WO2023109496A1 - 资源分配方法、装置、服务器和存储介质 - Google Patents

资源分配方法、装置、服务器和存储介质 Download PDF

Info

Publication number
WO2023109496A1
WO2023109496A1 PCT/CN2022/134871 CN2022134871W WO2023109496A1 WO 2023109496 A1 WO2023109496 A1 WO 2023109496A1 CN 2022134871 W CN2022134871 W CN 2022134871W WO 2023109496 A1 WO2023109496 A1 WO 2023109496A1
Authority
WO
WIPO (PCT)
Prior art keywords
communication load
resource allocation
cell group
dss
dss cell
Prior art date
Application number
PCT/CN2022/134871
Other languages
English (en)
French (fr)
Inventor
杜永生
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 WO2023109496A1 publication Critical patent/WO2023109496A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/14—Spectrum sharing arrangements between different networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/04—Wireless resource allocation
    • H04W72/044—Wireless resource allocation based on the type of the allocated resource
    • H04W72/0453—Resources in frequency domain, e.g. a carrier in FDMA
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/50—Allocation or scheduling criteria for wireless resources
    • H04W72/53—Allocation or scheduling criteria for wireless resources based on regulatory allocation policies

Definitions

  • the embodiments of the present application relate to the field of communication technologies, and in particular, to a resource allocation method, device, server, and storage medium.
  • Dynamic Spectrum Sharing is to allow 4G Long Term Evolution (4G LTE for short) and 5G New Radio (5G NR for short) to share the same spectrum, and to share time-frequency resources Dynamic allocation to 4G and 5G users. Dynamically and flexibly allocate spectrum resources for technologies of different standards in the same frequency band. This is because the 5G NR physical layer design has similarities to 4G LTE, which is the basis for dynamic spectrum sharing between 4G and 5G. The realization principle is to schedule NR users in LTE subframes under the same subcarrier spacing and similar time domain structure. First, it is necessary to ensure that the respective common channels in the 4G and 5G networks are independent of each other and not affected by each other.
  • the current basic principle is to analyze the activity rules of 4G users and 5G users through the study of past channel states, so as to make a prediction on the use of spectrum resources in the future. forecast.
  • This kind of prediction is smarter and more in line with the definition of cognitive radio.
  • this kind of prediction is more of a real-time prediction method, and only the data of the previous few cycles at the current moment are used for statistical evaluation to determine the resource allocation method in the next stage.
  • the main purpose of the embodiments of the present application is to provide a resource allocation method, device, server and storage medium.
  • the purpose is to improve the accuracy of the determined spectrum resource allocation method of the DSS cell group, so as to match the predicted resource with the actual service requirement.
  • the embodiment of the present application provides a resource allocation method, including: obtaining the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group; based on the preset prediction algorithm, according to the first A communication load array obtains the first predicted communication load of the DSS cell group; predicts the communication load of the DSS cell group according to the preset communication load prediction model, and obtains the second predicted communication load of the DSS cell group, wherein , the communication load prediction model is acquired based on the second communication load array training of the second historical period of the DSS cell group, the second historical period is greater than the first historical period; according to the first predicted communication The difference between the load and the second predicted communication load, determine the resource allocation strategy of the DSS cell group, and perform resource allocation to the DSS cell group according to the resource allocation strategy.
  • the embodiment of the present application also provides a resource allocation device, including: an acquisition module, configured to acquire the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group; the first prediction module, It is used to obtain the first predicted communication load of the DSS cell group according to the first communication load array based on the preset prediction algorithm; the second prediction module is used to calculate the DSS cell group according to the preset communication load prediction model Predicting the communication load, and obtaining the second predicted communication load of the DSS cell group, wherein the communication load prediction model is obtained based on the second communication load array training of the second historical period of the DSS cell group, the The second historical period is greater than the first historical period; the resource allocation module is configured to determine the resource allocation strategy of the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load, And perform resource allocation on the DSS cell group according to the resource allocation policy.
  • an acquisition module configured to acquire the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group
  • the first prediction module
  • an embodiment of the present application further provides a server, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the at least one processor An instruction executed by a processor, the instruction is executed by the at least one processor, so that the at least one processor can execute the above resource allocation method.
  • an embodiment of the present application further provides a computer-readable storage medium storing a computer program, and implementing the resource allocation method above when the computer program is executed by a processor.
  • the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group is obtained; based on the preset prediction algorithm, according to the first A communication load array obtains the first predicted communication load of the DSS cell group; predicts the communication load of the DSS cell group according to the preset communication load prediction model, and obtains the second predicted communication load of the DSS cell group, wherein , the communication load prediction model is acquired based on the second communication load array training of the second historical period of the DSS cell group, the second historical period is greater than the first historical period; according to the first predicted communication The difference between the load and the second predicted communication load, determine the resource allocation strategy of the DSS cell group, and perform resource allocation to the DSS cell group according to the resource allocation strategy.
  • FIG. 1 is a flowchart of a resource allocation method provided in an embodiment of the present application
  • FIG. 2 is a flowchart of step 104 of the resource allocation method provided by the embodiment of the present application.
  • FIG. 3 is a flowchart of a resource allocation method provided in an embodiment of the present application.
  • FIG. 4 is a flowchart of a resource allocation method provided in an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of a resource allocation device provided in an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a server provided in an embodiment of the present application.
  • the dynamic spectrum sharing technology is conducive to the smooth evolution from 4G to 5G, reduces the investment cost of 5G, and solves the problem of many 4G users and few 5G users in the early stage of 5G development. weak problem.
  • the current dynamic spectrum allocation method generally performs multiple confirmations and evaluations based on the current number of access users and loads of 4G users and 5G users, and finally adjusts the next stage to allocate spectrum resources for 4G users and 5G users for 4G users and 5G users Access to the terminal. Under this strategy, there are two problems as follows: 1. Handover delay problem: because the traffic and load of the current 4G users and 5G users need to be confirmed and evaluated many times in the previous cycles before the next resource allocation can be performed.
  • An embodiment of the present application relates to a resource allocation method, as shown in Figure 1, applied to a base station, including:
  • Step 101 acquiring a first array of communication loads in a first historical period of a specified dynamic spectrum sharing DSS cell group.
  • the designation of the DSS cell group is carried out at the calculation management center of the base station.
  • the historical communication load array of the DSS cell group can be stored according to the cell group identifier of the designated DSS cell group.
  • the first communication load array of the first historical period of the specified DSS cell group is acquired from the database of the.
  • what the first historical cycle defines may be the number of historical cycles, such as the first historical cycle refers to the past N cycles; the first historical cycle may also be limited by the length of the historical cycle, such as the first historical cycle refers to All cycles in the past 3 hours; here, there is no specific limitation on the way of defining the first historical cycle.
  • the first communication load array is actually composed of the communication loads of each historical period in the first historical period, and each communication load refers to the communication-related indicators concerned by the operator, such as traffic volume, uplink and downlink traffic, or weighted calculation indicators of the two etc.
  • Step 102 based on a preset prediction algorithm, obtain a first predicted communication load of the DSS cell group according to the first communication load array.
  • the prediction algorithm can be to calculate the communication load trend according to each communication load in the first communication load array, and obtain the first predicted communication load of the DSS cell group according to the communication load trend; the prediction algorithm can also be to Each communication load in the first communication load array is averaged, and the calculated average value is used as the first predicted communication load of the DSS cell group; wherein, the first predicted communication load of the DSS cell group refers to that the DSS cell group is in the next cycle The communication load prediction value of .
  • Step 103 Predict the communication load of the DSS cell group according to the preset communication load prediction model, and obtain the second predicted communication load of the DSS cell group, wherein the communication load prediction model is based on the second historical period of the DSS cell group.
  • the communication load array training is obtained, and the second history period is greater than the first history period.
  • the communication load prediction model is an intelligent model that can autonomously deduce the communication load of the DSS cell group in a certain period or in the future, so the communication load of the DSS cell group can be calculated by the communication load prediction model Reasoning, obtain the second predicted communication load of DSS cell group;
  • the second predicted communication load of DSS cell group refers to the communication load prediction value of DSS cell group in the next cycle;
  • the first predicted communication load and the second predicted communication load are The communication load prediction value of the DSS cell group in the same period, the difference between the first forecast communication load and the second forecast communication load is that the first forecast communication load is deduced from the data of a shorter historical period (such as: the past few period), it can be called short-term reasoning communication load, while the second predicted communication load is inferred from long historical period data (such as: the past few months or even years), which can be called long-term reasoning communication load.
  • the communication load prediction model is acquired based on the second communication load array training of the second historical period of the DSS cell group.
  • the second historical cycle defines the length of the historical cycle, for example, the second historical cycle refers to all cycles in the past 3 months or 1 year; compared with the first historical cycle, the second historical cycle The number of historical periods included in is much greater than the number of historical periods included in the first historical period.
  • the second communication load array is actually composed of communication loads of each historical period in the second historical period.
  • Step 104 Determine a resource allocation strategy for the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load, and allocate resources to the DSS cell group according to the resource allocation strategy.
  • determining the resource allocation strategy of the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load is actually judging the first predicted communication load and the second predicted communication load according to the difference accuracy.
  • Figure 2 the process of determining the resource allocation strategy of the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load is shown in Figure 2, including:
  • Step 201 detecting whether the difference falls within a preset load difference range.
  • the load difference range is actually the tolerance range of the difference between the first predicted communication load and the second predicted communication load.
  • step 202 is executed; when the difference is not within the load difference If the value is within the range, go to step 205.
  • Step 202 adding one to the value of the number of belonging times of the DSS cell group.
  • the difference between the first predicted communication load and the second predicted communication load falls within the load difference range, it means that the values predicted by the two forecasting methods are relatively close, but it is not yet possible to determine whether to use The first predicted communication load, or use the second predicted communication load for resource allocation, it is necessary to add 1 to the value of the number of belonging to the DSS cell group on the original basis; wherein, the value of the number of times of belonging to the DSS cell group is always accumulated , will not be cleared.
  • Step 203 detecting whether the value belonging to the number of times satisfies the first threshold.
  • the corresponding first threshold value is set for the number of belonging times, and the first threshold value indicates the number of times that the difference between the first predicted communication load and the second predicted communication load is within the load difference range; when the number of times belongs to When the value of the number of times reaches the first threshold, step 204 is performed, and when the value belonging to the number of times does not reach the first threshold, step 208 is performed.
  • Step 204 the resource allocation strategy is to allocate resources according to the second predicted communication load.
  • the corresponding resource allocation strategy is to allocate resources to the DSS cell group according to the second predicted communication load.
  • Step 205 add one to the value of the number of times that the DSS cell group does not belong to.
  • the difference between the first forecasted communication load and the second forecasted communication load does not belong to the range of load difference, it means that the values predicted by the two forecasting methods are far apart, but it is not yet possible to judge Whether to use the first predicted communication load or the second predicted communication load for resource allocation, it is necessary to add 1 to the value of the number of times that the DSS cell group does not belong to the original basis; wherein, the value of the number of times that the DSS cell group does not belong is It has been accumulating and will not be cleared.
  • Step 206 detecting whether a value that does not belong to the number of times satisfies the second threshold.
  • the number of non-belonging times is set with a corresponding second threshold value
  • the second threshold value represents the number of times that the difference between the first predicted communication load and the second predicted communication load is outside the range of the load difference
  • Step 207 the resource allocation strategy is to allocate resources according to the first predicted communication load.
  • the corresponding resource allocation strategy is to allocate resources to the DSS cell group according to the first predicted communication load.
  • Step 208 perform resource allocation according to the original resource allocation policy of the DSS cell group.
  • resource allocation is performed according to the original resource allocation policy of the DSS cell group.
  • resource allocation is performed on the spectrum resources of the DSS cell group according to the determined resource allocation strategy; and when the determined resource allocation strategy is resource allocation according to the first predicted communication load , it is necessary to add 1 to the value of the first resource allocation times of the DSS cell group, and when the value of the first resource allocation times meets the preset third threshold, it means that the communication load prediction model has aged, and a new round of communication load needs to be started
  • the 3rd threshold refers to the total number of times that the overall second forecast communication load is inconsistent with the first forecast communication load within a certain time frame; as the number of times of inconsistency within 100 times is At 30 o'clock, the communication load forecasting model needs to be updated, and at the 101st forecasting time, the value of the first resource allocation times will be updated to 0.
  • the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group is obtained; based on the preset prediction algorithm, according to the first communication load
  • the array acquires the first predicted communication load of the DSS cell group; predicts the communication load of the DSS cell group according to the preset communication load prediction model, and obtains the second predicted communication load of the DSS cell group, wherein the The communication load prediction model is obtained based on the second communication load array training of the second historical period of the DSS cell group, and the second historical period is greater than the first historical period; according to the first predicted communication load and the Determine the resource allocation strategy of the DSS cell group according to the difference between the second predicted communication loads, and perform resource allocation to the DSS cell group according to the resource allocation strategy.
  • An embodiment of the present application relates to a resource allocation method, as shown in Figure 3, applied to a base station, including:
  • Step 301 acquiring a first array of communication loads in a first historical period of a specified dynamic spectrum sharing DSS cell group.
  • this step is substantially the same as step 101 in the embodiment of the present application, and details are not repeated here.
  • Step 302 based on a preset prediction algorithm, obtain a first predicted communication load of the DSS cell group according to the first communication load array.
  • this step is substantially the same as step 102 in the embodiment of the present application, and details are not repeated here.
  • Step 303 acquiring the cell group ID of the DSS cell group, and identifying the scene of the DSS cell group to acquire the scene ID.
  • the cell group identifier is the only one that can identify the specified DSS cell group.
  • the scene identification of the specified DSS cell group can be performed to obtain the scene where the current DSS cell group is located, and generate a scene Logos, such as scene logos can be hot venues.
  • a communication load prediction model corresponding to the cell group identifier and the scenario identifier is obtained from a preset model database.
  • the model database exists in the computing management center of the base station, and each communication load forecasting model is also generated through training in the computing management center of the base station.
  • each communication load forecasting model it is first necessary to obtain the The second communication load array of the second historical period of the DSS cell group; then for each scene, based on the preset loss function, input the second communication load array corresponding to the scene into the pre-training model for training, and generate the scene corresponding Communication load forecasting model; after the communication load forecasting model of each scene is generated, the communication load forecasting model corresponding to the scene is saved to the model database according to the DSS cell group and the scene; wherein, the loss function refers to the difference between the predicted communication load and the actual communication load
  • the training process refers to iterating the model parameters according to the value of the loss function.
