CN110912768A - Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance - Google Patents
Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance Download PDFInfo
- Publication number
- CN110912768A CN110912768A CN201911061765.5A CN201911061765A CN110912768A CN 110912768 A CN110912768 A CN 110912768A CN 201911061765 A CN201911061765 A CN 201911061765A CN 110912768 A CN110912768 A CN 110912768A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- network
- evaluation index
- index
- fuzzy
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0811—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0829—Packet loss
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
- H04L43/087—Jitter
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0888—Throughput
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application relates to a gray correlation and fuzzy evaluation method and system for multi-path transmission network performance. The method comprises the following steps: acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information; calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment; selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network; and determining the performance of each network in the multi-path network according to the final evaluation result. The network performance analysis method can greatly improve the evaluation accuracy.
Description
Technical Field
The application relates to the technical field of network transmission, in particular to a gray correlation and fuzzy evaluation method and system for multi-path transmission network performance.
Background
In recent years, with The continuous development of network technology, video services have been developed rapidly, and various types of videos, such as ott (over The top) videos, live videos, and The like, have been emerging. In the video service, video transmission is a key loop, and the effect of video playing is directly influenced. The MPTCP multi-path parallel transmission technology refers to the technology that video data can be transmitted through a plurality of paths simultaneously in the video transmission process, the bandwidth is aggregated, and the network transmission rate is improved. Although the multi-path transmission technique has many transmission advantages, in actual network transmission, the transmission performance (e.g., efficiency, etc.) of the multi-path transmission path needs to be evaluated. However, currently, the main evaluation indexes of the communication performance of the traditional live video network are some network performance comprehensive evaluation methods under single-path transmission, which mainly include a triangular fuzzy number analytic hierarchy process, a linear weighting method, a principal component analysis method, a fuzzy comprehensive evaluation method, a BP neural network method and an improved support vector machine method. Wherein, the fuzzy analytic hierarchy process and the linear weighting process determine the weight by a subjective method, which causes subjective deviation; the principal component analysis method solves the problem of determining the evaluation weight, but can cause information loss; the fuzzy comprehensive evaluation method cannot solve the evaluation problem of relevance of fuzziness and randomness in the evaluation process; the BP neural network method and the improved support vector machine method adopt a fuzzy comprehensive evaluation method to obtain an evaluation value and then train and establish a model, and the quality of the model is limited by the fuzzy comprehensive evaluation method. These models cannot be used in multi-path networks. Therefore, at present, there is no modeling method for measuring or evaluating the network quality under the multipath transmission network and verifying the network quality through the actual network environment, so as to evaluate the video watching experience of the user to a certain extent.
Disclosure of Invention
In view of the above, it is necessary to provide a gray correlation and fuzzy evaluation method, system, computer device and storage medium capable of solving the performance evaluation of the multi-path transmission network.
A gray correlation and fuzzy evaluation method for multi-path transmission network performance, the method comprising:
acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network;
and determining the performance of each network in the multi-path network according to the final evaluation result.
In one embodiment, the method for establishing the network performance evaluation model includes:
establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set;
analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method, and establishing a fuzzy relation matrix;
and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
In one embodiment, before the step of analyzing each evaluation index in the evaluation index set by using a gray correlation analysis method to obtain a weight sequence of the evaluation index, the method further includes:
normalizing the evaluation indexes in the evaluation index set;
carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index;
and obtaining an evaluation index weight sequence according to the weight of each evaluation index.
In one embodiment, the step of performing weight calculation on the normalized evaluation indexes to obtain the weight of each evaluation index includes:
determining an optimal evaluation index sequence;
calculating a correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence;
calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient;
and calculating the weight of each evaluation index according to each relevance.
In one embodiment, the step of normalizing the evaluation indexes in the evaluation index set includes:
and normalizing the evaluation indexes in the evaluation index set by adopting a cost index normalization method and an efficiency index normalization method.
In one embodiment, the step of performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by using a membership function model to obtain a network performance evaluation model includes:
and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a triangular membership function model to obtain a network performance evaluation model.
A gray correlation and fuzzy evaluation system for multi-path transmission network performance, the system comprising:
the information acquisition module is used for acquiring the multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
the membership vector value calculation module is used for calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
the final evaluation result selection module is used for selecting the evaluation comment corresponding to the largest membership vector value as the final evaluation result of each network;
and the network performance determining module is used for determining the performance of each network in the multi-path network according to the final evaluation result.
In one embodiment, the method further comprises the following steps:
the network system construction module is used for establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set;
the evaluation index weight sequence obtaining module is used for analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
the fuzzy relation matrix establishing module is used for analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method and establishing a fuzzy relation matrix;
and the network performance evaluation model obtaining module is used for carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance is used for recording the relationship between the network evaluation index and the membership degree vector of the evaluation comment;
selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network;
and determining the performance of each network in the multi-path network according to the final evaluation result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance is used for recording the relationship between the network evaluation index and the membership degree vector of the evaluation comment;
selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network;
and determining the performance of each network in the multi-path network according to the final evaluation result.
The gray correlation and fuzzy evaluation method, system, computer equipment and storage medium for the multi-path transmission network performance firstly acquire multi-path transmission network information to be evaluated, wherein the multi-path network information comprises network quantity information and network evaluation index information, and each piece of network quantity information corresponds to the network evaluation index information one by one; and then inputting the network quantity information and the network evaluation index information into a pre-established network performance evaluation model, calculating to obtain a membership vector value of each evaluation comment of each network, selecting the evaluation comment corresponding to the maximum value in the membership vector as a final evaluation result of the network, and finally determining the network performance according to the final evaluation result. The network performance analysis method analyzes the established multipath transmission network by adopting a gray correlation analysis method and a fuzzy comprehensive analysis method, accurately finds out indexes influencing the network performance, and constructs a network performance evaluation model on the basis of the indexes as evaluation indexes.
Drawings
Fig. 1 is a schematic diagram of an application environment of a gray correlation and fuzzy evaluation method for multi-path transmission network performance according to an embodiment;
FIG. 2 is a flow diagram of a gray correlation and fuzzy evaluation method for multi-path transmission network performance in one embodiment;
fig. 3 is a schematic flow chart of a pre-established gray correlation and fuzzy evaluation method for multi-path transmission network performance in an embodiment;
FIG. 4 is a diagram illustrating an evaluation index and an evaluation comment membership of a network to be evaluated according to an embodiment;
FIG. 5 is a diagram of a live platform system in another embodiment;
fig. 6 is a schematic diagram of a variation curve of measured traffic of the network 1 with time in one embodiment;
fig. 7 is a schematic diagram of a variation curve of measured traffic of the network 2 with time in one embodiment;
fig. 8 is a schematic diagram of a variation curve of measured traffic of the network 3 with time in one embodiment;
fig. 9 is a schematic diagram of a measured traffic versus time curve of the network 4 in one embodiment;
fig. 10 is a schematic diagram illustrating a variation curve of the measured traffic of the network 5 with time according to an embodiment;
FIG. 11 is a block diagram of a gray correlation and fuzzy evaluation system for multi-path transmission network performance in accordance with an embodiment;
FIG. 12 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method is applied to the terminal 102 in fig. 1, the terminal may be a personal computer, a notebook computer, or the like, the terminal 102 is in communication connection with the detection device 104, and the detection device 104 is usually a network collector or the like. When the terminal 102 and the detection device 104 are connected by a local interface, the detection device 104 may send the acquired multipath transmission network information to be evaluated to the terminal 102.
In one embodiment, as shown in fig. 2, a gray correlation and fuzzy evaluation method for multipath transmission network performance is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
step S202, obtaining multipath transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
the multipath transmission network to be evaluated is a multipath transmission network which needs to be subjected to network performance testing, the multipath transmission network comprises at least two transmission networks, the larger the number of the transmission networks, the more the transmitted data information is, the information transmission speed can be improved to a certain extent, but the performances of all the networks are different, namely, some networks have good performances, and some networks have extremely poor performances, so that the networks need to be selected when in use. The multi-path transmission network information refers to basic information about a multi-path transmission network, and includes, for example, network type information, network number information (i.e., how many networks there are, the name of each network, etc.), and network evaluation index information (i.e., the type of an index affecting the network performance, and data of each evaluation index).
Step S204, calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
specifically, the gray correlation analysis method refers to a measure of the magnitude of the correlation between two systems, which varies with time or different objects, and is called correlation. In the system development process, if the trends of the two factors are consistent, namely the synchronous change degree is higher, the correlation degree of the two factors is higher; otherwise, it is lower. Therefore, the gray correlation analysis method is a method for measuring the degree of correlation between the factors according to the similarity or difference of the development trends between the factors, i.e., "gray correlation". The grey system theory proposes a concept of grey correlation analysis for each subsystem, and aims to find a numerical relationship between subsystems (or factors) in the system through a certain method.
