CN111988168A - Edge service deployment method and device and electronic equipment - Google Patents

Edge service deployment method and device and electronic equipment Download PDF

Info

Publication number
CN111988168A
CN111988168A CN202010723732.9A CN202010723732A CN111988168A CN 111988168 A CN111988168 A CN 111988168A CN 202010723732 A CN202010723732 A CN 202010723732A CN 111988168 A CN111988168 A CN 111988168A
Authority
CN
China
Prior art keywords
service
edge
mobility
user
edge node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010723732.9A
Other languages
Chinese (zh)
Other versions
CN111988168B (en
Inventor
时岩
赵旭辉
陈山枝
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.)
Beijing University of Posts and Telecommunications
Original Assignee
Beijing University of Posts and Telecommunications
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 Beijing University of Posts and Telecommunications filed Critical Beijing University of Posts and Telecommunications
Priority to CN202010723732.9A priority Critical patent/CN111988168B/en
Publication of CN111988168A publication Critical patent/CN111988168A/en
Application granted granted Critical
Publication of CN111988168B publication Critical patent/CN111988168B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The application provides an edge service deployment method and device and electronic equipment. The method comprises the steps of calculating service request estimators of all mobility characteristic blocks of a current time slice according to historical service request quantity of all mobility characteristic blocks, determining service requests of users corresponding to the mobility characteristic blocks in the current time slice aiming at any mobility characteristic block, obtaining a node set to be deployed of all mobility characteristic blocks according to the service requests of the users and all the service request estimators received by all nodes to be deployed, calculating service time delay and service deployment cost of all the node sets to be deployed, and accordingly selecting a target edge node set for deploying edge services corresponding to the service requests of all the users. By utilizing the mobility characteristic information of the user and learning the current user service requirement according to the historical user requirement, the problem of mobile edge application service deployment caused by mobility in the prior art is solved.