  • the cell group ID and the scenario ID need to be sent to the computing management center of the base station, and the computing management center obtains the corresponding model and return it.
  • the communication load prediction model corresponding to the cell group identifier and the scene identifier is not obtained from the model database, it means that the communication load prediction model corresponding to the cell group identifier and the scenario identifier is immature and cannot be put into use.
  • a general communication load forecasting model is acquired from the model database as a communication load forecasting model.
  • Step 305 Predict the communication load of the DSS cell group according to the preset communication load prediction model, and obtain the second predicted communication load of the DSS cell group, wherein the communication load prediction model is based on the second historical period of the DSS cell group.
  • the communication load array training is obtained, and the second history period is greater than the first history period.
  • this step is substantially the same as step 103 in the embodiment of the present application, and details are not repeated here.
  • Step 306 Determine a resource allocation strategy for the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load, and allocate resources to the DSS cell group according to the resource allocation strategy.
  • this step is substantially the same as step 104 in the embodiment of the present application, and details are not repeated here.
  • the scene of the DSS cell group can also be identified, and the corresponding communication load prediction model can be selected according to the scene of the DSS cell group, so that the obtained second predicted communication load is more accurate. It fits the actual application scenario and is more accurate.
  • An embodiment of the present application relates to a resource allocation method, as shown in Figure 4, applied to a base station, including:
  • Step 401 obtaining the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group
  • this step is substantially the same as step 101 in the embodiment of the present application, and details are not repeated here.
  • Step 402 based on a preset prediction algorithm, obtain a first predicted communication load of the DSS cell group according to the first communication load array.
  • this step is substantially the same as step 102 in the embodiment of the present application, and details are not repeated here.
  • Step 403 Predict the communication load of the DSS cell group according to the preset communication load prediction model, and obtain the second predicted communication load of the DSS cell group, wherein the communication load prediction model is based on the second historical period of the DSS cell group.
  • the communication load array training is obtained, and the second history period is greater than the first history period.
  • this step is substantially the same as step 103 in the embodiment of the present application, and details are not repeated here.
  • Step 404 acquiring the current communication quality and/or current communication load before resource allocation of the DSS cell group.
  • Step 405 according to the difference between the first predicted communication load and the second predicted communication load, determine the resource allocation strategy of the DSS cell group, and perform resource allocation to the DSS cell group according to the resource allocation strategy.
  • this step is substantially the same as step 104 in the embodiment of the present application, and details are not repeated here.
  • Step 406 acquiring the first communication quality and/or the first communication load after resource allocation of the DSS cell group.
  • the first communication quality and/or the first communication load of the resource allocation of the DSS cell group need to be recorded.
  • Step 407 acquiring the quality difference between the current communication quality and the first communication quality, and/or acquiring the load difference between the current communication load and the first communication load.
  • the quality gap before and after resource allocation of the DSS cell group is obtained; and/or, according to the recorded current communication load and the first communication load, the DSS The load gap before and after the resource allocation of the cell group.
  • Step 408 when the quality gap and/or the load gap meet the preset gap tolerance condition, wait for the next resource allocation period of the DSS cell group, otherwise, send an alarm message to the administrator of the DSS cell group.
  • the quality gap and/or the load gap after obtaining the quality gap and/or load gap, it is necessary to detect whether the quality gap and/or the load gap meet the preset gap tolerance condition, and when the quality gap and/or the load gap meet the gap tolerance condition , indicating that the change of communication quality and/or communication load before and after the resource allocation of the DSS cell group is within the normal range, it is possible to continue to judge the resource allocation mode of the DSS cell group, and wait for the next resource allocation period of the DSS cell group; and When the quality gap and/or the load gap do not meet the gap tolerance condition, it indicates that the communication quality and/or the communication load change of the DSS cell group before and after the resource allocation is abnormal, and at this time, it is necessary to stop the judgment of the resource allocation method for the DSS cell group, And send alarm information to the administrator of the DSS cell group, so that the administrator can reset the acquisition method of the resource allocation method of the DSS cell group.
  • step division of the above various methods is only for the sake of clarity of description. During implementation, it can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this application ; Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but not changing the core design of the algorithm and process are all within the scope of protection of this application.
  • FIG. 5 is The schematic diagram of the resource allocation device in this embodiment includes: an acquisition module 501 , a first prediction module 502 , a second prediction module 503 and a resource allocation module 504 .
  • the obtaining module 501 is configured to obtain the first communication load array of the first historical period of the specified dynamic spectrum sharing DSS cell group.
  • the first prediction module 502 is configured to obtain a first predicted communication load of the DSS cell group according to the first communication load array based on a preset prediction algorithm.
  • the second prediction module 503 is configured to predict the communication load of the DSS cell group according to a preset communication load prediction model, and obtain the second predicted communication load of the DSS cell group, wherein the communication load prediction model is based on The second communication load array training of the second historical period of the DSS cell group is obtained through training, and the second historical period is greater than the first historical period.
  • the resource allocation module 504 is configured to determine the resource allocation strategy of the DSS cell group according to the difference between the first predicted communication load and the second predicted communication load, and allocate the resource allocation strategy to the DSS according to the resource allocation strategy.
  • the cell group performs resource allocation.
  • this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in cooperation with the above method embodiment.
  • the relevant technical details and technical effects mentioned in the above embodiments are still valid in this embodiment, and will not be repeated here to reduce repetition.
  • the relevant technical details mentioned in this embodiment can also be applied in the above embodiments.
  • this system embodiment is mainly aimed at the description of the resource allocation method provided by the method embodiment at the software implementation level, and its implementation also needs to rely on hardware support, such as the functions of related modules can be deployed on the processor , so that the processor runs to implement the corresponding functions, in particular, the relevant data generated by the running can be stored in the memory for subsequent inspection and use.
  • modules involved in this embodiment are logical modules.
  • a logical unit can be a physical unit, or a part of a physical unit, or multiple physical units. Combination of units.
  • units that are not closely related to solving the technical problem proposed in the present application are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.
  • FIG. 6 Another embodiment of the present application relates to a server, as shown in FIG. 6 , including: at least one processor 601; and a memory 602 communicatively connected to the at least one processor 601; Instructions executed by the at least one processor 601, the instructions are executed by the at least one processor 601, so that the at least one processor 601 can execute the resource allocation methods in the foregoing embodiments.
  • the memory and the processor are connected by a bus
  • the bus may include any number of interconnected buses and bridges, and the bus connects one or more processors and various circuits of the memory together.
  • the bus may also connect together various other circuits such as peripherals, voltage regulators, and power management circuits, all of which are well known in the art and therefore will not be further described herein.
  • the bus interface provides an interface between the bus and the transceivers.
  • a transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing means for communicating with various other devices over a transmission medium.
  • the data processed by the processor is transmitted on the wireless medium through the antenna, and further, the antenna also receives the data and transmits the data to the processor.
  • the processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. Instead, memory can be used to store data that the processor uses when performing operations.
  • Another embodiment of the present application relates to a computer-readable storage medium storing a computer program.
  • the above method embodiments are implemented when the computer program is executed by the processor.
  • a storage medium includes several instructions to make a device ( It may be a single-chip microcomputer, a chip, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), magnetic disk or optical disc, etc. can store program codes. medium.