A fuzzy comprehensive analysis method, also called as a fuzzy comprehensive evaluation method, is a comprehensive evaluation method based on fuzzy mathematics. The comprehensive evaluation method converts qualitative evaluation into quantitative evaluation according to the membership theory of fuzzy mathematics, namely, fuzzy mathematics is used for making overall evaluation on objects or objects restricted by various factors. The method has the characteristics of clear result and strong systematicness, can better solve the problems of fuzziness and difficult quantization, and is suitable for solving various non-determinacy problems.
In this embodiment, a gray correlation analysis method and a fuzzy comprehensive analysis method are adopted to analyze the weight of each index in the network evaluation indexes, and then the indexes are arranged according to the weight (i.e. the order of the influence of each index on the network performance); then, establishing an evaluation matrix by a fuzzy comprehensive analysis method, and determining an evaluation comment; and constructing a network performance evaluation model according to the network evaluation index weight ranking and the evaluation matrix. When the network performance evaluation is needed, the corresponding evaluation result can be obtained only by inputting the corresponding data. In this embodiment, the membership vector value of the evaluation comment is selected as an evaluation result, that is, the network to be evaluated and the data corresponding to the network evaluation index are input into the network performance evaluation model, and the membership vector value of each evaluation comment corresponding to the network to be evaluated can be obtained. Among them, there are a plurality of evaluation comments.
Step S206, selecting the evaluation comment corresponding to the maximum membership vector value as the final evaluation result of each network;
and step S208, determining the performance of each network in the multi-path network according to the final evaluation result.
In this embodiment, the evaluation comment corresponding to the maximum value of the membership vector value is determined as the final evaluation result of each network, and the performance of each network can be determined according to the final evaluation result. In addition, the evaluation comments can be quantified when the performance of each network is determined according to the final evaluation result, so that the comprehensive scores of each network are directly calculated, and then the optimal network can be selected according to the scores.
The gray correlation and fuzzy evaluation method of the multi-path transmission network performance comprises the steps of firstly, obtaining multi-path transmission network information to be evaluated, wherein the multi-path network information comprises network quantity information and network evaluation index information, and each piece of network quantity information corresponds to the network evaluation index information one by one; and then inputting the network quantity information and the network evaluation index information into a pre-established network performance evaluation model, calculating to obtain a membership vector value of each evaluation comment of each network, selecting the evaluation comment corresponding to the maximum value in the membership vector as a final evaluation result of the network, and finally determining the network performance according to the final evaluation result. The network performance analysis method analyzes the established multipath transmission network by adopting a gray correlation analysis method and a fuzzy comprehensive analysis method, accurately finds out indexes influencing the network performance, and constructs a network performance evaluation model on the basis of the indexes as evaluation indexes.
In one embodiment, as shown in fig. 3, the establishment method of the network performance evaluation model includes:
step S302, a multi-path transmission network is established, an evaluation index is selected to construct an evaluation index set, and an evaluation comment is selected to construct an evaluation comment set;
establishing a multipath transmission network by establishing a multipath transmission network value, and then determining a network set according to the multipath transmission network, namely X, wherein l network objects in X are marked as X1-xl. Then selecting the evaluation indexes to determine an evaluation index set as U, wherein m indexes are recorded as U1-um(ii) a Selecting evaluation comments to construct an evaluation comment set V, wherein n comments are marked as V1-vn. In addition, the evaluation indexes comprise time delay, jitter, throughput, packet loss rate, communication rate and the like; the assessment comments include excellent, good, acceptable, poor, very poor, etc.
Step S304, analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
the weight of the network evaluation index (such as time delay, jitter, throughput, packet loss rate, connectivity rate, etc.) refers to the degree of influence of each index value on the network performance. And determining the index association degree, namely the proximity degree between each index and the optimal index by a grey association analysis method. The closer the degree is, the greater the degree of the index influencing the network performance is, namely the index weight is greater; conversely, the smaller the proximity, the smaller the final index weight. In this embodiment, weights of network evaluation indexes such as time delay, jitter, throughput, packet loss rate, and connectivity rate are analyzed by using a gray correlation analysis method, and then are sorted according to the weights to obtain an evaluation index weight sequence.
Step S306, analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method, and establishing a fuzzy relation matrix;
specifically, for each network to be evaluated (i.e., each network to be evaluated), the comment corresponding to the evaluation index value is ambiguous. Therefore, each evaluated network can construct a fuzzy relation matrix of each evaluation comment corresponding to each evaluation index. In this embodiment, a fuzzy comprehensive analysis method is used to construct a fuzzy relationship matrix of each evaluation comment under each evaluation index.
And S308, performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
The membership function model is determined according to membership functions, and the membership functions at least comprise 5 types, namely each evaluation comment corresponds to at least one membership evaluation function.