Description

Edge service deployment method and device and electronic equipment
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for edge service deployment, and an electronic device.
Background
The Mobile Edge network is a novel Mobile Edge Computing (MEC) based network, and can provide support for low delay and high Computing requirements of future Mobile applications, such as virtual reality, Mobile games, car networking applications, and the like.
Because a mobile user moves among different edge node service ranges and the space-time distribution rule of the user movement behavior causes that the number of mobile edge service requests from the mobile user for different edge nodes may be greatly different, for example, the number of service requests of edge nodes at certain positions is large, so that edge application service needs to be deployed, and certain edge nodes do not have service requests, so that edge application service does not need to be deployed. Therefore, an edge service deployment method for providing edge nodes is urgently needed.
Disclosure of Invention
The embodiment of the application aims to provide an edge service deployment method, an edge service deployment device and electronic equipment so as to provide an edge service deployment method of an edge node.
The specific technical scheme is as follows:
in a first aspect, an embodiment of the present application provides an edge service deployment method, which is applied to a manager in an edge service deployment system, where the edge service deployment system further includes a cloud platform and a plurality of edge nodes; the method comprises the following steps:
acquiring a mobility feature space, wherein the mobility feature space comprises a plurality of mobility feature blocks, mobility feature information and the mobility feature blocks have corresponding relations, the mobility feature information in different mobility feature blocks is different, and the mobility feature information represents the mobility features of a user;
acquiring the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
acquiring mobility characteristic information of each user in a current time slice, and respectively determining a mobility characteristic block corresponding to each user according to the mobility characteristic information of each user;
the method comprises the steps of obtaining service requests of users received by edge nodes in a current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; obtaining a node set to be deployed of each mobility characteristic block;
acquiring all edge node subsets of each node set to be deployed, wherein the edge node subsets comprise at least one node to be deployed;
aiming at any edge node subset, calculating service time delay and service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimators;
and selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the cost of deploying the service.
Optionally, dividing a preset time period into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DD is a mobility characteristic information dimension, and x is a D-dimensional mobility characteristic space;
the method comprises the steps of obtaining service requests of users received by edge nodes in a current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to a mobility feature block in the current time slice aiming at any mobility feature block; obtaining a set of nodes to be deployed of each mobility characteristic block, including:
setting the preset service request threshold according to the following formula:
Figure BDA0002600927990000021
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure BDA0002600927990000022
wherein N is a set of edge nodes within a time slice t;
Figure BDA0002600927990000031
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure BDA0002600927990000032
ptA set of mobility feature blocks for time slice t, where,
Figure BDA0002600927990000033
Figure BDA0002600927990000034
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure BDA0002600927990000035
representing mobility feature blocks
Figure BDA0002600927990000036
Number of service requests;
Figure BDA0002600927990000037
a set of nodes to be deployed representing time slice t.
Alternatively to this, the first and second parts may,
Figure BDA0002600927990000038
is denoted as LjWhere j ∈ {1, …, k }; k is the number of edge node subsets;
each edge node subset L is calculated according to the following formulajService delay of (2):
Figure BDA0002600927990000039
wherein:
Figure BDA00026009279900000310
Figure BDA00026009279900000311
Figure BDA00026009279900000312
wherein the content of the first and second substances,
Figure BDA00026009279900000313
is the service latency of a subset of the edge nodes,
Figure BDA00026009279900000314
Figure BDA00026009279900000315
representing the uncertainty of the estimate;
Figure BDA00026009279900000316
blocking as p for mobility featurestIs in the edge server subset Lj(n∈Lj) Number of service requests;
Figure BDA00026009279900000317
as a motion feature vector of
Figure BDA00026009279900000318
The mobility characteristics of the user m to which the user m belongs;
Figure BDA00026009279900000319
representing mobility feature blocks
Figure BDA00026009279900000320
A total service request estimator at a current time slice;
Figure BDA0002600927990000041
representing mobility characteristics is partitioned into
Figure BDA0002600927990000042
The service request amount of (2);
Figure BDA0002600927990000043
is blocked for mobility characteristics as
Figure BDA0002600927990000044
The set of user service requests of (a),
Figure BDA0002600927990000045
wherein the content of the first and second substances,
Figure BDA0002600927990000046
wherein the content of the first and second substances,
Figure BDA0002600927990000047
representing the response time delay when the edge node provides service;
Figure BDA0002600927990000048
representing response time delay when the cloud platform provides the service;
Figure BDA0002600927990000049
wherein, λ is the input data size of the edge service corresponding to the service request of the user; mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure BDA00026009279900000410
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure BDA00026009279900000411
wherein:
Figure BDA00026009279900000412
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
Optionally, in
Figure BDA00026009279900000413
In the case of a non-empty set, selecting a target edge node set for deploying an edge service corresponding to a service request of each user according to the service delay of each edge node subset and the cost of deploying the service, including:
in that
Figure BDA00026009279900000414
In the case of (a) in (b),
Figure BDA00026009279900000415
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure BDA0002600927990000051
In that
Figure BDA0002600927990000052
In the case of (a) in (b),
Figure BDA0002600927990000053
determining a target edge node set according to the following formula:
Figure BDA0002600927990000054
wherein the content of the first and second substances,
Figure BDA0002600927990000055
optionally, in
Figure BDA0002600927990000056
In the case of an empty set, selecting a target edge node set for deploying an edge service corresponding to a service request of each user according to the service delay of each edge node subset and the cost of deploying the service includes:
determining a target edge node set according to the following formula:
Figure BDA0002600927990000057
in a second aspect, an embodiment of the present application provides an edge service deployment apparatus, which applies a manager in an edge service deployment system, where the edge service deployment system further includes a cloud platform and a plurality of edge nodes; the device comprises:
the mobile terminal comprises a first acquisition module, a second acquisition module and a processing module, wherein the first acquisition module is used for acquiring a mobile characteristic space, the mobile characteristic space comprises a plurality of mobile characteristic blocks, mobile characteristic information and the mobile characteristic blocks have corresponding relations, the mobile characteristic information in different mobile characteristic blocks is different, and the mobile characteristic information represents the mobile characteristics of a user;
the second acquisition module is used for acquiring the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
the third acquisition module is used for acquiring the mobility characteristic information of each user in the current time slice and respectively determining the mobility characteristic blocks corresponding to each user according to the mobility characteristic information of each user;
the fourth acquisition module is used for acquiring the service requests of the users received by each edge node in the current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; obtaining a node set to be deployed of each mobility characteristic block;
