CN113825165A - 5G slice network congestion early warning method and device based on time chart network - Google Patents
5G slice network congestion early warning method and device based on time chart network Download PDFInfo
- Publication number
- CN113825165A CN113825165A CN202010558931.9A CN202010558931A CN113825165A CN 113825165 A CN113825165 A CN 113825165A CN 202010558931 A CN202010558931 A CN 202010558931A CN 113825165 A CN113825165 A CN 113825165A
- Authority
- CN
- China
- Prior art keywords
- network
- slice
- load
- slicing
- matrix
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/0284—Traffic management, e.g. flow control or congestion control detecting congestion or overload during communication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention relates to the technical field of communication, and discloses a 5G slice network congestion early warning method and a device based on a time chart network, wherein the method comprises the following steps: acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future. Through the mode, the embodiment of the invention can avoid the congestion of the slicing network in time and improve the early warning accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of communication, in particular to a 5G slice network congestion early warning method and device based on a time chart network.
Background
At present, the slice network congestion early warning is mainly realized by respectively setting threshold values for loads of all slice network nodes in a slice network, but the method is easy to cause the problems of frequent false alarm, low accuracy rate and the like. In addition, network congestion often occurs when the alarm is discovered through the method, and the avoidance of the slice network congestion is not helpful greatly. Meanwhile, the slicing network has various nodes, complex relationship among the nodes and higher difficulty in automatic detection, and no better early warning means for the slicing network congestion exists at present.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide a method and an apparatus for early warning of congestion in a 5G slice network based on a time graph network, which overcome the foregoing problems or at least partially solve the foregoing problems.
According to an aspect of an embodiment of the present invention, there is provided a 5G slice network congestion early warning method based on a time chart network, the method including: acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
In an alternative manner, the converting the slice load topology map into an adjacency matrix and a feature matrix includes: representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph; and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
In an alternative mode, the applying a pre-trained time graph network-based slice network load prediction model according to the adjacency matrix and the feature matrix to calculate and output load prediction values of the slice network nodes at a second number of future times includes: capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model; and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
In an optional manner, before the applying the pre-trained time graph network-based slicing network load prediction model according to the adjacency matrix and the feature matrix to calculate and output load prediction values of the slicing network nodes at a second number of future time instants, the method includes: collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes; acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix; and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
In an optional manner, the training the slice network load prediction model based on the time graph network by using the total data set to obtain the weight parameter of the converged slice network load prediction model includes: training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future; calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error; and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In an optional manner, the training the slice network load prediction model according to the historical adjacency matrix and the historical feature matrix in the total data set to obtain predicted load prediction values of the slice network nodes at a second number of future times includes: receiving the historical adjacency matrix and the historical feature matrix input by an application input layer; acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers; acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers; the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
In an optional manner, the determining whether slice network congestion exists according to the load predicted values of the slice network nodes at a second number of future times includes: judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not; and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
According to another aspect of the embodiments of the present invention, there is provided a 5G slice network congestion warning apparatus based on a time chart network, the apparatus including: the data acquisition module is used for acquiring the slice load topological graph of the latest first number of moments from the NSMF and converting the slice load topological graph into an adjacency matrix and a feature matrix; the load prediction module is used for calculating and outputting the load prediction values of the slicing network nodes at the second number of moments in the future according to the adjacent matrix and the characteristic matrix by applying a pre-trained slicing network load prediction model based on the time graph network; and the congestion judgment module is used for judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the steps of the congestion early warning method of the 5G slice network based on the time chart network.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, where the executable instruction causes the processor to execute the steps of the above-mentioned congestion warning method for a 5G slice network based on a time chart network.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
The foregoing description is only an overview of technical results of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the above and other objects, features, and advantages of the embodiments of the present invention can be more clearly understood.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic diagram illustrating a method for early warning of congestion in a 5G slice network based on a time graph network according to an embodiment of the present invention;
fig. 2 is a schematic flowchart illustrating a congestion early warning method for a 5G slice network based on a time graph network according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram illustrating a sliced network load prediction model of a 5G sliced network congestion early warning method based on a time graph network according to an embodiment of the present invention;
FIG. 4 shows a schematic diagram of an LSTM neuron in a slice network load prediction model of a 5G slice network congestion early warning method based on a time graph network provided by an embodiment of the invention;
fig. 5 is a schematic structural diagram illustrating a congestion early warning apparatus of a 5G slice network based on a time chart network according to an embodiment of the present invention;
fig. 6 shows a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
A Network Slice (Network Slice) is an end-to-end logical function and a physical or virtual resource set required by the end-to-end logical function, including an access Network, a transmission Network, a core Network, and the like, and the Network Slice can be regarded as a virtualized "private Network" in a 5G Network; the Network slice is constructed based on a unified infrastructure of Network Function Virtualization (NFV), and low-cost and efficient operation is achieved. Network slice techniques may enable logical isolation of a communication network, allowing network elements and functionality to be configured and reused in each network slice to meet specific industry application needs. The Slice Management architecture mainly includes a Communication Service Management Function (CSMF), a Network Slice Management Function (NSMF), and a Network Slice Subnet Management Function (NSSMF).
The CSMF completes the order and processing of the user service communication service, converts the communication service requirement of the operator/third-party client into the requirement for the network slice, sends the requirement for the network slice (such as creating, terminating, modifying the instance request of the network slice) to the NSMF through the interface between the CSMF and the NSMF, and acquires the management data (such as performance, fault data, etc.) of the network slice from the NSMF. The NSMF is responsible for receiving the network slice requirements sent by the CSMF, managing the life cycle, performance, faults and the like of the network slice examples, arranging the composition of the network slice examples, decomposing the requirements of the network slice examples into the requirements of each network slice subnet example or network function, and sending network slice subnet example management requests to each NSSMF. The NSSMF receives a network slice subnet deployment requirement issued by the NSMF, manages the network slice subnet instances, arranges the composition of the network slice subnet instances, maps SLA requirements of the network slice subnet into QoS requirements of network services, and issues a network service deployment request to an NFV orchestrator (NFV organization, NFVO) system of an European Telecommunication Standardization Institute (ETSI) NFV domain.
The slicing Network has many nodes and complex relationships, and the slicing Network is not a two-dimensional grid but a graph, which means that a Convolutional Neural Network (CNN) model cannot reflect the complex topology of the slicing Network and therefore cannot accurately capture the spatial dependency relationship. Therefore, the embodiment of the invention provides the advantage of using a time Graph Convolutional neural Network (T-GCN) to capture the spatial and Temporal dependencies simultaneously. The time-map convolutional neural network combines a map convolutional network (GCN) and a long-short term memory neural network (LSTM). GCN is used to learn complex topologies to capture spatial dependencies and LSTM is used to learn dynamic changes in the slice network load to capture temporal dependencies.
In the embodiment of the invention, as shown in fig. 1, the 5G slice network congestion early warning method based on the time graph network obtains slice load topological graphs of the latest M times from a network slice management function NSMF at each time; converting the slice load topological graph into an adjacent matrix A and a characteristic matrix X, wherein the adjacent matrix A is the connection relation of each node of the slice network, and the characteristic matrix X is the characteristic representation of the load time sequence of each node of the slice network at M moments; carrying out data normalization processing on the adjacency matrix A and the characteristic matrix X; inputting the preprocessed adjacent matrix A and the feature matrix X into a slice network load prediction model based on a time graph network; after the pre-trained slice network load prediction model is calculated, the load prediction value of each slice network node at the future T moment is output; and if yes, informing the NSMF to limit the current of the slice user related to the slice network node. Therefore, the slice network congestion can be avoided in time, and the early warning accuracy is improved.
Fig. 2 is a schematic flowchart illustrating a 5G slice network congestion warning method based on a time graph network according to an embodiment of the present invention. The 5G slice network congestion early warning method based on the time chart network is applied to a server side, and as shown in fig. 2, the 5G slice network congestion early warning method based on the time chart network comprises the following steps:
step S11: and acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix.
At each time, slice load topological graphs of the latest first number M of times are obtained from the NSMF. Wherein, the slicing network load topology can be represented as G ═ (V, E), V is a set of slicing network nodes V ═ V1，V2，V3，…，VN}，N is the number of the slicing network nodes in the slicing network load topological graph, and E is the set of edges. If slicing network node ViAnd slicing network node VjThere is a connection between e ij1, otherwise eij0. Converting the slice network load topological graph into an adjacency matrix A and a characteristic matrix X, specifically representing the connection relation of each slice network node as the adjacency matrix A of N X N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph; and according to the slice load topological graph, representing the characteristics of the load time series of the first number of moments of each slice network node as the characteristic matrix X of N X M, wherein M is the length of the load time series of the attribute of the slice network node.
Wherein e isijRepresenting a slicing network node ViAnd slicing network node VjThe connection relationship between the nodes of the slicing network is 1, otherwise, the connection relationship is 0, xitRepresenting the properties of the ith slice network node at time t. In the embodiment of the present invention, the slicing network node attribute, i.e., the network load, may be set up Call volume Per Second (CAPS), i.e., network concurrency volume (CAPS), or Transaction volume Per Second (TPS). M represents the time-series length of the attribute of the slicing network node, and since the number of attributes of the slicing network node at a certain time is 1, the time-series length of the feature matrix X is equal to the first number M.
The embodiment of the invention also carries out standardized preprocessing on the data, and respectively carries out the following steps on each dimension: (X-mean)/std, i.e., data by attribute (by column) minus its mean, and divided by its variance. After the standardized preprocessing, the convergence speed of a subsequent slice network load prediction model can be improved, and the precision of the model is improved.
Step S12: and calculating and outputting the load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix.
The slice network load prediction model of the embodiment of the invention is a time map convolution neural network (T-GCN) built by a map convolution network (GCN) and a long-short term memory neural network (LSTM). By utilizing the advantages of the time graph convolution neural network in the simultaneous extraction of the spatial and temporal dependency relationship, the graph convolution network GCN in the slice network load prediction model is specifically applied to capture the spatial characteristics of the slice network load topological graph according to the adjacency matrix and the characteristic matrix; inputting the obtained time sequence with the spatial features into an LSTM, learning the dynamic change of the slice network load by applying a long-short term memory neural network LSTM according to the spatial features to extract the temporal features, and outputting the load predicted values of the slice network nodes at a second number T of moments in the future. Each graph neural network layer can be written as a non-linear function:
H(l+1)＝f(H(l),A),
wherein H(0)X is the input data, H(l)And Z is output data, L is the number of layers of the graph neural network, and different slice network load prediction models are determined by selecting different f () and parameters. W(l)Is a parameter matrix of the ith neural network layer, is a nonlinear activation function such as ReLU, A is a adjacency matrix, and D is a node-degree diagonal matrix of A.
In the embodiment of the present invention, before step S12, pre-training of the slice network load prediction model is completed, and a weight parameter of convergence of the slice network load prediction model is obtained. Specifically, collecting a historical slice load topological graph from NSMF as a total data set, and converting the slice load topological graph into a historical adjacency matrix A and a historical feature matrix X; acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix Y; applying the total data set to the sliced network based on a time graph networkAnd training the load prediction model to obtain the weight parameters of the converged slice network load prediction model. The adjacency matrix A is N × N in shape, the feature matrix X is N × M in shape, and the label matrix Y is N × T in shape, wherein the attribute of the ith slice network node at time T is represented as Yit. And before the total data set is applied to train the slice network load prediction model, the data is preprocessed, and the specific preprocessing method is the same as the preceding one, and is not described again here. In the embodiment of the invention, 80% of the total data set is divided into the training set, 20% of the total data set is divided into the testing set, the training set is used for training the model, and the testing set is used for testing the performance of the model.
When a slice network load prediction model is trained, the slice network load prediction model is trained according to the historical adjacency matrix and the historical feature matrix in the total data set, and predicted load prediction values of the slice network nodes at a second number of moments in the future are obtained. Structure of the slicing network load prediction model referring to fig. 3, specifically, the application input layer receives the input historical adjacency matrix a and the historical feature matrix X. X in FIG. 3tThe attribute representing the node of the slice network at time t is input into the history feature matrix X, and also input into the history adjacency matrix a (not shown). Two graph convolution layers (GCNs) are applied to obtain a time series corresponding to the spatial features of the slice load topology. The time series is input into the subsequent long-short term memory Layer (LSTM), and two long-short term memory Layers (LSTM) are applied to obtain a feature vector comprising the spatial features and the temporal features of the slice load topology. The application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors. Wherein, the number of convolution kernels of the two graph convolution layers is 32 (namely the dimension of output), and the activation function is set to be 'relu'. The number of neurons in both long and short term memory Layers (LSTM) is set to 64 and the activation function is set to "relu". The long-short term memory Layer (LSTM) is a special type of recurrent neural network, and long-term information can be memorized by controlling the time for which values in a cache are stored, so that the long-term information is suitable for predicting time series. As shown in figure 4 of the drawings,each neuron has four inputs and one output, and each neuron stores a memorized value. Each LSTM neuron contains three gates: forgetting gate, input gate, output gate, forgetting gate ftControlling the internal state c of the last momentt-1How much information needs to be forgotten; input door itControlling candidate states at the current time
How much information needs to be saved; output gate otControlling the internal state c at the present momenttHow much information needs to be output to the external state ht. Specifically, the method is obtained by the following formula:
forget the door:
an input gate:
the state update function is obtained by a non-linear function:
internal state:
an output gate:
outputting an external state:
outputting an external state: y ist＝σ(W′ht)。
Wherein x istFor the feature vector input at the t-th time, ftIndicating forgetting gate, itIndication inputGo into door otRepresents an output gate, ctRepresenting the state of the neuron at time t, htRepresenting the external state of the neuron, i.e., the hidden state of the LSTM layer, W is the trainable weight matrix, b is the bias vector. Such as WiIs a weight matrix of the input gate, WfWeight matrix representing forgetting gate, WoIs a weight matrix of output gates, biIs an offset term of the input gate, bfIs a biased term of a forgetting gate, boThe offset term of the output gate is shown, the gate activation function is sigmoid (sigma), the value range is (0, 1), and the activation function of the output is tanh function. Equation (1) represents forget gate, new information is added in equations (2), (3), equation (4) fuses new and old information, and equations (5), (6) output information about the next timestamp that the current LSTM neuron has learned. Each link in the LSTM neuron contains a corresponding weight. The long-short term memory neural network has a better effect on the learning of long sequences.
The output layer is composed of a fully connected layer (sense). And setting the number of the neurons included in the output layer as a second number T, and setting the activation function as sigmoid, namely outputting the predicted historical load prediction value of each slice network node at the second number T of times in the future.
After a predicted historical load predicted value is obtained, calculating an error between the load predicted value of the slicing network node and the real node attribute value, and measuring the error by applying an objective function. The mean square error mse (mean Squared error) is selected as the loss function, i.e. the objective function (loss ═ mean _ Squared error'),
the training goal is to minimize this error. The training round number is set to 1000(epochs 1000), the batch size is set to 32(batch _ size 32), and the gradient descent optimization algorithm selects an adam optimizer for improving the learning speed of the traditional gradient descent (optimizer 'adam'). The neural network can find the optimal weight parameter which enables the target function to be minimum through gradient descent, and the neural network can learn the weight parameter automatically through training. Training with training setAnd (4) refining, so that the smaller the objective function is, the better the objective function is, and after each round of training, evaluating and verifying the network element function cutting slice network load prediction model by using a test set. And gradient descent optimization algorithm is applied to make the gradient of the slice network load prediction model descend, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In step S12, specifically, the adjacency matrix a and the feature matrix X are input into a pre-trained slice network load prediction model based on the time graph network, the weight parameters of the slice network load prediction model are the optimal weight parameters obtained by training, and the predicted load values of the slice network nodes at the time of the second number T in the future are calculated and output through the slice network load prediction model.
Step S13: and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
Specifically, whether the load predicted value of a third continuous number K of moments of a sliced network node exceeds a preset threshold value is judged; if yes, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node, so that the slicing network congestion can be avoided in time.
According to the embodiment of the invention, the constructed slicing network load prediction model based on the time graph network predicts the load prediction values of the slicing network nodes at the T moments in the future at each moment, further judges whether the corresponding slicing network nodes are likely to have congestion or not according to the load prediction values, and timely informs NSMF to limit the current of related slicing users when the congestion is likely to exist, so that the slicing network congestion can be timely avoided, and the automation of the 5G slicing network congestion early warning is improved. When congestion is judged, the slicing network node is determined to be possibly congested only when the load predicted value of a certain slicing network node at K continuous moments exceeds a preset threshold value, so that the generation of false early warning caused by single abnormal detection data can be eliminated, the early warning accuracy can be improved, and too frequent early warning can be prevented.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
Fig. 5 shows a schematic structural diagram of a congestion early warning device of a 5G slice network based on a time chart network in an embodiment of the present invention. As shown in fig. 5, the congestion early warning device for a 5G slice network based on a time chart network includes: a data acquisition module 501, a load prediction module 502, a congestion determination module 503, and a model training unit 504. Wherein:
the data obtaining module 501 is configured to obtain the slice load topological graph at the latest first number of moments from the NSMF, and convert the slice load topological graph into an adjacency matrix and a feature matrix; the load prediction module 502 is configured to calculate and output load prediction values of the slice network nodes at a second number of future times according to the adjacency matrix and the feature matrix by applying a pre-trained slice network load prediction model based on the time graph network; the congestion determining module 503 is configured to determine whether a slice network congestion exists according to the load prediction values of the slice network nodes at a second number of future times.
In an alternative manner, the data acquisition module 501 is configured to: representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph; and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
In an alternative approach, the load prediction module 502 is configured to: capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model; and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
In an alternative approach, the model training unit 504 is configured to: collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes; acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix; and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
In an alternative approach, the model training unit 504 is configured to: training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future; calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error; and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In an alternative manner, the model training unit 504 is further configured to: receiving the historical adjacency matrix and the historical feature matrix input by an application input layer; acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers; acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers; the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
In an alternative manner, the congestion determination module 503 is configured to: judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not; and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the 5G slice network congestion early warning method based on the time chart network in any method embodiment.
The executable instructions may be specifically configured to cause the processor to:
acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix;
calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix;
and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
In an alternative, the executable instructions cause the processor to:
representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph;
and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
In an alternative, the executable instructions cause the processor to:
capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model;
and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
In an alternative, the executable instructions cause the processor to:
collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes;
acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix;
and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
In an alternative, the executable instructions cause the processor to:
training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future;
calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error;
and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In an alternative, the executable instructions cause the processor to:
receiving the historical adjacency matrix and the historical feature matrix input by an application input layer;
acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers;
acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers;
the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
In an alternative, the executable instructions cause the processor to:
judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not;
and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
An embodiment of the present invention provides a computer program product, where the computer program product includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes a 5G slice network congestion early warning method based on a time chart network in any of the above-mentioned method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix;
calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix;
and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
In an alternative, the executable instructions cause the processor to:
representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph;
and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
In an alternative, the executable instructions cause the processor to:
capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model;
and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
In an alternative, the executable instructions cause the processor to:
collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes;
acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix;
and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
In an alternative, the executable instructions cause the processor to:
training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future;
calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error;
and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In an alternative, the executable instructions cause the processor to:
receiving the historical adjacency matrix and the historical feature matrix input by an application input layer;
acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers;
acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers;
the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
In an alternative, the executable instructions cause the processor to:
judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not;
and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
Fig. 6 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and a specific embodiment of the present invention does not limit a specific implementation of the device.
As shown in fig. 6, the computing device may include: a processor (processor)602, a communication Interface 604, a memory 606, and a communication bus 608.
Wherein: the processor 602, communication interface 604, and memory 606 communicate with one another via a communication bus 608. A communication interface 604 for communicating with network elements of other devices, such as clients or other servers. The processor 602 is configured to execute the program 610, and may specifically execute relevant steps in the above embodiment of the congestion warning method for a 5G slice network based on a time chart network.
In particular, program 610 may include program code comprising computer operating instructions.
The processor 602 may be a central processing unit CPU or an application Specific Integrated circuit asic or an Integrated circuit or Integrated circuits configured to implement embodiments of the present invention. The one or each processor included in the device may be the same type of processor, such as one or each CPU; or may be different types of processors such as one or each CPU and one or each ASIC.
And a memory 606 for storing a program 610. Memory 606 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 610 may specifically be configured to cause the processor 602 to perform the following operations:
acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix;
calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix;
and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
In an alternative, the program 610 causes the processor to:
representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph;
and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
In an alternative, the program 610 causes the processor to:
capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model;
and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
In an alternative, the program 610 causes the processor to:
collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes;
acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix;
and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
In an alternative, the program 610 causes the processor to:
training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future;
calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error;
and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
In an alternative, the program 610 causes the processor to:
receiving the historical adjacency matrix and the historical feature matrix input by an application input layer;
acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers;
acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers;
the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
In an alternative, the program 610 causes the processor to:
judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not;
and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
The embodiment of the invention obtains the slice load topological graph of the latest first number of moments from NSMF and converts the slice load topological graph into an adjacency matrix and a characteristic matrix; calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix; judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future, so that the slicing network congestion can be avoided in time, and the early warning accuracy is improved.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (10)
1. A5G slice network congestion early warning method based on a time chart network is characterized by comprising the following steps:
acquiring the slice load topological graph of the latest first number of moments from the NSMF, and converting the slice load topological graph into an adjacency matrix and a feature matrix;
calculating and outputting load predicted values of the slicing network nodes at a second number of future moments by applying a pre-trained slicing network load prediction model based on the time graph network according to the adjacency matrix and the feature matrix;
and judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
2. The method of claim 1, wherein the converting the slice load topology map into an adjacency matrix and a feature matrix comprises:
representing the connection relation of each slice network node as the adjacency matrix of N x N according to the slice load topological graph, wherein N is the number of the slice network nodes in the slice load topological graph;
and representing the characteristics of the load time series of the first number of moments of each slicing network node as the characteristic matrix of N x M according to the slicing load topological graph, wherein M is the length of the load time series of the slicing network node attribute.
3. The method of claim 1, wherein the applying a pre-trained time graph network based sliced network load prediction model from the adjacency matrix and the feature matrix to compute load prediction values for sliced network nodes outputting a second number of time instants in the future comprises:
capturing the spatial characteristics of the slicing network load topological graph according to the adjacency matrix and the characteristic matrix by applying a graph convolution network in the slicing network load prediction model;
and learning the dynamic change of the slicing network load according to the spatial features by applying a long-short term memory neural network to extract the temporal features, and outputting the load predicted values of the slicing network nodes at a second number of moments in the future.
4. The method of claim 1, wherein before applying the pre-trained time graph network-based sliced network load prediction model based on the adjacency matrix and the feature matrix to compute and output load prediction values for sliced network nodes at a second number of future times, comprising:
collecting historical slice load topological graphs from NSMF (non-subsampled finite field) as a total data set, and converting the slice load topological graphs into historical adjacency matrixes and historical feature matrixes;
acquiring real node attribute values of the slicing network nodes at a second number of moments in the future to be predicted to form a label matrix;
and training the slice network load prediction model based on the time graph network by applying the total data set to obtain the weight parameters of the converged slice network load prediction model.
5. The method of claim 4, wherein the applying the total data set to train the slice network load prediction model based on the time graph network to obtain the weight parameters of the converged slice network load prediction model comprises:
training the slicing network load prediction model according to the historical adjacency matrix and the historical characteristic matrix in the total data set, and obtaining predicted load prediction values of the slicing network nodes at a second number of moments in the future;
calculating an error between the load predicted value and the real node attribute value of the slicing network node, and applying an objective function to measure the error;
and gradient descent optimization algorithm is applied to make the gradient descent of the slice network load prediction model, and the optimal weight parameter of the slice network load prediction model which makes the target function minimum is obtained, wherein the optimal weight parameter is the weight parameter of the trained slice network load prediction model.
6. The method according to claim 5, wherein training the slice network load prediction model according to the historical adjacency matrix and the historical feature matrix in the total data set to obtain predicted load values of the slice network nodes at a second number of predicted future time instants comprises:
receiving the historical adjacency matrix and the historical feature matrix input by an application input layer;
acquiring a time sequence corresponding to the spatial characteristics of the slice load topological graph by applying the two graph convolution layers;
acquiring a feature vector comprising spatial features and temporal features of a slice load topological graph by applying two long-term and short-term memory layers;
the application output layer outputs the load prediction values of the slice network nodes at a second number of predicted future times in accordance with the feature vectors.
7. The method of claim 1, wherein the determining whether slice network congestion exists according to the load prediction values of the slice network nodes at a second number of future times comprises:
judging whether the load predicted value of a third continuous number of moments of the sliced network nodes exceeds a preset threshold value or not;
and if so, determining that the slicing network node is congested, and informing the NSMF to limit the current of the slicing users related to the slicing network node.
8. A5G slice network congestion early warning device based on a time chart network is characterized by comprising:
the data acquisition module is used for acquiring the slice load topological graph of the latest first number of moments from the NSMF and converting the slice load topological graph into an adjacency matrix and a feature matrix;
the load prediction module is used for calculating and outputting the load prediction values of the slicing network nodes at the second number of moments in the future according to the adjacent matrix and the characteristic matrix by applying a pre-trained slicing network load prediction model based on the time graph network;
and the congestion judgment module is used for judging whether the slicing network congestion exists according to the load predicted values of the slicing network nodes at the second number of moments in the future.
9. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, which causes the processor to execute the steps of the 5G slice network congestion warning method based on the time graph network according to any one of claims 1-7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the steps of the 5G slice network congestion warning method for a time graph-based network according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558931.9A CN113825165B (en) | 2020-06-18 | 2020-06-18 | 5G slice network congestion early warning method and device based on time diagram network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010558931.9A CN113825165B (en) | 2020-06-18 | 2020-06-18 | 5G slice network congestion early warning method and device based on time diagram network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113825165A true CN113825165A (en) | 2021-12-21 |
| CN113825165B CN113825165B (en) | 2023-08-04 |
Family
ID=78911692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010558931.9A Active CN113825165B (en) | 2020-06-18 | 2020-06-18 | 5G slice network congestion early warning method and device based on time diagram network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113825165B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358449A (en) * | 2022-03-21 | 2022-04-15 | 国网天津市电力公司电力科学研究院 | Electric vehicle charging load space-time distribution prediction method based on graph neural network |
| CN115296984A (en) * | 2022-08-08 | 2022-11-04 | 中国电信股份有限公司 | Method, device, equipment and storage medium for detecting abnormal network nodes |
| GB2628551A (en) * | 2023-03-27 | 2024-10-02 | Neueda Tech Ireland Limited | Network traffic prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106549806A (en) * | 2016-10-26 | 2017-03-29 | 清华大学 | A kind of network section manager and its management method |
| CN109154990A (en) * | 2016-06-03 | 2019-01-04 | 英特尔公司 | Lookup convolutional layer in convolutional neural networks |
| CN110383292A (en) * | 2017-04-07 | 2019-10-25 | 英特尔公司 | The method and system through budget and simplified training for deep neural network |
| US20200052991A1 (en) * | 2018-08-09 | 2020-02-13 | At&T Intellectual Property I, L.P. | Mobility network slice selection |
| US20200067935A1 (en) * | 2018-08-27 | 2020-02-27 | Ciena Corporation | Network architecture providing device identification and redirection using whitelisting traffic classification |
| US20200100137A1 (en) * | 2018-09-25 | 2020-03-26 | Verizon Patent And Licensing Inc. | Diversified ran architecture with congestion control based on spectrum re-allocation |
-
2020
- 2020-06-18 CN CN202010558931.9A patent/CN113825165B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109154990A (en) * | 2016-06-03 | 2019-01-04 | 英特尔公司 | Lookup convolutional layer in convolutional neural networks |
| CN106549806A (en) * | 2016-10-26 | 2017-03-29 | 清华大学 | A kind of network section manager and its management method |
| CN110383292A (en) * | 2017-04-07 | 2019-10-25 | 英特尔公司 | The method and system through budget and simplified training for deep neural network |
| US20200052991A1 (en) * | 2018-08-09 | 2020-02-13 | At&T Intellectual Property I, L.P. | Mobility network slice selection |
| US20200067935A1 (en) * | 2018-08-27 | 2020-02-27 | Ciena Corporation | Network architecture providing device identification and redirection using whitelisting traffic classification |
| US20200100137A1 (en) * | 2018-09-25 | 2020-03-26 | Verizon Patent And Licensing Inc. | Diversified ran architecture with congestion control based on spectrum re-allocation |
Non-Patent Citations (1)
| Title |
|---|
| 李亚光: "5G网络切片在智能电网领域应用探讨", 《通讯世界》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114358449A (en) * | 2022-03-21 | 2022-04-15 | 国网天津市电力公司电力科学研究院 | Electric vehicle charging load space-time distribution prediction method based on graph neural network |
| CN115296984A (en) * | 2022-08-08 | 2022-11-04 | 中国电信股份有限公司 | Method, device, equipment and storage medium for detecting abnormal network nodes |
| CN115296984B (en) * | 2022-08-08 | 2023-12-19 | 中国电信股份有限公司 | Abnormal network node detection method and device, equipment and storage medium |
| GB2628551A (en) * | 2023-03-27 | 2024-10-02 | Neueda Tech Ireland Limited | Network traffic prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113825165B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| CN109120462B (en) | Method and device for predicting opportunistic network link and readable storage medium | |
| US10761958B2 (en) | Automatically determining accuracy of a predictive model | |
| CN113825165A (en) | 5G slice network congestion early warning method and device based on time chart network | |
| CN110686633B (en) | Landslide displacement prediction method and device and electronic equipment | |
| CN114297036B (en) | Data processing method, device, electronic equipment and readable storage medium | |
| CN110942086A (en) | Data prediction optimization method, device and equipment and readable storage medium | |
| CN109471698B (en) | System and method for detecting abnormal behavior of virtual machine in cloud environment | |
| CN113037577B (en) | Network traffic prediction method, device and computer readable storage medium | |
| CN117110748A (en) | Transformer substation main equipment operation state abnormality detection method based on fusion terminal | |
| CN113541980A (en) | Network slice fault root cause positioning method and device, computing equipment and storage medium | |
| CN114911788B (en) | Data interpolation method and device and storage medium | |
| CN117215728B (en) | Agent model-based simulation method and device and electronic equipment | |
| CN115545334A (en) | Land use type prediction method, land use type prediction device, electronic device, and storage medium | |
| CN115062779A (en) | Event prediction method and device based on dynamic knowledge graph | |
| CN113541986B (en) | Fault prediction method and device for 5G slice and computing equipment | |
| CN112203311B (en) | Network element abnormity diagnosis method, device, equipment and computer storage medium | |
| CN111935005A (en) | Data transmission method, device, processing equipment and medium | |
| CN113765683A (en) | Cutover alarm shielding method and device for network slices | |
| CN114143163B (en) | Slice false alarm identification method and device based on graph attention network | |
| CN113822454B (en) | Method and device for predicting slice complaint processing resources | |
| CN113949633A (en) | 5G network slice disaster recovery pool resource management method and device based on machine learning | |
| CN111767934A (en) | Image identification method and device and electronic equipment | |
| CN113762978B (en) | Complaint delimiting method and device for 5G slicing user and computing equipment | |
| CN113810212B (en) | Root cause positioning method and device for 5G slice user complaints |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |