A method, apparatus, medium, and equipment for FTTR-B network slicing

Abstract

This application belongs to the field of communication network technology, specifically disclosing a method, apparatus, medium, and device for FTTR-B network slicing. The method includes: acquiring network data of an FTTR-B network; preprocessing the acquired FTTR-B network data; and inputting the preprocessed FTTR-B network data into a pre-trained FTTR-B network slicing model to achieve dynamic slice management and optimization of the FTTR-B network. This application enables high-precision, low-latency, and flexible slice management of FTTR-B networks.

Description

Technical Field

[0001] This application belongs to the field of communication network technology, specifically relating to an FTTR-B network slicing method, apparatus, medium, and equipment. Background Technology

[0002] Traditional network slicing technologies rely on static configuration or fixed resource allocation, making it difficult to adapt to the dynamically changing service requirements in FTTR-B scenarios (such as VR, IoT, and security monitoring). Existing solutions have shortcomings in resource utilization, latency control, and service QoS guarantees, especially lacking fine-grained slice management capabilities in complex home / enterprise environments. Specifically, when handling diverse service requirements such as high bandwidth, low latency, and large-scale connections, existing technologies often fail to achieve flexible resource allocation and dynamic adjustment, resulting in low network resource utilization and difficulty in guaranteeing service quality. Furthermore, existing solutions have many deficiencies in slice priority allocation, physical layer resource allocation, data link layer slice management, network layer slice orchestration, security and reliability assurance, and slice lifecycle management, failing to meet the efficient, flexible, and reliable slice management requirements of FTTR-B networks. Summary of the Invention

[0003] To address the shortcomings of existing technologies, the purpose of this application is to provide an FTTR-B network slicing method, apparatus, medium, and device. This application aims to provide high-precision, low-latency, and flexible slice management for FTTR-B networks.

[0004] To achieve the above objectives, this application provides the following technical solution:

[0005] An FTTR-B network slicing method is provided, the method comprising: acquiring network data of an FTTR-B network; preprocessing the acquired network data of the FTTR-B network; and inputting the preprocessed network data of the FTTR-B network into a pre-trained FTTR-B network slicing model to achieve dynamic slicing management and optimization of the FTTR-B network.

[0006] Optionally, the preprocessing of the acquired FTTR-B network data includes: cleaning the network data; converting the cleaned network data; detecting anomalies in the converted network data; and integrating and synchronizing the network data after anomaly detection.

[0007] Optionally, the FTTR-B network slicing model includes: a data input layer, a classification module, a resource allocation and optimization module, an orchestration and edge computing module, a slice prediction module, and a slice monitoring and self-healing module. The data input layer is used to input preprocessed FTTR-B network data and output a unified standardized tensor. The classification module is used to classify the preprocessed FTTR-B network data by type, service level, and priority based on the unified standardized tensor. The resource allocation and optimization module is used to generate the optimal bandwidth resource allocation scheme based on the classification results output by the classification module and the current network state. The orchestration and edge computing module is used to map the bandwidth resource allocation scheme to edge nodes. The slice prediction module is used to predict the changing trends of network resources and key performance indicators of the FTTR-B network based on the bandwidth resource allocation scheme mapped to edge nodes. The slice monitoring and self-healing module is used to monitor the slice operating status, detect anomalies, and execute self-healing strategies.

[0008] Optionally, the data input layer adopts a multimodal feature fusion structure.

[0009] Optionally, the classification module includes: an input layer, an encoding layer, an adaptive attention layer, a shared feature layer, and a multi-head decoder. The input layer is used to input a unified, standardized tensor output by the data input layer; the encoding layer is used to perform nonlinear mapping and dimensionality compression on the unified, standardized tensor for feature extraction; the adaptive attention layer is used to mine the correlations between features extracted by the encoding layer through a multi-head attention mechanism; the shared feature layer is used to integrate the outputs of the multi-head attention to form an abstract feature representation suitable for multiple classification tasks; and the multi-head decoder is used to output corresponding prediction results for the abstract feature representations of different classification tasks.

