simulation algorithm until the error converges to an acceptable range, and then use the new communication simulation algorithm as a benchmark for all simulation test scenarios.
  • the communication network monitoring system 32 now has a real-time monitoring function. Furthermore, the optimization and exploration of resource scheduling algorithms can be completed based on all existing data. Specifically, after all the above processes are completed, there will be corresponding actual scene data, actual network status data, and communication simulation algorithms for the real scene. Use these data to start optimizing the constructed virtual simulation scene. At this time, the virtual simulation environment The China Communications simulation algorithm has been updated based on the above test results, and then attempts to update the resource scheduling algorithm in the simulation environment based on the actual network status. Specific optimization can be explored in combination with scenario characteristics, user fairness requirements, artificial intelligence and other methods.
  • the new communication simulation algorithm calculates the new performance data of the terminal in the simulation environment, and injects the optimized algorithm into the virtual base station to ensure that the algorithm is completed within the specified time.
  • the algorithm is considered to have converged, and the resource scheduling algorithm is terminated. Optimize iterative process.
  • Step S406 Inject the optimized resource scheduling algorithm into the actual scenario.
  • the optimized resource scheduling algorithm in the simulation system is applied to the actual scenario.
  • the resource scheduling algorithm is updated, and then the communication network operation after adopting the new algorithm can be monitored in the graphical display system 34 according to the aforementioned process. status to verify the effectiveness of the algorithm.
  • the intelligent resource scheduling algorithm based on digital twins in this embodiment obtains the required environmental data, terminal data, and base station data by setting up the data collection system 31 and uploads them to the digital twin server 33.
  • the digital twin server 33 then classifies and stores the acquired data.
  • the communication network monitoring system 32 then further mines and analyzes the data collected by the digital twin server 33, diagnoses the current network, adjusts the resource scheduling algorithm in the simulation environment according to the network quality, and further deploys the algorithm after it is verified to be effective. to the base station corresponding to the actual scenario.
  • the graphical display system 34 uses the data in the communication network monitoring system 32 to realize real-time visual monitoring of the respective networks in the simulation and actual scenarios.
  • the digital twin of the wireless channel is realized, which greatly improves the efficiency of resource scheduling algorithm analysis and optimization.
  • FIG. 5 is a block diagram of a resource scheduling device according to an embodiment of the present disclosure. As shown in Figure 5, the device includes:
  • the first receiving module 52 is used to receive scene data of multiple physical objects in the actual scene
  • the first determination module 54 is used to determine the network quality in the actual scenario according to the scenario data;
  • the first adjustment module 56 is used to adjust the resource scheduling algorithm in the virtual simulation scenario according to the network quality to obtain the adjusted resource scheduling algorithm, wherein the virtual simulation scenario is constructed based on the scenario data;
  • the first deployment module 58 is used to deploy the adjusted resource scheduling algorithm to the base station in the actual scenario.
  • the device further includes:
  • the first injection module is used to inject the scene data and the constructed virtual entity into the virtual simulation scene.
  • the building module is also used to simulate a virtual terminal, a virtual base station, and a virtual channel respectively; and restore the actual scene based on the virtual terminal, the virtual base station, and the virtual channel.
  • the building module is also used to construct a virtual base station corresponding to the real base station based on the simulation results of at least one ISA architecture chip, wherein the virtual base station in the virtual simulation environment is different from the real base station.
  • the base station is consistent; construct an equivalent terminal hardware platform corresponding to the actual scenario, run the communication protocol stack of the real terminal on the equivalent terminal hardware platform to ensure that the virtual terminal matches the real terminal, and restore the virtual terminal in the virtual simulation environment The operating status of the real terminal; configure the virtual channel according to the actual channel data to restore the channel status in the actual scenario.
  • the device further includes:
  • the second receiving module is used to receive actual terminal data of the real terminal in the actual scenario, where the actual terminal data at least includes: actual location information and actual network communication performance data;
  • the associated storage module is used to associate and store the actual terminal data and the scene data.
  • the device further includes:
  • the second injection module is used to inject the actual position information into the virtual simulation scene
  • the location synchronization module is used to use the actual location information to synchronize the location of the virtual terminal in the virtual simulation scene.
  • the device further includes:
  • the first acquisition module is used to acquire communication status information from the actual terminal data, where the communication status information includes at least one of the following: average delay, sector throughput, and user packet loss;
  • the second determination module is used to determine the network quality according to the communication status information, and obtain network analysis data including the network quality.
  • the device further includes:
  • a sending module used to send the scene data, the actual terminal data and the network analysis data to the display interface, so that the display interface displays the operating status of the current communication network
  • the algorithm synchronization module is used to synchronize the resource scheduling algorithm of the virtual base station to the actual base station.
  • the device further includes:
  • the second acquisition module is used to acquire the virtual network communication performance data of the virtual terminal in the virtual simulation scenario
  • a comparison module used to compare the virtual network communication performance data with the actual network communication performance data
  • the second adjustment module is used to adjust the communication simulation algorithm of the virtual simulation scene so that the virtual network communication performance can be improved if the difference between the virtual network communication performance data and the actual network communication performance data does not meet the preset conditions.
  • the difference between the data and the actual network communication performance data satisfies the preset condition.
  • the device further includes:
  • An optimization module configured to optimize the communication simulation algorithm of the virtual simulation scenario based on the scenario data, the actual network communication performance data, and the communication simulation algorithm in the actual scenario, to obtain an optimized communication simulation algorithm
  • the second deployment module is used to deploy the optimized communication simulation algorithm to the base station in the actual scenario.
  • the device further includes:
  • the monitoring module is used to visually monitor the virtual simulation scene and the actual scene.
  • FIG. 6 is a block diagram of a digital twin-based resource scheduling algorithm adjustment device according to this embodiment.
  • the digital twin-based resource scheduling algorithm research system mainly includes:
  • Scene data database building module 62 is used to collect static environment data and dynamic state data in actual work scenarios, and collect various types of data. After analysis and processing, it can be used to build an equivalent virtual test environment in the digital twin simulation platform or to display network communication status in real time; the simulation model iterative optimization module 64 is responsible for collecting communication status in the actual network and virtual simulation. Finally, iterative optimization is performed to ensure the effectiveness of the communication simulation algorithm in the simulation system; the network performance evaluation prediction module 66 is used to optimize and explore the resource scheduling algorithm on the premise that the communication simulation algorithm is converging. First, through the simulation environment 1:1 Restore different actual scenarios, and then test the effectiveness of different resource scheduling algorithms for different scenarios. After comprehensively considering multiple dimensions to select a better resource scheduling algorithm, the resource scheduling algorithm is then used in actual scenarios to optimize the quality of the communication network.
  • Figure 7 is a block diagram of the resource scheduling system according to an embodiment of the present disclosure. As shown in Figure 7, it includes:
  • the data collection instrument 72 is used to collect scene data of various physical objects in actual scenes
  • the server 74 is wirelessly connected to the data collection instrument and used to execute any of the resource scheduling methods described above.
  • the data collection instrument 72 in this embodiment corresponds to the above-mentioned data collection system 31, and the server 74 may specifically include the above-mentioned communication network monitoring system 32 and digital twin server 33.
  • system further includes:
  • a display interface is used to receive scene data, actual terminal data and network analysis data sent by the server, and display the operating status of the current communication network according to the scene data, the actual terminal data and the network analysis data.
  • the display interface in this embodiment corresponds to the above-mentioned graphical display system 34.
  • Embodiments of the present disclosure also provide a computer-readable storage medium that stores a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.
  • the computer-readable storage medium may include but is not limited to: U disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM) , mobile hard disk, magnetic disk or optical disk and other media that can store computer programs.
  • ROM read-only memory
  • RAM random access memory
  • mobile hard disk magnetic disk or optical disk and other media that can store computer programs.
  • Embodiments of the present disclosure also provide an electronic device, including a memory and a processor.
  • a computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
  • the above-mentioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the above-mentioned processor, and the input-output device is connected to the above-mentioned processor.
  • modules or steps of the present disclosure can be implemented using general-purpose computing devices, and they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices. superior, They may be implemented in program code executable by a computing device, such that they may be stored in a storage device for execution by a computing device, and in some cases may be executed in a sequence different from that shown or described herein. The steps may be implemented by making them into individual integrated circuit modules, or by making multiple modules or steps into a single integrated circuit module. As such, the present disclosure is not limited to any specific combination of hardware and software.