Landscapes

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

Abstract

本申请实施例涉及通信技术领域，涉及一种资源分配方法、装置、服务器和存储介质。资源分配方法包括：获取指定DSS小区组的第一历史周期的第一通信负荷数组；基于预设预测算法，根据第一通信负荷数组获取DSS小区组的第一预测通信负荷；根据预设通信负荷预测模型对DSS小区组的通信负荷进行预测，获取DSS小区组的第二预测通信负荷，通信负荷预测模型是基于DSS小区组的第二历史周期的第二通信负荷数组训练获取的，第二历史周期大于第一历史周期；根据第一预测通信负荷和第二预测通信负荷间的差值，确定DSS小区组的资源分配策略，根据资源分配策略对DSS小区组进行资源分配。

Description

资源分配方法、装置、服务器和存储介质
相关申请
本申请要求于2021年12月13号申请的、申请号为202111521921.9的中国专利申请的优先权。
技术领域
本申请实施例涉及通信技术领域，特别涉及一种资源分配方法、装置、服务器和存储介质。
背景技术
动态频谱共享(Dynamic Spectrum Sharing，简称DSS)，就是允许4G长期演进(4G Long Term Evolution，简称4G LTE)和5G新空口(5G New Radio，简称5G NR)共享相同的频谱，并将时频资源动态分配给4G和5G用户。在同一频段内为不同制式的技术动态、灵活的分配频谱资源。这是因为5G NR物理层设计与4G LTE具有相似之处，这是4G和5G之间实现动态频谱共享的基础。其实现原理是在相同的子载波间隔和相似的时域结构下，在LTE子帧中调度NR用户，先要确保4G和5G网络中各自的公共信道相互独立且相互不受影响，比如确保5G NR的参考信号与LTE的参考信号在时频资源分配上不会发生冲突，然后将5G NR的用户数据插入LTE子帧。目前存在基于多播/组播单频网络(Multicast Broadcast Single Frequency Network，简称MBSFN)、基于5G的mini-slot和基于速率匹配的三种资源分配形式的频谱资源共享技术。
然而，对于如上频谱资源进行动态分配时，应该分配多少资源到5G，目前基本原理在于通过对过去的信道状态的学习来分析4G用户和5G用户的活动规律，从而对未来的频谱资源使用情况做出预测。这种预测更加智能，更符合对认知无线电的定义。但是，这种预测由于网元的计算存储资源限制，更多的采取实时预测的方式，只采用当前时刻的前几个周期的数据进行统计评估，来决定下一阶段资源分配的方式。这种方式对于由于4G用户和5G用户的长期发展趋势，突发事件影响，每天的潮汐效应，都不可避免会产生预测失效的问题，从而导致预测资源和实际业务需求不匹配，影响用户体验。
发明内容
本申请实施例的主要目的在于提出一种资源分配方法、装置、服务器和存储介质。旨在提高所确定的DSS小区组的频谱资源分配方式的准确率，从而使得预测资源和实际业务需求相匹配。
为实现上述目的，本申请实施例提供了一种资源分配方法，包括：获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所 述第二历史周期大于所述第一历史周期；根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。
为实现上述目的，本申请实施例还提供一种资源分配装置，包括：获取模块，用于获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；第一预测模块，用于基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；第二预测模块，用于根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期；资源分配模块，用于根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。
为实现上述目的，本申请实施例还提供了一种服务器，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行上述的资源分配方法。
为实现上述目的，本申请实施例还提供了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资源分配方法。
本申请提出的资源分配方法，在DSS小区组的资源分配的过程中，获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期；根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。通过使用短期历史数据获取的第一预测通信负荷和长期历史数获取的第二预测通信负荷的差值来确定DSS小区组的资源分配方式，使得本申请能够提高所确定的DSS小区组的频谱资源分配方式的准确率，从而使得预测资源和实际业务需求相匹配；解决了现有技术中仅依靠多次短期历史数据来评估资源分配方式所导致的DSS小区组的资源分配的准确率不高，出现预测资源和实际业务需求不匹配，影响用户体验的技术问题。
附图说明
图1是本申请实施方式提供的资源分配方法的流程图；
图2是本申请实施方式提供的资源分配方法的步骤104的流程图；
图3是本申请实施方式提供的资源分配方法的流程图；
图4是本申请实施方式提供的资源分配方法的流程图；
图5是本申请实施方式提供的资源分配装置的结构示意图；
图6是本申请实施方式提供的服务器的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的各实施例进行详细的阐述。然而，本领域的普通技术人员可以理解，在本申请各实施例中，为了使读者更好地理解本申请而提出了许多技术细节。但是，即使没有这些技术细节和基于以下各实施例的种种变化和修改，也可以实现本申请所要求保护的技术方案。以下各个实施例的划分是为了描述方便，不应对本申请的具体实现方式构成任何限定，各个实施例在不矛盾的前提下可以相互结合相互引用。
动态频谱共享技术有利于4G向5G平滑演进，降低5G投资成本，解决5G发展早期，4G用户多，5G用户很少的问题；同时也能通过4G信号解决5G频段较高，信号穿透能力较弱的问题。目前的动态频谱分配方式一般根据4G用户和5G用户的当前的接入用户数量和负荷，进行多次确认评估，最后调整下一个阶段分配4G用户和5G用户的频谱资源用于4G用户和5G用户于终端接入。在这种策略下，存在如下两个问题：1.切换时延问题：因为需要经过前面几个周期多次确认评估当前4G用户和5G用户的话务和负荷才能进行下一次资源分配，切换时延较长，如果当前面临的是一个较长时间的用户话务和负荷的高峰期，则会由于评估时长较长，导致其中的话务质量损耗较大，用户体验受损。另外如果动态转换时间过长，譬如达到100ms，会导致某些5G用户的流量已经从波峰切换到波谷时，DSS小区组调度器才从4G转换到5G，而这时的5G用户已经不再需要被调度了。2.准确率问题：这种仅靠前面几个周期实时评估出的下一个周期的资源分配方式，比较单一，准确率不高，容易出现评估资源和实际业务需求不匹配的情况，影响用户体验。
本申请的一个实施例涉及一种资源分配方法，如图1所示，应用在基站上，包括：
步骤101，获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组。
在一示例实施中，DSS小区组的指定是在基站的计算管理中心进行的，在DSS小区组指定之后，可以根据指定的DSS小区组的小区组标识，从存储DSS小区组的历史通信负荷数组的数据库中获取到指定的DSS小区组的第一历史周期的第一通信负荷数组。其中，第一历史周期限定的可以是历史周期的个数，如第一历史周期是指过去的N个周期；第一历史周期限定的也可以是历史周期的长度，如第一历史周期是指过去3小时内的全部周期；此处并不对第一历史周期的限定方式进行具体的限定。第一通信负荷数组实际是第一历史周期内各历史周期的通信负荷组成，每一个通信负荷是指运营者关注的通信相关指标，例如话务量、上下行流量、或二者的加权计算指标等等。