[0010] Optionally, the resource allocation and optimization module includes: a convolutional encoder, an LSTM temporal modeling layer, and an Actor-Critic policy output layer, wherein the convolutional encoder is used to extract spatial correlation features from the prediction results output by the classification module; the LSTM temporal modeling layer is used to process the sequence information in the spatial correlation features output by the convolutional encoder; and the Actor-Critic policy output layer is used to generate resource allocation actions based on the output of the LSTM temporal modeling layer and evaluate their long-term benefits.

[0011] This application also provides an FTTR-B network slicing device, the device comprising: an acquisition module for acquiring network data of an FTTR-B network; a preprocessing module for preprocessing the acquired network data of the FTTR-B network; and a slice management module for inputting the preprocessed network data of the FTTR-B network into a pre-trained FTTR-B network slicing model to achieve dynamic slice management and optimization of the FTTR-B network.

[0012] Optionally, the preprocessing module includes: a cleaning submodule for cleaning network data; a conversion submodule for converting the cleaned network data; an anomaly detection submodule for detecting anomalies in the converted network data; and an integration and synchronization submodule for integrating and synchronizing the network data after anomaly detection.

[0013] This application also provides a storage medium including instructions that, when executed on a computer, cause the computer to perform the method as described in the preceding claim.

[0014] This application also provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method as described in any of the preceding claims.

[0015] Compared with the prior art, the beneficial effects of this application are as follows:

[0016] This application constructs an intelligent network slicing system based on FTTR-B (Fiber to the Room Enhanced Networking), enabling a closed-loop management mechanism for unified preprocessing, efficient classification, intelligent resource allocation, edge task orchestration, performance trend prediction, and real-time self-healing control of multi-source heterogeneous network data. Compared to traditional static slicing methods, this application possesses high precision, low latency, and adaptive optimization capabilities, effectively improving network resource utilization, quality of service assurance capabilities, and service scheduling flexibility. It is particularly suitable for meeting the diverse, highly reliable, and dynamically changing communication needs of enterprise environments. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an FTTR-B network slicing method according to an embodiment of this application;

[0018] Figure 2 This is a schematic diagram of the structure of an FTTR-B network slicing model provided in another embodiment of this application;

[0019] Figure 3 This is a schematic diagram of the structure of an FTTR-B network slicing device provided in another embodiment of this application;

[0020] Figure 4 This is a schematic diagram of the structure of a storage medium provided in one embodiment of this application;

[0021] Figure 5 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0022] Specific embodiments of this application will now be described in detail with reference to the accompanying drawings. While specific embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0023] It should be noted that certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that different terms may be used to refer to the same component. This specification and claims do not distinguish components based on differences in terminology, but rather on differences in function. The terms "comprising" or "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising but not limited to." The following descriptions in the specification are preferred embodiments for carrying out this application; however, these descriptions are for the purpose of understanding the general principles of the specification and are not intended to limit the scope of this application. The scope of protection of this application shall be determined by the appended claims.

[0024] To facilitate understanding of the embodiments of this application, the following will provide further explanation and description with reference to the accompanying drawings and specific embodiments, and the accompanying drawings do not constitute a limitation on the embodiments of this application.

[0025] Figure 1 This is a flowchart illustrating an exemplary embodiment of a network slicing method based on FTTR-B provided in this application, as shown below. Figure 1 As shown, the method includes the following steps:

[0026] S100: Acquire network data from the FTTR-B network. This network data includes, for example, service requirement data, network resource data, dynamic environment data, policy and security data, and cross-domain collaboration data. Service requirement data includes service type (eMBB / URLLC / mMTC), SLA metrics (bandwidth, latency, jitter, reliability requirements), and priority labels (e.g., 5QI level, billing priority). Network resource data includes physical layer data (fiber link loss, available wavelengths, optical power margin), wireless data (base station load rate, spectrum utilization, MIMO configuration), core network data (NFV resource pool status (vCPU / memory / storage), SDN flow table capacity), and edge-side data (MEC computing resources, cache status, transmission latency). Dynamic environment data includes channel quality, terminal mobility, and traffic characteristics. Policy and security data includes slice templates, QoS mapping tables, and security policies. Cross-domain collaboration data includes transport network status, cloud resource scheduling policies, and billing rules.