Landscapes

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

Abstract

本公开实施例提供了一种资源调度方法、装置、系统、存储介质及电子系统，该方法包括：接收实际场景中多种实物的场景数据；根据场景数据确定实际场景中的网络质量；根据网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，虚拟仿真场景是基于场景数据构建的；将调整后的资源调度算法部署到实际场景的基站中。

Description

一种资源调度方法、装置、系统、存储介质及电子系统
相关申请的交叉引用
本公开基于2022年08月30日提交的发明名称为“一种资源调度方法、装置、系统、存储介质及电子系统”的中国专利申请CN202211062154.4，并且要求该专利申请的优先权，通过引用将其所公开的内容全部并入本公开。
技术领域
本公开实施例涉及通信领域，具体而言，涉及一种资源调度方法、装置、系统、存储介质及电子系统。
背景技术
随着通信技术的飞速发展，通信技术与多个领域有了更多的交叉融合，这也对传输延迟以及传输质量提出了更高的要求。不同于有线网络通信，无线网络通信往往要面临更为复杂的通信环境以及更为紧张的资源分配，而如何提高无线资源利用率最大化提高用户体验主要面临如下几个问题：首先，随着通信技术的发展无线通信领域可用频谱资源越来越少，与此同时更多的通信业务需求以及用户数量的增加都对无线通信带宽使用提出了较高的要求；其次，一方面为了保证用户通信质量终端侧需要尽可能接收大功率基站信号，而另一方面为了保证终端手机电池寿命需要尽可能减小传输数据功率；最后，终端用户移动的自由性以及城市化建设完善，不可避免得在电磁波传播过程中引入了多径衰落和阴影效应，这些进一步恶化了电磁波传播条件，对通信质量造成了不可忽视的影响。当前针对资源调度算法优化主要通过基于数值分析的仿真软件进行，这种方式存在多个局限性，包括：场景构建复杂、难以针对真实场景进行优化；仿真算法难以应用在真实环境中，往往需要做软件层面适配及转换。
针对相关技术中通过基于数值分析的仿真软件进行资源调度算法优化，场景构建复杂、难以针对真实场景进行优化且仿真算法难以应用在真实环境中的问题，尚未提出解决方案。
发明内容
本公开实施例提供了一种资源调度方法、装置、系统、存储介质及电子系统，以至少解决相关技术中通过基于数值分析的仿真软件进行资源调度算法优化，场景构建复杂、难以针对真实场景进行优化且仿真算法难以应用在真实环境中的问题。
根据本公开的一个实施例，提供了一种资源调度方法，该方法包括：接收实际场景中多种实物的场景数据；根据场景数据确定实际场景中的网络质量；根据网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，虚拟仿真场景是基于场景数据构建的；将调整后的资源调度算法部署到实际场景的基站中。
根据本公开的另一个实施例，还提供了一种资源调度装置，该装置包括：第一接收模块，用于接收实际场景中多种实物的场景数据；第一确定模块，用于根据场景数据确定实际场景 中的网络质量；第一调整模块，用于根据网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，虚拟仿真场景是基于场景数据构建的；第一部署模块，用于将调整后的资源调度算法部署到实际场景的基站中。
根据本公开的另一个实施例，还提供了一种资源调度系统，包括：数据采集仪器，用于采集实际场景中多种实物的场景数据；服务器，与数据采集仪器无线连接，用于执行上述任一项实施例中的资源调度方法。
根据本公开的又一个实施例，还提供了一种计算机可读的存储介质，所述存储介质中存储有计算机程序，其中，所述计算机程序被处理器运行时执行上述任一项方法实施例中的步骤。
根据本公开的又一个实施例，还提供了一种电子系统，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行上述任一项方法实施例中的步骤。
附图说明
图1是本公开实施例的资源调度方法的移动终端的硬件结构框图；
图2是根据本公开实施例的资源调度方法的流程图；
图3是根据本实施例的基于数字孪生的资源调度算法处理系统的框图；
图4是根据本实施例的基于数字孪生的资源调度算法处理的流程图；
图5是根据本公开实施例的资源调度系统的框图；
图6是根据本实施例的基于数字孪生的资源调度算法调整装置的框图；
图7是根据本公开实施例的资源调度系统的框图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本公开的实施例。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