步骤102，基于预设预测算法，根据第一通信负荷数组获取DSS小区组的第一预测通信负荷。
在一示例实施中，预测算法可以是根据第一通信负荷数组中的各通信负荷计算出通信负荷的走势，根据通信负荷的走势获取DSS小区组的第一预测通信负荷；预测算法也可以是对第一通信负荷数组中的各通信负荷进行求平均值，将计算的平均值作为DSS小区组的第一预测通信负荷；其中，DSS小区组的第一预测通信负荷是指DSS小区组在下一个周期的通信负荷预测值。
步骤103，根据预设通信负荷预测模型对DSS小区组的通信负荷进行预测，获取DSS小区组的第二预测通信负荷，其中，通信负荷预测模型是基于DSS小区组的第二历史周期的第二通信负荷数组训练获取的，第二历史周期大于第一历史周期。
在一示例实施中，通信负荷预测模型是一个能够自主推理出DSS小区组在某个周期或未来一段时间内的通信负荷的智能模型，因此可以通过通信负荷预测模型对DSS小区组的通信负荷进行推理，获取DSS小区组的第二预测通信负荷；其中，DSS小区组的第二预测通信负荷是指DSS小区组在下一个周期的通信负荷预测值；第一预测通信负荷和第二预测通信负荷是DSS小区组在同一个周期的通信负荷预测值，第一预测通信负荷和第二预测通信负荷的不同之处在于：第一预测通信负荷是较短历史周期数据推理出来的(如：过去几个周期)，可以称为短期推理的通信负荷，而第二预测通信负荷是长历史周期数据推理出来的(如：过去几个月甚至几年)，可以称为长期推理的通信负荷。
在一示例实施中，通信负荷预测模型是基于DSS小区组的第二历史周期的第二通信负荷数组训练获取的。其中，第二历史周期限定的是历史周期的长度，如第二历史周期是指过去3个月或者1年内的全部周期；第二历史周期相比于第一历史周期来说，第二历史周期内所包含的历史周期的个数是远大于第一历史周期内所包含的历史周期的个数。第二通信负荷数组实际是第二历史周期内各历史周期的通信负荷组成。
步骤104，根据第一预测通信负荷和第二预测通信负荷间的差值，确定DSS小区组的资源分配策略，并根据资源分配策略对DSS小区组进行资源分配。
在一示例实施中，根据第一预测通信负荷和第二预测通信负荷间的差值来确定DSS小区组的资源分配策略实际上是根据差值来判断第一预测通信负荷和第二预测通信负荷的准确性。具体的，根据第一预测通信负荷和第二预测通信负荷间的差值来确定DSS小区组的资源分配策略的过程如图2所示，包括：
步骤201，检测差值是否属于预设的负荷差值范围。
在一示例实施中，负荷差值范围实际上第一预测通信负荷和第二预测通信负荷间差距的容忍范围，当差值在负荷差值范围内时，执行步骤202；当差值不在负荷差值范围内时，执行步骤205。
步骤202，给DSS小区组的属于次数的值加一。
在一示例实施中，当第一预测通信负荷和第二预测通信负荷间的差值属于负荷差值范围时，说明两种预测方法预测出来的值较为接近，但此时还不能够判断是使用第一预测通信负荷，还是使用第二预测通信负荷来进行资源分配，需要给DSS小区组的属于次数的值在原有基础上加1；其中，DSS小区组的属于次数的值是一直处于累加的，不会被清零。
步骤203，检测属于次数的值是否满足第一阈值。
在一示例实施中，属于次数设置有相对应的第一阈值，第一阈值表示第一预测通信负荷和第二预测通信负荷间的差值在负荷差值范围之内的发生次数；当属于次数的值达到第一阈值时，则执行步骤204，当属于次数的值没有达到第一阈值时，则执行步骤208。
步骤204，资源分配策略为根据第二预测通信负荷进行资源分配。
在一示例实施中，当属于次数的值达到第一阈值时，对应的资源分配策略为根据第二预测通信负荷对DSS小区组进行资源分配。
步骤205，给DSS小区组的不属于次数的值加一。
在一示例实施中，当第一预测通信负荷和第二预测通信负荷间的差值不属于负荷差值范围时，说明两种预测方法预测出来的值相差较远，但此时还不能够判断是使用第一预测通信负荷，还是使用第二预测通信负荷来进行资源分配，需要给DSS小区组的不属于次数的值在 原有基础上加1；其中，DSS小区组的不属于次数的值是一直处于累加的，不会被清零。
步骤206，检测不属于次数的值是否满足第二阈值。
在一示例实施中，不属于次数设置有相对应的第二阈值，第二阈值表示第一预测通信负荷和第二预测通信负荷间的差值在负荷差值范围之外的发生次数；当不属于次数的值达到第二阈值时，则执行步骤207，当不属于次数的值没有达到第二阈值时，则执行步骤208。
步骤207，资源分配策略为根据第一预测通信负荷进行资源分配。
在一示例实施中，当不属于次数的值达到第二阈值时，对应的资源分配策略为根据第一预测通信负荷对DSS小区组进行资源分配。
步骤208，根据DSS小区组的原始资源分配策略进行资源分配。
在一示例实施中，当属于次数的值没有达到第一阈值，以及当不属于次数的值达到第二阈值时，根据DSS小区组的原始资源分配策略进行资源分配。
在一示例实施中，在资源分配策略确定好之后，根据确定好的资源分配策略对DSS小区组的频谱资源进行资源分配；而当确定的资源分配策略为根据第一预测通信负荷进行资源分配时，需要给DSS小区组的第一资源分配次数的值加1，且在第一资源分配次数的值满足预设第三阈值时，说明通信负荷预测模型已经老化，需要启动新的一轮通信负荷预测模型的训练，来更新通信负荷预测模型；其中，第三阈值是指在一定时间范围内总体第二预测通信负荷和第一预测通信负荷不一致的总次数；如在100次内不一致的次数为30时，就需要更新通信负荷预测模型，而在第101次预测时，第一资源分配次数的值会更新为0。
本申请实施例，在DSS小区组的资源分配的过程中，获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期；根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。通过使用短期历史数据获取的第一预测通信负荷和长期历史数获取的第二预测通信负荷的差值来确定DSS小区组的资源分配方式，使得本申请能够提高所确定的DSS小区组的频谱资源分配方式的准确率，从而使得预测资源和实际业务需求相匹配；解决了现有技术中仅依靠多次短期历史数据来评估资源分配方式所导致的DSS小区组的资源分配的准确率不高，出现预测资源和实际业务需求不匹配，影响用户体验的技术问题。
本申请的一个实施例涉及一种资源分配方法，如图3所示，应用在基站上，包括：
步骤301，获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组。
在一示例实施中，本步骤与本申请实施例的步骤101大致相同，此处不一一赘述。
步骤302，基于预设预测算法，根据第一通信负荷数组获取DSS小区组的第一预测通信负荷。
在一示例实施中，本步骤与本申请实施例的步骤102大致相同，此处不一一赘述。
步骤303，获取DSS小区组的小区组标识，并识别DSS小区组的场景获取场景标识。
在一示例实施中，小区组标识是唯一能够标识指定DSS小区组的，在DSS小区组指定之后，可以对指定的DSS小区组进行场景识别，获取当前DSS小区组所处的场景，并生成 场景标识，如场景标识可以为热点场馆。
步骤304，从预设的模型数据库中获取与小区组标识和场景标识对应的通信负荷预测模型。
在一示例实施中，模型数据库存在于基站的计算管理中心的，各通信负荷预测模型也是通过基站的计算管理中心进行训练生成的，在生成各通信负荷预测模型时，首先需要获取在各场景下DSS小区组的第二历史周期的第二通信负荷数组；之后对于每一个场景，基于预设损失函数，将与场景对应的第二通信负荷数组输入到预训练模型中进行训练，生成场景对应的通信负荷预测模型；在生成各场景的通信负荷预测模型之后，便根据DSS小区组和场景将场景对应的通信负荷预测模型保存至模型数据库；其中，损失函数是指预测通信负荷和实际通信负荷之间的差距，训练过程是指根据损失函数的值对模型参数进行迭代。
