A method, device, storage medium and equipment for dynamically adjusting resource allocation
By building a MCS threshold determination model, using user experience data and channel quality data for preprocessing, and dynamically adjusting the MCS threshold, the problem that resource allocation method in 5G communication system cannot effectively solve the interference between users, and maximize spatial multiplexing and efficient resource allocation to meet the performance requirements of terminal equipment and users.
Patent Information
- Application Number
- CN202011373400.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-11-30
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2040-11-30
AI Technical Summary
The resource allocation method in the existing 5G communication system cannot effectively solve the interference problem between users, resulting in the inability to meet the service quality requirements of terminal equipment and the service-level agreement performance of users, and the calculation volume is large and the spectrum efficiency is low.
By building an MCS threshold determination model, preprocessing is performed using user experience data, channel quality data and spectrum efficiency data, and dynamically adjusting the MCS threshold to achieve dynamic adjustment of resource allocation, maximize spatial multiplexing, and meet the QoS requirements of terminal equipment and User SLA performance.
It achieves the maximum spatial multiplexing under the conditions of ensuring user SLA, meets the QoS requirements of terminal equipment, and improves network spectrum efficiency, avoids interference between users.
Smart Images

Figure CN114641078B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communication technology, and in particular to a method, device, storage medium and equipment for dynamically adjusting resource allocation. Background Art
[0002] With the rapid development of the fifth generation wireless systems (5G), the types of terminal devices are also increasing. In order to meet the high bandwidth requirements of a large number of terminal devices, the 5G communication system introduces large-scale multiple input multiple output (MIMO) transmission technology to support multi-user spatial multiplexing of the same frequency, thereby achieving higher spectrum efficiency. However, due to factors such as the mobility of device terminals and cost reduction, when multiple users reuse the same frequency, they interfere with each other (interference in the same cell or interference in adjacent cells). This interference between users will cause jitter in packet delay, packet reliability and bandwidth, and the greater the interference, the greater the jitter, so that the base station may not be able to meet the quality of service (QoS) requirements of the terminal device, and thus cannot guarantee the performance of the user's service level agreement (SLA).
[0003] Therefore, in order to guarantee the user's SLA, there are two commonly used resource allocation methods for the QoS requirements of the device terminal in the 5G communication system: one is the resource allocation method based on the maximum approximate sum rate. Although this method can comprehensively calculate the scheduling priority of each user based on the data volume, QoS parameters, channel quality and historical rate of the user's service to maximize the capacity, this method needs to traverse the interference relationship between the user and the selected user set in different combinations, and select the user combination with the interference between users lower than the threshold until the maximum likelihood sum function no longer increases. As a result, each time a user is selected using this method, all unselected users must be traversed, and the amount of calculation will increase rapidly with the number of users. In addition, the fixed threshold is difficult to match the QoS requirements of different business scenarios, and all pairing combinations cannot be traversed, so the optimal solution cannot be found. Another commonly used resource allocation method is a resource allocation method based on interference minimization. For the same time-frequency resource, resources are allocated according to the first-come, first-served (FIFO) principle according to the waiting delay of the device terminal. The same time-frequency resource is allocated to only one user, and the time-frequency resource is not spatially multiplexed, so that the user packet delay requirements can be met and mutual interference between users can be avoided. However, since multiple cells measure the channel of the same user, the channel overhead increases, and the transmission delay between cells or sites causes the neighboring cells to be unable to obtain user interference information in a timely and efficient manner, this method cannot effectively avoid the interference from adjacent cells. In addition, since this method uses a conservative low MCS threshold and a non-spatial multiplexing strategy to avoid interference and guarantee packet delay, it sacrifices network spectrum efficiency, which may result in the failure to meet the bandwidth requirements of the service. Summary of the invention
[0004] The embodiments of the present application provide a method, apparatus, storage medium and device for dynamically adjusting resource allocation, which helps to overcome the shortcomings of existing resource allocation methods. By learning the relationship between different terminal device business scenario combinations and different threshold thresholds and SLA completion, the threshold threshold configuration value with the highest SLA completion in the current scenario is quickly found for dynamic adjustment of resource allocation, thereby achieving maximum spatial reuse while ensuring the user's SLA, which not only meets the QoS requirements of the terminal device, but also ensures the user's SLA performance.
[0005] In a first aspect, the present application provides a method for dynamically adjusting resource allocation, the method comprising: when dynamically adjusting resource allocation, first obtaining user information data in a current network scenario, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data, and then preprocessing the user experience data to obtain preprocessed user experience data; and preprocessing the channel quality data to obtain preprocessed channel quality data, and then inputting the preprocessed user experience data and the preprocessed channel quality data and the spectrum efficiency data into a pre-constructed MCS threshold determination model to determine the MCS threshold in the current network scenario, and then determining the spatial multiplexing user set based on the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation.