In a preferred embodiment, the step of performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by using a membership function model to obtain a network performance evaluation model includes: and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a triangular membership function model to obtain a network performance evaluation model.
In this embodiment, a triangular membership function is used to perform fuzzy operation modeling. Let the length of the base of the triangle membership function be 1.6, and the constant values be 0, 0.2, 0.4, 0.6, 0.8, and 1, respectively, as shown in fig. 4. The assessment scores were excellent, good, qualified, poor, very poor. For example, if a certain index of the evaluation network is equal to 0.8, the index value is 1, 0.75, 0.5, 0.25, 0 for excellent, good, qualified, bad, and bad membership degrees according to fig. 4. The network performance evaluation model constructed by the method is simple and intuitive, on one hand, the operation is simple, and on the other hand, the result can be intuitively seen from the graph.
In one embodiment, before the step of analyzing each evaluation index in the evaluation index set by using a gray correlation analysis method to obtain a weight sequence of the evaluation indexes, the method further includes:
normalizing the evaluation indexes in the evaluation index set; carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index; and obtaining an evaluation index weight sequence according to the weight of each evaluation index.
In this embodiment, to solve the dimensional difference between the evaluation indexes, normalization processing must be performed on the indexes before evaluation; after normalization, weights of the evaluation indexes are calculated, and then the evaluation indexes are arranged according to the weights (usually, the evaluation indexes are arranged in descending order of the weights), so that an evaluation index weight sequence can be obtained.
In a preferred embodiment, the step of normalizing the evaluation indexes in the evaluation index set includes: and normalizing the evaluation indexes in the evaluation index set by adopting a cost index normalization method and an efficiency index normalization method.
In this embodiment, the evaluation index is normalized by using two normalization methods, respectively.
In one embodiment, the step of performing weight calculation on the normalized evaluation indexes to obtain the weight of each evaluation index includes:
determining an optimal evaluation index sequence; calculating a correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence; calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient; and calculating the weight of each evaluation index according to each association degree.
In order to facilitate understanding of the manner in which the network performance evaluation model is built, a detailed embodiment is given. The method comprises the following specific steps: (a) let the evaluation network set be X, wherein there are l network objects in X, and mark as X1-xl. The evaluation index set is U, and m indexes are recorded as U1-umThe evaluation comment set is V, and n comments are recorded as V1-vn. (b) In order to solve the dimensional difference between the evaluation network index values, the indexes need to be normalized before evaluation. Let the jth evaluation index ujThe variation range is [ u ]j min，uj max]Then the cost index is normalized to:
wherein u isij(i 1,2, …, l, j 1,2, …, m) is the j index value in the i evaluation network; and the benefit index is normalized as follows:
(3) network commentThe weight of the estimated index (such as time delay, jitter, throughput, packet loss rate, connectivity rate, etc.) refers to the degree of influence of each index value on the network performance. And determining the index association degree, namely the proximity degree between each index and the optimal index through grey association analysis. The closer the degree is, the greater the degree of the index influencing the network performance is, namely the index weight is greater; conversely, the smaller the proximity, the smaller the final index weight. The network performance index weight calculation process is specifically as follows: 1) determining an optimal index sequence:
in the formula uj ＊And normalizing the processed result of the optimal value of the jth evaluation index in all the evaluation networks. When the index u1Is time delay, then uij *Selecting the minimum value of time delay in the evaluation index set as the optimal index of time delay, and normalizing to obtain u1 *Otherwise, using the benefit type index, and taking the maximum value of the index as the optimal index; 2) calculating grey correlation coefficients, and respectively obtaining the correlation coefficients between the jth evaluation index and the optimal index value of the ith evaluation network:
in the formula: rho is equal to [0,1 ]]Generally, ρ is 0.5; 3) and (3) calculating the index association degree: calculating the association degree between each evaluation intuition and the optimal index value, and after the jth index value of the evaluated object is averaged, obtaining the association degree between the jth evaluation index and the optimal index value:
4) converting the relevance degree into weight, and performing normalization processing to obtain index weight sequence A ═ a (a)1,a2,…,am) Wherein:
d) for each network object, the assessment comment corresponding to the assessment index is ambiguous. Thus, each network object maySo as to construct a fuzzy relation matrix corresponding to the evaluation comment under each evaluation index. The membership functions for the category 5 comments are shown in table 1. In Table 1, rjk(i) For the ith network object xiMiddle j index ujCorresponding grade vkThe degree of membership of (a) can be finally determined as a fuzzy relation matrix r (i) ═ rjk(i))m×nWherein table 1 is a membership function corresponding to the category 5 assessment comments, and the specific contents are shown in the following table:
table 1 shows membership functions corresponding to 5-type assessment comments
e) The method adopts a matrix operation model to perform fuzzy operation on the index weight sequence A and the fuzzy relation matrix R (i), namely:
after normalization processing, b is selected according to the maximum membership principlek(i) The evaluation comment corresponding to the maximum value in (1) is used as the final comment. Quantifying the evaluation comment set V and respectively giving specific scores Vk. Finally, the expression of the comprehensive score is recorded as:
verification examples
In order to verify the effectiveness of the gray correlation and fuzzy evaluation method of the multipath transmission network performance, an effect embodiment is provided. In this embodiment, the live broadcast platforms in fig. 5 are taken as an example to evaluate the network performance of the multipath transmission network formed between the live broadcast platforms. The Push end in fig. 5 is a video coding server, and is used for encoding a video source file into a video data stream in FFMPEG. The MPTCP protocol stack in the Server encapsulates the video data stream of the application layer into an MPTCP protocol packet for multi-path transmission, and the video data stream reaches a Server end, i.e. a video stream Server end in fig. 5, and the specific implementation manner is as follows: (1) creating a main connection of MPTCP protocol data, adding a new MPTCP data connection sub-stream to a network connection except the main connection at the two ends of a video coding server and a video stream server, and sending data packets through a plurality of TCP sub-streams by using a polling packet scheduling algorithm to achieve the effect of concurrent transmission; (2) in the transmission process, if the single network connection breaks down to generate cutoff, other network connections can automatically bear the data volume of the disconnected network connection, and the effect of smooth transition and no cutoff of the whole transmission is achieved. Network evaluation is carried out on the live broadcast system by adopting a pre-established network performance evaluation model; specifically, an evaluation network set X in the live broadcast system has 5 networks, which are respectively marked as a network 1, a network 2, a network 3, a network 4 and a network 5; the elements in the evaluation index set U are time delay, time delay jitter, packet loss rate, communication rate and throughput; the elements in the assessment comment set V were excellent, good, qualified, bad, very bad, assigned values of 90,80,60,50,40, respectively. The performance of each network was evaluated using a grey fuzzy evaluation model, and table 2 shows the values of each evaluation index for that network. The network 1 is a local area network environment, and the networks 2 to 5 are real network environments simulated by a Nornet international test bed, wherein: network 1: for the local area network environment, the city where the Push, the Server and the Client end are located is a haikou; and 2, network 2: the cities where the Push, Server and Client terminals are located are respectively as follows: push: bergenderver, Trondheimclient, Haikou; network 3: push, Bergen server, Trondheim client, Kristianstrand; and (4) network: push, narvik server, haikouclient, trondheim; and (5) network: push: haikou server: bergen client: essen. Table 2 shows the values of the evaluation indexes in the 5 evaluation networks, which are as follows:
table 2 shows the values of the evaluation indexes in the 5 evaluation networks
The gray weight vector a obtained by calculation is (0.2204, 0.1715, 0.2211, 0.1933, 0.1937), and the influence of packet loss rate and time delay on the network performance is large in view of the weight sequence; the delay jitter has minimal impact on network performance. Finally, the membership vector of each network corresponding to each comment is obtained, as shown in table 3 below:
table 3 shows membership vectors of 5 evaluation networks corresponding to each comment
| Network set | Is excellent in | Good effect | Qualified | Difference (D) | Is very poor |
| B(1) | 0.3654 | 0.2857 | 0.1823 | 0.1529 | 0.0684 |
| B(2) | 0.2237 | 0.2484 | 0.1806 | 0.2640 | 0.1242 |
| B(3) | 0.2470 | 0.2826 | 0.2065 | 0.1657 | 0.0865 |
| B(4) | 0.0750 | 0.1556 | 0.2283 | 0.2826 | 0.2855 |
| B(5) | 0.2153 | 0.2189 | 0.2439 | 0.1724 | 0.1195 |
From the membership result vector, each network has five membership vector scores, wherein the maximum membership score determines the network's rank. For example, the five membership-degree comment values of the network 1 are respectively: 0.3654, 0.2857, 0.1823, 0.1529 and 0.0684, wherein the maximum value is 0.3654, the corresponding comment value is excellent grade, and the final evaluation result of the network 1 is excellent according to the maximum membership rule; the five membership scores of the network 4 are respectively: 0.0750, 0.1556, 0.2283, 0.2826, 0.2855 with a maximum value of 0.2855, the corresponding comment rating was poor. Similarly, network 3 is good, network 5 is good, and network 2 is bad. Finally, 5 network performance comprehensive scores of 74.88, 58.43, 68.23, 54.13 and 63.15 are obtained through a comprehensive score calculation formula, and the performance sequences are sequentially network 1, network 3, network 5, network 2 and network 4.
In addition, fig. 6 to fig. 10 are schematic diagrams of visual expression of actual data traffic results of the client under 5 different network test scenarios in table 2, and it can be known from the diagrams that the method of the present invention is substantially consistent with the actually measured visual expression results, which indicates that the model is effective and feasible.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Also, at least some of the steps in fig. 2-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at each time, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 11, a gray correlation and fuzzy evaluation system for performance of a multi-path transmission network is provided, including:
an information obtaining module 110, configured to obtain multipath transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
a membership vector value calculation module 112, configured to calculate a membership vector value of each evaluation comment corresponding to each network in the multipath network according to the network quantity information, the network evaluation index information, and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
a final evaluation result selection module 114, configured to select the evaluation comment corresponding to the largest membership vector value as the final evaluation result of each network;
and a network performance determining module 116, configured to determine performance of each network in the multi-path network according to the final evaluation result.
In one embodiment, the method further comprises the following steps: the network system construction module is used for establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set;
the evaluation index weight sequence obtaining module is used for analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
the fuzzy relation matrix establishing module is used for analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method and establishing a fuzzy relation matrix;
and the network performance evaluation model obtaining module is used for carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
In one embodiment, the method further comprises the following steps:
the normalization module is used for performing normalization processing on the evaluation indexes in the evaluation index set;
the weight calculation module is used for carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index;
and the evaluation index weight sequence obtaining module is also used for obtaining an evaluation index weight sequence according to the weight of each evaluation index.
In one embodiment, the weight calculation module comprises: the evaluation index sequence determination module is used for determining an optimal evaluation index sequence;
the correlation coefficient calculation module is used for calculating the correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence;
the association degree calculation module is used for calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient;
and the weight calculation module is also used for calculating the weight of each evaluation index according to each association degree.
In one embodiment, the normalization module is further configured to normalize the evaluation indexes in the evaluation index set by using a cost index normalization method and a performance index normalization method.
In one embodiment, the network performance evaluation model obtaining module is further configured to perform fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by using a triangular membership function model to obtain the network performance evaluation model.
For the specific definition of the gray correlation and fuzzy evaluation system for the performance of the multipath transmission network, reference may be made to the above definition of the gray correlation and fuzzy evaluation method for the performance of the multipath transmission network, and details are not described herein again. The various modules in the gray correlation and fuzzy evaluation system for the performance of the multi-path transmission network can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 12. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data of the resistance equivalent model and the equivalent submodel, and storing equivalent resistance, working resistance and contact resistance obtained in the process of executing calculation. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a gray correlation and fuzzy evaluation method for multi-path transmission network performance.
Those skilled in the art will appreciate that the architecture shown in fig. 12 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have an arrangement of components for each.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information; calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment; selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network; and determining the performance of each network in the multi-path network according to the final evaluation result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the establishment method of the network performance evaluation model comprises the following steps: establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set; analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence; analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method, and establishing a fuzzy relation matrix; and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: before the step of analyzing each evaluation index in the evaluation index set by using a grey correlation analysis method to obtain an evaluation index weight sequence, the method further comprises the following steps: normalizing the evaluation indexes in the evaluation index set; carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index; and obtaining an evaluation index weight sequence according to the weight of each evaluation index.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the step of performing weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index includes: determining an optimal evaluation index sequence; calculating a correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence; calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient; and calculating the weight of each evaluation index according to each relevance.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the step of normalizing the evaluation indexes in the evaluation index set includes: and normalizing the evaluation indexes in the evaluation index set by adopting a cost index normalization method and an efficiency index normalization method.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the step of performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model comprises the following steps: and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a triangular membership function model to obtain a network performance evaluation model.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information; calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment; selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network; and determining the performance of each network in the multi-path network according to the final evaluation result.
In one embodiment, the computer program when executed by the processor further performs the steps of: the establishment method of the network performance evaluation model comprises the following steps: establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set; analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence; analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method, and establishing a fuzzy relation matrix; and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
In one embodiment, the computer program when executed by the processor further performs the steps of: before the step of analyzing each evaluation index in the evaluation index set by using a grey correlation analysis method to obtain an evaluation index weight sequence, the method further comprises the following steps: normalizing the evaluation indexes in the evaluation index set; carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index; and obtaining an evaluation index weight sequence according to the weight of each evaluation index.
In one embodiment, the computer program when executed by the processor further performs the steps of: the step of performing weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index includes: determining an optimal evaluation index sequence; calculating a correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence; calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient; and calculating the weight of each evaluation index according to each relevance.
In one embodiment, the computer program when executed by the processor further performs the steps of: the step of normalizing the evaluation indexes in the evaluation index set includes: and normalizing the evaluation indexes in the evaluation index set by adopting a cost index normalization method and an efficiency index normalization method.
In one embodiment, the computer program when executed by the processor further performs the steps of: the step of performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model comprises the following steps: and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a triangular membership function model to obtain a network performance evaluation model.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may comprise processes such as those of the embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, the scope of the present description should be considered as being described in the present specification.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A gray correlation and fuzzy evaluation method for multi-path transmission network performance, the method comprising:
acquiring multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
selecting the evaluation comment corresponding to the maximum membership vector value as a final evaluation result of each network;
and determining the performance of each network in the multi-path network according to the final evaluation result.
2. The method of claim 1, wherein the network performance evaluation model is established in a manner that includes:
establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set;
analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method, and establishing a fuzzy relation matrix;
and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
3. The method of claim 2, wherein the step of analyzing each evaluation index in the set of evaluation indexes by using a gray correlation analysis method to obtain a weighted sequence of evaluation indexes is preceded by the step of:
normalizing the evaluation indexes in the evaluation index set;
carrying out weight calculation on the evaluation indexes after the normalization processing to obtain the weight of each evaluation index;
and obtaining an evaluation index weight sequence according to the weight of each evaluation index.
4. The method according to claim 3, wherein the step of performing weight calculation on the normalized evaluation indexes to obtain the weight of each evaluation index comprises:
determining an optimal evaluation index sequence;
calculating a correlation coefficient between each evaluation index and the corresponding optimal evaluation index in the optimal evaluation index sequence;
calculating the association degree of each evaluation index and the corresponding optimal evaluation index according to the association coefficient;
and calculating the weight of each evaluation index according to each relevance.
5. The method according to claim 3, wherein the step of normalizing the evaluation indexes in the evaluation index set comprises:
and normalizing the evaluation indexes in the evaluation index set by adopting a cost index normalization method and an efficiency index normalization method.
6. The method according to any one of claims 2 to 5, wherein the step of performing fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by using a membership function model to obtain a network performance evaluation model comprises:
and carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a triangular membership function model to obtain a network performance evaluation model.
7. A gray correlation and fuzzy evaluation system for multi-path transmission network performance, the system comprising:
the information acquisition module is used for acquiring the multi-path transmission network information to be evaluated; the multi-path transmission network information comprises network quantity information and network evaluation index information;
the membership vector value calculation module is used for calculating the membership vector value of each evaluation comment corresponding to each network in the multi-path network according to the network quantity information, the network evaluation index information and a pre-established network performance evaluation model; the pre-established network performance model is established by analyzing the established multi-path transmission network by adopting a grey correlation analysis method and a fuzzy comprehensive analysis method and is used for recording the relation between the network evaluation index and the membership degree vector of the evaluation comment;
the final evaluation result selection module is used for selecting the evaluation comment corresponding to the largest membership vector value as the final evaluation result of each network;
and the network performance determining module is used for determining the performance of each network in the multi-path network according to the final evaluation result.
8. The system of claim 7, further comprising:
the network system construction module is used for establishing a multi-path transmission network, selecting an evaluation index to construct an evaluation index set, and selecting an evaluation comment to construct an evaluation comment set;
the evaluation index weight sequence obtaining module is used for analyzing each evaluation index in the evaluation index set by adopting a grey correlation analysis method to obtain an evaluation index weight sequence;
the fuzzy relation matrix establishing module is used for analyzing the evaluation indexes in the evaluation index set and the evaluation comments in the evaluation comment set by adopting a fuzzy comprehensive analysis method and establishing a fuzzy relation matrix;
and the network performance evaluation model obtaining module is used for carrying out fuzzy operation modeling on the evaluation index weight sequence and the fuzzy relation matrix by adopting a membership function model to obtain a network performance evaluation model.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911061765.5A CN110912768A (en) | 2019-11-01 | 2019-11-01 | Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911061765.5A CN110912768A (en) | 2019-11-01 | 2019-11-01 | Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110912768A true CN110912768A (en) | 2020-03-24 |
Family
ID=69816305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911061765.5A Pending CN110912768A (en) | 2019-11-01 | 2019-11-01 | Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110912768A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111581642A (en) * | 2020-05-03 | 2020-08-25 | 付贵龙 | Internet safety protection system |
| CN111861284A (en) * | 2020-08-06 | 2020-10-30 | 城云科技（中国）有限公司 | Risk assessment and early warning method for social management unit |
| CN112637132A (en) * | 2020-12-01 | 2021-04-09 | 北京邮电大学 | Network anomaly detection method and device, electronic equipment and storage medium |
| CN113271256A (en) * | 2021-04-06 | 2021-08-17 | 北京邮电大学 | Information age multi-path transmission method and system |
| CN113541993A (en) * | 2020-04-21 | 2021-10-22 | ***通信集团四川有限公司 | Network evaluation method and device, network index processing method, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8903995B1 (en) * | 2012-07-19 | 2014-12-02 | Netapp, Inc. | Performance impact analysis of network change |
| CN104331773A (en) * | 2014-11-05 | 2015-02-04 | 国家电网公司 | Comprehensive assessment method for power network planning schemes |
-
2019
- 2019-11-01 CN CN201911061765.5A patent/CN110912768A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8903995B1 (en) * | 2012-07-19 | 2014-12-02 | Netapp, Inc. | Performance impact analysis of network change |
| CN104331773A (en) * | 2014-11-05 | 2015-02-04 | 国家电网公司 | Comprehensive assessment method for power network planning schemes |
Non-Patent Citations (1)
| Title |
|---|
| 钟赟等: "基于灰色关联的网络性能模糊评估", 《空军工程大学学报（自然科学版）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113541993A (en) * | 2020-04-21 | 2021-10-22 | ***通信集团四川有限公司 | Network evaluation method and device, network index processing method, equipment and medium |
| CN113541993B (en) * | 2020-04-21 | 2023-08-18 | ***通信集团四川有限公司 | Network evaluation method and device, network index processing method, device and medium |
| CN111581642A (en) * | 2020-05-03 | 2020-08-25 | 付贵龙 | Internet safety protection system |
| CN111861284A (en) * | 2020-08-06 | 2020-10-30 | 城云科技（中国）有限公司 | Risk assessment and early warning method for social management unit |
| CN112637132A (en) * | 2020-12-01 | 2021-04-09 | 北京邮电大学 | Network anomaly detection method and device, electronic equipment and storage medium |
| CN112637132B (en) * | 2020-12-01 | 2022-03-11 | 北京邮电大学 | Network anomaly detection method and device, electronic equipment and storage medium |
| CN113271256A (en) * | 2021-04-06 | 2021-08-17 | 北京邮电大学 | Information age multi-path transmission method and system |
| CN113271256B (en) * | 2021-04-06 | 2022-08-30 | 北京邮电大学 | Information age multi-path transmission method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110912768A (en) | Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance | |
| CN109902708B (en) | Recommendation model training method and related device | |
| CN110187990B (en) | Virtual machine hybrid standby dynamic reliability assessment method based on mode transfer | |
| Xie et al. | Sequential and adaptive sampling for matrix completion in network monitoring systems | |
| US11057787B2 (en) | Method and test system for mobile network testing as well as prediction system | |
| CN110009225A (en) | Risk evaluating system construction method, device, computer equipment and storage medium | |
| CN106612511B (en) | Wireless network throughput evaluation method and device based on support vector machine | |
| CN113489619A (en) | Network topology inference method and device based on time series analysis | |
| CN111800414A (en) | Convolutional neural network-based traffic anomaly detection method and system | |
| CN111310918B (en) | Data processing method, device, computer equipment and storage medium | |
| CN111797320A (en) | Data processing method, device, equipment and storage medium | |
| CN114565226A (en) | Index processing method, server and storage medium | |
| Davalos et al. | Vertical handoff algorithms—A new approach for performance evaluation | |
| CN113468403A (en) | User information prediction method based on big data mining and cloud computing AI (Artificial Intelligence) service system | |
| CN110263106B (en) | Collaborative public opinion fraud detection method and device | |
| CN116975520A (en) | Reliability evaluation method, device, equipment and storage medium for AB experiment | |
| CN110475244B (en) | Terminal management method, system, device, terminal and storage medium | |
| Hegedűs et al. | Towards building method level maintainability models based on expert evaluations | |
| Davoudi | Effects of user interactions on online social recommender systems | |
| Berg et al. | Fractal geometry of equilibrium payoffs in discounted supergames | |
| CN116187754A (en) | Production line fault positioning method, equipment and readable storage medium | |
| CN109547236A (en) | Electronic data uploads storage method, readable storage medium storing program for executing and terminal | |
| CN111598390B (en) | Method, device, equipment and readable storage medium for evaluating high availability of server | |
| JP4668851B2 (en) | Quality class determination apparatus, quality class determination method, and program | |
| CN114254381A (en) | Data evaluation method, device, equipment and medium based on multi-party security calculation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200324 |