本公开实施例中所提供的方法实施例可以在移动终端、计算机终端或者类似的运算系统中执行。以运行在移动终端上为例，图1是本公开实施例的资源调度方法的移动终端的硬件结构框图，如图1所示，移动终端可以包括一个或多个(图1中仅示出一个)处理器102(处理器102可以包括但不限于微处理器MCU或可编程逻辑器件FPGA等的处理系统)和用于存储数据的存储器104，其中，上述移动终端还可以包括用于通信功能的传输设备106以及输入输出设备108。本领域普通技术人员可以理解，图1所示的结构仅为示意，其并不对上述移动终端的结构造成限定。例如，移动终端还可包括比图1中所示更多或者更少的组件，或者具有与图1所示不同的配置。
存储器104可用于存储计算机程序，例如，应用软件的软件程序以及模块，如本公开实施例中的资源调度方法对应的计算机程序，处理器102通过运行存储在存储器104内的计算机程序，从而执行各种功能应用以及资源调度，即实现上述的方法。存储器104可包括高速随机存储器，还可包括非易失性存储器，如一个或者多个磁性存储系统、闪存、或者其他非易失性固态存储器。在一些实例中，存储器104可进一步包括相对于处理器102远程设置的 存储器，这些远程存储器可以通过网络连接至移动终端。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
传输系统106用于经由一个网络接收或者发送数据。上述的网络具体实例可包括移动终端的通信供应商提供的无线网络。在一个实例中，传输系统106包括一个网络适配器(Network Interface Controller，简称为NIC)，其可通过基站与其他网络设备相连从而可与互联网进行通讯。在一个实例中，传输系统106可以为射频(Radio Frequency，简称为RF)模块，其用于通过无线方式与互联网进行通讯。
在本实施例中提供了一种运行于上述移动终端或网络架构的资源调度方法，图2是根据本公开实施例的资源调度方法的流程图，如图2所示，该流程包括如下步骤：
步骤S202，接收实际场景中多种实物的场景数据；
本实施例中的场景数据可以利用卫星、采集车、测量仪等多种数据采集仪器采集。
步骤S204，根据该场景数据确定该实际场景中当前通信网络的网络质量；
步骤S206，根据该网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，该虚拟仿真场景是基于该场景数据构建的；
本实施例中的资源调度算法具体可以是用于调度所服务的终端的无线资源调度算法。
步骤S208，将调整后的资源调度算法部署到该实际场景的基站中。
通过上述步骤S202至S208，可以解决相关技术中通过基于数值分析的仿真软件进行资源调度算法优化，场景构建复杂、难以针对真实场景进行优化且仿真算法难以应用在真实环境中的问题，根据场景数据对当前通信网络进行诊断，得到网络质量，根据场景数据构建的虚拟仿真场景，基于网络质量对虚拟仿真场景的资源调度算法进行调整，将调整后的资源调度算法部署到真实场景中，以实现对通信网络质量优化。
在一实施例中，根据该场景数据构建该虚拟仿真场景所需的虚拟实体，其中，该场景数据至少包括以下之一：经纬度、物理尺寸、材料属性、海拔高度；将该场景数据与构建的虚拟实体注入该虚拟仿真场景中。
构建虚拟仿真场景所需的虚拟实体包括但不局限于基站、房屋、街灯、消防栓、防护网等公共设备及建筑，各类物体的场景数据则主要包括经纬度、物理尺寸、材料属性、海拔高度等。
上述根据该场景数据构建该虚拟仿真场景所需的虚拟实体具体可以包括：分别模拟虚拟终端、虚拟基站以及虚拟信道；通过该虚拟终端、该虚拟基站以及该虚拟信道的结合还原该实际场景。具体的，以通用服务器为基础构建软件化硬件平台，通过对不同ISA架构芯片进行软件仿真得到仿真结果，在该通用服务器上构建真实基站对应的虚拟基站，虚拟仿真环境中的虚拟基站与真实基站一致；以该通用服务器为基础构建与该实际场景对应的等效终端硬件平台，在该等效终端硬件平台上运行真实终端的通信协议栈以保证该虚拟终端与该真实终端的软件一致，在该虚拟仿真环境中还原该真实终端的运行状态；利用该通用服务器根据实际信道数据对该虚拟信道进行配置，以还原该实际场景中的信道状态。
在另一实施例中，接收该实际场景中真实终端的实际终端数据，其中，该实际终端数据至少包括：实际位置信息、实际网络通信性能数据；将实际终端数据与该场景数据进行关联存储。进一步的，将该实际位置信息注入该虚拟仿真场景中；利用该实际位置信息对该虚拟仿真场景中的虚拟终端与该真实终端进行位置同步。将实际位置信息注入虚拟仿真场景，在 虚拟仿真场景中利用实际位置信息既可以实现虚拟终端与真实终端的位置实时同步，也可以在后期算法迭代优化中用于通信场景复现，便于智能资源调度算法探索优化。
在另一实施例中，从实际终端数据中获取当前通信网络的通信状态信息，其中，通信状态信息至少包括以下之一：平均时延、扇区吞吐量、用户丢包情况；根据该通信状态信息确定该网络质量，得到包括该网络质量的网络分析数据。进一步的，将场景数据、实际终端数据以及网络分析数据发送给显示界面，以使该显示界面显示当前通信网络的运行状态；将虚拟仿真场景中虚拟基站的资源调度算法同步至实际场景中实际基站所采用的资源调度算法。
在另一实施例中，获取虚拟仿真场景中虚拟终端的虚拟网络通信性能数据；将虚拟网络通信性能数据与实际网络通信性能数据进行对比；若虚拟网络通信性能数据与实际网络通信性能数据的差值不满足预设条件，则对虚拟仿真场景的通信仿真算法进行调整，以使虚拟网络通信性能数据与实际网络通信性能数据的差值满足该预设条件。本实施例中的网络通信性能数据主要包括：上行速率、下行速率、接收功率、信噪比、信号与干扰加噪声比、用户吞吐量等。
在另一实施例中，根据场景数据、实际网络通信性能数据以及实际场景中的通信仿真算法对虚拟仿真场景的通信仿真算法进行优化，得到优化后的通信仿真算法；将优化后的通信仿真算法部署到实际场景的基站中。保证算法在规定时间内完成，当终端性能满足性能需求后即可认为算法已收敛，此时虚拟网络通信性能数据与实际网络通信性能数据的差值满足预设条件，结束资源调度算法优化过程。
本实施例还可以对虚拟仿真场景与实际场景进行可视化监控，具体可以将整个过程中实际场景以及虚拟仿真场景的状态实时显示在图形化界面中。
图3是根据本实施例的基于数字孪生的资源调度算法处理系统的框图，如图3所示，包括数据采集系统31、通信网络监控系统32、数字孪生服务器33、图形化显示系统34，其中，环境采集系统31与数字孪生服务器33交互，通信网络监控系统32与数字孪生服务器33交互，图形化显示系统34与通信网络监控系统32交互。在本实施例中，考虑到静态环境短期内变化概率较小，因此数据采集系统31与数字孪生服务器33数据交互既可采用无线通信电路又可以采用有线通信电路；通信网络监控系统32需要保证数据的实时有效性，因此与数字孪生服务器33间数据交互必须采用有线通信电路；同样的，图形化显示系统34需要采用有线通信电路与通信网络监控系统32相连，保证实时显示模式下数据有效性。
图4是根据本实施例的基于数字孪生的资源调度算法处理的流程图，如图4所示，包括：
步骤S401，接收场景数据，基于场景数据构建虚拟仿真场景；
利用卫星、采集车、测量仪等多种数据采集仪器收集实际场景中多种实物的场景数据，构建虚拟仿真场景所需的虚拟实体包括但不局限于基站、房屋、街灯、消防栓、防护网等公共设备及建筑，各类物体的场景数据则主要包括经纬度、物理尺寸、材料属性、海拔高度等；将上述获取到的场景数据通过无线通信电路或有限通信电路上传至数字孪生服务器33，数字孪生服务器33接着对收集到的数据按不同场景按标签进行分类，并将这些数据以数字化方式存储在服务器的数据库中，同时将所有的静态数据注入数字孪生仿真系统中，后续图形化显示系统34根据这些静态数据构建实际场景图示。
步骤S402，进行资源调度算法调度(具体可以是无线资源调度算法)；
当实际场景中有终端接入小区后，基站开始采用预设的资源调度算法对当前基站服务的 所有终端进行调度，与此同时，基站上传与资源调度算法相关参数至数字孪生服务器33，参数主要包括：工作频率、工作带宽、发射功率、经纬度、海拔高度、天线配置等，数字孪生服务器33将基站数据与相应场景进行关联后分类存储；
步骤S403，接收实时采集的实际场景的实际终端数据，其中，实际终端数据具体包括字实际位置信息与实际网络通信性能数据；
利用实际场景中部署的各类传感器采集实际场景中各个终端的实际位置信息，包括：移动速率、经纬度等，同时收集每个终端的实际网络通信性能数据，主要包括：上行速率、下行速率、接收功率、信噪比、信号与干扰加噪声比、用户吞吐量等。将利用各种数据采集器获取到的终端数据实时上传到数字孪生服务器33中，数字孪生服务器33对收集到的终端位置信息、通信状态进行存储统计，同时将终端相关的数据与静态场景数据相关联，构成不同真实场景下的通信网络状态数据库。
在利用采集到的各类真实环境数据前，仿真系统中首先需要分别模拟虚拟终端、虚拟基站以及虚拟信道，通过三者紧密结合实现1：1还原真实通信网络中主体组件。由于实际基站由ARM+DSP异构芯片构成，而数字孪生模型中难以直接对芯片硬件行为进行模拟，因此考虑以通用x86服务器为基础实现软件化硬件平台，通过对不同ISA架构芯片进行软件仿真，实现在x86服务器上构建等效真实基站模型。该虚拟基站一方面具备与真实基站相同的硬件处理能力，能够保证仿真环境中得到的优化算法可适应真实芯片中指令、内存、IO处理能力；另一方面可直接运行真实基站中驱动、BSP、OS以及APP等软件程序，完整还原真实基站运行状态。实际终端则由ARM主控芯片及多个加速器IP构成，仿真系统中同样以x86服务器为基础构建等效终端硬件平台，在该平台上运行真实终端完整通信协议栈保证了虚拟终端与真实终端软件一致性，在仿真环境中还原真实终端运行状态。虚拟信道则利用x86服务器根据实际信道数据进行相应配置，还原真实场景中复杂信道状态以应对多种应用场景。
步骤S404，将实际位置信息注入虚拟仿真环境；
步骤S405，对资源调度算法进行优化，得到优化后的资源调度算法；
对数字孪生服务器33构建的通信网络状态数据库进行处理：一方面，将数字孪生服务器33中存储的所有终端位置信息注入虚拟仿真环境，在仿真环境中利用终端位置信息既可以实现虚拟终端与真实终端位置实时同步，也可以在后期算法迭代优化中用于通信场景复现，便于智能资源调度算法探索优化。另一方面，数字孪生服务器33将所有终端状态信息通过有线通信电路上传至通信网络监控系统32，通信网络监控系统32则负责对获得的所有网络通信性能数据进行统计及挖掘，利用这些数据获取当前通信网络中各个用户公平性、整体的平均时延、扇区吞吐量以及用户丢包情况等通信状态信息，进一步地，利用通信网络方面公知理论对根据这些数据进一步诊断分析，诊断当前通信网络拥塞情况与通信质量。
紧接着，通信网络监控系统32对通信网络分析完毕后，通信网络监控系统32将场景数据、分析数据都发送至图形化显示系统34，图形化显示系统34根据这些数据实时显示当前网络运行状态；待图形化显示系统34能够实时显示实际场景通信网络状态后，考虑将数字孪生仿真平台与实际测试环境做进一步同步：将数字孪生仿真平台中基站资源调度算法同步至实际基站所采用的资源调度算法，保证仿真环境与实际环境一致性。
接着仿真系统根据注入的实际资源调度算法，以及通信仿真算法对仿真系统中各个终端状态进行数值分析，获取每个虚拟终端的虚拟网络通信性能数据，主要包括：上行速率、下 行速率、接收功率、信噪比、信号与干扰加噪声比、用户吞吐量等；
进一步地，将终端在仿真系统的虚拟网络通信性能数据上传至通信网络监控系统32中，通信网络监控系统32对仿真数据做类似于对实际网络通信性能数据的处理，完成分类存储、数据挖掘及系统诊断后再将所有的数据上传至图形化显示系统34，图形化显示系统34根据数据实现实时显示仿真环境网络状态，再加上已有的真实场景通信网络状态显示，如此一来，通信网络运维人员便可实现同时对真实场景与仿真场景进行监控；与此同时，通信网络监控系统32将终端的仿真数据与实际数据进行比对，若误差较大则对虚拟平台中通信仿真算法(具体可以是无线通信仿真算法)进行调整，修改通信仿真算法直至误差收敛至在可接受范围内，后续则将新的通信仿真算法作为基准用于所有仿真测试场景。
根据以上步骤，此时通信网络监控系统32已具备实时监控功能。进一步的，根据已有的所有数据还可以完成对资源调度算法优化探索。具体而言，上述所有过程完成后，针对真实场景便有了相应的实际场景数据、实际网络状态数据、通信仿真算法，利用这些数据开始对构建的虚拟仿真场景进行优化，此时的虚拟仿真环境中通信仿真算法已根据上述测试结果做了更新，接着针对实际网络状态尝试更新仿真环境中资源调度算法，具体优化可结合场景特征、用户公平性需求、人工智能等多种方式进行探索，同时结合新的通信仿真算法计算仿真环境中终端新的性能数据，将优化后算法注入虚拟基站中，保证算法在规定时间内完成，当终端性能满足性能需求后即可认为算法已收敛，结束资源调度算法优化迭代过程。
步骤S406，将优化后的资源调度算法注入实际场景中。
进一步的，将仿真系统中优化后的资源调度算法应用至实际场景中，至此完成了资源调度算法的更新，再根据前述流程便可在图形化显示系统34中监控采用新算法后的通信网络运行状态，验证算法的有效性。
最后，对前面在仿真环境中深度还原的真实场景做进一步调整，一方面可以添加新的自定义运行虚拟终端或修改虚拟终端状态，另一方面可以对虚拟信道进行调整，分析当前已优化的资源调度算法在新场景中的性能，若性能数据不满足预期或有损失可进一步优化算法，提升算法通用性以保证最终算法适应多种场景，待算法符合性能指标后可将相应软件直接更新至实际基站中，无需做仿真代码到真实代码转换。
本实施例的基于数字孪生的智能资源调度算法通过设置数据采集系统31获取所需的环境数据、终端数据、基站数据上传至数字孪生服务器33中，数字孪生服务器33再对获取的数据进行分类存储便于场景复现，接着通信网络监控系统32再对数字孪生服务器33采集的数据再进一步挖掘分析，对当前网络进行诊断，根据网络质量调整仿真环境中资源调度算法，待算法验证有效后再进一步部署至相应实际场景的基站中，与此同时，在整个资源调度算法过程中图形化显示系统34利用通信网络监控系统32中数据实现对仿真及实际场景各自网络的实时可视化监控。至此，通过在仿真环境中注入真实场景数据，实现了无线信道的数字孪生，极大提高了资源调度算法分析及优化效率。
根据本公开的另一个实施例，还提供了一种资源调度装置，图5是根据本公开实施例的资源调度装置的框图，如图5所示，该装置包括：
第一接收模块52，用于接收实际场景中多种实物的场景数据；
第一确定模块54，用于根据该场景数据确定该实际场景中的网络质量；
第一调整模块56，用于根据该网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，该虚拟仿真场景是基于该场景数据构建的；
第一部署模块58，用于将该调整后的资源调度算法部署到该实际场景的基站中。
在一实施例中，该装置还包括：
构建模块，用于根据该场景数据构建该虚拟仿真场景所需的虚拟实体，其中，该场景数据至少包括以下之一：经纬度、物理尺寸、材料属性、海拔高度；
第一注入模块，用于将该场景数据与构建的所述虚拟实体注入该虚拟仿真场景中。
在一实施例中，该构建模块，还用于分别模拟虚拟终端、虚拟基站以及虚拟信道；根据该虚拟终端、该虚拟基站以及该虚拟信道还原该实际场景。
在一实施例中，该构建模块，还用于根据至少一种ISA架构芯片下的仿真结果，构建真实基站对应的虚拟基站，其中，所述虚拟仿真环境中的所述虚拟基站与所述真实基站一致；构建与该实际场景对应的等效终端硬件平台，在该等效终端硬件平台上运行真实终端的通信协议栈以保证该虚拟终端与该真实终端匹配，在该虚拟仿真环境中还原该真实终端的运行状态；根据实际信道数据对该虚拟信道进行配置，以还原该实际场景中的信道状态。
在一实施例中，该装置还包括：
第二接收模块，用于接收该实际场景中真实终端的实际终端数据，其中，该实际终端数据至少包括：实际位置信息、实际网络通信性能数据；
关联存储模块，用于将实际终端数据与该场景数据进行关联存储。
在一实施例中，该装置还包括：
第二注入模块，用于将该实际位置信息注入该虚拟仿真场景中；
位置同步模块，用于利用该实际位置信息对该虚拟仿真场景中的虚拟终端进行位置同步。
在一实施例中，该装置还包括：
第一获取模块，用于从该实际终端数据中获取通信状态信息，其中，该通信状态信息至少包括以下之一：平均时延、扇区吞吐量、用户丢包情况；
第二确定模块，用于根据该通信状态信息确定该网络质量，得到包括该网络质量的网络分析数据。
在一实施例中，该装置还包括：
发送模块，用于将该场景数据、该实际终端数据以及该网络分析数据发送给显示界面，以使该显示界面显示该当前通信网络的运行状态；
算法同步模块，用于将该虚拟基站的资源调度算法同步至该实际基站中。
在一实施例中，该装置还包括：
第二获取模块，用于获取该虚拟仿真场景中虚拟终端的虚拟网络通信性能数据；
对比模块，用于将该虚拟网络通信性能数据与该实际网络通信性能数据进行对比；
第二调整模块，用于若该虚拟网络通信性能数据与该实际网络通信性能数据的差值不满足预设条件，则对该虚拟仿真场景的通信仿真算法进行调整，以使该虚拟网络通信性能数据与该实际网络通信性能数据的差值满足该预设条件。
在一实施例中，该装置还包括：
优化模块，用于根据该场景数据、该实际网络通信性能数据以及该实际场景中的通信仿真算法对该虚拟仿真场景的通信仿真算法进行优化，得到优化后的通信仿真算法；
第二部署模块，用于将该优化后的通信仿真算法部署到该实际场景的基站中。
在一实施例中，该装置还包括：
监控模块，用于对该虚拟仿真场景与该实际场景进行可视化监控。
图6是根据本实施例的基于数字孪生的资源调度算法调整装置的框图，如图6所示，基于数字孪生的资源调度算法研究系统主要包括：
场景数据数据库构建模块62、仿真模型迭代优化模块64以及网络性能评估预测模块66，其中，场景数据库构建模块62，用于采集实际工作场景中静态环境数据以及动态状态数据，采集到的各类数据进行分析处理后既可用于在数字孪生仿真平台中构建等价的虚拟测试环境也可用于实时显示网络通信状态；仿真模型迭代优化模块64，用于则负责在收集实际网络与虚拟仿真中通信状态后，通过迭代优化以保证仿真系统中通信仿真算法的有效性；网络性能评估预测模块66，用于在通信仿真算法在收敛的前提下，对资源调度算法优化探索，首先通过仿真环境1∶1还原不同实际场景，接着针对不同场景测试不同资源调度算法有效性，在多维度综合考量选取较优的资源调度算法后，再将该资源调度算法用于实际场景以实现对通信网络质量优化。
根据本公开的另一个实施例，还提供了一种资源调度系统，图7是根据本公开实施例的资源调度系统的框图，如图7所示，包括：
数据采集仪器72，用于采集实际场景中多种实物的场景数据；
服务器74，与所述数据采集仪器无线连接，用于执行上述任一项所述的资源调度方法。
本实施例中的数据采集仪器72对应上述的数据采集系统31，服务器74具体可以包括上述的通信网络监控系统32、数字孪生服务器33。
在一实施例中，所述系统还包括：
显示界面，用于接收所述服务器发送的场景数据、实际终端数据以及网络分析数据，并根据所述场景数据、所述实际终端数据以及所述网络分析数据显示当前通信网络的运行状态。
本实施例中的显示界面对应上述的图形化显示系统34。
本公开的实施例还提供了一种计算机可读存储介质，该计算机可读存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
在一个示例性实施例中，上述计算机可读存储介质可以包括但不限于：U盘、只读存储器(Read-Only Memory，简称为ROM)、随机存取存储器(Random Access Memory，简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本公开的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
在一个示例性实施例中，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
本实施例中的具体示例可以参考上述实施例及示例性实施方式中所描述的示例，本实施例在此不再赘述。
显然，本领域的技术人员应该明白，上述的本公开的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上， 它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本公开不限制于任何特定的硬件和软件结合。
以上所述仅为本公开的示例性实施例而已，并不用于限制本公开，对于本领域的技术人员来说，本公开可以有各种更改和变化。凡在本公开的原则之内，所作的任何修改、等同替换、改进等，均应包含在本公开的保护范围之内。

Claims (16)

  1. 一种资源调度方法，包括：
    接收实际场景中多种实物的场景数据；
    根据所述场景数据确定所述实际场景中的网络质量；
    根据所述网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，所述虚拟仿真场景是基于所述场景数据构建的；
    将所述调整后的资源调度算法部署到所述实际场景的基站中。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    根据所述场景数据构建所述虚拟仿真场景所需的虚拟实体，其中，所述场景数据包括经纬度、物理尺寸、材料属性、海拔高度中的至少一个；
    将所述场景数据与构建的所述虚拟实体注入所述虚拟仿真场景中。
  3. 根据权利要求2所述的方法，其中，根据所述场景数据构建所述虚拟仿真场景所需的虚拟实体包括：
    分别模拟虚拟终端、虚拟基站以及虚拟信道；
    根据所述虚拟终端、所述虚拟基站以及所述虚拟信道还原所述实际场景。
  4. 根据权利要求3所述的方法，其中，根据所述虚拟终端、所述虚拟基站以及所述虚拟信道还原所述实际场景，包括：
    根据至少一种架构芯片下的仿真结果，构建真实基站对应的虚拟基站；
    构建与所述实际场景对应的等效终端硬件平台，在所述等效终端硬件平台上运行真实终端的通信协议栈以保证所述虚拟终端与所述真实终端匹配；
    根据实际信道数据对所述虚拟信道进行配置，以还原所述实际场景中的信道状态。
  5. 根据权利要求1所述的方法，其中，所述方法还包括：
    接收所述实际场景中真实终端的实际终端数据，其中，所述实际终端数据至少包括：实际位置信息、实际网络通信性能数据；
    将所述实际终端数据与所述场景数据进行关联存储。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    将所述实际位置信息注入所述虚拟仿真场景中；
    利用所述实际位置信息对所述虚拟仿真场景中的虚拟终端进行位置同步。
  7. 根据权利要求5所述的方法，其中，所述方法还包括：
    从所述实际终端数据中获取通信状态信息，其中，所述通信状态信息至少包括以下之一：平均时延、扇区吞吐量、用户丢包情况；
    根据所述通信状态信息确定所述网络质量，得到包括所述网络质量的网络分析数据。
  8. 根据权利要求7所述的方法，其中，所述方法还包括：
    将所述场景数据、所述实际终端数据以及所述网络分析数据发送给显示界面，以使所述显示界面显示当前通信网络的运行状态；
    将所述虚拟基站的资源调度算法同步至所述实际基站中。
  9. 根据权利要求5所述的方法，其中，所述方法还包括：
    获取所述虚拟仿真场景中虚拟终端的虚拟网络通信性能数据；
    将所述虚拟网络通信性能数据与所述实际网络通信性能数据进行对比；
    若所述虚拟网络通信性能数据与所述实际网络通信性能数据的差值不满足预设条件，则对所述虚拟仿真场景的通信仿真算法进行调整，以使所述虚拟网络通信性能数据与所述实际网络通信性能数据的差值满足所述预设条件。
  10. 根据权利要求5所述的方法，其中，所述方法还包括：
    根据所述场景数据、所述实际网络通信性能数据以及所述实际场景中的通信仿真算法对所述虚拟仿真场景的通信仿真算法进行优化，得到优化后的通信仿真算法；
    将所述优化后的通信仿真算法部署到所述实际场景的基站中。
  11. 根据权利要求1至10中任一项所述的方法，其中，所述方法还包括：
    对所述虚拟仿真场景与所述实际场景进行可视化监控。
  12. 一种资源调度装置，包括：
    第一接收模块，用于接收实际场景中多种实物的场景数据；
    第一确定模块，用于根据所述场景数据确定所述实际场景中的网络质量；
    第一调整模块，用于根据所述网络质量对虚拟仿真场景中的资源调度算法进行调整，得到调整后的资源调度算法，其中，所述虚拟仿真场景是基于所述场景数据构建的；
    第一部署模块，用于将所述调整后的资源调度算法部署到所述实际场景的基站中。
  13. 一种资源调度系统，包括：
    数据采集仪器，用于采集实际场景中多种实物的场景数据；
    服务器，与所述数据采集仪器无线连接，用于执行权利要求1至11中任一项所述的资源调度方法。
  14. 根据权利要求13所述的系统，其中，所述系统还包括：
    显示界面，用于接收所述服务器发送的场景数据、实际终端数据以及网络分析数据，并根据所述场景数据、所述实际终端数据以及所述网络分析数据显示当前通信网络的运行状态。
  15. 一种计算机可读的存储介质，所述存储介质中存储有计算机程序，其中，所述计算机程序被处理器运行时执行所述权利要求1至11任一项中所述的方法。
  16. 一种电子系统，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行所述权利要求1至11任一项中所述的方法。
PCT/CN2023/108230 2022-08-30 2023-07-19 一种资源调度方法、装置、系统、存储介质及电子系统 WO2024045932A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211062154.4 2022-08-30
CN202211062154.4A CN117693059A (zh) 2022-08-30 2022-08-30 一种资源调度方法、装置、系统、存储介质及电子系统