[0006] Compared with traditional technologies, since the embodiment of the present application pre-builds an MCS threshold determination model, the model can be used to quickly and dynamically adjust the MCS thresholds corresponding to different network scenarios, so as to maximize spatial reuse while ensuring the user's SLA, thereby not only meeting the QoS requirements of the terminal device, but also ensuring the user's SLA performance.
[0007] In a possible implementation, the user experience data is preprocessed to obtain preprocessed user experience data; the channel quality data is preprocessed to obtain preprocessed channel quality data, including: normalizing the user experience data according to the service quality QoS requirements corresponding to the user to obtain normalized user experience data; using the differential transformation method, normalizing the channel quality data to obtain normalized channel quality data.
[0008] In a possible implementation, the spatial multiplexing user set is determined according to the MCS threshold and the spectrum efficiency data, including: selecting users in descending order according to user priority to join the initial spatial multiplexing user set, and obtaining a spatial multiplexing user set that meets preset conditions; wherein the initial spatial multiplexing user set is an empty set; the preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and the spectrum efficiency value corresponding to the spatial multiplexing user set after the i-th user is added is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before the i-th user is added; wherein i is a positive integer greater than 0. In this way, it can be ensured that users in the spatial multiplexing user set can reuse the same spectrum resources.
[0009] In a possible implementation, an MCS threshold determination model is constructed, including obtaining training user information data under different training network scenarios; wherein the training user information data includes training user experience data, training channel quality data, and training spectrum efficiency data; preprocessing the training user experience data to obtain preprocessed training user experience data; preprocessing the training channel quality data to obtain preprocessed training channel quality data; training an initial MCS threshold determination model according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data, and the MCS threshold labels corresponding to different training network scenarios to generate an MCS threshold determination model.
[0010] In a possible implementation, the initial MCS threshold determination model is a neural network model.
[0011] In a possible implementation, the method also includes: obtaining verification user information data under different verification network scenarios; wherein the verification user information data includes verification user experience data, verification channel quality data and verification spectrum efficiency data; preprocessing the verification user experience data to obtain preprocessed verification user experience data; preprocessing the verification channel quality data to obtain preprocessed verification channel quality data; inputting the preprocessed verification user experience data, the preprocessed verification channel quality data and the verification spectrum efficiency data into the MCS threshold determination model to obtain the MCS threshold corresponding to the verification network scenario; when the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario, the verification user information data is re-used as training user information data to update the MCS threshold determination model.
[0012] In the second aspect, the present application also provides a dynamic adjustment device for resource allocation, which includes: a first acquisition unit, used to acquire user information data in the current network scenario, wherein the user information data includes user experience data, channel quality data and spectrum efficiency data; a first preprocessing unit, used to preprocess the user experience data to obtain preprocessed user experience data; preprocess the channel quality data to obtain preprocessed channel quality data; a first determination unit, used to input the preprocessed user experience data, the preprocessed channel quality data and the spectrum efficiency data into a pre-constructed MCS threshold determination model to determine the MCS threshold in the current network scenario; a second determination unit, used to determine the spatial multiplexing user set according to the MCS threshold and the spectrum efficiency data, so as to realize dynamic adjustment of resource allocation.
[0013] In one possible implementation, the first preprocessing unit is specifically used to: normalize the user experience data according to the service quality QoS requirements corresponding to the user to obtain normalized user experience data; use the differential transformation method to normalize the channel quality data to obtain normalized channel quality data.
[0014] In one possible implementation, the first determination unit is specifically used to: select users in order from high to low according to user priority to join the initial spatial multiplexing user set, and obtain a spatial multiplexing user set that meets preset conditions; wherein, the initial spatial multiplexing user set is an empty set; the preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and that the spectrum efficiency value corresponding to the spatial multiplexing user set after adding the i-th user is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before adding the i-th user; i is a positive integer greater than 0.
[0015] In one possible implementation, the device also includes: a second acquisition unit, used to acquire training user information data under different training network scenarios; wherein the training user information data includes training user experience data, training channel quality data and training spectrum efficiency data; a second preprocessing unit, used to preprocess the training user experience data to obtain preprocessed training user experience data; preprocess the training channel quality data to obtain preprocessed training channel quality data; a training unit, used to train the initial MCS threshold determination model according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data and the MCS threshold labels corresponding to different training network scenarios to generate an MCS threshold determination model.
[0016] In a possible implementation, the initial MCS threshold determination model is a neural network model.