[0027] S200: Preprocess the network data of the acquired FTTR-B network;

[0028] S300: Input the preprocessed network data of the FTTR-B network into the pre-trained FTTR-B network slicing model to achieve dynamic slicing management and optimization of the FTTR-B network.

[0029] In another exemplary embodiment, step S200, the preprocessing of the acquired FTTR-B network data, includes the following steps:

[0030] S201: Perform data cleaning on network data;

[0031] This step begins by checking for duplicate records in each network dataset to ensure the uniqueness of each data entry. Next, missing data needs to be addressed, typically in two ways: imputation to fill in missing values ​​or deletion of records with a large number of missing values. Then, outliers and erroneous data need to be identified and corrected using statistical methods (such as box plot analysis). Finally, to facilitate further analysis, the data needs to be formatted uniformly; for example, date formats should be standardized, or numerical units should be unified to a single standard unit.

[0032] The above processing provides clean and high-quality data for subsequent model analysis, avoiding analysis errors or biases caused by dirty data.

[0033] S202: Perform data conversion on the cleaned network data;

[0034] In this step, the purpose of data transformation is to convert the cleaned data into a format suitable for analysis and modeling. First, feature extraction is performed on the cleaned data. For example, features such as year, month, day, or hour are extracted from timestamps, or information such as proportions or differences are extracted from numerical data. Next, for categorical data (such as gender, region, etc.), it needs to be converted into numerical form through encoding. For example, one-hot encoding can be used to convert categorical variables into binary vectors, or label encoding can be used to assign an integer value to each category. Through data transformation, the data can be presented in a form more suitable for analysis, thereby improving the efficiency and accuracy of subsequent analysis.

[0035] S203: Perform anomaly detection on the network data after data conversion;

[0036] In this step, the purpose of anomaly detection is to identify erroneous data, fraudulent activities, or other abnormal behavior. Statistical methods (such as standard deviation) can be used to identify outlier data points that deviate from the mean, or visualization tools such as box plots can be used to view the data distribution and mark potential outliers. Anomaly detection helps improve the robustness of the model, ensuring that the model is not affected by anomalous data.

[0037] S204: Integrate and synchronize network data after anomaly detection.

[0038] In this step, data integration and synchronization are used to consolidate different types of data and ensure their consistency. During the data integration phase, the first step is to ensure time, format, and semantic alignment across all data types. For example, when processing data from multiple time zones, a unified time format is needed; for numerical data in different units, standardization is required. Secondly, conflicts between network data must be resolved. If different types of data are inconsistent on the same variable (e.g., different measurement standards or different encoding methods), appropriate data needs to be selected through prioritization or rules. Data synchronization ensures that data across different types remains consistent and is updated promptly.

[0039] Data integration and synchronization can combine different types of data into a unified dataset, ensuring data consistency, integrity, and timeliness, thereby providing strong data support for subsequent model analysis.

[0040] In another exemplary embodiment, in step S200, as Figure 2 As shown, the FTTR-B network slicing model includes: a data input layer, a classification module, a resource allocation and optimization module, an orchestration and edge computing module, a slice prediction module, and a slice monitoring and self-healing module. Specifically, the data input layer takes preprocessed FTTR-B network data as input and outputs a unified standardized tensor; the classification module classifies the preprocessed FTTR-B network data by type, service level, and priority based on the unified standardized tensor; the resource allocation and optimization module generates the optimal bandwidth resource allocation scheme based on the classification results output by the classification module and the current network state; the orchestration and edge computing module maps the bandwidth resource allocation scheme to edge nodes; the slice prediction module predicts the changing trends of network resources and key performance indicators of the FTTR-B network based on the bandwidth resource allocation scheme mapped to edge nodes; and the slice monitoring and self-healing module monitors the slice operation status, detects anomalies, and executes self-healing strategies.

[0041] The following section provides a detailed description of the structure of each module and the data processing procedure described above.

[0042] The data input layer is designed as a multimodal feature fusion structure. This structure constructs corresponding feature embedding layers for each of the preprocessed FTTR-B network data. Then, fully connected layers are placed after each feature embedding layer to perform non-linear mapping and dimensional alignment on the output of each feature embedding layer, achieving feature dimension unification. Next, a Dropout regularization mechanism is implemented after each fully connected layer to prevent overfitting, while the ReLU activation function is used to enhance the model's expressive power. Finally, the features output from each channel are concatenated into a unified standardized tensor through a concatenation layer, which serves as the input to subsequent modules.

[0043] The classification module comprises an input layer, an encoding layer, an adaptive attention layer, a shared feature layer, and a multi-head decoder. The input layer takes a uniform, standardized tensor from the data input layer as input. The encoding layer consists of two fully connected layers. The first fully connected layer maps the standardized tensor to a 128-dimensional feature dimension and uses the ReLU activation function to enhance non-linear expressiveness, then employs Dropout to prevent overfitting. The second fully connected layer further compresses the 128-dimensional standardized tensor to 64 dimensions to form a stable intermediate representation. The adaptive attention layer uses a multi-head attention mechanism to model the autocorrelation of the feature dimensions encoded by the encoding layer. By calculating the importance weights of features in different dimensions, it adaptively strengthens the feature information most relevant to the current classification task and further mines the correlations between features to obtain context-aware feature representations. Finally, the enhanced features output from the adaptive attention layer are uniformly mapped to the shared feature layer to capture a general abstract feature representation applicable to multiple classification tasks. Finally, the multi-head decoder deploys multiple parallel fully connected classification subnetworks, each of which outputs prediction results for a specific classification task: including a service type decoding head (using Softmax for mutually exclusive category classification), a service level decoding head (predicting different SLA levels), and a priority label decoding head (supporting multi-label output and can be activated using Sigmoid).

[0044] Specifically, the service type decoding header is represented as follows:

[0045]

[0046] in, This represents the second-layer weight matrix of the service type decoding header; This represents the first-layer weight matrix of the service type decoding header; This represents the first-layer bias vector of the service type decoding header; This represents the first-layer bias vector of the service type decoding header; This represents the output vector of the shared feature layer.

[0047] Service Level Decoder header is represented as:

[0048]

[0049] in, This indicates the output of the service level decoding header; This represents the second-layer weight matrix of the service level decoder; This represents the first-layer weight matrix of the service level decoder; This represents the first-layer bias vector of the service level decoding header; This represents the second-layer bias vector of the service level decoding header; This represents the output vector of the shared feature layer.

[0050] The priority tag decoding header is represented as follows:

[0051] in, This indicates the output of the priority tag decoding header; This represents the second-layer weight matrix of the priority tag decoding header; This represents the first-layer weight matrix of the priority tag decoding header; This represents the first-layer bias vector of the priority tag decoding header; This represents the second-layer bias vector of the priority tag decoding header; This represents the output vector of the shared feature layer.

[0052] The resource allocation and optimization module includes a convolutional encoder, an LSTM temporal modeling layer, and an Actor-Critic policy output layer. The convolutional encoder extracts spatial relevance features from the prediction results output by the classification module to enhance the local perception capability of the feature representation. The convolutional encoder includes two two-dimensional convolutional layers with ReLU activation functions to extract spatial relevance features from the prediction results output by the classification module. The LSTM temporal modeling layer processes the sequence information in the spatial relevance features output by the convolutional encoder, mining the dynamic dependency between resource changes and slice requests to enhance the model's memory of historical decisions and trend perception capability. The Actor-Critic policy output layer generates resource allocation actions based on the output of the LSTM temporal modeling layer and evaluates their long-term returns. The Actor-Critic policy output layer includes an Actor network and a Critic network. The Actor network generates the resource allocation action for the current moment (e.g., bandwidth allocation ratio, computational resource mapping, etc.) based on the output of the LSTM temporal modeling layer, while the Critic network predicts the long-term reward value of the current state. Specifically, the Actor-Critic policy output layer takes the output of the LSTM temporal modeling layer as input to further perform intelligent decision optimization. Specifically, spatial correlation features extracted by the convolutional encoder are input to the LSTM temporal modeling layer to capture their dynamic evolution over time. The hidden state vector output by the LSTM temporal modeling layer, as a high-dimensional representation of the current system state, is input to the Actor-Critic policy output layer. The Actor network generates specific resource scheduling actions based on this state, such as dynamically allocating a certain type of URLLC service to a less loaded MEC node. Simultaneously, the Critic network estimates the long-term value of the current state to guide policy optimization and updates. In this way, the model can adaptively adjust resource allocation strategies in a dynamic network environment, thereby effectively improving overall SLA satisfaction, resource utilization efficiency, and scheduling response capabilities.

[0053] The orchestration and edge computing module transforms the scheduling decisions output by the resource allocation and optimization module into executable deployment schemes, and performs efficient orchestration and mapping of tasks on edge nodes. This module first receives a resource scheduling action vector from the Actor network, which contains allocation suggestions for multiple dimensions such as computing resources, bandwidth resources, task type, and priority. Then, the received action vector, along with environmental context information such as the current network topology, edge node resource load, and link latency, is input into a graph neural network (GNN) to construct a task-node matching association graph. Based on this, the module uses task priority ranking, resource adaptability scoring, and multi-objective optimization algorithms (such as heuristic search or reinforcement learning-based strategies) for decision reasoning to determine which edge node each task should be scheduled to, what resources it should occupy, and the corresponding startup timing and lifecycle management parameters. Finally, the module outputs a task scheduling table, an edge node resource allocation list, and corresponding service chain configuration instructions, and feeds the results back to the edge computing platform controller to complete task deployment and runtime status monitoring.

[0054] In summary, by introducing a flexible graph modeling and adaptive strategy selection mechanism, this module can achieve dynamic adaptation of resources and tasks, ensuring that tasks achieve optimal orchestration in a multi-node, multi-constraint environment, while taking into account quality of service (QoS), computational efficiency, and system stability.

[0055] The slice prediction module is used to predict the resource requirements, lifecycle status, and key performance indicators (KPIs) trends of future network slices. The slice prediction module includes an input representation layer, a task context encoding layer, a temporal modeling layer, a context fusion layer, and a multi-head prediction layer. First, the input representation layer receives multi-source data output from the orchestration and edge computing module, including, for example, the deployment status of tasks on each edge node, historical resource usage records (such as CPU, memory, and bandwidth utilization), service chain topology, task scheduling timestamps, and QoS indicators (such as latency, packet loss rate, and throughput) during operation. This layer embeds and encodes category information (such as task type and service level), normalizes numerical information, and constructs a unified time-series feature tensor to provide standardized input for subsequent modeling. Next, the task context encoding layer further vectorizes the static attribute information of tasks (such as priority, SLA requirements, and service type) to construct a task semantic context vector, capturing the differences in resource sensitivity and service quality among different tasks, providing prior knowledge for task prediction. Subsequently, the temporal modeling layer processes the aforementioned time-series features using LSTM or Transformer networks, learning the dynamic dependencies of resource states over time and capturing potential periodic fluctuations, sudden behaviors, and their impact on subsequent system states. Next, the context fusion layer fuses the task semantic vector with the temporal representation of each time step, employing concatenation or attention mechanisms to enhance the prediction model's perception of task characteristics, enabling targeted modeling of resource change patterns under different task types. Finally, the multi-head prediction layer performs parallel output predictions on the fused representations. Each output head corresponds to a target variable, such as CPU utilization, memory usage, latency trends, SLA default risk, or slice overload probability for several future time steps. Quantifiable prediction results are output through regression or classification, providing a basis for subsequent resource reservation, slice re-arrangement, or elastic scaling strategies.

[0056] The slice monitoring and self-healing module is used to continuously perceive the operational status of network slices, detect anomalies, and recover from faults. This module specifically includes a state aggregation layer, a prediction consistency analysis layer, an anomaly detection layer, a self-healing strategy decision layer, and an execution and feedback layer. First, the state aggregation layer receives real-time system operational metrics (such as edge node resource utilization, link load, service chain topology, etc.) and future resource and KPI trends output by the slice prediction module. It aligns and merges these two types of information to construct a unified time-series state representation, which serves as input for subsequent layers. Next, the prediction consistency analysis layer compares the error between predicted values ​​and actual observations within a sliding time window, calculates multidimensional deviation indicators (such as MAE or RMSE), and determines whether the system's current behavior deviates from the predicted trend, thereby identifying model failure or potential operational drift. Subsequently, the anomaly detection layer further performs in-depth analysis of the state sequence, using statistical rules or deep anomaly detection methods (such as LSTM autoencoders, Isolation Forest, etc.) to identify potential resource bottlenecks, QoS degradation, or SLA violations, and assigns an anomaly label or risk score to each slice. For detected anomalies, the self-healing strategy decision layer generates the most appropriate self-healing action based on the system state and anomaly type, combined with the built-in rule engine and strategy learning model. This action could include edge node migration, service instance restart, elastic scaling, or schedule reconfiguration. Finally, the execution and feedback layer distributes the selected self-healing action to the edge controller or resource orchestrator, records the strategy execution results and service recovery effects, and feeds this information back to the strategy model for continuous optimization. This enables the system to possess rapid response, intelligent adaptation, and self-healing capabilities through learning and evolution.

[0057] Below, this application will provide an exemplary description of the scheme described in this application with specific data. Table 1 shows the network data of the FTTR-B network obtained in this application:

[0058] Table 1

[0059]

[0060] Inputting the data shown in Table 1 into the FTTR-B slicing model will finally output the results shown in Table 2:

[0061] Table 2

[0062]

[0063] Based on the slicing results shown in Table 2, this application successfully identifies high-priority URLLC service requirements and assigns them high service levels and priority labels through the classification module. Subsequently, the resource allocation module dynamically matches reasonable computing and bandwidth resources based on reinforcement learning strategies, ensuring the achievement of low latency and high reliability goals. The orchestration module further uses graph neural networks to accurately deploy tasks to the optimal MEC nodes, achieving efficient service chain mapping and lifecycle control. The slice prediction module predicts KPI change trends in advance, providing decision support for resource reservation and elastic scaling. The monitoring and self-healing module continuously ensures the stability and robustness of system operation. Overall, this application fully demonstrates the closed-loop control capability of "perception-decision-execution-feedback," which can significantly improve the intelligence, flexibility, and quality of service assurance capabilities of FTTR-B network slicing.

[0064] In another exemplary embodiment, such as Figure 3 As shown, this application also provides an FTTR-B network slicing device, the device comprising: an acquisition module 100 for acquiring network data of an FTTR-B network; a preprocessing module 200 for preprocessing the acquired network data of the FTTR-B network; and a slice management module 300 for inputting the preprocessed network data of the FTTR-B network into a pre-trained FTTR-B network slicing model to achieve dynamic slice management and optimization of the FTTR-B network.

[0065] Based on the above embodiments, refer to Figure 4 The computer-readable storage medium of exemplary embodiments of this application will be described below. Please refer to [link / reference]. Figure 4 The computer-readable storage medium shown is an optical disc 40, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it implements the steps described in the above method embodiments, such as acquiring network data of the FTTR-B network; preprocessing the acquired network data of the FTTR-B network; and inputting the preprocessed network data of the FTTR-B network into a pre-trained FTTR-B network slicing model to achieve dynamic slicing management and optimization of the FTTR-B network. The specific implementation methods of each step will not be repeated here.

[0066] It should be noted that the computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be described in detail here.

[0067] Based on the above embodiments, this application also provides an electronic device, which is described below with reference to... Figure 5 An electronic device for file downloading according to an exemplary embodiment of this application will be described.

[0068] Figure 5 A block diagram is shown of an exemplary electronic device 50 suitable for implementing embodiments of the present application. The electronic device 50 may be a computer system or a cloud server. Figure 5 The electronic device 50 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0069] like Figure 5 As shown, the electronic device 50 includes, but is not limited to: one or more processors or processing units 501, system memory 502, and bus 503 connecting different system components (including system memory 502 and processing unit 501).

[0070] Electronic device 50 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 50, including volatile and non-volatile media, removable and non-removable media.

[0071] System memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 5021 and / or cache memory 5022. Electronic device 50 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 5023 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 5 (Not shown in the image, usually referred to as "hard drive"). Although not shown in... Figure 5 The diagram illustrates that a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) can be provided. In these cases, each drive can be connected to bus 503 via one or more data media interfaces. System memory 502 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0072] A program / utility 5025 having a set (at least one) of program modules 5024 may be stored, for example, in system memory 502, and such program modules 5024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment. Program modules 5024 typically perform the functions and / or methods described in the embodiments of this application.

[0073] Electronic device 50 can also communicate with one or more external devices 504 (such as a keyboard, pointing device, display, etc.). This communication can be performed through input / output (I / O) interface 505. Furthermore, electronic device 50 can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapter 506. Figure 5 As shown, network adapter 506 communicates with other modules of electronic device 50 (such as processing unit 501) via bus 503. It should be understood that, although... Figure 5 As not shown, it can be used in conjunction with electronic device 50 with other hardware and / or software modules.

[0074] The processing unit 501 executes various functional applications and data processing by running programs stored in the system memory 502. For example, it acquires network data from the FTTR-B network; preprocesses the acquired FTTR-B network data; and inputs the preprocessed FTTR-B network data into a pre-trained FTTR-B network slicing model to achieve dynamic slicing management and optimization of the FTTR-B network. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the file concurrent download device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0075] In the description of this application, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0076] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0078] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0079] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0080] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions that enable a computer device (which may be a personal computer, a cloud server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0081] The above embodiments are only for illustrating the technical concept and features of this application, and are intended to enable those skilled in the art to understand the content of this application and implement it accordingly. They should not be construed as limiting the scope of protection of this application. All equivalent changes or modifications made in accordance with the spirit and essence of this application should be included within the scope of protection of this application.

Claims

1. An FTTR-B network slicing method, characterized in that, The method includes: Obtain network data from the FTTR-B network; The acquired FTTR-B network data is preprocessed; The preprocessed network data of the FTTR-B network is input into the pre-trained FTTR-B network slicing model to achieve dynamic slicing management and optimization of the FTTR-B network. The FTTR-B network slicing model includes a data input layer, a classification module, a resource allocation and optimization module, an orchestration and edge computing module, a slice prediction module, and a slice monitoring and self-healing module. The data input layer is used to input the preprocessed network data of the FTTR-B network and output a uniform normalized tensor. The classification module is used to classify the network data of the preprocessed FTTR-B network according to type, service level, and priority based on a unified standardized tensor. The resource allocation and optimization module is used to generate the optimal bandwidth resource allocation scheme based on the classification results output by the classification module and the current network status. The orchestration and edge computing module is used to map bandwidth resource allocation schemes to edge nodes; The slice prediction module is used to predict the changing trends of network resources and key performance indicators of the FTTR-B network based on the bandwidth resource allocation scheme mapped to edge nodes; The slice monitoring and self-healing module is used to monitor the slice's running status, detect anomalies, and execute self-healing strategies. The slice monitoring and self-healing module includes a state aggregation layer, a prediction consistency analysis layer, an anomaly detection layer, a self-healing strategy decision layer, and an execution and feedback layer. For detected anomalies, the self-healing strategy decision layer generates the most suitable self-healing action based on the system status and anomaly type, combined with the built-in rule engine and strategy learning model.

2. The method according to claim 1, characterized in that, The preprocessing of the acquired FTTR-B network data includes: Perform data cleaning on network data; Perform data transformation on the cleaned network data; Perform anomaly detection on the converted network data; Integrate and synchronize network data after anomaly detection.

3. The method according to claim 1, characterized in that, The data input layer adopts a multimodal feature fusion structure.

4. The method according to claim 1, characterized in that, The classification module includes: The input layer, encoding layer, adaptive attention layer, shared feature layer, and multi-head decoder are as follows: The input layer is used to input the uniform, standardized tensor output by the data input layer; The coding layer is used to perform nonlinear mapping and dimensionality compression on the uniform, standardized tensor for feature extraction; Adaptive attention layers are used to mine the correlations between features extracted by the encoding layer through a multi-head attention mechanism; The shared feature layer is used to integrate the output of multi-head attention to form an abstract feature representation applicable to multiple classification tasks; Multi-head decoders are used to output corresponding prediction results based on the abstract feature representations for different classification tasks.

5. The method according to claim 1, characterized in that, The resource allocation and optimization module includes: The system consists of a convolutional encoder, an LSTM temporal modeling layer, and an Actor-Critic policy output layer. The convolutional encoder is used to extract spatial correlation features from the prediction results output by the classification module; The LSTM temporal modeling layer is used to process the sequence information in the spatial correlation features output by the convolutional encoder; The Actor-Critic strategy output layer is used to generate resource allocation actions based on the output of the LSTM-based temporal modeling layer and to evaluate their long-term benefits.

6. An FTTR-B network slicing device, characterized in that, The device includes: The acquisition module is used to acquire network data from the FTTR-B network. The preprocessing module is used to preprocess the network data of the acquired FTTR-B network; The slice management module is used to input the preprocessed network data of the FTTR-B network into the pre-trained FTTR-B network slice model to achieve dynamic slice management and optimization of the FTTR-B network. The FTTR-B network slicing model includes a data input layer, a classification module, a resource allocation and optimization module, an orchestration and edge computing module, a slice prediction module, and a slice monitoring and self-healing module. The data input layer is used to input the preprocessed network data of the FTTR-B network and output a uniform normalized tensor. The classification module is used to classify the network data of the preprocessed FTTR-B network according to type, service level, and priority based on a unified standardized tensor. The resource allocation and optimization module is used to generate the optimal bandwidth resource allocation scheme based on the classification results output by the classification module and the current network status. The orchestration and edge computing module is used to map bandwidth resource allocation schemes to edge nodes; The slice prediction module is used to predict the changing trends of network resources and key performance indicators of the FTTR-B network based on the bandwidth resource allocation scheme mapped to edge nodes; The slice monitoring and self-healing module is used to monitor the slice's running status, detect anomalies, and execute self-healing strategies. The slice monitoring and self-healing module includes a state aggregation layer, a prediction consistency analysis layer, an anomaly detection layer, a self-healing strategy decision layer, and an execution and feedback layer. For detected anomalies, the self-healing strategy decision layer generates the most suitable self-healing action based on the system status and anomaly type, combined with the built-in rule engine and strategy learning model.

7. The apparatus according to claim 6, characterized in that, The preprocessing module includes: The cleaning submodule is used to clean network data; The conversion submodule is used to convert the cleaned network data. The anomaly detection submodule is used to perform anomaly detection on the network data after data conversion. The integration and synchronization submodule is used to integrate and synchronize network data after anomaly detection.

8. A storage medium, characterized in that, It includes instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 5.

9. An electronic device, characterized in that, The electronic device includes: Memory, processor, and computer programs stored in memory and executable on the processor, wherein, When the processor executes the program, it implements the method as described in any one of claims 1 to 5.

Images