Publications (1)

Publication Number Publication Date
WO2024045932A1 true WO2024045932A1 (zh) 2024-03-07

Family

ID=90100313

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/108230 WO2024045932A1 (zh) 2022-08-30 2023-07-19 一种资源调度方法、装置、系统、存储介质及电子系统

Country Status (2)

Country Link
CN (1) CN117693059A (zh)
WO (1) WO2024045932A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118075798A (zh) * 2024-04-18 2024-05-24 香港中文大学（深圳） 一种基于功率损耗的基站选择及发射功率优化方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102026259A (zh) * 2010-12-06 2011-04-20 西安交通大学 一种LTE-A系统中针对CoMP技术的系统级仿真方法
CN112118287A (zh) * 2020-08-07 2020-12-22 北京工业大学 基于交替方向乘子算法与移动边缘计算的网络资源优化调度决策方法
CN113395723A (zh) * 2021-06-11 2021-09-14 西安交通大学 基于强化学习的5g nr下行调度时延优化系统
CN114050961A (zh) * 2021-11-08 2022-02-15 南京大学 一种大规模网络仿真系统及资源动态调度分配方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102026259A (zh) * 2010-12-06 2011-04-20 西安交通大学 一种LTE-A系统中针对CoMP技术的系统级仿真方法
CN112118287A (zh) * 2020-08-07 2020-12-22 北京工业大学 基于交替方向乘子算法与移动边缘计算的网络资源优化调度决策方法
CN113395723A (zh) * 2021-06-11 2021-09-14 西安交通大学 基于强化学习的5g nr下行调度时延优化系统
CN114050961A (zh) * 2021-11-08 2022-02-15 南京大学 一种大规模网络仿真系统及资源动态调度分配方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118075798A (zh) * 2024-04-18 2024-05-24 香港中文大学（深圳） 一种基于功率损耗的基站选择及发射功率优化方法

Also Published As

Publication number Publication date
CN117693059A (zh) 2024-03-12

Similar Documents

Publication Publication Date Title
US11451452B2 (en) Model update method and apparatus, and system
US20230087821A1 (en) Information processing method and related device
CN112327667B (zh) 面向大规模无人集群网络的半实物仿真要素设计方法
CN109862580B (zh) 一种网络优化方法及装置
CN110636102B (zh) 一种基于4g/5g无线网络的无人机通信系统及方法
EP4075843A1 (en) Method and apparatus for reporting measurement information, and method and apparatus for collecting measurement information
WO2024045932A1 (zh) 一种资源调度方法、装置、系统、存储介质及电子系统
CN114402654A (zh) 用于无线电接入网数据收集的装置
US20220394570A1 (en) Message sending method and apparatus, message receiving method and apparatus, and device and storage medium
Nardini et al. Using Simu5G as a realtime network emulator to test MEC apps in an end-to-end 5G testbed
Kumar et al. EMEEDP: Enhanced multi-hop energy efficient distributed protocol for heterogeneous wireless sensor network
CN113036930B (zh) 一种电网数据通讯管理系统
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
US11134402B1 (en) Systems and methods for beamforming and network optimization based on user equipment usage data derived from battery dissipation signatures
WO2023246517A1 (zh) 一种构建方法、第一通信节点、存储介质及构建系统
WO2023066046A1 (zh) 一种合约管理方法、装置及系统
EP1817931B1 (en) Simulating a mobile network with shared access channels
CN102802184B (zh) 一种实现无线网络信道仿真的方法、装置和系统
Zhongmei et al. A study for application research of 5G data acquisition and testing
CN114143243A (zh) 一种射频测试方法及系统
CN106028372A (zh) 一种基于sdn融合异构无线网络的系统
CN102547821B (zh) 一种全向发射定向接收站型的下行覆盖预测方法及装置
WO2024140022A1 (zh) 一种通信方法、装置、可读存储介质及芯片系统
CN108600119A (zh) 一种面向c-ran基带处理的数据缓冲区管理方法
EP4345699A1 (en) Training method for gan, machine learning system and communication apparatus

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: 23858968

Country of ref document: EP

Kind code of ref document: A1