在一示例实施中，在获取与小区组标识和场景标识对应的通信负荷预测模型时，需要将小区组标识和场景标识发送至基站的计算管理中心，计算管理中心从模型数据库中获取相对应的模型并返回。而当从模型数据库中未获取到与小区组标识和场景标识对应的通信负荷预测模型时，说明与该小区组标识和场景标识对应的通信负荷预测模型未成熟，不能够投入使用，此时可以从模型数据库获取通用通信负荷预测模型作为通信负荷预测模型。
步骤305，根据预设通信负荷预测模型对DSS小区组的通信负荷进行预测，获取DSS小区组的第二预测通信负荷，其中，通信负荷预测模型是基于DSS小区组的第二历史周期的第二通信负荷数组训练获取的，第二历史周期大于第一历史周期。
在一示例实施中，本步骤与本申请实施例的步骤103大致相同，此处不一一赘述。
步骤306，根据第一预测通信负荷和第二预测通信负荷间的差值，确定DSS小区组的资源分配策略，并根据资源分配策略对DSS小区组进行资源分配。
在一示例实施中，本步骤与本申请实施例的步骤104大致相同，此处不一一赘述。
本申请的实施方式，在其他实施例的基础之上还可以对DSS小区组的场景进行识别，根据DSS小区组的场景来选取对应的通信负荷预测模型，使得所获取的第二预测通信负荷更贴合于实际应用场景，更加准确。
本申请的一个实施例涉及一种资源分配方法，如图4所示，应用在基站上，包括：
步骤401，获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；
在一示例实施中，本步骤与本申请实施例的步骤101大致相同，此处不一一赘述。
步骤402，基于预设预测算法，根据第一通信负荷数组获取DSS小区组的第一预测通信负荷。
在一示例实施中，本步骤与本申请实施例的步骤102大致相同，此处不一一赘述。
步骤403，根据预设通信负荷预测模型对DSS小区组的通信负荷进行预测，获取DSS小区组的第二预测通信负荷，其中，通信负荷预测模型是基于DSS小区组的第二历史周期的第二通信负荷数组训练获取的，第二历史周期大于第一历史周期。
在一示例实施中，本步骤与本申请实施例的步骤103大致相同，此处不一一赘述。
步骤404，获取DSS小区组资源分配前的当前通信质量和/或当前通信负荷。
在一示例实施中，在对DSS小区组进行资源分配之前，需要将DSS小区组的当前通信质量和/或当前通信负荷记录下来。
步骤405，根据第一预测通信负荷和第二预测通信负荷间的差值，确定DSS小区组的资 源分配策略，并根据资源分配策略对DSS小区组进行资源分配。
在一示例实施中，本步骤与本申请实施例的步骤104大致相同，此处不一一赘述。
步骤406，获取DSS小区组资源分配后的第一通信质量和/或第一通信负荷。
在一示例实施中，当DSS小区组进行资源分配完成之后，需要将DSS小区组的资源分配后的第一通信质量和/或第一通信负荷记录下来。
步骤407，获取当前通信质量和第一通信质量的质量差距，和/或，获取当前通信负荷和第一通信负荷的负荷差距。
在一示例实施中，根据所记录的当前通信质量和第一通信质量，获取DSS小区组进行资源分配前后的质量差距；和/或，根据所记录的当前通信负荷和第一通信负荷，获取DSS小区组进行资源分配前后的负荷差距。
步骤408，当质量差距和/或负荷差距满足预设差距容忍条件时，则等待DSS小区组的下一个资源分配周期，否则，向DSS小区组的管理员发送告警信息。
在一示例实施中，在获取到质量差距和/或负荷差距之后，需要检测质量差距和/或负荷差距是否满足预设的差距容忍条件，而在质量差距和/或负荷差距满足差距容忍条件时，说明DSS小区组的资源分配前后的通信质量和/或通信负荷的变化在正常范围内，可以继续对DSS小区组进行资源分配方式的判断，等待该DSS小区组的下一个资源分配周期；而在质量差距和/或负荷差距不满足差距容忍条件时，说明DSS小区组的资源分配前后的通信质量和/或通信负荷的变化异常，此时需要停止对DSS小区组进行资源分配方式的判断，并向DSS小区组的管理员发送告警信息，以供管理员重新设定DSS小区组进行资源分配方式的获取方法。
本申请的实施方式，在其他实施例的基础之上还可以通过对资源分配前后的通信负荷和通信质量进行比较，来判断资源分配策略的确定方式是否合理，使得本申请更加智能化。
上面各种方法的步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本申请的保护范围内；对算法中或者流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其算法和流程的核心设计都在该申请的保护范围内。
本申请的另一个实施例涉及一种资源分配装置，下面对本实施例的资源分配装置的细节进行具体的说明，以下内容仅为方便理解提供的实现细节，并非实施本例的必须，图5是本实施例所述的资源分配装置的示意图，包括：获取模块501、第一预测模块502、第二预测模块503和资源分配模块504。
其中，获取模块501，用于获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组。
第一预测模块502，用于基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷。
第二预测模块503，用于根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期。
资源分配模块504，用于根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资 源分配。
不难发现，本实施例为与上述方法实施例对应的系统实施例，本实施例可以与上述方法实施例互相配合实施。上述实施例中提到的相关技术细节和技术效果在本实施例中依然有效，为了减少重复，这里不再赘述。相应地，本实施例中提到的相关技术细节也可应用在上述实施例中。
需要说明的是，本系统实施例主要是针对方法实施例提供的资源分配方法在软件实现层面上的描述，其实现还需要依托于硬件的支持，如相关模块的功能可以被部署到处理器上，以便处理器运行实现相应的功能，特别地，运行产生的相关数据可以被存储到存储器中以便后续检查和使用。
值得一提的是，本实施例中所涉及到的各模块均为逻辑模块，在实际应用中，一个逻辑单元可以是一个物理单元，也可以是一个物理单元的一部分，还可以以多个物理单元的组合实现。此外，为了突出本申请的创新部分，本实施例中并没有将与解决本申请所提出的技术问题关系不太密切的单元引入，但这并不表明本实施例中不存在其它的单元。
本申请另一个实施例涉及一种服务器，如图6所示，包括：至少一个处理器601；以及，与所述至少一个处理器601通信连接的存储器602；其中，所述存储器602存储有可被所述至少一个处理器601执行的指令，所述指令被所述至少一个处理器601执行，以使所述至少一个处理器601能够执行上述各实施例中的资源分配方法。
其中，存储器和处理器采用总线方式连接，总线可以包括任意数量的互联的总线和桥，总线将一个或多个处理器和存储器的各种电路连接在一起。总线还可以将诸如外围设备、稳压器和功率管理电路等之类的各种其他电路连接在一起，这些都是本领域所公知的，因此，本文不再对其进行进一步描述。总线接口在总线和收发机之间提供接口。收发机可以是一个元件，也可以是多个元件，比如多个接收器和发送器，提供用于在传输介质上与各种其他装置通信的单元。经处理器处理的数据通过天线在无线介质上进行传输，进一步，天线还接收数据并将数据传送给处理器。
处理器负责管理总线和通常的处理，还可以提供各种功能，包括定时，外围接口，电压调节、电源管理以及其他控制功能。而存储器可以被用于存储处理器在执行操作时所使用的数据。
本申请另一个实施例涉及一种计算机可读存储介质，存储有计算机程序。计算机程序被处理器执行时实现上述方法实施例。
即，本领域技术人员可以理解，实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得一个设备(可以是单片机，芯片等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本领域的普通技术人员可以理解，上述各实施方式是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (10)

  1. 一种资源分配方法，包括：
    获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；
    基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；
    根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期；
    根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。
  2. 根据权利要求1所述的资源分配方法，其中，所述资源分配策略包括：根据所述第一预测通信负荷进行资源分配、根据所述第二预测通信负荷进行资源分配和根据所述DSS小区组的原始资源分配策略进行资源分配；所述方法还包括：
    当所述DSS小区组的所述资源分配策略为根据所述第一预测通信负荷进行资源分配时，给所述DSS小区组的第一资源分配次数的值加1；
    当所述第一资源分配次数的值满足预设第三阈值时，则更新所述通信负荷预测模型。
  3. 根据权利要求1所述的资源分配方法，其中，所述根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，包括：
    检测所述差值是否属于预设的负荷差值范围；
    当所述差值属于所述负荷差值范围时，给所述DSS小区组的属于次数的值加一，并检测所述属于次数的值是否满足第一阈值；当所述属于次数的值满足所述第一阈值时，所述资源分配策略为根据所述第二预测通信负荷进行资源分配，否则，根据所述DSS小区组的原始资源分配策略进行资源分配；或者，
    当所述差值不属于所述负荷差值范围时，给所述DSS小区组的不属于次数的值加一，并检测所述不属于次数的值是否满足第二阈值；当所述不属于次数的值满足所述第二阈值时，所述资源分配策略为根据所述第一预测通信负荷进行资源分配，否则，根据所述原始资源分配策略进行资源分配。
  4. 根据权利要求1所述的资源分配方法，其中，所述根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，之前包括：
    获取所述DSS小区组的小区组标识，并识别所述DSS小区组的场景获取场景标识；
    从预设的模型数据库中获取与所述小区组标识和所述场景标识对应的所述通信负荷预测模型。
  5. 根据权利要求4所述的资源分配方法，其中，所述方法还包括：
    当从所述模型数据库中未获取到与所述小区组标识和所述场景标识对应的所述通信负荷预测模型时，从所述模型数据库获取通用通信负荷预测模型作为所述通信负荷预测模型。
  6. 根据权利要求4所述的资源分配方法，其中，所述方法还包括：
    获取在各场景下所述DSS小区组的第二历史周期的第二通信负荷数组；
    对于每一个所述场景，基于预设损失函数，将与所述场景对应的所述第二通信负荷数组 输入到预训练模型中进行训练，生成所述场景对应的所述通信负荷预测模型；
    根据所述DSS小区组和所述场景将所述场景对应的所述通信负荷预测模型保存至所述模型数据库。
  7. 根据权利要求1至6中任一项所述的资源分配方法，其中，所述根据所述资源分配策略对所述DSS小区组进行资源分配，之前包括：获取所述DSS小区组资源分配前的当前通信质量和/或当前通信负荷；
    所述根据所述资源分配策略对所述DSS小区组进行资源分配，之后包括：
    获取所述DSS小区组资源分配后的第一通信质量和/或第一通信负荷；
    获取所述当前通信质量和所述第一通信质量的质量差距，和/或，获取所述当前通信负荷和所述第一通信负荷的负荷差距；
    当所述质量差距和/或所述负荷差距满足预设差距容忍条件时，则等待所述DSS小区组的下一个资源分配周期，否则，向所述DSS小区组的管理员发送告警信息。
  8. 一种资源分配装置，包括：
    获取模块，设置为获取指定的动态频谱共享DSS小区组的第一历史周期的第一通信负荷数组；
    第一预测模块，设置为基于预设预测算法，根据所述第一通信负荷数组获取所述DSS小区组的第一预测通信负荷；
    第二预测模块，设置为根据预设通信负荷预测模型对所述DSS小区组的通信负荷进行预测，获取所述DSS小区组的第二预测通信负荷，其中，所述通信负荷预测模型是基于所述DSS小区组的第二历史周期的第二通信负荷数组训练获取的，所述第二历史周期大于所述第一历史周期；
    资源分配模块，设置为根据所述第一预测通信负荷和所述第二预测通信负荷间的差值，确定所述DSS小区组的资源分配策略，并根据所述资源分配策略对所述DSS小区组进行资源分配。
  9. 一种服务器，包括：
    至少一个处理器；以及，
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1至7中任一项所述的资源分配方法。
  10. 一种计算机可读存储介质，存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至7中任一项所述的资源分配方法。
PCT/CN2022/134871 2021-12-13 2022-11-29 资源分配方法、装置、服务器和存储介质 WO2023109496A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111521921.9 2021-12-13
CN202111521921.9A CN116347453A (zh) 2021-12-13 2021-12-13 资源分配方法、装置、服务器和存储介质

Publications (1)

Publication Number Publication Date
WO2023109496A1 true WO2023109496A1 (zh) 2023-06-22

Family

ID=86774792

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/134871 WO2023109496A1 (zh) 2021-12-13 2022-11-29 资源分配方法、装置、服务器和存储介质

Country Status (2)

Country Link
CN (1) CN116347453A (zh)
WO (1) WO2023109496A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118042550A (zh) * 2024-04-10 2024-05-14 深圳市英迈通信技术有限公司 一种5g智能手机信号优化方法和系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109565841A (zh) * 2016-08-10 2019-04-02 高通股份有限公司 用于副链路中的子带调度的信令机制
CN110784334A (zh) * 2018-07-24 2020-02-11 阿瓦亚公司 用于自我分配资源的系统
WO2021079178A1 (en) * 2019-10-25 2021-04-29 Telefonaktiebolaget Lm Ericsson (Publ) Method for dynamic spectrum sharing for loosely coupled systems
US11178577B1 (en) * 2020-02-17 2021-11-16 Sprint Spectrum L.P. Dynamically combining air-interface resource reservations

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109565841A (zh) * 2016-08-10 2019-04-02 高通股份有限公司 用于副链路中的子带调度的信令机制
CN110784334A (zh) * 2018-07-24 2020-02-11 阿瓦亚公司 用于自我分配资源的系统
WO2021079178A1 (en) * 2019-10-25 2021-04-29 Telefonaktiebolaget Lm Ericsson (Publ) Method for dynamic spectrum sharing for loosely coupled systems
US11178577B1 (en) * 2020-02-17 2021-11-16 Sprint Spectrum L.P. Dynamically combining air-interface resource reservations

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ERICSSON: "Core part: NR Dynamic spectrum sharing (DSS)", 3GPP DRAFT; RP-202549, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. TSG RAN, no. Electronic Meeting; 20201207 - 20201211, 30 November 2020 (2020-11-30), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051963107 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118042550A (zh) * 2024-04-10 2024-05-14 深圳市英迈通信技术有限公司 一种5g智能手机信号优化方法和系统

Also Published As

Publication number Publication date
CN116347453A (zh) 2023-06-27

Similar Documents

Publication Publication Date Title
US9414384B2 (en) State-driven secondary cell activation and deactivation
CN110651494B (zh) 广泛分布的无线网络中自适应跟踪和分配容量的系统和方法
RU2543614C2 (ru) Способ и устройство для управления мощностью базовой станции
JP2017532917A (ja) ライセンスされないキャリアを占有する送信方法、装置及びアクセスポイント
EP3499818B9 (en) Method and device for load processing
WO2023109496A1 (zh) 资源分配方法、装置、服务器和存储介质
CN103188715B (zh) 无线资源自动监控调度的方法及装置
US9030983B2 (en) Power saving method and device for a cellular radio system
US11736954B2 (en) Capacity planning method and apparatus
US20120164955A1 (en) Method and Apparatus for Cell Control
CN110677854A (zh) 载频容量调整的方法、装置、设备和介质
CN114885376B (zh) 一种帧结构配置方法、装置及存储介质
CA3234895A1 (en) Network capacity optimization method, apparatus, and system
CN111954224B (zh) 一种同频干扰的处理方法及装置
CN116743669A (zh) 一种深度强化学习分组调度方法、系统、终端及介质
CN112752319A (zh) 网络切换方法、装置、终端及存储介质
EP4175352A1 (en) Information transmission method and device, storage medium, and electronic device
US20220377652A1 (en) Resource availability check
CN110139294A (zh) 一种唤醒区域确定方法、网络设备及用户终端
WO2021197463A1 (zh) 节能指示方法、装置及计算机存储介质
WO2024139968A1 (zh) 小区节能闭载的配置方法、设备、装置及存储介质
US20240205958A1 (en) Method performed by network node and network node
WO2022121513A1 (zh) 性能指标至差值的生成方法、装置、电子设备及存储介质
CN114630365B (zh) 小区健康状态检测的方法及装置
WO2024040961A1 (zh) 一种数据处理方法、基站及存储介质

Legal Events

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

Ref document number: 22906247

Country of ref document: EP

Kind code of ref document: A1