Spectrum management method and system, electronic equipment and storage medium

Abstract

The invention discloses a spectrum management method and system, electronic equipment and a storage medium, and the method comprises the steps: dynamically collecting spectrum state data through a first core, inputting the data into a preset regression model in a second core, and carrying out the prediction to obtain first spectrum allocation data, so as to carry out the spectrum resource allocation; acquiring environment frequency spectrum data, and performing interference suppression processing through a preset filter in the third core according to the environment frequency spectrum data to obtain suppressed frequency spectrum data; performing allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data; constructing a preset priority model according to a preset network state index to determine priority data; and performing allocation adjustment on the second spectrum allocation data according to the priority data to obtain target spectrum allocation data so as to perform spectrum resource adjustment. According to the embodiment of the invention, efficient and reliable spectrum management can be realized, and the spectrum resource utilization rate and the system communication efficiency are improved. The method can be widely applied to the technical field of communication.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a spectrum management method, system, electronic device and storage medium. Background Art

[0002] With the rapid development of smart grids, the demand for distribution network communications is growing. In related technologies, traditional spectrum management methods are difficult to adapt to multi-service and dynamic interference environments, and the spectrum resource utilization rate is low, making it difficult to meet the real-time and high-efficiency requirements in complex network scenarios.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a spectrum management method, system, electronic device and storage medium, which can achieve efficient and reliable spectrum management and effectively improve spectrum resource utilization and system communication efficiency.

[0005] To achieve the above object, an embodiment of the present application provides a spectrum management method, which includes the following steps:

[0006] Dynamically collect spectrum status data through the first core;

[0007] The spectrum state data is input into a preset regression model in the second core to predict first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data; wherein the preset regression model is obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model;

[0008] Acquire environmental spectrum data, and perform interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data;

[0009] Perform allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data;

[0010] Constructing a preset priority model according to a preset network status indicator to determine priority data through the preset priority model;

[0011] The second spectrum allocation data is allocated and adjusted according to the priority data to obtain target spectrum allocation data, so as to adjust spectrum resources through the target spectrum allocation data.

[0012] In some embodiments, after performing the allocation adjustment of the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, so as to adjust spectrum resources through the target spectrum allocation data, the method further includes:

[0013] Obtaining spectrum allocation feedback information;

[0014] Load balancing adjustment is performed through a dynamic load balancing model in the fourth core according to the spectrum allocation feedback information.

[0015] In some embodiments, before executing the step of inputting the spectrum status data into the second core to predict the preset regression model to obtain the first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data, the method further includes:

[0016] The importance of each feature in the preset feature set is evaluated by the gradient boosting decision tree model to obtain preset evaluation data;

[0017] Determining a target feature from the preset feature set according to the preset evaluation data;

[0018] The target features are weighted by a weighted sampling algorithm to obtain weight data;

[0019] The random forest regression model is constructed to perform model training on the random forest regression model through the target feature and the weight data to obtain the preset regression model.

[0020] In some embodiments, the acquiring of environmental spectrum data, and performing interference suppression processing through a preset filter in a third core according to the environmental spectrum data to obtain suppressed spectrum data, includes:

[0021] Dynamically collect the environmental spectrum data; wherein the environmental spectrum data includes channel occupancy, signal strength data and interference characteristic data;

[0022] Performing quality assessment on the environmental spectrum data to obtain a signal quality assessment result;

[0023] Performing fast Fourier transform analysis on the signal quality assessment result to obtain a Fourier transform analysis result;

[0024] Performing frequency band mapping on the Fourier transform analysis result to obtain frequency band mapping data;

[0025] According to the frequency band mapping data, interference suppression is performed through the preset filter to obtain first suppression signal data; wherein the preset filter is obtained by adjusting the filter parameters of the adaptive filter through the least mean square algorithm;

[0026] A target modulation algorithm is determined according to the frequency band mapping data, so as to modulate the first suppression signal data by the target modulation algorithm to obtain the suppression spectrum data.

[0027] In some embodiments, determining a target modulation algorithm according to the frequency band mapping data includes:

[0028] Determine interference frequency band information according to the frequency band mapping data;

[0029] The target modulation algorithm is determined by analyzing the interference frequency band information.

[0030] In some embodiments, the step of constructing a preset priority model according to a preset network status indicator to determine the priority data through the preset priority model includes:

[0031] The preset priority model is constructed by preset network status indicators; wherein the preset network status indicators include channel quality indicators, throughput indicators and delay requirement indicators;

[0032] Dynamically obtain preset priority indicator data to preprocess the preset priority indicator data to generate a network state vector; wherein the preset priority indicator data corresponds to the preset network state indicator;

[0033] The network state vector is input into the preset priority model to calculate and obtain the priority data.

[0034] In some embodiments, the step of adjusting the second spectrum allocation data according to the priority data to obtain target spectrum allocation data includes:

[0035] Determine frequency band allocation information according to the priority data, user throughput data and delay requirement data;

[0036] The second spectrum allocation data is adjusted for resource allocation according to the frequency band allocation information to obtain the target spectrum allocation data.

[0037] To achieve the above object, another aspect of an embodiment of the present application provides a spectrum management system, the system comprising:

[0038] The first module is used to dynamically collect spectrum status data through the first core;

[0039] The second module is used to input the spectrum status data into a preset regression model in the second core to predict and obtain first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data; wherein the preset regression model is obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model;

[0040] The third module is used to obtain environmental spectrum data, and perform interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data;

[0041] A fourth module is used to perform allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data;

[0042] A fifth module is used to construct a preset priority model according to a preset network status indicator to determine the priority data through the preset priority model;

[0043] The sixth module is configured to adjust the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, so as to adjust spectrum resources through the target spectrum allocation data.

[0044] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising:

[0045] at least one processor;

[0046] at least one memory for storing at least one program;

[0047] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0048] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0049] The embodiments of the present application include at least the following beneficial effects: The present application provides a spectrum management method, system, electronic device and storage medium. The scheme dynamically collects spectrum status data through the first core, and inputs the spectrum status data into the preset regression model in the second core to predict the first spectrum allocation data, so as to allocate spectrum resources through the first spectrum allocation data. Among them, the embodiment of the present invention optimizes the random forest regression model through the gradient boosting decision tree model to obtain the preset regression model, so as to improve the model's responsiveness to signal changes. Next, the embodiment of the present invention obtains the environmental spectrum data, and performs interference suppression processing through the preset filter in the third core according to the environmental spectrum data to obtain the suppressed spectrum data, and then optimizes the allocation according to the suppressed spectrum data and the first spectrum allocation data to obtain the second spectrum allocation data. Further, the embodiment of the present invention constructs a preset priority model according to the preset network status indicator, so as to determine the priority data through the preset priority model, and then adjusts the allocation of the second spectrum allocation data according to the priority data to obtain the target spectrum allocation data, so as to adjust the spectrum resources through the target spectrum allocation data, thereby realizing efficient and reliable spectrum allocation and management. It is easy to understand that the embodiment of the present invention can realize efficient management of spectrum resources by means of multiple parallel computing cores. Among them, the embodiment of the present invention performs initial spectrum allocation through a preset regression model obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model in the second core to obtain first spectrum allocation data, and then performs interference suppression processing in the third core to optimize the spectrum allocation scheme, and finally further optimizes the spectrum allocation in combination with the priority data to obtain target spectrum allocation data, thereby effectively improving the spectrum resource utilization and system communication efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flowchart of the steps of the spectrum management method provided by an embodiment of the present invention;

[0051] Figure 2 It is a schematic diagram of a multi-core architecture collaborative scheduling process provided by an embodiment of the present invention;

[0052] Figure 3 is a schematic diagram of a spectrum adaptive optimization process provided by an embodiment of the present invention;

[0053] Figure 4 is a schematic diagram of an interference suppression process provided by an embodiment of the present invention;

[0054] Figure 5 Schematic diagram of a priority control mechanism for a multi-user scenario provided by an embodiment of the present invention;

[0055] Figure 6 is a schematic diagram of the structure of a spectrum management system provided in an embodiment of the present application;

[0056] Figure 7 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.

[0058] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".

[0059] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0061] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0062] 16-Quadrature Amplitude Modulation (16-QAM): is a modulation technique that transmits data by adjusting the amplitude and phase of the signal on the same carrier.

[0063] Gradient Boosting Decision Tree (GBDT): is an ensemble learning method that improves model prediction performance based on the combination of multiple decision trees.

[0064] Least Mean Square (LMS) algorithm: is an adaptive filtering algorithm used to optimize filter parameters in signal processing.

[0065] With the rapid development of smart grids, the demand for distribution network communications is growing. In related technologies, traditional spectrum management methods are difficult to adapt to multi-user, multi-service and dynamic interference environments, resulting in low spectrum resource utilization. In addition, related technologies mostly use fixed allocation or simple dynamic adjustment based on a single-core architecture, which is difficult to meet the real-time and high-efficiency requirements in complex network scenarios. The static configuration mode of spectrum resources cannot fully cope with changes in the wireless communication environment, limiting the improvement of distribution network communication performance.

[0066] In view of this, a spectrum management method, system, electronic device and storage medium are provided in an embodiment of the present application. The scheme dynamically collects spectrum status data through a first core, and performs initial spectrum allocation through a preset regression model obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model in a second core to obtain first spectrum allocation data, and then performs interference suppression processing in a third core to optimize the spectrum allocation scheme, and finally further optimizes the spectrum allocation in combination with priority data to obtain target spectrum allocation data, thereby effectively improving spectrum resource utilization and system communication efficiency.

[0067] The spectrum management method provided in the embodiment of the present application relates to the field of communication technology. The spectrum management method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server, or can be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the spectrum management method, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0069] Figure 1 is an optional flowchart of the spectrum management method provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S110 to S160.

[0070] Step S110: dynamically collecting spectrum status data through the first core.

[0071] Step S120: Input the spectrum status data into the preset regression model in the second core to predict and obtain first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data. The preset regression model is obtained by optimizing and training the random forest regression model through the gradient boosting decision tree model.

[0072] Step S130: Acquire environmental spectrum data, and perform interference suppression processing on the environmental spectrum data through a preset filter in the third core to obtain suppressed spectrum data.

[0073] Step S140: performing allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data.

[0074] Step S150: constructing a preset priority model according to the preset network status indicator to determine the priority data through the preset priority model.

[0075] Step S160: adjusting the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, so as to adjust the spectrum resources through the target spectrum allocation data.

[0076] During the working process of this specific embodiment, the embodiment of the present invention first dynamically collects spectrum status data through the first core, and inputs the spectrum status data into the preset regression model in the second core to predict the first spectrum allocation data, so as to allocate spectrum resources through the first spectrum allocation data. Specifically, the spectrum status data in the embodiment of the present invention refers to the environmental spectrum status, including parameters such as bandwidth occupancy and interference intensity (-90dBm to -50dBm). For example, the embodiment of the present invention monitors the environmental spectrum status in real time at a time interval of 100ms through the first core to obtain spectrum status data. In addition, the preset regression model in the embodiment of the present invention is obtained by optimizing and training the random forest regression (RF) model through the gradient boosting decision tree (GBDT) model. For example, the embodiment of the present invention optimizes the training process of the random forest regression (RF) model by introducing the feature importance evaluation mechanism in the gradient boosting decision tree (GBDT) model to enhance the model's ability to respond to signal changes. Accordingly, the embodiment of the present invention generates a spectrum allocation plan for the user based on the dynamic allocation algorithm through the second core, such as giving priority to key services with a delay requirement of less than 50ms. Among them, an embodiment of the present invention inputs the collected spectrum status data into a preset regression model to predict the frequency band availability and the optimal analysis strategy within a future period of time (such as 500ms), and obtains the first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data. For example, the allocation parameters are dynamically adjusted according to the predicted first spectrum allocation resources, and the frequency band resources required for delay-sensitive tasks are allocated preferentially, thereby improving the spectrum utilization.

[0077] Next, the embodiment of the present invention obtains environmental spectrum data, and performs interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data, and then performs allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data. Specifically, the environmental spectrum data in the embodiment of the present invention refers to the current environmental spectrum information obtained by dynamic monitoring by a high-precision spectrum monitoring module. After allocating spectrum resources through the first matching allocation data, the embodiment of the present invention dynamically monitors the environmental spectrum data, such as collecting environmental spectrum data every 10ms. Then, the embodiment of the present invention performs interference suppression on the environmental spectrum data, and performs filtering processing by inputting the environmental spectrum data into the preset filter in the third core to suppress the corresponding interference signal, retain the target signal, and obtain the suppressed spectrum data. Accordingly, the embodiment of the present invention optimizes the spectrum allocation of the current spectrum allocation data, i.e., the first spectrum allocation data, according to the suppressed spectrum data to obtain the second spectrum allocation data, thereby being able to effectively suppress interference signals and improve anti-interference capability.

[0078] Finally, the embodiment of the present invention constructs a preset priority model according to the preset network status indicator, so as to determine the priority data through the preset priority model, and then adjusts the second spectrum allocation data according to the priority data to obtain the target spectrum data, so as to adjust the spectrum resources through the target spectrum allocation data, thereby realizing efficient and reliable spectrum management. Specifically, the preset network status indicator in the embodiment of the present invention refers to the indicator parameters of the current operation status and performance of the network, such as network bandwidth, throughput, delay, etc. Accordingly, the embodiment of the present invention constructs a preset priority model according to the determined preset network status indicator to divide different user priority levels and obtain priority data. For example, the embodiment of the present invention constructs a preset priority model according to the corresponding network status indicator, and divides the users into several different priority levels according to the network status data collected in real time to obtain priority data. Accordingly, the embodiment of the present invention allocates and adjusts the second spectrum allocation data according to the priority data obtained by the division, so as to dynamically adjust the spectrum allocation based on the priority spectrum control mechanism to obtain the target allocation data, thereby improving the flexibility and balance of resource allocation.

[0079] In some embodiments of the present invention, after performing allocation adjustment on the second spectrum allocation data according to the priority data to obtain the target spectrum allocation data, so as to adjust the spectrum resources through the target spectrum allocation data, the spectrum management method provided by the embodiment of the present invention further includes but is not limited to the following steps:

[0080] Obtain spectrum allocation feedback information.

[0081] Load balancing adjustment is performed through the dynamic load balancing model in the fourth core according to the spectrum allocation feedback information.

[0082] In this specific embodiment, the embodiment of the present invention first obtains spectrum allocation feedback information, and performs load balancing adjustment through the dynamic load balancing model in the fourth core according to the spectrum allocation feedback information. Specifically, since the embodiment of the present invention adopts multiple parallel computing cores to manage spectrum resources, in order to alleviate the resource bottleneck problem, the embodiment of the present invention performs global scheduling through the fourth core to ensure system load balancing. Among them, the spectrum allocation feedback information in the embodiment of the present invention refers to the feedback information obtained after executing the target spectrum allocation data optimized by the third core, such as frequency band reuse information and spectrum utilization. Accordingly, the fourth core in the embodiment of the present invention acts as a global scheduler, and performs task allocation in each core component through a dynamic load balancing algorithm (for example, the frequency range is 1.5GHz to 2.5GHz), thereby achieving load balancing adjustment and alleviating the resource bottleneck problem. For example, if Figure 2As shown, in the collaborative scheduling process, the embodiment of the present invention collects spectrum status data through the first core, allocates frequency bands through the second core, then optimizes the strategy through the third core, and finally coordinates global task scheduling through the fourth core, and feeds back the results to the user terminal.

[0083] In some embodiments of the present invention, before executing the input of spectrum status data into the preset regression model in the second core to predict the first spectrum allocation data so as to allocate spectrum resources through the first spectrum allocation data, the spectrum management method provided by the embodiment of the present invention further includes but is not limited to the following steps:

[0084] The importance of each feature in the preset feature set is evaluated through the gradient boosting decision tree model to obtain the preset evaluation data.

[0085] The target feature is determined from a preset feature set according to preset evaluation data.

[0086] The target features are weighted by a weighted sampling algorithm to obtain weighted data.

[0087] Construct a random forest regression model to train the random forest regression model through target features and weight data to obtain a preset regression model.

[0088] In this specific embodiment, the embodiment of the present invention first evaluates the importance of each feature in the preset feature set through a gradient boosting decision tree model to obtain preset evaluation data. Specifically, the preset feature set in the embodiment of the present invention refers to a spectrum state data feature set, including features such as channel occupancy, noise power and throughput. In order to enable the random forest regression model to pay more attention to key data and rare data during the training process, the embodiment of the present invention inputs each feature data in the preset feature set into the gradient boosting decision tree model for importance evaluation, thereby obtaining corresponding preset evaluation data, that is, importance evaluation data of each feature. Then, the embodiment of the present invention determines the target feature from the preset feature set according to the preset evaluation data. Specifically, the embodiment of the present invention obtains the importance evaluation data of each feature through the gradient boosting decision tree model analysis, selects the feature with a higher importance evaluation value from the preset feature set as the target feature, such as taking the feature with the preset evaluation data greater than the preset threshold as the target feature, thereby optimizing the feature selection of the random forest regression model, and then enhancing the model's ability to respond to signal changes. Then, the embodiment of the present invention assigns weights to the target feature through a weighted sampling algorithm to obtain weight data. Specifically, the embodiment of the present invention uses weighted sampling to assign higher weights to frequency band data with interference intensity lower than a preset threshold (such as -70dBm), thereby further improving the model's ability to learn rare and critical data. At the same time, the embodiment of the present invention constructs a random forest regression model to train the random forest regression model in combination with target features and weight data to obtain a preset regression model. Specifically, after the embodiment of the present invention determines the target features through a gradient boosting decision tree model and uses a weighted sampling algorithm to assign corresponding weight data, the corresponding feature data is extracted from the sample data set according to the target features, and the model is trained in combination with the weight data to obtain a preset regression model. Exemplarily, if Figure 3As shown, the embodiment of the present invention uses a data set containing 10,000 samples during the training process, and the features include channel occupancy, noise power and throughput. Accordingly, the embodiment of the present invention combines the iterative optimization of the gradient boosting decision tree model to train a model of 1,000 decision trees, sets the maximum depth to 20, the minimum number of split samples to 5, and adopts the weighted mean square error optimization target. Accordingly, during the operation of the embodiment of the present invention, the first core collects real-time spectrum data every 200ms and inputs it into the optimized model to predict the frequency band availability and optimal allocation strategy within the next 500ms, and outputs the confidence interval evaluation result. In addition, the second core dynamically adjusts the allocation parameters according to the model prediction results, prioritizes the allocation of frequency band resources required for delay-sensitive tasks, and further improves the utilization efficiency of the spectrum. It is easy to understand that the embodiment of the present invention can effectively improve the allocation efficiency and stability of spectrum resources by optimizing the random forest regression model in combination with the gradient boosting decision tree algorithm, and further performs weight allocation of features through the weighted sampling algorithm, which can effectively improve the model's learning ability for rare and critical data.

[0089] In some embodiments of the present invention, obtaining environmental spectrum data, and performing interference suppression processing through a preset filter in a third core according to the environmental spectrum data to obtain suppressed spectrum data include but are not limited to the following steps:

[0090] Dynamically collect environmental spectrum data, including channel occupancy, signal strength data, and interference characteristic data.

[0091] Perform quality assessment on environmental spectrum data to obtain a signal quality assessment result.

[0092] Perform fast Fourier transform analysis on the signal quality assessment result to obtain a Fourier transform analysis result.

[0093] Perform frequency band mapping on the Fourier transform analysis result to obtain frequency band mapping data.

[0094] According to the frequency band mapping data, interference suppression is performed through a preset filter to obtain first suppression signal data. The preset filter is obtained by adjusting filter parameters of an adaptive filter through a least mean square algorithm.

[0095] A target modulation algorithm is determined according to the frequency band mapping data, so as to modulate the first suppression signal data by the target modulation algorithm to obtain suppression spectrum data.

[0096] In this specific embodiment, the embodiment of the present invention first dynamically collects environmental spectrum data, and performs quality assessment on the environmental spectrum data to obtain a signal quality assessment result. Specifically, the environmental spectrum data in the embodiment of the present invention includes channel occupancy, signal strength data and interference characteristic data. Among them, the channel occupancy in the embodiment of the present invention refers to the proportion of the channel being effectively used within a period of time, that is, the utilization rate of channel resources. In addition, the signal strength data in the embodiment of the present invention refers to the energy or power size of the signal when it is transmitted in the channel. At the same time, the interference characteristic data in the embodiment of the present invention refers to the influence of various interference factors existing in the channel on signal transmission, such as co-channel interference, adjacent channel interference, etc. For example, the embodiment of the present invention collects environmental spectrum data every 10ms, including channel occupancy, signal strength and interference characteristics, the sampling frequency is set to 10kHz, and the coverage frequency band range is 300MHz to 3GHz. Accordingly, the embodiment of the present invention performs signal quality assessment on the collected spectrum data, such as signal-to-noise ratio, interference level, etc., to obtain the corresponding signal quality assessment result. Next, the embodiment of the present invention performs fast Fourier transform analysis on the signal evaluation result to obtain the Fourier transform analysis result, and then performs frequency band mapping on the Fourier transform analysis result to obtain frequency band mapping data. Specifically, the embodiment of the present invention transmits the signal evaluation result to the fast Fourier transform (FFT) analysis module to perform spectrum analysis through the fast Fourier transform algorithm, locate the frequency, bandwidth and power distribution of the interference signal, and obtain the Fourier transform analysis result. Then, the embodiment of the present invention performs frequency band mapping through the Fourier transform analysis result to distinguish the effective frequency band from the interference frequency band, that is, to distinguish the interference signal from the target signal, and identify the effective frequency band and the interference frequency band.

[0097] Further, the embodiment of the present invention performs interference suppression through a preset filter according to the frequency band mapping data to obtain the first suppression signal data. Specifically, the embodiment of the present invention transmits the frequency band mapping result, that is, the frequency band mapping data, to the multi-core processing unit for parallel analysis. Accordingly, the embodiment of the present invention analyzes the spectrum data through multi-core parallel, performs interference management and suppression, and evaluates the signal state. Among them, the embodiment of the present invention dynamically analyzes the spectrum state to adjust the interference suppression strategy according to the change, and then accurately suppresses the interference signal through the adaptive filter, and retains the target signal to obtain the first suppression signal. Correspondingly, the preset filter in the embodiment of the present invention adjusts the filter parameters of the adaptive filter through the least mean square (LMS) algorithm. In the embodiment of the present invention, the interference suppression adopts a spectrum reconstruction method based on adaptive filtering, adjusts the filter parameters through the LMS algorithm, and accurately suppresses the interference signal of the power corresponding interference threshold, such as higher than -50dBm, while retaining the integrity of the target signal. In addition, the embodiment of the present invention determines the target modulation algorithm according to the frequency band mapping data, so as to modulate the first suppression signal data through the target modulation algorithm to obtain the suppressed spectrum data. Specifically, the embodiment of the present invention determines the corresponding target modulation algorithm by performing interference analysis on the frequency band mapping data. Then, the embodiment of the present invention switches the modulation mode to the target modulation algorithm to modulate the first suppression signal data to obtain spectrum data after interference suppression, that is, suppressed spectrum data. It is easy to understand that the embodiment of the present invention switches the signal to a modulation scheme with stronger anti-interference ability by dynamically adjusting the modulation algorithm for a specific interference frequency band, thereby effectively improving the reliability of spectrum management. For example, Figure 4 As shown, Figure 4 A schematic diagram of the interference suppression process provided by an embodiment of the present invention. In addition, after the modulation obtains the suppressed spectrum data, the embodiment of the present invention also performs a signal integrity assessment, and when it is determined that the signal integrity assessment passes, the spectrum information after interference suppression is output. Conversely, the embodiment of the present invention implements an error feedback mechanism to feed back the corresponding suppression effect data to the parallel processing unit to adjust the filtering and modulation strategies.

[0098] In some embodiments of the present invention, determining a target modulation algorithm according to the frequency band mapping data includes but is not limited to the following steps:

[0099] The interference frequency band information is determined according to the frequency band mapping data.

[0100] Analyze the interference frequency band information and determine the target modulation algorithm.

[0101] In this specific embodiment, the embodiment of the present invention first determines the interference frequency band information according to the frequency band mapping data, and then analyzes the interference frequency band information to determine the target modulation algorithm. Specifically, the interference frequency band information in the embodiment of the present invention refers to the frequency band information of the interference signal present in the frequency band mapping data. Accordingly, the embodiment of the present invention matches the corresponding target modulation algorithm according to the frequency band information of the interference signal determined by the analysis. For example, Figure 4 As shown, the embodiment of the present invention analyzes the input frequency band mapping data through a parallel analysis unit to evaluate the corresponding interference information. Then, the embodiment of the present invention determines the target modulation algorithm based on the interference information obtained by the evaluation, and then dynamically switches the corresponding modulation mode. For example, the embodiment of the present invention determines the target modulation algorithm based on the specific interference frequency band in the frequency band mapping data, and then switches the modulation scheme to modulation by the target modulation algorithm, such as switching to a 16QAM modulation scheme, to enhance the anti-interference capability.

[0102] In some embodiments of the present invention, a preset priority model is constructed according to a preset network status indicator to determine priority data through the preset priority model, including but not limited to the following steps:

[0103] The preset priority model is constructed by using preset network status indicators, wherein the preset network status indicators include channel quality indicators, throughput indicators, and delay requirement indicators.

[0104] Dynamically obtain preset priority indicator data to preprocess the preset priority indicator data and generate a network state vector, wherein the preset priority indicator data corresponds to the preset network state indicator.

[0105] The network state vector is input into a preset priority model to calculate the priority data.

[0106] In this specific embodiment, the embodiment of the present invention first constructs a preset priority model by presetting network indicators. Specifically, the preset network status indicators in the embodiment of the present invention include channel quality indicators, throughput indicators and delay demand indicators. Among them, the channel quality indicator in the embodiment of the present invention reflects channel quality information, the throughput indicator reflects user throughput information, and the delay demand indicator reflects the delay demand of the user or service. Accordingly, the embodiment of the present invention constructs a preset priority model by combining network status indicators such as channel quality indicators, throughput indicators and delay demand indicators, and prioritizes users, such as high, medium and low priorities. At the same time, the embodiment of the present invention dynamically obtains preset priority indicator data to preprocess the preset priority indicator data, generate a network state vector, and then input the network state vector into the preset priority model to calculate the priority data. Specifically, the preset priority indicator data in the embodiment of the present invention corresponds to the preset network status indicator. For example, the embodiment of the present invention dynamically obtains channel quality data, such as signal strength, interference, bandwidth and other information, and collects user throughput data, that is, real-time throughput data of each user (reflecting business needs), and simultaneously obtains delay demand data of each user, such as delay tolerance, service level requirements, etc. Accordingly, the embodiment of the present invention summarizes the network status of the acquired preset priority indicator data, and performs preliminary processing on the channel quality data, throughput data, delay requirement data, etc., to generate a corresponding network state vector. Next, the embodiment of the present invention generates the input of the preset priority model according to the network state vector, and inputs it into the preset priority model to calculate the priority data.

[0107] In some embodiments of the present invention, the second spectrum allocation data is allocated and adjusted according to the priority data to obtain the target spectrum allocation data, including but not limited to the following steps:

[0108] Frequency band allocation information is determined based on priority data, user throughput data, and delay requirement data.

[0109] Resource allocation is adjusted for the second spectrum allocation data according to the frequency band allocation information to obtain target spectrum allocation data.

[0110] In this specific embodiment, the embodiment of the present invention first determines the frequency band allocation information according to the priority data, user throughput data and delay requirement data, and then adjusts the resource allocation of the second spectrum allocation data according to the frequency band allocation format to obtain the target spectrum allocation data. Specifically, after calculating the priority data, the embodiment of the present invention adjusts the spectrum allocation strategy through a dynamic scheduling algorithm. Among them, the embodiment of the present invention dynamically adjusts the resource allocation according to the user's priority data, throughput and delay requirements to determine the corresponding frequency band allocation information. For example, high-quality frequency bands are allocated to high-priority users, and suboptimal frequency bands are reserved for low-priority users to optimize frequency band reuse. At the same time, the embodiment of the present invention performs frequency band optimization and reuse on unallocated frequency bands to improve the overall utilization of the spectrum and ensure balance. Then, after determining the corresponding frequency band allocation information, the embodiment of the present invention adjusts the resource allocation of each user in the second spectrum allocation data according to the frequency band allocation information to obtain the target spectrum allocation data. Exemplarily, if Figure 5 As shown, Figure 5 Schematic diagram of the priority control mechanism for multi-user scenarios provided by the embodiment of the present invention. Accordingly, the embodiment of the present invention can be applied to complex demand scenarios of multiple users and multiple services in distribution network communication through a priority-based spectrum control mechanism. For example, in the embodiment of the present invention, the system collects network status data such as channel quality, user throughput and delay requirements in real time, and constructs a priority model to divide users into three priorities: high, medium and low. At the same time, according to the user's business needs and channel conditions, the comprehensive priority index is calculated, and the spectrum resources are allocated using a dynamic scheduling algorithm. Among them, high-priority users are allocated high-quality frequency bands with a channel signal-to-noise ratio higher than 20dB and interference lower than -70dBm, while suboptimal frequency bands are reserved for low-priority users to ensure the balance and flexibility of resource utilization. In addition, the scheduling algorithm in the embodiment of the present invention is updated every 100ms, and the priority weights are set to 0.7 for high priority, 0.2 for medium priority, and 0.1 for low priority, and the resource allocation strategy is dynamically adjusted to alleviate the impact of burst traffic on key services. At the same time, the embodiment of the present invention optimizes the reuse of unallocated frequency bands to improve the overall spectrum utilization efficiency of the system.

[0111] It is easy to understand that the embodiment of the present invention adopts a quad-core processor architecture, in which the first core is responsible for real-time monitoring of spectrum data, the second core generates a spectrum allocation plan based on a dynamic allocation algorithm, the third core optimizes the allocation plan, and the fourth core coordinates task allocation, so as to achieve efficient management of spectrum resources. Accordingly, the embodiment of the present invention optimizes the RF model by introducing the GBDT algorithm, and adopts a weighted sampling strategy to improve the learning ability of rare data. Among them, the first core collects data every 200ms and inputs it into the model, and the second core adjusts the frequency band allocation strategy according to the prediction results. At the same time, the embodiment of the present invention is based on a priority spectrum control mechanism, and through a dynamic scheduling algorithm, the user priority is calculated in real time, so that high-priority users can be allocated high-quality frequency bands, and low-priority users can obtain suboptimal frequency bands, which effectively improves the flexibility and balance of frequency band allocation. In addition, the embodiment of the present invention analyzes the spectrum in real time based on the FFT algorithm, locates the interference signal, and adopts adaptive filtering and LMS algorithm to accurately suppress the interference signal, while adjusting the modulation mode to enhance the anti-interference ability.

[0112] See also Figure 6 The embodiment of the present application further provides a spectrum management system, which can implement the above-mentioned spectrum management method, and the system includes:

[0113] The first module 210 is configured to dynamically collect spectrum status data through a first core.

[0114] The second module 220 is used to input the spectrum status data into the preset regression model in the second core to predict the first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data. The preset regression model is obtained by optimizing and training the random forest regression model through the gradient boosting decision tree model.

[0115] The third module 230 is used to obtain environmental spectrum data, and perform interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data.

[0116] The fourth module 240 is configured to perform allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data.

[0117] The fifth module 250 is used to construct a preset priority model according to the preset network status indicator to determine the priority data through the preset priority model.

[0118] The sixth module 260 is configured to adjust the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, so as to adjust the spectrum resources through the target spectrum allocation data.

[0119] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0120] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above spectrum management method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0121] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0122] See also Figure 7 , Figure 7 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0123] The processor 310 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0124] The memory 320 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 320 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 320, and the processor 310 is called to execute the spectrum management method of the embodiment of the present application;

[0125] Input / output interface 330, used to implement information input and output;

[0126] Communication interface 340, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0127] bus 350 , which transmits information between the various components of the device (e.g., processor 310 , memory 320 , input / output interface 330 , and communication interface 340 );

[0128] The processor 310 , the memory 320 , the input / output interface 330 and the communication interface 340 are connected to each other in communication within the device via the bus 350 .

[0129] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned spectrum management method is implemented.

[0130] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0131] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0132] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0133] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0134] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0136] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0137] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0138] In the several embodiments provided in the present application, it should be understood that the disclosed 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 above 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0139] The units described above 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.

[0140] 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.

[0141] 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, 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 multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: 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), disk or optical disk and other media that can store programs.

[0142] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A spectrum management method, characterized in that: The method comprises the following steps: Dynamically collect spectrum status data through the first core; The spectrum state data is input into a preset regression model in the second core to predict first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data; wherein the preset regression model is obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model; Acquire environmental spectrum data, and perform interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data; Perform allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data; Constructing a preset priority model according to a preset network status indicator to determine priority data through the preset priority model; The second spectrum allocation data is allocated and adjusted according to the priority data to obtain target spectrum allocation data, so as to adjust spectrum resources through the target spectrum allocation data.

2. The method according to claim 1, characterized in that After performing the step of adjusting the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, and adjusting spectrum resources by using the target spectrum allocation data, the method further includes: Obtaining spectrum allocation feedback information; Load balancing adjustment is performed through a dynamic load balancing model in the fourth core according to the spectrum allocation feedback information.

3. The method according to claim 1, characterized in that Before executing the step of inputting the spectrum status data into the preset regression model in the second core to predict and obtain first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data, the method further includes: The importance of each feature in the preset feature set is evaluated by the gradient boosting decision tree model to obtain preset evaluation data; Determining a target feature from the preset feature set according to the preset evaluation data; The target features are weighted by a weighted sampling algorithm to obtain weight data; The random forest regression model is constructed to perform model training on the random forest regression model through the target feature and the weight data to obtain the preset regression model.

4. The method according to claim 2, characterized in that: The acquiring of environmental spectrum data, and performing interference suppression processing through a preset filter in a third core according to the environmental spectrum data to obtain suppressed spectrum data, includes: Dynamically collect the environmental spectrum data; wherein the environmental spectrum data includes channel occupancy, signal strength data and interference characteristic data; Performing quality assessment on the environmental spectrum data to obtain a signal quality assessment result; Performing fast Fourier transform analysis on the signal quality assessment result to obtain a Fourier transform analysis result; Performing frequency band mapping on the Fourier transform analysis result to obtain frequency band mapping data; According to the frequency band mapping data, interference suppression is performed through the preset filter to obtain first suppression signal data; wherein the preset filter is obtained by adjusting the filter parameters of the adaptive filter through the least mean square algorithm; A target modulation algorithm is determined according to the frequency band mapping data, so as to modulate the first suppression signal data by the target modulation algorithm to obtain the suppression spectrum data.

5. The method according to claim 4, characterized in that The determining a target modulation algorithm according to the frequency band mapping data comprises: Determine interference frequency band information according to the frequency band mapping data; The target modulation algorithm is determined by analyzing the interference frequency band information.

6. The method according to claim 1, characterized in that The step of constructing a preset priority model according to a preset network status indicator to determine the priority data through the preset priority model includes: The preset priority model is constructed by preset network status indicators; wherein the preset network status indicators include channel quality indicators, throughput indicators and delay requirement indicators; Dynamically obtain preset priority indicator data to preprocess the preset priority indicator data to generate a network state vector; wherein the preset priority indicator data corresponds to the preset network state indicator; The network state vector is input into the preset priority model to calculate and obtain the priority data.

7. The method according to claim 6, characterized in that The step of adjusting the second spectrum allocation data according to the priority data to obtain target spectrum allocation data includes: Determine frequency band allocation information according to the priority data, user throughput data and delay requirement data; The second spectrum allocation data is adjusted for resource allocation according to the frequency band allocation information to obtain the target spectrum allocation data.

8. A spectrum management system, characterized in that: The system comprises: The first module is used to dynamically collect spectrum status data through the first core; The second module is used to input the spectrum status data into a preset regression model in the second core to predict first spectrum allocation data, so as to allocate spectrum resources according to the first spectrum allocation data; wherein the preset regression model is obtained by optimizing and training a random forest regression model through a gradient boosting decision tree model; The third module is used to obtain environmental spectrum data, and perform interference suppression processing through a preset filter in the third core according to the environmental spectrum data to obtain suppressed spectrum data; A fourth module is used to perform allocation optimization according to the suppressed spectrum data and the first spectrum allocation data to obtain second spectrum allocation data; A fifth module is used to construct a preset priority model according to a preset network status indicator to determine the priority data through the preset priority model; The sixth module is configured to adjust the second spectrum allocation data according to the priority data to obtain target spectrum allocation data, so as to adjust spectrum resources through the target spectrum allocation data.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images