a fifth acquisition module, configured to acquire all edge node subsets of each to-be-deployed node set, where the edge node subsets include at least one to-be-deployed node;
the computing module is used for computing the service delay and the service deployment cost of any edge node subset according to the service request of the user received by each node to be deployed and each service request estimator;
and the selecting module is used for selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the service deployment cost.
Optionally, dividing a preset time period into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DD is a mobility characteristic information dimension, and x is a D-dimensional mobility characteristic space;
the fourth acquisition module is specifically configured to:
setting the preset service request threshold according to the following formula:
Figure BDA0002600927990000061
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure BDA0002600927990000062
wherein N is a set of edge nodes within a time slice t;
Figure BDA0002600927990000063
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure BDA0002600927990000064
ptA set of mobility feature blocks for time slice t, where,
Figure BDA0002600927990000065
Figure BDA0002600927990000066
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure BDA0002600927990000067
representing mobility feature blocks
Figure BDA0002600927990000068
Number of service requests;
Figure BDA0002600927990000071
a set of nodes to be deployed representing time slice t.
Alternatively to this, the first and second parts may,
Figure BDA0002600927990000072
is denoted as LjWhere j ∈ {1, …, k }; k is the number of edge node subsets; the fourth acquisition module is specifically configured to:
each edge node subset L is calculated according to the following formulajService delay of (2):
Figure BDA0002600927990000073
wherein:
Figure BDA0002600927990000074
Figure BDA0002600927990000075
Figure BDA0002600927990000076
wherein the content of the first and second substances,
Figure BDA0002600927990000077
is the service latency of a subset of the edge nodes,
Figure BDA0002600927990000078
Figure BDA0002600927990000079
representing the uncertainty of the estimate;
Figure BDA00026009279900000710
blocking as p for mobility featurestIs in the edge server subset Lj(n∈Lj) Number of service requests;
Figure BDA00026009279900000711
as a motion feature vector of
Figure BDA00026009279900000712
The mobility characteristics of the user m to which the user m belongs;
Figure BDA00026009279900000713
representing mobility feature blocks
Figure BDA00026009279900000714
A total service request estimator at a current time slice;
Figure BDA00026009279900000715
representing mobility characteristics is partitioned into
Figure BDA00026009279900000716
The service request amount of (2);
Figure BDA00026009279900000717
is blocked for mobility characteristics as
Figure BDA00026009279900000718
The set of user service requests of (a),
Figure BDA00026009279900000719
wherein the content of the first and second substances,
Figure BDA00026009279900000720
wherein the content of the first and second substances,
Figure BDA0002600927990000081
representing the response time delay when the edge node provides service;
Figure BDA0002600927990000082
representing response time delay when the cloud platform provides the service;
Figure BDA0002600927990000083
wherein, λ is the input data size of the edge service corresponding to the service request of the user; mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure BDA0002600927990000084
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure BDA0002600927990000085
wherein:
Figure BDA0002600927990000086
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
Optionally, in
Figure BDA0002600927990000087
In the case of a non-empty set, the selection module is specifically configured to:
in that
Figure BDA0002600927990000088
In the case of (a) in (b),
Figure BDA0002600927990000089
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure BDA00026009279900000810
In that
Figure BDA00026009279900000811
In the case of (a) in (b),
Figure BDA00026009279900000812
determining a target edge node set according to the following formula:
Figure BDA0002600927990000091
wherein the content of the first and second substances,
Figure BDA0002600927990000092
optionally, in
Figure BDA0002600927990000093
In the case of an empty set, the selection module is specifically configured to:
determining a target edge node set according to the following formula:
Figure BDA0002600927990000094
in a third aspect, an embodiment of the present application provides an electronic device, including: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
a memory for storing a computer program;
a processor, configured to implement the edge service deployment method according to any one of the first aspect or the second aspect when executing a program stored in a memory.
In a fourth aspect, an embodiment of the present application provides a storage medium, where instructions are stored in the storage medium, and when the storage medium is run on a computer, the storage medium causes the computer to execute the edge service deployment method according to any one of the first aspect.
In a fifth aspect, an embodiment of the present application provides a computer program product containing instructions, which when run on a computer, causes the computer to perform the edge service deployment method according to any one of the first aspect.
The method, the device and the electronic equipment for edge service deployment provided by the embodiment of the application acquire mobility feature information of each user in a current time slice, respectively determine mobility feature blocks corresponding to each user according to the mobility feature information of each user, acquire service requests of the users received by each edge node in the current time slice, take the edge nodes with the quantity of the received service requests smaller than a preset service request quantity threshold value as nodes to be deployed, determine the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block, acquire a node set to be deployed of each mobility feature block, acquire all edge node subsets of each node set to be deployed, wherein the edge node subsets comprise at least one node to be deployed, and estimate quantities according to the service requests and each service request of the users received by each node to be deployed aiming at any edge node subset, calculating the service delay and the service deployment cost of the edge node subsets, selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay and the service deployment cost of each edge node subset, learning the current user service requirement according to the historical user requirement by utilizing the mobility characteristic information of the user, and determining the edge node for deploying the edge service according to the current user service requirement, thereby solving the problem that the prior art does not adapt to the waste of edge node resources caused by the dynamic change of the mobile edge service request caused by the movement of the user. Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic diagram of an edge service deployment method according to an embodiment of the present application;
fig. 2 is a schematic diagram of an edge service deployment apparatus according to an embodiment of the present application;
fig. 3 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The number of user requests is usually unknown before the mobile edge application service is deployed to a particular edge node, and the revenue for the mobile edge application service deployment depends mainly on the number of user requests. Therefore, the mobile edge service deployment strategy must adapt to the dynamic change of the mobile edge service request caused by the user movement, and when the edge service is deployed to the edge node without adapting to the dynamic change of the mobile edge service request caused by the user movement, the waste of the edge node resource is caused.
In view of the foregoing problems, embodiments of the present application disclose an edge service deployment method, an edge service deployment device, and an electronic device, which are described below.
An embodiment of the present application provides an edge service deployment method, which is applied to a manager in an edge service deployment system, where the edge service deployment system further includes a cloud platform and a plurality of edge nodes, referring to fig. 1, fig. 1 is a schematic diagram of the edge service deployment method according to the embodiment of the present application, and includes:
step 110, obtaining a mobility feature space, where the mobility feature space includes a plurality of mobility feature blocks, mobility feature information and the mobility feature blocks have a corresponding relationship, and mobility feature information in different mobility feature blocks is different, where the mobility feature information indicates a mobility feature of a user.