[0017] In one possible implementation, the device also includes: a third acquisition unit, used to acquire verification user information data under different verification network scenarios; wherein the verification user information data includes verification user experience data, verification channel quality data and verification spectrum efficiency data; a third preprocessing unit, used to preprocess the verification user experience data to obtain preprocessed verification user experience data; preprocess the verification channel quality data to obtain preprocessed verification channel quality data; the acquisition unit, used to input the preprocessed verification user experience data, the preprocessed verification channel quality data, and the verification spectrum efficiency data into the MCS threshold determination model to obtain the MCS threshold corresponding to the verification network scenario; an updating unit, used to use the verification user information data again as training user information data to update the MCS threshold determination model when the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario.
[0018] In a third aspect, the present application further provides a dynamic adjustment device for resource allocation, the dynamic adjustment device for resource allocation comprising: a memory, a processor;
[0019] A memory is used to store instructions; a processor is used to execute the instructions in the memory to execute the method in the above-mentioned first aspect and any possible implementation manner thereof.
[0020] In a fourth aspect, the present application further provides a computer-readable storage medium, comprising instructions, which, when executed on a computer, enables the computer to execute the method in the above-mentioned first aspect and any possible implementation thereof.
[0021] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:
[0022] When dynamically adjusting resource allocation, the embodiment of the present application first obtains user information data in the current network scenario, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data, and then preprocesses the user experience data to obtain preprocessed user experience data; and preprocesses the channel quality data to obtain preprocessed channel quality data, and then inputs the preprocessed user experience data, the preprocessed channel quality data, and the spectrum efficiency data into a pre-constructed MCS threshold determination model to determine the MCS threshold in the current network scenario, and then the spatial multiplexing user set can be determined based on the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation. It can be seen that since the embodiment of the present application pre-constructs the MCS threshold determination model, the model can be used to quickly and dynamically adjust the MCS thresholds corresponding to different network scenarios, so as to maximize spatial multiplexing while ensuring the user SLA, thereby not only meeting the QoS requirements of the terminal device, but also ensuring the user's SLA performance. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 A schematic diagram of an application scenario of an embodiment of the present application;
[0024] Figure 2 A flowchart of a method for dynamically adjusting resource allocation provided in an embodiment of the present application;
[0025] Figure 3 A schematic diagram of a process for determining a spatial multiplexing user set according to an MCS threshold and spectrum efficiency data provided in an embodiment of the present application;
[0026] Figure 4 A structural block diagram of a dynamic adjustment device for resource allocation provided in an embodiment of the present application;
[0027] Figure 5 A schematic diagram of the structure of a dynamic adjustment device for resource allocation provided in an embodiment of the present application. DETAILED DESCRIPTION
[0028] The embodiments of the present application provide a method, apparatus, storage medium and device for dynamically adjusting resource allocation, which can maximize spatial reuse while ensuring the user's SLA, not only meeting the QoS requirements of the terminal device, but also ensuring the user's SLA performance.
[0029] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0030] The present application can be applied in the field of communication technology, and the application scenarios of the products will be introduced below.
[0031] like Figure 1 As shown, the fifth generation core network (5GC) 103 sends the pre-configured QoS requirements (such as video or audio QoS requirements, etc.) of the service to the base station (BS) 102 according to the user service type. BS102 measures the channel quality of multiple users within its service range, and the user equipment (UE) 101 reports the channel quality indicator (CQI) and antenna channel in the channel measurement and the SLA completion status (such as historical rate) to the base station 102. In order to learn the hidden features between the user service quality QoS requirements and the channel quality through the neural network, the modulation and coding scheme (MCS) threshold configuration value with the highest SLA completion in the current scenario is determined to output the spatial multiplexing user combination under the premise of ensuring the SLA, and realize the dynamic adjustment of resource allocation.
[0032] It should be understood that the embodiments of the present application can also be applied to other scenarios that require dynamic adjustment of resource allocation, and other application scenarios are not listed one by one here.
[0033] Based on the above application scenarios, the present application embodiment provides a method for dynamically adjusting resource allocation, which can be applied to the base station 102. Figure 2 As shown, the method includes:
[0034] S201: Acquire user information data in the current network scenario, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data.
[0035] In this embodiment, in order to maximize spatial reuse while ensuring user SLA, it is first necessary to obtain user information data in the current network scenario to perform subsequent step S202. The user information data includes user experience data, channel quality data, and spectrum efficiency data.
[0036] Specifically, user experience data may include actual measured values such as packet loss rate, packet delay, packet rate, etc. Packet delay refers to the time measured on the communication interface from the source sending a given information to the destination successfully receiving the given information.
[0037] Spectral efficiency refers to the total amount of data that can be transmitted within the bandwidth constraints of a digital communication system. It is a measure of the efficiency with which the physical layer communication protocol (sometimes medium access control, channel access protocol) can use the limited spectrum.
[0038] S202: Preprocess the user experience data to obtain preprocessed user experience data; preprocess the channel quality data to obtain preprocessed channel quality data.
[0039] In this embodiment, after obtaining user information data including user experience data, channel quality data and spectrum efficiency data in the current network scenario through step S201, in order to determine the optimal MCS threshold, the user experience data may be further preprocessed to obtain preprocessed user experience data, and the channel quality data may be preprocessed to obtain preprocessed channel quality data, so as to execute the subsequent step S203.
[0040] In a possible implementation of the embodiment of the present application, the user experience data may be normalized according to the service quality QoS requirements corresponding to the user to obtain normalized user experience data. In addition, the channel quality data may be normalized using a differential transformation method to obtain normalized channel quality data for performing subsequent step S203.
[0041] Specifically, according to the user's QoS requirements (such as packet delay, bandwidth, reliability, etc.), encoding (such as One-Hot Enconding) can be performed according to different QoS requirements. The total number of online users with different encodings within the current preset range (such as a cell) is counted, which is defined here as N i , and i∈[1,K], where K refers to the total number of service types in the current network environment. And obtain the state vector U=[N1,N2,…N K On this basis, the QoS requirements of various services are periodically monitored, and the compliance rate of each service is statistically obtained. The business compliance rate is discretized from 0 to 100 to obtain a K×100 state space.
[0042] At the same time, the channel measurement values CQI of different users obtained can be transformed into an n×n diagonal matrix Among them, n refers to the total number of users in the current preset range (such as a cell) at the current moment. Then, it is combined with the user correlation matrix Superposition is performed to obtain a user channel measurement matrix (defined as H here), that is, H=D+(1-C).
[0043] S203: Input the preprocessed user experience data, the preprocessed channel quality data, and the spectrum efficiency data into a pre-built MCS threshold determination model to determine the MCS threshold in the current network scenario.
[0044] In this embodiment, after obtaining the preprocessed user experience data and the preprocessed channel quality data through step S202, the preprocessed user experience data, the preprocessed channel quality data and the spectrum efficiency data can be further input into a pre-built MCS threshold determination model to determine the MCS threshold under the current network scenario, so as to execute the subsequent step S204 and realize dynamic adjustment of resource allocation.
[0045] S204: Determine a set of spatial multiplexing users according to the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation.
[0046] In this embodiment, after determining the MCS threshold in the current network scenario through step S203, all users in the spatial multiplexing user set can be further determined based on the MCS threshold and the spectrum efficiency data obtained through step S201, so that dynamic adjustment of resource allocation can be achieved. Specifically, an optional implementation method is to first sort all users in the network scenario from high to low according to user priority, and then select users in order from high to low according to user priority to join the initial spatial multiplexing user set to obtain a spatial multiplexing user set that meets preset conditions. Among them, the initial spatial multiplexing user set is an empty set. The preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and the spectrum efficiency value corresponding to the spatial multiplexing user set after adding the i-th user is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before adding the i-th user, and i is a positive integer greater than 0.
[0047] Specifically, if Figure 3 As shown, it shows a flow chart of determining a spatial multiplexing user set according to the MCS threshold and spectrum efficiency data provided by an embodiment of the present application. The specific implementation process is: first, all user terminals in the current network scenario are sorted from high to low according to priority to form a user set S, that is, S = {UE1, UE2, ...UE Q}, and set the initial spatial multiplexing user set V to an empty set, and define the spectrum efficiency of the spatial multiplexing user set V as SE'; then, select the i-th user UE from the user set S i , and calculate the joining user UE i After that, the approximate channel quality values of all users in the set V are not lower than the protection threshold corresponding to the MCS threshold. If not, the i-th user UE iRemove from the set S. If yes, then further calculate the i-th user UE i The spectral efficiency of the set after adding set V And judge Is it not less than the number of UEs joining the i-th user? i The spectral efficiency value SE' corresponding to the spatial multiplexing user set V before, if not, the i-th user UE i Remove from the set S. If so, the i-th user UE i Add set V, update set V, and update the spectrum efficiency from SE' to Realize dynamic adjustment of resource allocation.
[0048] In summary, the present embodiment provides a method for dynamically adjusting resource allocation. When dynamically adjusting resource allocation, user information data in the current network scenario is first obtained, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data. Then, the user experience data is preprocessed to obtain preprocessed user experience data; and the channel quality data is preprocessed to obtain preprocessed channel quality data. Then, the preprocessed user experience data, the preprocessed channel quality data, and the spectrum efficiency data are input into a pre-constructed MCS threshold determination model to determine the MCS threshold in the current network scenario. Then, the spatial multiplexing user set can be determined based on the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation. It can be seen that since the embodiment of the present application pre-constructs the MCS threshold determination model, the model can be used to quickly and dynamically adjust the MCS thresholds corresponding to different network scenarios to maximize spatial multiplexing while ensuring the user SLA, thereby not only meeting the QoS requirements of the terminal device, but also ensuring the user's SLA performance.
[0049] Next, the construction process of the MCS threshold determination model is introduced, which may specifically include the following steps A1-A3:
[0050] Step A1: Acquire training user information data in different training network scenarios; wherein the training user information data includes training user experience data, training channel quality data and training spectrum efficiency data.
[0051] In this embodiment, in order to construct the MCS threshold determination model, a lot of preparatory work needs to be done in advance. In addition, in order to improve the accuracy of the prediction results of the MCS threshold determination model, the embodiment of the present application collects corresponding user information data (including user experience data, channel quality data, and spectrum efficiency data, etc.) as training data in different network scenarios, which is used to perform model training in various network scenarios, so as to further improve the accuracy of the model in determining the MCS threshold.
[0052] Step A2: preprocess the training user experience data to obtain preprocessed training user experience data; preprocess the training channel quality data to obtain preprocessed training channel quality data.
[0053] In this embodiment, after obtaining user information data including training user experience data, training channel quality data and training spectrum efficiency data in different training network scenarios through step A1, in order to train an MCS threshold determination model with higher prediction accuracy, the training user experience data can be further preprocessed to obtain preprocessed training user experience data, and the training channel quality data can be preprocessed to obtain preprocessed training channel quality data. The preprocessed training channel quality data can be used as input data of the model to perform the subsequent step A3.
[0054] Step A3: Train the initial MCS threshold determination model according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data, and the MCS threshold labels corresponding to different training network scenarios to generate an MCS threshold determination model.
[0055] In this embodiment, after obtaining the preprocessed training user experience data and the preprocessed training channel quality data, they can be input into the initial MCS threshold determination model together with the training spectrum efficiency data to determine the MCS prediction thresholds corresponding to different training network scenarios. Then, the MCS prediction thresholds corresponding to different training network scenarios can be compared with the MCS threshold labels corresponding to different training network scenarios (i.e., the real manual labeling results), and the model parameters can be updated according to the difference between the two until the preset conditions are met, such as when the difference change is very small, the update of the model parameters is stopped, the training of the MCS threshold determination model is completed, and a trained MCS threshold determination model is generated.
[0056] An optional implementation is that the initial MCS threshold determination model can be a neural network model (such as a convolutional neural network (CNN)). In addition, in order to train an MCS threshold determination model with better prediction effect, during the training process, the cost function used in this embodiment is as follows:
[0057]
[0058] Among them, K represents the total number of service types corresponding to users in the current network environment; L represents the SLA completion status obtained by the interaction between the base station and the user, which can be specifically measured by the SLA compliance rate R corresponding to the i-th service. i Multiply by the spectrum efficiency value SE corresponding to this type of service i That is, L = Ri ×SE i ; b represents the spectrum efficiency corresponding to the baseline MCS threshold. The value of b does not depend on π and estimates the expected result. It is mainly used to reduce the change of gradient; p θ (π i ) indicates that the MCS threshold is selected as π i probability.
[0059] Through the above embodiments, the training user information data in different training network scenarios can be used to train and generate the MCS threshold determination model. Further, the generated MCS threshold determination model can be verified using the verification user information data in different verification network scenarios. The specific verification process can include the following steps B1-B4:
[0060] Step B1: Acquire verification user information data in different verification network scenarios; wherein the verification user information data includes verification user experience data, verification channel quality data, and verification spectrum efficiency data.
[0061] In actual applications, in order to verify the MCS threshold determination model, it is first necessary to obtain verification user information data under different verification network scenarios, including verification user experience data, verification channel quality data, and verification spectrum efficiency data. Among them, the verification user information data refers to the user experience data that can be used to verify the MCS threshold determination model. After obtaining the verification user information data under different verification network scenarios, you can continue to execute step B2.
[0062] Step B2: preprocess the verified user experience data to obtain preprocessed verified user experience data; preprocess the verified channel quality data to obtain preprocessed verified channel quality data.
[0063] In actual applications, after obtaining the verification user information data including verification user experience data, verification channel quality data and verification spectrum efficiency data in different verification network scenarios through step B1, it cannot be directly used to verify the MCS threshold determination model. Instead, it is necessary to preprocess the verification user experience data to obtain preprocessed verification user experience data, and preprocess the verification channel quality data to obtain preprocessed verification channel quality data. Then, the preprocessed verification user experience data and preprocessed verification channel quality data can be used to verify the MCS threshold determination model.
[0064] Step B3: input the preprocessed verified user experience data, the preprocessed verified channel quality data, and the verified spectrum efficiency data into the MCS threshold determination model to obtain the MCS threshold corresponding to the verified network scenario.
[0065] In the specific implementation process, after obtaining the preprocessed verification user experience data and the preprocessed verification channel quality data through step B2, the preprocessed verification user experience data, the preprocessed verification channel quality data and the verification spectrum efficiency data can be further input into the MCS threshold determination model to obtain the prediction result of the MCS threshold corresponding to the verification network scenario, and then step B4 can be continued.
[0066] Step B4: When the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario, the verification user information data is used again as the training user information data to update the MCS threshold determination model.
[0067] In actual applications, after obtaining the prediction result of the MCS threshold corresponding to the verification network scenario through step B3, it can be further compared with the manual marking result of the MCS threshold corresponding to the verification network scenario. When the prediction result of the MCS threshold corresponding to the verification network scenario is inconsistent with the manual marking result of the MCS threshold corresponding to the verification network scenario, the verification user information data can be used again as training user information data to update the MCS threshold determination model.
[0068] Through the above embodiments, the MCS threshold determination model can be effectively verified using the verification user information data under different verification network scenarios. When the prediction result of the MCS threshold corresponding to the verification network scenario is inconsistent with the manual marking result of the MCS threshold corresponding to the verification network scenario, the MCS threshold determination model can be adjusted and updated in time, which helps to improve the determination precision and accuracy of the MCS threshold determination model.
[0069] In summary, the MCS threshold determination model trained by this embodiment can use the preprocessed user experience data, preprocessed channel quality data and spectrum efficiency data to determine the MCS threshold in the current network scenario, and then use the MCS threshold to determine the set of spatially multiplexed users, thereby maximizing spatial multiplexing while ensuring the user's SLA, which not only meets the QoS requirements of the terminal device, but also ensures the user's SLA performance.
[0070] In order to better implement the above solution of the embodiment of the present application, the following also provides related devices for implementing the above solution. Figure 4 As shown, the embodiment of the present application provides a dynamic adjustment device 400 for resource allocation. The device 400 may include: a first acquisition unit 401, a first preprocessing unit 402, a first determination unit 403, and a second determination unit 404. The first acquisition unit 401 is used to support the device 400 to perform Figure 2In the embodiment shown in S201, the first pre-processing unit 402 is used to support the device 400 to perform Figure 2 S202 in the illustrated embodiment. The first determining unit 403 is used to support the device 400 to execute Figure 2 S203 in the illustrated embodiment. The second determining unit 404 is used to support the device 400 to execute Figure 2 S204 in the illustrated embodiment. Specifically,
[0071] A first acquisition unit 401 is used to acquire user information data in a current network scenario, where the user information data includes user experience data, channel quality data, and spectrum efficiency data;
[0072] The first preprocessing unit 402 is used to preprocess the user experience data to obtain preprocessed user experience data; preprocess the channel quality data to obtain preprocessed channel quality data;
[0073] A first determination unit 403 is used to input the preprocessed user experience data, the preprocessed channel quality data and the spectrum efficiency data into a pre-built MCS threshold determination model to determine the MCS threshold in the current network scenario;
[0074] The second determining unit 404 is used to determine the spatial multiplexing user set according to the MCS threshold and the spectrum efficiency data to achieve dynamic adjustment of resource allocation.
[0075] In an implementation of this embodiment, the first preprocessing unit 402 is specifically configured to:
[0076] According to the service quality QoS requirements corresponding to the user, the user experience data is normalized to obtain normalized user experience data; and the channel quality data is normalized using a differential transformation method to obtain normalized channel quality data.
[0077] In one implementation of this embodiment, the first determining unit 403 is specifically used for:
[0078] Select users in descending order according to user priority to join the initial spatial multiplexing user set, and obtain a spatial multiplexing user set that meets preset conditions;
[0079] Among them, the initial spatial multiplexing user set is an empty set; the preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and the spectrum efficiency value corresponding to the spatial multiplexing user set after adding the i-th user is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before adding the i-th user; i is a positive integer greater than 0.
[0080] In one implementation of this embodiment, the device further includes:
[0081] A second acquisition unit is used to acquire training user information data in different training network scenarios; wherein the training user information data includes training user experience data, training channel quality data and training spectrum efficiency data;
[0082] A second preprocessing unit is used to preprocess the training user experience data to obtain preprocessed training user experience data; and preprocess the training channel quality data to obtain preprocessed training channel quality data;
[0083] The training unit is used to train the initial MCS threshold determination model according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data and the MCS threshold labels corresponding to different training network scenarios to generate the MCS threshold determination model.
[0084] In one implementation of this embodiment, the initial MCS threshold determination model is a neural network model.
[0085] In one implementation of this embodiment, the device further includes:
[0086] A third acquisition unit is used to acquire verification user information data in different verification network scenarios; wherein the verification user information data includes verification user experience data, verification channel quality data and verification spectrum efficiency data;
[0087] A third preprocessing unit is used to preprocess the verified user experience data to obtain preprocessed verified user experience data; preprocess the verified channel quality data to obtain preprocessed verified channel quality data;
[0088] An obtaining unit, used to input the preprocessed verified user experience data, the preprocessed verified channel quality data, and the verified spectrum efficiency data into an MCS threshold determination model to obtain an MCS threshold corresponding to the verified network scenario;
[0089] The updating unit is used to update the MCS threshold determination model by reusing the verification user information data as the training user information data when the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario.
[0090] In summary, the present embodiment provides a dynamic adjustment device for resource allocation. When dynamically adjusting resource allocation, the user information data in the current network scenario is first obtained, wherein the user information data includes user experience data, channel quality data and spectrum efficiency data. Then, the user experience data is preprocessed to obtain preprocessed user experience data; and the channel quality data is preprocessed to obtain preprocessed channel quality data. Then, the preprocessed user experience data, the preprocessed channel quality data and the spectrum efficiency data are input into the pre-constructed MCS threshold determination model to determine the MCS threshold in the current network scenario. Then, the spatial multiplexing user set can be determined according to the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation. It can be seen that since the embodiment of the present application pre-constructs the MCS threshold determination model, the model can be used to quickly and dynamically adjust the MCS thresholds corresponding to different network scenarios to maximize spatial multiplexing while ensuring the user SLA, thereby not only meeting the QoS requirements of the terminal device, but also ensuring the user's SLA performance.
[0091] See also Figure 5 The embodiment of the present application provides a resource allocation dynamic adjustment device 500, the device includes a memory 501, a processor 502 and a communication interface 503,
[0092] Memory 501, used for storing instructions;
[0093] Processor 502 is used to execute instructions in memory 501 to execute the above application Figure 2 The method for dynamically adjusting resource allocation in the illustrated embodiment;
[0094] The communication interface 503 is used for communication.
[0095] The memory 501, the processor 502 and the communication interface 503 are interconnected via a bus 504; the bus 504 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0096] In a specific embodiment, the processor 502 is used to first obtain user information data in the current network scenario when dynamically adjusting resource allocation, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data, and then preprocess the user experience data to obtain preprocessed user experience data; and preprocess the channel quality data to obtain preprocessed channel quality data, and then input the preprocessed user experience data and the preprocessed channel quality data and spectrum efficiency data into a pre-built MCS threshold determination model to determine the MCS threshold in the current network scenario, and then determine the spatial multiplexing user set based on the MCS threshold and spectrum efficiency data to achieve dynamic adjustment of resource allocation. Please refer to the above for the detailed processing process of the processor 502. Figure 2 The detailed description of S201, S202, S203 and S204 in the illustrated embodiment will not be repeated here.
[0097] The above-mentioned memory 501 can be a random-access memory (RAM), a flash memory (flash), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a register, a hard disk, a mobile hard disk, a CD-ROM or any other form of storage medium known to those skilled in the art.
[0098] The processor 502 may be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
[0099] The communication interface 503 may be, for example, an interface card, etc., and may be an Ethernet interface or an asynchronous transfer mode (ATM) interface.
[0100] An embodiment of the present application also provides a computer-readable storage medium, including instructions, which, when executed on a computer, enables the computer to execute the above-mentioned dynamic adjustment method for resource allocation.
[0101] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.
[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0103] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0105] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0106] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.
[0107] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for dynamically adjusting resource allocation, characterized in that: The method comprises: Acquire user information data in the current network scenario, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data; Preprocessing the user experience data to obtain preprocessed user experience data; preprocessing the channel quality data to obtain preprocessed channel quality data; Inputting the preprocessed user experience data, the preprocessed channel quality data and the spectrum efficiency data into a pre-built MCS threshold determination model to determine the MCS threshold in the current network scenario; According to the MCS threshold and the spectrum efficiency data, a spatial multiplexing user set is determined to achieve dynamic adjustment of resource allocation.
2. The method according to claim 1, characterized in that Preprocessing the user experience data to obtain preprocessed user experience data; Preprocessing the channel quality data to obtain preprocessed channel quality data includes: Normalizing the user experience data according to the user's corresponding QoS requirements to obtain normalized user experience data; The channel quality data is normalized by using a differential transformation method to obtain normalized channel quality data.
3. The method according to claim 1, characterized in that The determining, according to the MCS threshold and the spectrum efficiency data, a set of spatial multiplexing users includes: Select users in descending order according to user priority to join the initial spatial multiplexing user set, and obtain a spatial multiplexing user set that meets preset conditions; Among them, the initial spatial multiplexing user set is an empty set; the preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and the spectrum efficiency value corresponding to the spatial multiplexing user set after adding the i-th user is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before adding the i-th user; i is a positive integer greater than 0.
4. The method according to claim 1, characterized in that: Constructing the MCS threshold determination model includes: Acquire training user information data in different training network scenarios; the training user information data includes training user experience data, training channel quality data and training spectrum efficiency data; Preprocessing the training user experience data to obtain preprocessed training user experience data; preprocessing the training channel quality data to obtain preprocessed training channel quality data; The initial MCS threshold determination model is trained according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data and the MCS threshold labels corresponding to the different training network scenarios to generate the MCS threshold determination model.
5. The method according to claim 4, characterized in that The initial MCS threshold determination model is a neural network model.
6. The method according to any one of claims 4 to 5, characterized in that: The method further comprises: Acquire verification user information data under different verification network scenarios; the verification user information data includes verification user experience data, verification channel quality data and verification spectrum efficiency data; Preprocessing the verified user experience data to obtain preprocessed verified user experience data; preprocessing the verified channel quality data to obtain preprocessed verified channel quality data; Inputting the preprocessed verified user experience data, the preprocessed verified channel quality data, and the verified spectrum efficiency data into the MCS threshold determination model to obtain the MCS threshold corresponding to the verified network scenario; When the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario, the verification user information data is used again as the training user information data to update the MCS threshold determination model.
7. A dynamic adjustment device for resource allocation, characterized in that: The device comprises: A first acquisition unit, configured to acquire user information data in a current network scenario, wherein the user information data includes user experience data, channel quality data, and spectrum efficiency data; A first preprocessing unit is used to preprocess the user experience data to obtain preprocessed user experience data; and to preprocess the channel quality data to obtain preprocessed channel quality data; A first determination unit, configured to input the preprocessed user experience data, the preprocessed channel quality data, and the spectrum efficiency data into a pre-constructed MCS threshold determination model to determine an MCS threshold in a current network scenario; The second determination unit is used to determine the spatial multiplexing user set according to the MCS threshold and the spectrum efficiency data to achieve dynamic adjustment of resource allocation.
8. The device according to claim 7, characterized in that The first preprocessing unit is specifically used for: According to the service quality QoS requirements corresponding to the user, the user experience data is normalized to obtain normalized user experience data; and the channel quality data is normalized using a differential transformation method to obtain normalized channel quality data.
9. The device according to claim 7, characterized in that The first determining unit is specifically configured to: Select users in descending order according to user priority to join the initial spatial multiplexing user set, and obtain a spatial multiplexing user set that meets preset conditions; Among them, the initial spatial multiplexing user set is an empty set; the preset conditions include that the approximate channel quality values of all users in the spatial multiplexing user set are not lower than the protection threshold corresponding to the MCS threshold, and the spectrum efficiency value corresponding to the spatial multiplexing user set after adding the i-th user is not lower than the spectrum efficiency value corresponding to the spatial multiplexing user set before adding the i-th user; i is a positive integer greater than 0.
10. The device according to claim 7, characterized in that The device also includes: A second acquisition unit is used to acquire training user information data in different training network scenarios; the training user information data includes training user experience data, training channel quality data and training spectrum efficiency data; A second preprocessing unit is used to preprocess the training user experience data to obtain preprocessed training user experience data; and preprocess the training channel quality data to obtain preprocessed training channel quality data; A training unit is used to train an initial MCS threshold determination model according to the preprocessed training user experience data, the preprocessed training channel quality data, the training spectrum efficiency data and the MCS threshold labels corresponding to the different training network scenarios to generate the MCS threshold determination model.
11. The device according to claim 10, characterized in that The initial MCS threshold determination model is a neural network model.
12. The device according to any one of claims 10 to 11, characterized in that: The device also includes: A third acquisition unit is used to acquire verification user information data in different verification network scenarios; the verification user information data includes verification user experience data, verification channel quality data and verification spectrum efficiency data; A third preprocessing unit is used to preprocess the verified user experience data to obtain preprocessed verified user experience data; preprocess the verified channel quality data to obtain preprocessed verified channel quality data; An obtaining unit, configured to input the preprocessed verified user experience data, the preprocessed verified channel quality data, and the verified spectrum efficiency data into the MCS threshold determination model to obtain the MCS threshold corresponding to the verified network scenario; An updating unit is used to use the verification user information data as the training user information data to update the MCS threshold determination model when the MCS threshold corresponding to the verification network scenario is inconsistent with the MCS threshold marking result corresponding to the verification network scenario.
13. A dynamic adjustment device for resource allocation, characterized in that: The device includes a memory and a processor; The memory is used to store instructions; The processor is used to execute the instructions in the memory and perform the method according to any one of claims 1 to 6.
14. A computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 6.
