CN114599042A - Network state sensing method and device, electronic equipment and storage medium - Google Patents

Network state sensing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114599042A
CN114599042A CN202210208897.1A CN202210208897A CN114599042A CN 114599042 A CN114599042 A CN 114599042A CN 202210208897 A CN202210208897 A CN 202210208897A CN 114599042 A CN114599042 A CN 114599042A
Authority
CN
China
Prior art keywords
network
data
service
network state
evaluation
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.)
Pending
Application number
CN202210208897.1A
Other languages
Chinese (zh)
Inventor
刘蓓
邓胜超
粟欣
高晖
赵明
许希斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Original Assignee
Tsinghua University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tsinghua University filed Critical Tsinghua University
Priority to CN202210208897.1A priority Critical patent/CN114599042A/en
Publication of CN114599042A publication Critical patent/CN114599042A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The disclosure relates to a network state sensing method and device, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring network data according to a knowledge base; obtaining a network state evaluation parameter according to the network data, the service type and the network state evaluation model; and determining a network state evaluation result according to the resource demand, the actual resource quantity and the network state evaluation parameter. According to the network state sensing method disclosed by the embodiment of the invention, the network data can be automatically selected according to the knowledge base so as to accurately evaluate the state of the current network, the data dimension of the network data can be reduced, all the network data do not need to be completely collected, the collection amount of the network data can be reduced, the resource overhead is saved, the network state evaluation result can be automatically obtained through the resource demand amount, the actual resource amount and the network state evaluation parameter, the labor cost is reduced, and the time span between the data collection and the data analysis is shortened.

Description

Network state sensing method and device, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of wireless communication technologies, and in particular, to a network status sensing method and apparatus, an electronic device, and a storage medium.
Background
Currently, 5G networks are widely applied, the traditional industry and manufacturing industry are rapidly transformed towards digitization, the internet of things is rapidly developed, wireless networks are rapidly developed towards personalization and diversification, and network performance requirements and network resource scheduling become more important factors for network development. More emerging applications and scenarios such as augmented reality, holographic communications, etc. will also emerge in future 6G networks. At that time, the requirements of ultrahigh connection density, ultra-large bandwidth requirement, ultra-low network delay and the like will put higher requirements on the availability, reliability and expandability of the network. In order to meet the requirements, the 6G network will comprise a series of heterogeneous and dense networks, which will bring problems such as high data collection resource overhead, information redundancy, low network state analysis efficiency and the like to the monitoring of the network state.
The network state can not be monitored without analyzing the network performance parameters. Currently, network state analysis is mainly divided into two parts, namely data acquisition and data analysis. The network performance data acquisition includes drive test, fixed point test, MR (measurement report) data acquisition, KPI (key performance indicator) data acquisition, and the like. Measuring various performance indexes at regular time, fixed point and large scale by using measuring equipment, and reporting after storing; the data analysis is that professional engineers use a relevant data analysis method to analyze the acquired network performance parameters, determine the current network state according to the analysis result, and have a large time span between the data acquisition and the data analysis in the time dimension.
However, for future 6G networks, the ultra-large device connection density will present a great challenge to a large-scale and systematic way of collecting various network performance indexes. On the other hand, the current way of sensing the network state cannot meet the requirements of high reliability and low time delay of the future 6G application on the network.
Disclosure of Invention
The disclosure provides a network state sensing method and device, electronic equipment and a storage medium.
According to an aspect of the present disclosure, there is provided a network state awareness method, including: acquiring network data corresponding to the current network service according to a preset knowledge base, wherein the knowledge base comprises a mapping relation between the service type of the network service and the type of the network data; obtaining a network state evaluation parameter according to the network data, the service type of the current network service and a pre-trained network state evaluation model; and determining a network state evaluation result according to the resource demand quantity, the actual resource quantity and the network state evaluation parameter of the current network service.
In one possible implementation, the method further includes: acquiring various types of sample network data according to the sample network service; acquiring a sample network evaluation index corresponding to the sample network service; and acquiring a mapping relation between the sample network evaluation index and the sample network data to establish the knowledge base.
In one possible implementation, the method further includes: obtaining a sample network evaluation index according to the knowledge base and the sample network data; inputting the sample network evaluation index into a network state evaluation model to obtain a sample evaluation parameter of the sample network service; determining model loss of the network state evaluation model according to the sample evaluation parameters and the actual state of the sample network service; and training the network state evaluation model according to the model loss.
In a possible implementation manner, acquiring network data corresponding to a current network service according to a preset knowledge base includes: determining the service type of the current network service; determining a corresponding target service type in the knowledge base according to the service type; determining the type of the corresponding network data according to the target service type; and acquiring the network data corresponding to the current network service according to the type of the network data.
In a possible implementation manner, obtaining a network state evaluation parameter according to the network data, the service type of the current network service, and a pre-trained network state evaluation model includes: obtaining a network evaluation index corresponding to the current network service by using the network data and the knowledge base; and inputting the network evaluation index into a network state evaluation model to obtain the network state evaluation parameter.
In a possible implementation manner, determining a network state evaluation result according to the resource demand amount of the current network service, the actual resource amount, and the network state evaluation parameter includes: obtaining a network utility index according to the resource demand and the actual resource quantity; and obtaining the network state evaluation result according to the network utility index and the network state evaluation parameter.
In one possible implementation, the method further includes: and according to the network state evaluation result, adjusting the mapping relation between the service type of the network service and the type of the network data to obtain an adjusted knowledge base.
According to an aspect of the present disclosure, there is provided a network state awareness apparatus, including: the network data acquisition module is used for acquiring network data corresponding to the current network service according to a preset knowledge base, wherein the knowledge base comprises a mapping relation between the service type of the network service and the type of the network data; the evaluation module is used for obtaining a network state evaluation parameter according to the network data, the service type of the current network service and a pre-trained network state evaluation model; and the evaluation module is used for determining a network state evaluation result according to the resource demand quantity, the actual resource quantity and the network state evaluation parameter of the current network service.
In one possible implementation, the apparatus further includes: the knowledge base establishing module is used for acquiring various types of sample network data according to the sample network service; acquiring a sample network evaluation index corresponding to the sample network service; and acquiring a mapping relation between the sample network evaluation index and the sample network data to establish the knowledge base.
In one possible implementation, the apparatus further includes: the training module is used for obtaining a sample network evaluation index according to the knowledge base and the sample network data; inputting the sample network evaluation index into a network state evaluation model to obtain a sample evaluation parameter of the sample network service; determining model loss of the network state evaluation model according to the sample evaluation parameters and the actual state of the sample network service; and training the network state evaluation model according to the model loss.
In one possible implementation manner, the network data obtaining module is further configured to: determining the service type of the current network service; determining a corresponding target service type in the knowledge base according to the service type; determining the type of the corresponding network data according to the target service type; and acquiring the network data corresponding to the current network service according to the type of the network data.
In one possible implementation, the evaluation module is further configured to: obtaining a network evaluation index corresponding to the current network service by using the network data and the knowledge base; and inputting the network evaluation index into a network state evaluation model to obtain the network state evaluation parameter.
In one possible implementation, the evaluation module is further configured to: obtaining a network utility index according to the resource demand and the actual resource quantity; and obtaining the network state evaluation result according to the network utility index and the network state evaluation parameter.
In one possible implementation, the apparatus further includes: and the adjusting module is used for adjusting the mapping relation between the service type of the network service and the type of the network data according to the network state evaluation result to obtain an adjusted knowledge base.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the above-described method.
According to the network state sensing method disclosed by the embodiment of the invention, the network data can be automatically selected according to the knowledge base so as to accurately evaluate the state of the current network, the data dimension of the network data can be reduced, all the network data do not need to be completely collected, the collection amount of the network data can be reduced, the resource overhead is saved, the network state evaluation result can be automatically obtained through the resource demand amount, the actual resource amount and the network state evaluation parameter, the labor cost is reduced, the time span between the data collection and the data analysis is shortened, and the time consistency of the analysis result and the actual network state is improved. The method can better meet the requirements of high reliability and low time delay in a high-complexity and ultra-dense heterogeneous network. And the knowledge base can be continuously updated without manual participation, so that the accuracy of network state evaluation is kept at a higher level.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.
Fig. 1 shows a flow diagram of a network state awareness method according to an embodiment of the present disclosure;
FIG. 2 shows a schematic diagram between entities of a knowledge base, in accordance with an embodiment of the present disclosure;
FIG. 3 shows a schematic diagram of a knowledge base in accordance with an embodiment of the present disclosure;
FIG. 4 shows a schematic diagram of a network dynamics perception simulation effect according to an embodiment of the present disclosure;
FIG. 5 shows a schematic diagram of a network state assessment model according to an embodiment of the present disclosure;
fig. 6 shows an application schematic diagram of a network state awareness method according to an embodiment of the present disclosure;
FIG. 7 shows a block diagram of a network state awareness apparatus according to an embodiment of the present disclosure;
FIG. 8 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure;
fig. 9 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure.
Detailed Description
Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.
In the related technology, in the network state monitoring process, data acquisition and data analysis have large span in time dimension, delay is large, data redundancy is large, data acquisition amount is large, resource occupation is high, and the like. Specifically, the method comprises the following steps:
fig. 1 shows a flow chart of a network state awareness method according to an embodiment of the present disclosure, as shown in fig. 1, the method includes:
in step S11, network data corresponding to the current network service is acquired according to a preset knowledge base, where the knowledge base includes a mapping relationship between a service type of the network service and a type of the network data;
in step S12, obtaining a network state evaluation parameter according to the network data, the service type of the current network service, and a pre-trained network state evaluation model;
in step S13, a network status evaluation result is determined according to the resource demand amount of the current network service, the actual resource amount, and the network status evaluation parameter.
According to the network state sensing method disclosed by the embodiment of the disclosure, the network data can be automatically selected according to the knowledge base so as to accurately evaluate the state of the current network, the data dimension of the network data can be reduced, all the network data do not need to be completely collected, the collection amount of the network data can be reduced, the resource overhead is saved, the network state evaluation result can be automatically obtained through the resource demand amount, the actual resource amount and the network state evaluation parameter, the labor cost is reduced, the time span between data collection and data analysis is shortened, and the time consistency of the analysis result and the actual network state is improved. The method can better meet the requirements of high reliability and low time delay in a high-complexity and ultra-dense heterogeneous network.
In a possible implementation manner, in the service processing performed by the network, network data in various aspects such as a user, a base station, a core network, and the like may be obtained, and in an example, network data reflecting performance of the network may be obtained, for example, network data reflecting different levels such as a control plane, a service plane, a network load capacity, coverage interference, and the like may be obtained. The above network data may be bottom layer data that directly reflects performance indicators of a network in a certain aspect, that is, KPI (key performance indicator) data, however, these data are various in types, and have high data dimensions, and the occupied amount of processing resources required for acquisition is large. Moreover, the network data may be associated with each other, for example, a certain network data may be represented by one or more other network data through some mapping relationship, which results in redundancy of data collection. Further, the real state of the network is often closely related to specific services, network resource overhead, the number of network access users, user experience, and the like, and only the underlying network data cannot directly reflect the real state of the network. In order to characterize the real network state, a multi-dimensional network state characterization system surrounding users, services, network data and network states can be established. The whole characterization system can comprehensively characterize the current network state from the user and the network. As described above, KPI data is directly obtained underlying data, and directly describes the performance of a network in a certain aspect, but these performances cannot directly reflect the specific situation of the network when performing a certain service, in an example, KPI data such as 5G signal-to-interference-and-noise ratio, 5G reference signal received power, 5G reference signal received quality, and the like can be obtained in a video service, but these data are underlying data, and the numerical values of these data cannot directly reflect the real situation of video playing, for example, whether video playing is successful, whether video playing is smooth, and the like. Therefore, the KPI data can be converted into network evaluation indexes such as video playing success rate, video downloading average rate, video playing waiting time, video playing average pause times, and the like, that is, KQI (key quality indicator) data, which is also an index directly reflecting a network state at a user view angle. Therefore, for each service, a corresponding network evaluation index can be determined, and a relationship between the network evaluation index and the network data, that is, a mapping relationship between the service type of the network service in the knowledge base and the type of the network data of different layers can be determined.
In one possible implementation, the network evaluation index may be reflected by one or more network data, for example, by performing weighted summation on the one or more network data to obtain the network evaluation index. When determining the network evaluation index, which categories of network data to select for weighted summation may be preset, or may be automatically selected by way of machine learning, which is not limited by the present disclosure. The weight for weighted summation may also be preset, or may be obtained by way of machine learning, which is not limited by this disclosure.
In one possible implementation manner, a knowledge base may be established, where the knowledge base includes a mapping relationship between a service type of a network service and a type of network data, and a mapping relationship between a network evaluation index and network data, and the method further includes: acquiring various types of sample network data according to the sample network service; acquiring a sample network evaluation index corresponding to the sample network service; and acquiring a mapping relation between the sample network evaluation index and the sample network data to establish the knowledge base.
In one possible implementation, various network data may be obtained for the network service, and various sample network data may be obtained for the sample network service when the knowledge base is established. After the sample network data is obtained, the sample network data can be subjected to data preprocessing, including data cleaning, normalization, data correlation analysis and the like. The data cleaning is to solve the data quality problems such as data missing, data duplication and the like, so that the data is more suitable for training and using the machine learning neural network. Normalization is to eliminate the adverse effects caused by singular sample data. The data correlation analysis is to reduce the redundancy of the training samples, and on the premise that the correlation of multiple items of data is high, some unnecessary data are removed, so that the training complexity can be reduced, and the calculation resources can be saved.
In one possible implementation, the network evaluation index may be an index that is preset specifically for each network service. For example, in the case of network traffic blWhen relevant network data is collected, a preprocessed network data set X is obtained, where X ═ X1，x2，…，xkThat is, the network data set X includes k (k is a positive integer) types of network data, and the network data set X and the sample network service b may be presetlCorresponding m (k is positive integer) network evaluation index sets
Figure BDA00035322772900000611
Figure BDA0003532277290000061
And determine the network data (e.g., which may be part of the data in the network data set X) required to calculate each network evaluation index by way of machine learning.
In a possible implementation, by the above method, it is possible to determine
Figure BDA0003532277290000062
Mapping relation with partial network data in network data set X, wherein the partial network data form a data set
Figure BDA0003532277290000063
(subset of network data set X), and similarly,
Figure BDA0003532277290000064
has relevance with partial network data in the network data set X, and the data set formed by the partial network data is
Figure BDA0003532277290000065
Figure BDA0003532277290000066
Has relevance with partial network data in the network data set X, and the data set formed by the partial network data is
Figure BDA0003532277290000067
The types of the network data corresponding to the network evaluation indexes may be repeated, so that the union of the data sets can be obtained
Figure BDA0003532277290000068
Figure BDA0003532277290000069
And the evaluation index prediction submodel is input as an evaluation index prediction submodel of the network state evaluation model, is converted into a network evaluation index based on a pre-established knowledge base, and evaluates the network state.
In a possible implementation manner, the storage form in the knowledge base adopts a business-divided storage manner, each business is classified according to the class to which each business belongs, and the network evaluation indexes associated with each business and the relationship between each network evaluation index and network data are respectively stored under each business. The relationship between the network evaluation index and the network data is expressed in a matrix form as follows:
Figure BDA00035322772900000610
wherein the matrix has m rows and k columns, the row representation and the service blAnd the relevant network evaluation indexes represent network data. And when a certain network evaluation index is in relation with the network data, taking the value of the corresponding position as 1, otherwise, taking the value as 0.
FIG. 2 shows a schematic diagram between entities of a knowledge base that may be built in the form of a knowledge graph, according to an embodiment of the disclosure. That is, the level-by-level association may be performed in a hierarchical manner. In an example, the knowledge graph is divided into five layers in total, and may be divided into an overall network, a service class, a sub-service, a network evaluation index KQI, and a network data KPI, and further, specific mapping relationships may be stored, for example, a weight when the KPI is weighted and summed to obtain the KQI, a calculation manner when a network state evaluation parameter of the sub-service is obtained through the KQI, a calculation manner when the network state evaluation parameter of the service class is determined through the network state evaluation parameter of the sub-service, and the like, which are not limited by the present disclosure.
Fig. 3 is a schematic diagram illustrating a knowledge base established according to an embodiment of the present disclosure, and in an example, the knowledge base may also be represented in the form of associated nodes, each node in fig. 3 may represent one type of network data or network evaluation index of each service in a current network, and an association relationship between the network evaluation index and the network data may be determined by a connection relationship between the nodes, which is not limited in the present disclosure.
In an example, taking a video service as an example, the network data that can be acquired may include a 5G signal-to-interference-and-noise ratio (sinr), a 1 st strong 5G reference signal received power, a 2 nd strong 5G reference signal received power, a 5G reference signal received quality, a 1 st strong 5G reference signal received quality, a 5G received signal strength indication (rssi), a number of downlink scheduling subframes (NR PDCCH), a 5G physical downlink shared channel (PDCCH) block error rate, a number of DL PRBs per slot, a 5G physical downlink shared channel (PDCCH) retransmission block error rate, a total number of NR downlink acknowledgements per second (NR/DL), a minimum rate of a 5G downlink RLC layer, a number of NR/downlink unacknowledged times per second (NR/DL), a minimum rate of a 5G downlink physical layer, a number of NR/uplink non-retransmitted PRBs per second, a minimum rate of a 5G downlink MAC layer, a number of NR/uplink non-retransmitted PRBs per slot, an average number of MCS adjustments per second (5G uplink), a double-link downlink physical layer throughput rate, a channel (PDCCH) rate (DL, The modulation mode with the most DL per second, the throughput rate of a dual-connection downlink MAC layer, the modulation mode with the most DL per second, the throughput rate of a dual-connection downlink RLC, the modulation occupation ratio of DL 16QAM per second, the throughput rate of a dual-connection downlink PDCP, the Rank with the most DL per second, the total number of NR downlink TBs, the Rank with the most DL per second, the average Rank per second of NR downlinks, the number of DL PRBs per second, the average MCS of NR downlinks, the transmission power of an NR physical uplink shared channel, the average CQIWB per second, the total power of NR transmission, the average PHR of NR PDSCH demodulation reference signals, the signal-to-interference-noise ratio of NR PDSCH demodulation reference signals, two event codes of an NR layer, the signal-to-interference-noise ratio of NR PDCCH demodulation reference signals, the Rank indication value, and the like, and the total 40 network data are obtained, namely the data dimension is 40 dimensions. The data can be used for carrying out weighted summation to obtain the network evaluation index of the average pause times of video playing. That is, if the network evaluation index is used to directly reflect the network state, the method is more intuitive, and the occupation of data calculation and storage resources can be greatly reduced.
In an example, as described above, redundancy may exist among a plurality of types of network data, or some network data may not have high correlation with the network evaluation index, the network data may be filtered, for example, whether correlation exists among the network data may be determined by a statistical method, data redundancy may be removed, data dimensionality may be reduced, and data redundancy may be removed by a correlation analysis or the like. Further, the network data can be further screened by methods of random forest, principal component analysis, neural network, etc., and the weight of the network data is calculated to obtain the network evaluation index through the weighted summation of part of the network data, for example, by the above processing, 13 indexes such as 5G signal-to-interference-and-noise ratio, DL 16QAM modulation ratio per second, 5G physical downlink shared channel block error rate, NR physical uplink shared channel transmission power, 5G physical downlink shared channel retransmission block error rate, signal-to-interference-and-noise ratio of NR PDSCH demodulation reference signal, minimum rate of 5G downlink RLC layer, number of PDCCH downlink scheduling subframes, minimum rate of 5G downlink physical layer, number of PRBs per time slot, average modulation degree per second of 5G uplink, number of non-retransmission PRBs per second of NR uplink, and maximum modulation mode per second of DL can be screened out, so that the dimensionality of the data in calculating the network evaluation index is greatly reduced, the method reduces the occupation of operation and storage resources, simultaneously reduces the complexity of the mapping relation between the service type of the network service and the type of the network data in the knowledge base, also reduces the training difficulty of the network state evaluation model, and can improve the training efficiency and the network performance.
Fig. 4 is a schematic diagram illustrating a network dynamic sensing simulation effect according to an embodiment of the present disclosure, in which, taking the video service as an example, if network data of all dimensions (e.g., 40-dimensional network data) are directly used to predict a network state evaluation parameter, a training process of the prediction model is inferior to a training process in which a network evaluation index corresponding to the video service and network data corresponding to the network evaluation index are preset or a network evaluation index and network data are screened in the training process, in terms of training difficulty, training efficiency, resource consumption, and the like, in the example, 20000 groups of sample data are respectively obtained to form a training set, and 2599 groups of sample data are obtained to form a test set. The former training data maintains 40 dimensions, and the latter training data can select the 13 dimensions, or screen out 13 dimensions in the training. After training on the training set, the test is carried out on the test set, the model loss of the former is 0.02, the model loss of the latter is 0.04, the prediction precision of the former is 0.8301, the prediction precision of the latter is 0.8153, the former is slightly good, but the difference is extremely small. However, when considering time efficiency, it is necessary to consider whether to cull network data that does not contribute much to accuracy, especially for future 6G applications. Considering that the difference between the prediction accuracy of the two data sets is very small, on the premise, the key focused indexes can be determined as training time, memory consumption and test time. After screening network data, training time is reduced from 248s of the former to 146s, and compared with the former, the reduction of the training time of the latter reaches 39%. The predicted time consumption of the former is 0.225s, the predicted time consumption of the latter is 0.191s, and the reduction of the predicted time consumption of the latter reaches 15.1% compared with the former. The latter has better performance whether training time or prediction time is consumed. In addition to the consideration in the time dimension, resource consumption is also an important point to be considered. The former consumes 42.0429Mb of memory resources, and because the network data with low correlation is removed, the latter consumes 24.8203Mb of memory resources when training, and the reduction in resource consumption reaches 40.2%.
Fig. 5 shows a schematic diagram of a network state assessment model according to an embodiment of the present disclosure, the method further comprising: obtaining a sample network evaluation index according to the knowledge base and the sample network data; inputting the sample network evaluation index into a network state evaluation model to obtain a sample evaluation parameter for the sample network service; determining the model loss of the network state evaluation model according to the sample evaluation parameters and the actual state of the sample network service; and training the network state evaluation model according to the model loss. In a possible implementation manner, the sample network data may be weighted and summed based on the mapping relationship in the knowledge base to obtain the sample network evaluation index. In the training process, sample network data of preset types in a knowledge base can be input aiming at each sample network evaluation index, and weighted summation is carried out on the basis of the mapping relation to obtain the sample network evaluation index. The present disclosure is not so limited.
In one possible implementation, during training, a corresponding network evaluation index may be selected based on the traffic type. For example, a desired network evaluation index may be determined based on the traffic type, and input of sample network data corresponding to the sample network evaluation index may be received. And obtaining the sample network evaluation index based on the mapping relation between the sample network evaluation index and the sample network data in the knowledge base.
In a possible implementation manner, the sample network evaluation index may be input into a network state evaluation model to obtain a sample evaluation parameter of a sample network service, where the sample evaluation parameter may be used to describe a state of a network, a model loss of the network state evaluation model may be determined based on a difference between the state and an actual state of the sample network service, and then the model loss may be propagated in reverse to adjust parameters of the network state evaluation model, after multiple training, the test may be performed in a test set, and if the model loss is less than or equal to a threshold value during the test, or converges, the training may be completed to obtain the trained network state evaluation model.
In one possible implementation, after obtaining the trained network state evaluation model and knowledge base, the network state evaluation model and knowledge base may be used to determine the network state when a certain network service is executed. In step S11, the current network service may be any network service, and the network data required to be acquired by the current network service may be determined based on the mapping relationship in the knowledge base. Step S11 may include: determining the service type of the current network service; determining a corresponding target service type in the knowledge base according to the service type; determining the type of the corresponding network data according to the target service type; and acquiring the network data corresponding to the current network service according to the type of the network data.
In one possible implementation, the knowledge base may be deployed in a real network environment, and a service type of a current network service, for example, a video service, etc., may be determined, which is not limited by the present disclosure. And further searching in the knowledge base according to the service types to match the corresponding target service types. For example, if the same service type is included in the knowledge base, the type of the network data corresponding to the target service type may be directly used as the network data required for evaluating the network status. If the completely same service type cannot be retrieved, matching the similar service type according to the service category as the target service type, using the type of the network data corresponding to the target service type as the network data required for evaluating the network state, temporarily storing the network data corresponding to the service type in a knowledge base, and if the evaluation result is not accurate, performing corresponding adjustment. Furthermore, the network data of the corresponding type can be acquired by acquiring the network data in the real network environment based on the required network data.
In one possible implementation manner, in step S12, the network state evaluation parameter may be obtained by using the collected network data corresponding to the current network service. For example, network data and traffic types may be input into a network state evaluation model to obtain the network state evaluation parameters.
In one possible implementation, step S12 may include: obtaining a network evaluation index corresponding to the current network service by using the network data and the knowledge base; and inputting the network evaluation index into a network state evaluation model to obtain the network state evaluation parameter.
In an example, the corresponding network evaluation index may be determined based on the service type, and the input of the network data is received based on the network evaluation index and the mapping relationship in the knowledge base, so as to obtain a specific numerical value of the network evaluation index, and determine the network state evaluation parameter based on the specific numerical value. Further, the network state evaluation parameters can be input into the network state evaluation model, and the network state evaluation model can be operated based on the operation mode obtained by training to obtain the network state evaluation parameters. The network state evaluation parameter may evaluate the network state from the perspective of the user's true experience.
In a possible implementation manner, the above obtained network state evaluation parameter may further determine whether the evaluation result is accurate, and in step S13, a network state evaluation result may be obtained to determine whether the evaluation result is accurate. Step S13 may include: obtaining a network utility index according to the resource demand and the actual resource quantity; and obtaining the network state evaluation result according to the network utility index and the network state evaluation parameter.
In one possible implementation, whether the user demand can be satisfied can be determined based on the relationship between the resource demand amount and the actual resource amount, and whether the evaluation of the network state is accurate can be determined based on the result.
In one possible implementation, the network utility index Q may be obtained first based on the resource demand amount and the actual resource amount, for example, the network utility index Q may be determined by the following equation (2):
Figure BDA0003532277290000091
wherein N isrIs the actual amount of resources, N, of the networkaThe resource demand requested for the user. When Q is 1, it indicates that the current network resource can meet the user requirement, and when Q is 0, it indicates that the current network resource cannot meet the user requirement.
In one possible implementation, the network state evaluation parameter E may be utilizedsAnd determining whether the evaluation of the network state is accurate or not according to the network utility index QEvaluation result of collateral Condition EbFor example, the network state evaluation result EbCan be determined by the following equation (3):
Eb＝Q-Es (3)
in one possible implementation, Es∈[0，1]Thus, when Q is 0, Eb∈[-1，0]. At this time EbThe smaller (e.g., less than a certain threshold, or absolute value greater than a certain threshold) then EsThe larger the network state evaluation result EbThe current network state is in a good range, but the actual network state cannot meet the user requirement, and the evaluation of the network state can be considered to be inaccurate.
In one possible implementation, conversely, EbThe greater (e.g., greater than or equal to a certain threshold, or absolute value less than or equal to a certain threshold) EsThe smaller the network state evaluation result EbIndicates that the current network state is in a poor range and the actual network state cannot meet the user requirements, and therefore, the evaluation of the network state, i.e., the network state evaluation parameter E, can be considered to be accuratesClose to the actual state. Therefore, when EbWhen the value is less than 0, the larger the value is, the more accurate the evaluation of the network state is.
In one possible implementation, E is equal to 1 when Qb∈[0，1]. When Eb is smaller (e.g., less than a threshold) then EsThe larger the network state evaluation result EbThe current network state is in a good range, the actual network state can meet the user requirement, and the evaluation of the network state can be considered to be accurate, namely, the network state evaluation parameter EsClose to the actual state.
In one possible implementation, conversely, EbThe greater (e.g., greater than or equal to a certain threshold) EsThe smaller the network state evaluation result EbThe current network state is in a poor range, but the actual network state can meet the user requirements and is in a good range, so that the evaluation of the network state can be considered to be inaccurate. Therefore, when EbIf the value is more than 0, the smaller the value is, the evaluation of the network state is carried outThe more accurate the price.
In a possible implementation manner, based on the above network state evaluation result, it may be determined whether the evaluation of the network state is accurate, that is, whether an accurate network state evaluation parameter E is obtainedsOr whether correct network data is collected, whether correct network evaluation indexes are obtained, whether an accurate knowledge base is obtained, and/or whether an accurate network state evaluation model is obtained. If the evaluation result is not accurate, the type of the network data may be adjusted, the knowledge base is updated, and the network state evaluation model is further trained to improve the accuracy of the evaluation of the network state, and the method further comprises the following steps: and according to the network state evaluation result, adjusting the mapping relation between the service type of the network service and the type of the network data to obtain an adjusted knowledge base. In an example, the type of network data may be increased to promote data dimensionality and thus accuracy of network state evaluation. The manner in which the knowledge base is adjusted is not limited by this disclosure.
In one possible implementation, the adjustment process may be iteratively performed until the accuracy of the network state evaluation meets the requirement. In the process of continuously updating various services in the network, the knowledge base can be continuously updated through the adjustment mode through the network state sensing, the accuracy of network state evaluation is improved, a higher level is kept, in addition, the whole process does not need manual participation, and the consumption of the whole process on time and network resources is greatly reduced while the labor cost is saved.
According to the network state sensing method disclosed by the embodiment of the invention, the network data can be automatically selected according to the knowledge base so as to accurately evaluate the state of the current network, the data dimension of the network data can be reduced, all the network data do not need to be completely collected, the collection amount of the network data can be reduced, the resource overhead is saved, the network state evaluation result can be automatically obtained through the resource demand amount, the actual resource amount and the network state evaluation parameter, the labor cost is reduced, the time span between the data collection and the data analysis is shortened, and the time consistency of the analysis result and the actual network state is improved. The method can better meet the requirements of high reliability and low time delay in a high-complexity and ultra-dense heterogeneous network. And the knowledge base can be continuously updated without manual participation, so that the accuracy of network state evaluation is kept at a higher level.
Fig. 6 is a schematic diagram illustrating an application of a network state awareness method according to an embodiment of the present disclosure, and as shown in fig. 6, the network state awareness method may include multiple stages.
In one possible implementation, in the offline training stage, network data of multiple dimensions may be obtained as an offline data set, and data preprocessing, such as data cleaning, normalization, data correlation analysis, and the like, is performed on the network data in the offline data set. And training the network state evaluation model through the preprocessed data set to obtain the trained network state evaluation model, and establishing a knowledge base comprising a mapping relation between the service type of the network service and the type of the network data.
In one possible implementation, the established knowledge base and the trained network state evaluation model may be applied to an actual network environment. In the autonomous-aware network dynamic-aware phase, current network traffic, e.g., video traffic, etc., may be determined. And inquiring and matching in the knowledge base to determine whether the knowledge base comprises the service type of the current network service, and if so, directly acquiring the network data corresponding to the service type by the perception strategy. If not, the sensing strategy is to determine a similar network service in the service class and take the network data corresponding to the similar network service as the network data to be collected.
In a possible implementation manner, in a network state characterization stage, relevant network data may be collected based on the above sensing strategy, and a network evaluation index is obtained through a trained network state evaluation model, and further, a network state evaluation parameter may be determined.
In one possible implementation, in the characterization result evaluation stage, it may be evaluated whether the network state evaluation parameter is accurate, i.e., whether the actual network state can be accurately represented. For example, a traffic type of a current network traffic may be determined, and resource requirements, that is, a resource requirement amount of a user and an actual resource amount that can be provided in the traffic type, are determined, and then a network utility index is obtained based on formula (2), and a network status evaluation result is obtained based on formula (3), so as to determine whether evaluation of a network status, that is, whether a network status evaluation parameter is accurate, is determined according to the network status evaluation result. And feeds back the previous stages.
In one possible implementation, in the external feedback stage, it may be determined whether the sensing policy is accurate based on the network state evaluation parameter, e.g., whether the network traffic is matched correctly, or whether the data collection is correct, etc., e.g., if the network state evaluation parameter is accurate, the network traffic is considered matched correctly or the data collection is correct. Otherwise, the network service matching is incorrect, or the data collection is incorrect.
In a possible implementation manner, in the internal feedback stage, the evaluation result of the sensing strategy can be obtained, and further analysis is performed based on the evaluation result, for example, the network state evaluation result can be read, and if the sensing strategy is accurate and the network state evaluation result is accurate, the knowledge base does not need to be adjusted; if the perception strategy is not accurate, the perception strategy can be adjusted, data acquisition is carried out again, the network state is evaluated, and then whether the network state evaluation parameters are accurate or not is evaluated; and if the perception strategy is accurate but the network state evaluation result is not accurate, the knowledge base can be adjusted, the mapping relation between the network service and the network data is updated, the network data is collected again, the network state is evaluated, and then whether the network state evaluation parameters are accurate or not is evaluated.
In a possible implementation manner, the feedback processing can be automatically executed to obtain a more accurate knowledge base, the evaluation accuracy of the network state is kept at a higher level in the development of the network service, meanwhile, the labor cost can be saved, the training efficiency is improved, and the resource consumption is reduced.
It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted. Those skilled in the art will appreciate that in the above methods of the specific embodiments, the specific order of execution of the steps should be determined by their function and possibly their inherent logic.
In addition, the present disclosure also provides a network state sensing device, an electronic device, a computer-readable storage medium, and a program, which can be used to implement any one of the network state sensing methods provided by the present disclosure, and reference is made to corresponding descriptions in the method section for corresponding technical solutions and descriptions, which are not described again.
Fig. 7 shows a block diagram of a network state awareness apparatus according to an embodiment of the disclosure, as shown in fig. 7, the apparatus comprising: the network data acquiring module 11 is configured to acquire network data corresponding to a current network service according to a preset knowledge base, where the knowledge base includes a mapping relationship between a service type of the network service and a type of the network data; the evaluation module 12 is configured to obtain a network state evaluation parameter according to the network data, the service type of the current network service, and a pre-trained network state evaluation model; and the evaluation module 13 is configured to determine a network state evaluation result according to the resource demand amount of the current network service, the actual resource amount, and the network state evaluation parameter.
In one possible implementation, the apparatus further includes: the knowledge base establishing module is used for acquiring various types of sample network data according to the sample network service; acquiring a sample network evaluation index corresponding to the sample network service; and acquiring a mapping relation between the sample network evaluation index and the sample network data to establish the knowledge base.
In one possible implementation, the apparatus further includes: the training module is used for obtaining a sample network evaluation index according to the knowledge base and the sample network data; inputting the sample network evaluation index into a network state evaluation model to obtain a sample evaluation parameter of the sample network service; determining model loss of the network state evaluation model according to the sample evaluation parameters and the actual state of the sample network service; and training the network state evaluation model according to the model loss.
In one possible implementation manner, the network data obtaining module is further configured to: determining the service type of the current network service; determining a corresponding target service type in the knowledge base according to the service type; determining the type of the corresponding network data according to the target service type; and acquiring the network data corresponding to the current network service according to the type of the network data.
In one possible implementation, the evaluation module is further configured to: obtaining a network evaluation index corresponding to the current network service by using the network data and the knowledge base; and inputting the network evaluation index into a network state evaluation model to obtain the network state evaluation parameter.
In one possible implementation, the evaluation module is further configured to: obtaining a network utility index according to the resource demand and the actual resource quantity; and obtaining the network state evaluation result according to the network utility index and the network state evaluation parameter.
In one possible implementation, the apparatus further includes: and the adjusting module is used for adjusting the mapping relation between the service type of the network service and the type of the network data according to the network state evaluation result to obtain an adjusted knowledge base.
In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, will not be described again here.
Embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the above-mentioned method. The computer readable storage medium may be a non-volatile computer readable storage medium.
An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to invoke the memory-stored instructions to perform the above-described method.
The disclosed embodiments also provide a computer program product comprising computer readable code, which when run on a device, a processor in the device executes instructions for implementing the network state awareness method provided in any of the above embodiments.
The embodiments of the present disclosure also provide another computer program product for storing computer readable instructions, which when executed cause a computer to perform the operations of the network state awareness method provided in any of the above embodiments.
The electronic device may be provided as a terminal, server, or other form of device.
Fig. 8 illustrates a block diagram of an electronic device 800 in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
Referring to fig. 8, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communications component 816.
The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.
The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense an edge of a touch or slide action, but also detect a duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in the position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in the temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.
Fig. 9 illustrates a block diagram of an electronic device 1900 in accordance with an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. Referring to fig. 9, electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., applications, executable by processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.
The electronic device 1900 may further include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system, such as Windows Server, stored in memory 1932TM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTMOr the like.
In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.
The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
Computer program instructions for carrying out operations of the present disclosure may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.
Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or improvements to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (10)

1. A network state awareness method, comprising:
acquiring network data corresponding to the current network service according to a preset knowledge base, wherein the knowledge base comprises a mapping relation between the service type of the network service and the type of the network data;
obtaining a network state evaluation parameter according to the network data, the service type of the current network service and a pre-trained network state evaluation model;
and determining a network state evaluation result according to the resource demand quantity, the actual resource quantity and the network state evaluation parameter of the current network service.
2. The method of claim 1, further comprising:
acquiring various types of sample network data according to the sample network service;
acquiring a sample network evaluation index corresponding to the sample network service;
and acquiring a mapping relation between the sample network evaluation index and the sample network data to establish the knowledge base.
3. The method of claim 2, further comprising:
obtaining a sample network evaluation index according to the knowledge base and the sample network data;
inputting the sample network evaluation index into a network state evaluation model to obtain a sample evaluation parameter of the sample network service;
determining model loss of the network state evaluation model according to the sample evaluation parameters and the actual state of the sample network service;
and training the network state evaluation model according to the model loss.
4. The method of claim 1, wherein obtaining network data corresponding to the current network service according to a preset knowledge base comprises:
determining the service type of the current network service;
determining a corresponding target service type in the knowledge base according to the service type;
determining the type of the corresponding network data according to the target service type;
and acquiring the network data corresponding to the current network service according to the type of the network data.
5. The method of claim 1, wherein obtaining network state estimation parameters according to the network data and the traffic type of the current network traffic and a pre-trained network state estimation model comprises:
obtaining a network evaluation index corresponding to the current network service by using the network data and the knowledge base;
and inputting the network evaluation index into a network state evaluation model to obtain the network state evaluation parameter.
6. The method of claim 1, wherein determining a network status evaluation result according to the resource demand amount of the current network service, the actual resource amount, and the network status evaluation parameter comprises:
obtaining a network utility index according to the resource demand and the actual resource quantity;
and obtaining the network state evaluation result according to the network utility index and the network state evaluation parameter.
7. The method of claim 1, further comprising:
and according to the network state evaluation result, adjusting the mapping relation between the service type of the network service and the type of the network data to obtain an adjusted knowledge base.
8. A network state aware apparatus, comprising:
the network data acquisition module is used for acquiring network data corresponding to the current network service according to a preset knowledge base, wherein the knowledge base comprises a mapping relation between the service type of the network service and the type of the network data;
the evaluation module is used for obtaining a network state evaluation parameter according to the network data, the service type of the current network service and a pre-trained network state evaluation model;
and the evaluation module is used for determining a network state evaluation result according to the resource demand quantity, the actual resource quantity and the network state evaluation parameter of the current network service.
9. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having computer program instructions stored thereon, which when executed by a processor implement the method of any one of claims 1 to 7.
CN202210208897.1A 2022-03-04 2022-03-04 Network state sensing method and device, electronic equipment and storage medium Pending CN114599042A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210208897.1A CN114599042A (en) 2022-03-04 2022-03-04 Network state sensing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210208897.1A CN114599042A (en) 2022-03-04 2022-03-04 Network state sensing method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114599042A true CN114599042A (en) 2022-06-07

Family

ID=81815177

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210208897.1A Pending CN114599042A (en) 2022-03-04 2022-03-04 Network state sensing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114599042A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124321A (en) * 2017-07-10 2017-09-01 山东浪潮商用系统有限公司 A kind of network operation condition predicting model based on big data
CN110390387A (en) * 2018-04-20 2019-10-29 伊姆西Ip控股有限责任公司 Deep learning application used resource is assessed
CN111294819A (en) * 2018-12-07 2020-06-16 中国移动通信集团陕西有限公司 Network optimization method and device
US20210012239A1 (en) * 2019-07-12 2021-01-14 Microsoft Technology Licensing, Llc Automated generation of machine learning models for network evaluation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107124321A (en) * 2017-07-10 2017-09-01 山东浪潮商用系统有限公司 A kind of network operation condition predicting model based on big data
CN110390387A (en) * 2018-04-20 2019-10-29 伊姆西Ip控股有限责任公司 Deep learning application used resource is assessed
CN111294819A (en) * 2018-12-07 2020-06-16 中国移动通信集团陕西有限公司 Network optimization method and device
US20210012239A1 (en) * 2019-07-12 2021-01-14 Microsoft Technology Licensing, Llc Automated generation of machine learning models for network evaluation

Similar Documents

Publication Publication Date Title
EP3886004A1 (en) Method for training classification model, classification method and device, and storage medium
CN110782034A (en) Neural network training method, device and storage medium
CN109412900A (en) A kind of network state knows the method and device of method for distinguishing, model training
CN109684047A (en) Event-handling method, device, equipment and computer storage medium
WO2019184640A1 (en) Indicator determination method and related device thereto
KR20070112281A (en) Apparatus and methods for product acceptance testing on a wireless device
CN108875993B (en) Invitation behavior prediction method and device
WO2019062405A1 (en) Application program processing method and apparatus, storage medium, and electronic device
WO2019062369A1 (en) Application management method and apparatus, storage medium, and electronic device
JP7342942B2 (en) METHODS, DEVICES AND COMPUTER PROGRAM PRODUCTS
CN110019382A (en) User's cohesion index determines method, apparatus, storage medium and electronic equipment
CN111461304A (en) Training method for classifying neural network, text classification method, text classification device and equipment
CN114760339A (en) Fault prediction method, apparatus, device, medium, and product
CN110309357A (en) Using the method for data recommendation, the method, apparatus of model training and storage medium
CN113038501B (en) Network link optimization method and device and electronic equipment
US20230004776A1 (en) Moderator for identifying deficient nodes in federated learning
CN110969240A (en) Pruning method, device, equipment and medium for deep convolutional neural network
US11990057B2 (en) Electronic infrastructure for digital content delivery and/or online assessment management
CN113132136B (en) Satisfaction degree prediction model establishment method, satisfaction degree prediction device and electronic equipment
CN113052198B (en) Data processing method, device, equipment and storage medium
CN112783779A (en) Test case generation method and device, electronic equipment and storage medium
CN114599042A (en) Network state sensing method and device, electronic equipment and storage medium
EP4349055A2 (en) Dimensioning of telecommunication infrastructure
CN114510305A (en) Model training method and device, storage medium and electronic equipment
CN112256892A (en) Video recommendation method and device, electronic equipment and storage medium

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