The edge service deployment method in the embodiment of the present application may be implemented by an electronic device, and specifically, the electronic device is any server that can provide an edge service, for example, a computer, a digital broadcast terminal, a messaging device, a game console, and the like.
The edge service deployment system comprises a plurality of edge nodes and a cloud platform; the edge node is used for deploying edge services, and when receiving a service request of a user, the edge services respond to the service request and provide services for the user; the cloud platform is used for deploying edge services, and under the condition that the edge node does not deploy the edge services corresponding to the service requests of the users, the cloud platform receives the service requests of the users forwarded by the edge node, responds to the service requests and provides the services to the users.
In order to accommodate mobility characteristics of users and mobile edge service deployment issues caused by unknown number of service requests of users, a user mobility characteristic information space may be obtained. Mobility characteristics information may be defined from multiple dimensions, thereby forming a multi-dimensional mobility characteristics space. And then the value range of the mobility characteristic information in each dimension can be divided according to different granularities according to needs, so that the whole mobility characteristic space is divided into a plurality of mobility characteristic blocks. For a certain mobile user, the edge service placement manager may sense and collect mobility feature information through mobile equipment and a big data technology carried by the user, so as to construct a historical mobility feature information set of the user, where the mobility feature information indicates a mobility feature of the user, the mobility feature information may include time, location, user gender, age, occupation, and the like when the user sends a service request, specifically, the mobility feature information may be one-dimensional information or multidimensional information, specifically, the setting is performed according to an actual situation, and is not limited herein, and each mobility feature information may correspond to a certain mobility feature block according to a value thereof.
For example, the user mobility feature information is two-dimensional information, and includes time and a position of a service request sent by a user, the mobility feature space is a two-dimensional space, the mobility feature space is divided to obtain a mobility feature block set representing the time and the position of the service request sent by the user, and each mobility feature block is a rectangle. Furthermore, the user mobility characteristic information is three-dimensional information and comprises time for sending the service request by the user, a position for sending the service request by the user and occupation of the user, the mobility characteristic space is a three-dimensional space, the mobility characteristic space is divided to obtain a set of occupational mobility characteristic blocks representing the time and the position for sending the service request by the user and the user, and each mobility characteristic block is a cuboid.
In order to predict the number of service requests of the current user, when the mobility characteristic information of each user is similar, the service requests of each user are also similar.
For example, people prefer to use mobile text and voice communication services and instant messaging software services in residential areas around 9 pm; using an online sales platform and online retailer services in a business region at 8 pm; it is predicted that the user request sent by the user at the same location is the same for the same time period, e.g., the user in the residential area at about 9 pm sends a service request for mobile text and voice messaging services and a service request for instant messaging software services.
Denote the mobility feature space as χ ═ 0,1]DD is the mobility characteristic information dimension, and χ is the mobility characteristic of D dimensionMarking a space; in particular, there is L>0，1≥α>And 0, alpha is a hello index, which characterizes that when the mobility information of the users is similar, the service request number of the users is also similar, and the size of alpha depends on the similarity of the mobility characteristic vectors of the users and the similarity of the service request number, namely, when the following hello continuity formula is satisfied, the mobility characteristic information of the users is similar, and the service request of the users is also similar.
|μn(x1)-μn(x2)|≤L||x1-x2||α
Wherein x1, x2 belongs to χ, χ 1 is the mobility characteristic information vector of user 1, χ 2 is the mobility characteristic information vector of user 2, | x1-x2| | is the euclidean distance between vector x1 and vector x 2; l and α represent the proximity of the service requests of the user 1 and the user 2 when the mobility characteristic information of the user 1 and the user 2 is close to a certain extent. Mu.sn(x1) is the expected value of the service request quantity of the user with the mobility feature information vector of x1 on the edge server n. Mu.sn(x2) is the expected value of the amount of service requests on the edge server n by the user with mobility profile information vector x 2. Wherein, mun(x1)＝E(d(x1))，μn(x2) ═ E (d (x 2)). Where d (x1) represents the number of service requests of x1 user and d (x2) represents the number of service requests of x2 user.
Step 120, obtaining the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a period of time within a preset time period.
In order to adapt to the problem of mobile edge service deployment caused by the unknown number of service requests of the user, the historical number of service requests of each mobility feature block can be obtained, so that the current number of service requests can be predicted according to the historical number of service requests, namely, the service request estimation quantity of each mobility feature block of the current time slice is calculated.
For example, the predetermined time period is divided into T discrete time slices, T being the predetermined time period length, for eachSetting a counter for each mobility feature block
Figure BDA0002600927990000131
And the number of service requests sent to the edge node n by the users with the corresponding relation between the mobility characteristic information and the mobility characteristic block p in the time slice t is shown.
Figure BDA0002600927990000132
Is set to 0.
Figure BDA0002600927990000133
A set of service requests representing users of mobility feature block p at historical time slice t,
Figure BDA0002600927990000134
the mobility characteristic information representing the current time slice t corresponds to an estimate of the service request for the user of the mobility characteristic block p,
Figure BDA0002600927990000135
the calculation is carried out by a sample averaging method, specifically,
Figure BDA0002600927990000136
wherein
Figure BDA0002600927990000137
That is, the number of service requests observed is a counter that is set in blocks according to each mobility characteristic
Figure BDA0002600927990000138
Is obtained by counting.
And calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block, so that the method can adapt to the mobile edge service deployment problem caused by the service request quantity of unknown users.
Step 130, obtaining mobility characteristic information of each user in the current time slice, and respectively determining the mobility characteristic blocks corresponding to each user according to the mobility characteristic information of each user.
At time slice t, the mobility feature block set in the mobility feature space is denoted as ptM is a user set in a time slice t; m is equal to {1, …, M }, and the mobility characteristic vector of the user M is expressed as the mobility characteristic vector of the user M at the current time slice t
Figure BDA0002600927990000139
According to
Figure BDA00026009279900001310
Determining the mobility characteristic block corresponding to the user as
Figure BDA00026009279900001311
Then
Figure BDA00026009279900001312
Wherein the mobility feature vector is used to represent mobility feature information of the user.
Step 140, obtaining service requests of users received by each edge node in the current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; and obtaining a node set to be deployed of each mobility characteristic block.
The method comprises the steps of obtaining service requests of users received by each edge node in a current time slice, and taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, so that the deviation caused by uncertainty of mobility feature blocks obtained by dividing a mobility feature space can be fully considered, edge nodes without edge services are fully utilized, and a better edge service deployment scheme can be obtained.
In one possible embodiment, the predetermined time period is divided into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DAnd D is the dimension of mobility characteristic information,χ is a D-dimensional mobility feature space; 1/r ofTSide length of a block for mobility characteristics; (r)T)DThe number of blocks for mobility features;
the service requests of the users received by the edge nodes in the current time slice are obtained, the edge nodes with the service requests smaller than a preset service request threshold value are used as nodes to be deployed, and the service requests of the users corresponding to the mobility feature blocks in the current time slice are determined aiming at any mobility feature block; obtaining a set of nodes to be deployed of each mobility characteristic block, including:
setting the preset service request threshold according to the following formula:
Figure BDA0002600927990000141
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure BDA0002600927990000142
wherein N is a set of edge nodes within a time slice t;
Figure BDA0002600927990000143
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure BDA0002600927990000144
ptA set of mobility feature blocks for time slice t, where,
Figure BDA0002600927990000145
Figure BDA0002600927990000146
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure BDA0002600927990000147
representing mobility feature blocks
Figure BDA0002600927990000148
Number of service requests;
Figure BDA0002600927990000151
a set of nodes to be deployed representing time slice t.
Step 150, obtaining all edge node subsets of each to-be-deployed node set, where the edge node subsets include at least one to-be-deployed node.
Figure BDA0002600927990000152
Is denoted as LjWherein j belongs to {1, …, k }, and k is the number of the edge node subsets; the number of edge node subsets may be set according to actual conditions, and the number of edge nodes in each edge node subset may also be set according to actual conditionsjIs that
Figure BDA0002600927990000153
All subsets are aggregated.
Step 160, for any edge node subset, calculating the service delay and the service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimators.
And aiming at any edge node subset, calculating the service delay and the service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimators. And determining an optimal mobile edge service deployment strategy by calculating the service delay of the edge node subset and the cost of deploying the service.
In one possible embodiment of the method according to the invention,
Figure BDA0002600927990000154
is denoted as LjWhere j ∈ {1, …, k };
calculating the service delay of the edge node subset according to the following formula:
Figure BDA0002600927990000155
wherein:
Figure BDA0002600927990000156
Figure BDA0002600927990000157
Figure BDA0002600927990000161
wherein the content of the first and second substances,
Figure BDA0002600927990000162
is the service latency of a subset of the edge nodes,
Figure BDA0002600927990000163
Figure BDA0002600927990000164
representing the uncertainty of the estimate;
Figure BDA0002600927990000165
blocking as p for mobility featurestIs in the edge server subset Lj(n∈Lj) Number of service requests;
Figure BDA0002600927990000166
as a motion feature vector of
Figure BDA0002600927990000167
The mobility characteristics of the user m to which the user m belongs;
Figure BDA0002600927990000168
representing mobility feature blocks
Figure BDA0002600927990000169
A total service request estimator at a current time slice;
Figure BDA00026009279900001610
representing mobility characteristics is partitioned into
Figure BDA00026009279900001611
The service request amount of (2);
Figure BDA00026009279900001612
is blocked for mobility characteristics as
Figure BDA00026009279900001613
The set of user service requests of (a),
Figure BDA00026009279900001614
wherein the content of the first and second substances,
Figure BDA00026009279900001615
wherein the content of the first and second substances,
Figure BDA00026009279900001616
representing the response time delay when the edge node provides service;
Figure BDA00026009279900001617
representing response time delay when the cloud platform provides the service;
Figure BDA00026009279900001618
wherein λ is userThe size of the input data of the edge service corresponding to the service request of (1); mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure BDA00026009279900001619
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure BDA00026009279900001620
wherein:
Figure BDA0002600927990000171
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
Step 170, according to the service delay of each edge node subset and the cost of service deployment, selecting a target edge node set for deploying the edge service corresponding to the service request of each user.
And selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the service deployment cost. After the edge service corresponding to the service request of each user is deployed, each edge node provides corresponding service for the user according to the received service request of the user.
The method comprises the steps of obtaining mobility characteristic information of each user in a current time slice, respectively determining mobility characteristic blocks corresponding to each user according to the mobility characteristic information of each user, obtaining service requests of the users received by each edge node in the current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, determining the service requests of the users corresponding to the mobility characteristic blocks in the current time slice aiming at any mobility characteristic block, obtaining a node set to be deployed of each mobility characteristic block, obtaining all edge node subsets of each node set to be deployed, wherein the edge node subsets comprise at least one node to be deployed, and calculating service delay and service deployment cost of the edge node subsets aiming at any edge node subset according to the service requests of the users and service request estimators received by each node to be deployed, according to the service delay of each edge node subset and the service deployment cost, a target edge node set is selected for deploying the edge service corresponding to the service request of each user, and the current user service requirement is learned according to the historical user requirement by utilizing the mobility characteristic information of the user, so that the problem of mobile edge application service deployment caused by mobility in the prior art is solved.
In one possible embodiment, in
Figure BDA0002600927990000172
In the case of a non-empty set, selecting a target edge node set for deploying an edge service corresponding to the service request of each user according to the service delay of each edge node subset and the cost of deploying the service includes:
in that
Figure BDA0002600927990000173
In the case of (a) in (b),
Figure BDA0002600927990000174
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure BDA0002600927990000181
In that
Figure BDA0002600927990000182
In the case of (a) in (b),
Figure BDA0002600927990000183
determining a target edge node set according to the following formula:
Figure BDA0002600927990000184
wherein the content of the first and second substances,
Figure BDA0002600927990000185
in one possible embodiment, in
Figure BDA0002600927990000186
In the case of an empty set, selecting a target edge node set to deploy an edge service corresponding to the service request of each user according to the service delay of each edge node subset and the cost of deploying the service includes:
determining a target edge node set according to the following formula:
Figure BDA0002600927990000187
referring to fig. 2, fig. 2 is a schematic diagram of an edge service deployment apparatus according to an embodiment of the present application, where the apparatus is applied to a manager in an edge service deployment system, and the edge service deployment system further includes a cloud platform and a plurality of edge nodes; the above-mentioned device includes:
the first acquiring module 210 is configured to acquire a mobility feature space, where the mobility feature space includes a plurality of mobility feature blocks, mobility feature information and the mobility feature blocks have a corresponding relationship, and mobility feature information in different mobility feature blocks is different, where the mobility feature information indicates a mobility feature of a user.
A second collecting module 220, configured to obtain the historical service request quantity of each mobility feature block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
a third collecting module 230, configured to obtain mobility feature information of each user in a current time slice, and determine a mobility feature block corresponding to each user according to the mobility feature information of each user;
a fourth acquisition module 240, configured to acquire service requests of users received by each edge node in a current time slice, use the edge nodes whose number of received service requests is smaller than a preset service request number threshold as nodes to be deployed, and determine, for any mobility feature block, a service request of a user corresponding to the mobility feature block in the current time slice; obtaining a node set to be deployed of each mobility characteristic block;
a fifth acquiring module 250, configured to acquire all edge node subsets of each to-be-deployed node set, where the edge node subsets include at least one to-be-deployed node;
a calculating module 260, configured to calculate, for any edge node subset, service delay and service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimator;
a selecting module 270, configured to select a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the cost of deploying the service.
In one possible embodiment, the predetermined time period is divided into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DD is a mobility characteristic information dimension, and x is a D-dimensional mobility characteristic space;
the fourth acquisition module 240 is specifically configured to:
setting the preset service request threshold according to the following formula:
Figure BDA0002600927990000191
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure BDA0002600927990000192
wherein N is a set of edge nodes within a time slice t;
Figure BDA0002600927990000193
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure BDA0002600927990000194
ptA set of mobility feature blocks for time slice t, where,
Figure BDA0002600927990000195
Figure BDA0002600927990000196
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure BDA0002600927990000201
representing mobility feature blocks
Figure BDA0002600927990000202
Number of service requests;
Figure BDA0002600927990000203
a set of nodes to be deployed representing time slice t.
In one possible embodiment of the method according to the invention,
Figure BDA0002600927990000204
is denoted as LjWhere j ∈ {1, …, k }; k is the number of edge node subsets; the fourth acquisition module 240 is specifically configured to:
each edge node subset L is calculated according to the following formulajService delay of (2):
Figure BDA0002600927990000205
wherein:
Figure BDA0002600927990000206
Figure BDA0002600927990000207
Figure BDA0002600927990000208
wherein the content of the first and second substances,
Figure BDA0002600927990000209
is the service latency of a subset of the edge nodes,
Figure BDA00026009279900002010
Figure BDA00026009279900002011
representing the uncertainty of the estimate;
Figure BDA00026009279900002012
blocking as p for mobility featurestUser in the border clothesServer subset Lj(n∈Lj) Number of service requests;
Figure BDA00026009279900002013
as a motion feature vector of
Figure BDA00026009279900002014
The mobility characteristics of the user m to which the user m belongs;
Figure BDA00026009279900002015
representing mobility feature blocks
Figure BDA00026009279900002016
A total service request estimator at a current time slice;
Figure BDA00026009279900002017
representing mobility characteristics is partitioned into
Figure BDA00026009279900002018
The service request amount of (2);
Figure BDA00026009279900002019
is blocked for mobility characteristics as
Figure BDA00026009279900002020
The set of user service requests of (a),
Figure BDA00026009279900002021
wherein the content of the first and second substances,
Figure BDA0002600927990000211
wherein the content of the first and second substances,
Figure BDA0002600927990000212
representing the response time delay when the edge node provides service;
Figure BDA0002600927990000213
representing response time delay when the cloud platform provides the service;
Figure BDA0002600927990000214
wherein, λ is the input data size of the edge service corresponding to the service request of the user; mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure BDA0002600927990000215
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure BDA0002600927990000216
wherein:
Figure BDA0002600927990000217
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
In one possible embodiment, in
Figure BDA0002600927990000218
In the case of a non-empty set, the selecting module 270 is specifically configured to:
in that
Figure BDA0002600927990000219
In the case of (a) in (b),
Figure BDA00026009279900002110
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure BDA00026009279900002111
In that
Figure BDA0002600927990000221
In the case of (a) in (b),
Figure BDA0002600927990000222
determining a target edge node set according to the following formula:
Figure BDA0002600927990000223
wherein the content of the first and second substances,
Figure BDA0002600927990000224
in one possible embodiment, in
Figure BDA0002600927990000225
In the case of an empty set, the selecting module 270 is specifically configured to:
determining a target edge node set according to the following formula:
Figure BDA0002600927990000226
with regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
An embodiment of the present invention further provides an electronic device, as shown in fig. 3, where fig. 3 is a schematic diagram of the electronic device according to the embodiment of the present application, and the electronic device includes: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 are communicated with each other through the communication bus 340,
the memory 330 is used for storing computer programs;
the processor 310 is configured to implement the following steps when executing the computer program stored in the memory 330:
acquiring a mobility feature space, wherein the mobility feature space comprises a plurality of mobility feature blocks, mobility feature information and the mobility feature blocks have corresponding relations, the mobility feature information in different mobility feature blocks is different, and the mobility feature information represents the mobility features of users;
acquiring the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
acquiring mobility characteristic information of each user in a current time slice, and respectively determining a mobility characteristic block corresponding to each user according to the mobility characteristic information of each user;
the method comprises the steps of obtaining service requests of users received by edge nodes in a current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; obtaining a node set to be deployed of each mobility characteristic block;
acquiring all edge node subsets of each node set to be deployed, wherein the edge node subsets comprise at least one node to be deployed;
aiming at any edge node subset, calculating the service delay and the service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimators;
and selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the service deployment cost.
In one possible embodiment, the processor 310, when executing the program stored in the memory 330, may further implement any of the edge service deployment methods described above.
The communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the terminal and other equipment.
The Memory may include a Random Access Memory (RAM) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, which stores instructions that, when executed on a computer, cause the computer to execute any of the above-mentioned edge service deployment methods in the above-mentioned embodiments.
In yet another embodiment, a computer program product containing instructions is provided, which when run on a computer, causes the computer to perform any of the above-described edge service deployment methods in the embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described above in accordance with the embodiments of the invention may be generated, in whole or in part, when the computer program instructions described above are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, the technical features in the various alternatives can be combined to form the scheme as long as the technical features are not contradictory, and the scheme is within the scope of the disclosure of the present application. Relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the same element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the electronic device, and the storage medium, since they are substantially similar to the method embodiments, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiments.
The above description is only a preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims (10)

1. The edge service deployment method is characterized by being applied to a manager in an edge service deployment system, wherein the edge service deployment system further comprises a cloud platform and a plurality of edge nodes; the method comprises the following steps:
acquiring a mobility feature space, wherein the mobility feature space comprises a plurality of mobility feature blocks, mobility feature information and the mobility feature blocks have a corresponding relation, the mobility feature information in different mobility feature blocks is different, and the mobility feature information represents the mobility features of a user;
acquiring the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
acquiring mobility characteristic information of each user in a current time slice, and respectively determining a mobility characteristic block corresponding to each user according to the mobility characteristic information of each user;
the method comprises the steps of obtaining service requests of users received by edge nodes in a current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; obtaining a node set to be deployed of each mobility characteristic block;
acquiring all edge node subsets of each node set to be deployed, wherein the edge node subsets comprise at least one node to be deployed;
aiming at any edge node subset, calculating service time delay and service deployment cost of the edge node subset according to the service request of the user received by each node to be deployed and the service request estimators;
and selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the cost of deploying the service.
2. The method of claim 1, wherein the predetermined time period is divided into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DD is a mobility characteristic information dimension, and x is a D-dimensional mobility characteristic space;
the method comprises the steps of obtaining service requests of users received by edge nodes in a current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to a mobility feature block in the current time slice aiming at any mobility feature block; obtaining a set of nodes to be deployed of each mobility characteristic block, including:
setting the preset service request threshold according to the following formula:
Figure FDA0002600927980000021
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure FDA0002600927980000022
wherein N is a set of edge nodes within a time slice t;
Figure FDA0002600927980000023
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure FDA0002600927980000024
ptA set of mobility feature blocks for time slice t, where,
Figure FDA0002600927980000025
Figure FDA0002600927980000026
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure FDA0002600927980000027
representing mobility feature blocks
Figure FDA0002600927980000028
Number of service requests;
Figure FDA0002600927980000029
a set of nodes to be deployed representing time slice t.
3. The method of claim 2,
Figure FDA00026009279800000210
is denoted as LjWherein j belongs to {1, …, k }, and k is the number of the edge node subsets;
each edge node subset L is calculated according to the following formulajService delay of (2):
Figure FDA00026009279800000211
wherein:
Figure FDA00026009279800000212
Figure FDA00026009279800000213
Figure FDA0002600927980000031
wherein the content of the first and second substances,
Figure FDA0002600927980000032
is the service latency of a subset of the edge nodes,
Figure FDA0002600927980000033
Figure FDA0002600927980000034
the uncertainty of the estimate is represented by a representation,
Figure FDA0002600927980000035
blocking as p for mobility featurestIs in the edge server subset Lj(n∈Lj) Number of service requests;
Figure FDA0002600927980000036
as a motion feature vector of
Figure FDA0002600927980000037
The mobility characteristics of the user m to which the user m belongs;
Figure FDA0002600927980000038
representing mobility feature blocks
Figure FDA0002600927980000039
A total service request estimator at a current time slice;
Figure FDA00026009279800000310
representing mobility characteristics is partitioned into
Figure FDA00026009279800000311
The service request amount of (2);
Figure FDA00026009279800000312
is blocked for mobility characteristics as
Figure FDA00026009279800000313
The set of user service requests of (a),
Figure FDA00026009279800000314
wherein the content of the first and second substances,
Figure FDA00026009279800000315
wherein the content of the first and second substances,
Figure FDA00026009279800000316
representing the response time delay when the edge node provides service;
Figure FDA00026009279800000317
representing response time delay when the cloud platform provides the service;
Figure FDA00026009279800000318
wherein, λ is the input data size of the edge service corresponding to the service request of the user; mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure FDA00026009279800000319
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure FDA00026009279800000320
wherein:
Figure FDA0002600927980000041
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
4. The method of claim 3, wherein the step of removing the metal layer is performed in a batch process
Figure FDA0002600927980000042
In the case of a non-empty set, selecting a target edge node set for deploying an edge service corresponding to a service request of each user according to the service delay of each edge node subset and the cost of deploying the service, including:
in that
Figure FDA0002600927980000043
In the case of (a) in (b),
Figure FDA0002600927980000044
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure FDA0002600927980000045
In that
Figure FDA0002600927980000046
In the case of (a) in (b),
Figure FDA0002600927980000047
determining a target edge node set according to the following formula:
Figure FDA0002600927980000048
wherein the content of the first and second substances,
Figure FDA0002600927980000049
5. the method of claim 3, wherein the step of removing the metal layer is performed in a batch process
Figure FDA00026009279800000410
In the case of an empty set, selecting a target edge node set for deploying an edge service corresponding to a service request of each user according to the service delay of each edge node subset and the cost of deploying the service includes:
determining a target edge node set according to the following formula:
Figure FDA00026009279800000411
6. the edge service deployment device is characterized in that a manager in an edge service deployment system is applied, and the edge service deployment system further comprises a cloud platform and a plurality of edge nodes; the device comprises:
the mobile terminal comprises a first acquisition module, a second acquisition module and a processing module, wherein the first acquisition module is used for acquiring a mobile characteristic space, the mobile characteristic space comprises a plurality of mobile characteristic blocks, mobile characteristic information and the mobile characteristic blocks have corresponding relations, the mobile characteristic information in different mobile characteristic blocks is different, and the mobile characteristic information represents the mobile characteristics of a user;
the second acquisition module is used for acquiring the historical service request quantity of each mobility characteristic block; calculating the service request estimation quantity of each mobility characteristic block of the current time slice according to the historical service request quantity of each mobility characteristic block; the time slice represents a time period in a preset time period;
the third acquisition module is used for acquiring the mobility characteristic information of each user in the current time slice and respectively determining the mobility characteristic blocks corresponding to each user according to the mobility characteristic information of each user;
the fourth acquisition module is used for acquiring the service requests of the users received by each edge node in the current time slice, taking the edge nodes with the number of the received service requests smaller than a preset service request number threshold value as nodes to be deployed, and determining the service requests of the users corresponding to the mobility feature blocks in the current time slice aiming at any mobility feature block; obtaining a node set to be deployed of each mobility characteristic block;
a fifth acquisition module, configured to acquire all edge node subsets of each to-be-deployed node set, where the edge node subsets include at least one to-be-deployed node;
the computing module is used for computing the service delay and the service deployment cost of any edge node subset according to the service request of the user received by each node to be deployed and each service request estimator;
and the selecting module is used for selecting a target edge node set for deploying the edge service corresponding to the service request of each user according to the service delay of each edge node subset and the service deployment cost.
7. The apparatus of claim 6, wherein the predetermined time period is divided into T discrete time slices; denote the mobility feature space as χ ═ 0,1]DD is a mobility characteristic information dimension, and x is a D-dimensional mobility characteristic space;
the fourth acquisition module is specifically configured to:
setting the preset service request threshold according to the following formula:
Figure FDA0002600927980000061
wherein 1 is more than or equal to alpha and is more than 0; α is the Herdel index;
the set of nodes to be deployed is represented as:
Figure FDA0002600927980000062
wherein N is a set of edge nodes within a time slice t;
Figure FDA0002600927980000063
for the set of users on edge node N within a time slice T, T belongs to {1, …, T }, N belongs to N; m represents any user and satisfies
Figure FDA0002600927980000064
ptA set of mobility feature blocks for time slice t, where,
Figure FDA0002600927980000065
Figure FDA0002600927980000066
representing mobility characteristic blocks to which the user m belongs in the time slice t;
Figure FDA0002600927980000067
representing mobility feature blocks
Figure FDA0002600927980000068
Number of service requests;
Figure FDA0002600927980000069
a set of nodes to be deployed representing time slice t.
8. The apparatus of claim 7,
Figure FDA00026009279800000610
is denoted as LjWhere j ∈ {1, …, k }; the number of edge node subsets; the fourth acquisition module is specifically configured to:
each edge node subset L is calculated according to the following formulajService delay of (2):
Figure FDA00026009279800000611
wherein:
Figure FDA00026009279800000612
Figure FDA00026009279800000613
Figure FDA0002600927980000071
wherein the content of the first and second substances,
Figure FDA0002600927980000072
is the service latency of a subset of the edge nodes,
Figure FDA0002600927980000073
Figure FDA0002600927980000074
the uncertainty of the estimate is represented by a representation,
Figure FDA0002600927980000075
blocking as p for mobility featurestIs in the edge server subset Lj(n∈Lj) Number of service requests;
Figure FDA0002600927980000076
as a motion feature vector of
Figure FDA0002600927980000077
To a userm belongs to mobility feature blocks;
Figure FDA0002600927980000078
representing mobility feature blocks
Figure FDA0002600927980000079
A total service request estimator at a current time slice;
Figure FDA00026009279800000710
representing mobility characteristics is partitioned into
Figure FDA00026009279800000711
The service request amount of (2);
Figure FDA00026009279800000712
is blocked for mobility characteristics as
Figure FDA00026009279800000713
The set of user service requests of (a),
Figure FDA00026009279800000714
wherein the content of the first and second substances,
Figure FDA00026009279800000715
wherein the content of the first and second substances,
Figure FDA00026009279800000716
representing the response time delay when the edge node provides service;
Figure FDA00026009279800000717
representing response time delay when the cloud platform provides the service;
Figure FDA00026009279800000718
wherein, λ is the input data size of the edge service corresponding to the service request of the user; mu is a calculation resource period required for calculating the edge service corresponding to the service request of the user;
Figure FDA00026009279800000719
is the transmission rate between user m and edge node n in time slice t, fnIs the processing speed of the edge node n; f. ofCThe processing speed of the cloud platform; ctThe transmission rate between the edge node n and the cloud platform is obtained; h istSending a service request to a user until the user receives the time for providing a service response for the user by the cloud platform;
each edge node subset L is calculated according to the following formulajDeployment service cost of (2):
Figure FDA00026009279800000720
wherein:
Figure FDA0002600927980000081
wherein, ω is the deployment cost of deploying edge service at an edge node; f (omega. L)jL) is at the edge node subset LjThe deployment cost of the edge node in (1) to deploy the edge service.
9. The apparatus of claim 8, wherein the apparatus is used in a process of manufacturing a semiconductor device
Figure FDA0002600927980000082
In the case of a non-empty set, the selection module is specifically configured to:
in that
Figure FDA0002600927980000083
In the case of (a) in (b),
Figure FDA0002600927980000084
beta, L are constants, LtExpressed as a set of target edge nodes; determining a target edge node set l according to the following formulat：
Figure FDA0002600927980000085
In that
Figure FDA0002600927980000086
In the case of (a) in (b),
Figure FDA0002600927980000087
determining a target edge node set according to the following formula:
Figure FDA0002600927980000088
wherein the content of the first and second substances,
Figure FDA0002600927980000089
10. an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program stored in the memory, implementing the method of any of claims 1-5.
CN202010723732.9A 2020-07-24 2020-07-24 Edge service deployment method and device and electronic equipment Active CN111988168B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010723732.9A CN111988168B (en) 2020-07-24 2020-07-24 Edge service deployment method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010723732.9A CN111988168B (en) 2020-07-24 2020-07-24 Edge service deployment method and device and electronic equipment

Publications (2)

Publication Number Publication Date
CN111988168A true CN111988168A (en) 2020-11-24
CN111988168B CN111988168B (en) 2021-11-26

Family

ID=73438144

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010723732.9A Active CN111988168B (en) 2020-07-24 2020-07-24 Edge service deployment method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN111988168B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112799789A (en) * 2021-03-22 2021-05-14 腾讯科技（深圳）有限公司 Node cluster management method, device, equipment and storage medium
CN112995280A (en) * 2021-02-03 2021-06-18 北京邮电大学 Data distribution method and device for multi-content demand service
CN113472844A (en) * 2021-05-26 2021-10-01 北京邮电大学 Edge computing server deployment method, device and equipment for Internet of vehicles

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975330A (en) * 2016-06-27 2016-09-28 华为技术有限公司 Virtual network function deployment method, device and system adopting NEC (network edge computing)
CN108933815A (en) * 2018-06-15 2018-12-04 燕山大学 A kind of control method of the Edge Server of mobile edge calculations unloading
CN110096318A (en) * 2019-05-08 2019-08-06 北京邮电大学 A kind of task discharging method and device based on mobile edge calculations
CN110187973A (en) * 2019-05-31 2019-08-30 浙江大学 A kind of service arrangement optimization method towards edge calculations
US20190273804A1 (en) * 2018-03-04 2019-09-05 Netskrt Systems, Inc. System and apparatus for intelligently caching data based on predictable schedules of mobile transportation environments
CN110381131A (en) * 2019-07-15 2019-10-25 北京奇艺世纪科技有限公司 Implementation method, mobile terminal, server and the storage medium of MEC node identification
CN110662238A (en) * 2019-10-24 2020-01-07 南京大学 Reinforced learning scheduling method and device for burst request under edge network
CN111163178A (en) * 2020-01-10 2020-05-15 中国地质大学（武汉） Game theory-based service deployment and task unloading method in edge computing
CN111371603A (en) * 2020-02-27 2020-07-03 长沙市源本信息科技有限公司 Service instance deployment method and device applied to edge computing

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975330A (en) * 2016-06-27 2016-09-28 华为技术有限公司 Virtual network function deployment method, device and system adopting NEC (network edge computing)
US20190273804A1 (en) * 2018-03-04 2019-09-05 Netskrt Systems, Inc. System and apparatus for intelligently caching data based on predictable schedules of mobile transportation environments
CN108933815A (en) * 2018-06-15 2018-12-04 燕山大学 A kind of control method of the Edge Server of mobile edge calculations unloading
CN110096318A (en) * 2019-05-08 2019-08-06 北京邮电大学 A kind of task discharging method and device based on mobile edge calculations
CN110187973A (en) * 2019-05-31 2019-08-30 浙江大学 A kind of service arrangement optimization method towards edge calculations
CN110381131A (en) * 2019-07-15 2019-10-25 北京奇艺世纪科技有限公司 Implementation method, mobile terminal, server and the storage medium of MEC node identification
CN110662238A (en) * 2019-10-24 2020-01-07 南京大学 Reinforced learning scheduling method and device for burst request under edge network
CN111163178A (en) * 2020-01-10 2020-05-15 中国地质大学（武汉） Game theory-based service deployment and task unloading method in edge computing
CN111371603A (en) * 2020-02-27 2020-07-03 长沙市源本信息科技有限公司 Service instance deployment method and device applied to edge computing

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
戚凯强，杨晨阳，韩圣千: "基于实测数据集预测用户请求行为对主动边缘缓存的影响", 《信号处理》 *
赵磊: "面向移动边缘计算的边缘服务器部署及资源分配研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112995280A (en) * 2021-02-03 2021-06-18 北京邮电大学 Data distribution method and device for multi-content demand service
CN112799789A (en) * 2021-03-22 2021-05-14 腾讯科技（深圳）有限公司 Node cluster management method, device, equipment and storage medium
CN112799789B (en) * 2021-03-22 2023-08-11 腾讯科技（深圳）有限公司 Node cluster management method, device, equipment and storage medium
CN113472844A (en) * 2021-05-26 2021-10-01 北京邮电大学 Edge computing server deployment method, device and equipment for Internet of vehicles

Also Published As

Publication number Publication date
CN111988168B (en) 2021-11-26

Similar Documents

Publication Publication Date Title
CN111988168B (en) Edge service deployment method and device and electronic equipment
CN110297848B (en) Recommendation model training method, terminal and storage medium based on federal learning
CN107305611B (en) Method and device for establishing model corresponding to malicious account and method and device for identifying malicious account
US10679136B2 (en) Decision processing and information sharing in distributed computing environment
CN104081392A (en) Influence scores for social media profiles
WO2020244230A1 (en) Resource transfer method, apparatus and device, and red packet issuing method, apparatus and device
CN111488529B (en) Information processing method, information processing apparatus, server, and storage medium
CN109886300A (en) A kind of user's clustering method, device and equipment
CN107357649B (en) Method and device for determining system resource deployment strategy and electronic equipment
CN110750498A (en) Object access method, device and storage medium
CN113572721B (en) Abnormal access detection method and device, electronic equipment and storage medium
CN111274012B (en) Service scheduling method, device, electronic equipment and storage medium
CN111881469A (en) Data processing method and device
CN114125813B (en) Signal coverage range determining method based on mobile phone signaling and related device
CN110019372B (en) Data monitoring method, device, server and storage medium
CN110650438B (en) User standing area similarity judgment method, device, equipment and medium
CN110020129B (en) Click rate correction method, prediction method, device, computing equipment and storage medium
CN110708361A (en) System, method and device for determining grade of digital content publishing user and server
CN111984867B (en) Network resource determining method and device
CN114996578A (en) Model training method, target object selection method, device and electronic equipment
CN109146122A (en) A kind of probability forecasting method, device, electronic equipment and computer storage medium
CN115130026A (en) Target object determination method, device, medium and electronic equipment
CN112015924A (en) Streaming media caching method and device and computer storage medium
CN111104528A (en) Picture obtaining method and device and client
CN105468603A (en) Data selection method and apparatus

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant