CN111988787B - Task network access and service placement position selection method and system - Google Patents
Task network access and service placement position selection method and system Download PDFInfo
- Publication number
- CN111988787B CN111988787B CN202010733646.6A CN202010733646A CN111988787B CN 111988787 B CN111988787 B CN 111988787B CN 202010733646 A CN202010733646 A CN 202010733646A CN 111988787 B CN111988787 B CN 111988787B
- Authority
- CN
- China
- Prior art keywords
- task
- network access
- service
- service placement
- optimal solution
- 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.)
- Active
Links
- 238000010187 selection method Methods 0.000 title claims description 13
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000005265 energy consumption Methods 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 230000007704 transition Effects 0.000 claims abstract description 15
- 239000002245 particle Substances 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000004590 computer program Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000001934 delay Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present disclosure provides a method and a system for selecting a network access and service placement position of a task, comprising the following steps: obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system; generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task; obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function; optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities; the method and the device can simultaneously consider the two attributes of delay and energy consumption, so that the delay is lower, the energy consumption is smaller, the QoS requirement of a user is met, and the task unloading rate is improved.
Description
Technical Field
The present disclosure relates to the field of mobile communications technologies, and in particular, to a method and system for selecting a network access and service placement location of a task.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the explosive growth of smart devices, many emerging applications, such as augmented reality, face recognition, interactive games, etc., are receiving more and more attention. Such applications not only require intensive computing resources, but also impose higher demands on latency. Mobile devices are limited in both computational power and energy due to physical size limitations. Whereas traditional cloud computing provides a centralized service for applications, it is inevitable that large end-to-end delays occur due to the large distance between the service hosting cloud and the user. Thus, a new calculation paradigm of moving edge calculation has been proposed.
Mobile edge computing is widely recognized as a promising technique that breaks the boundary between a substantial increase in computing demands and an ever-increasing demand for user quality of service (Quality of Service, qoS). The mobile edge computing system stores a large amount of computing resources and services by deploying an edge cloud in the vicinity of a user, so that cloud computing capabilities and IT environments can be brought close to the user, thereby achieving the purposes of reducing latency and saving device energy.
The inventor discovers that the situation of multi-user preemption of resources and network congestion can occur because the computing and storage resources of the edge cloud of the system are limited; the current network access and service placement method based on the task in the mobile edge computing scene is generally single in considered influencing factors, and the final network access and service placement position selection method cannot obviously reduce the overall performance of the system.
Disclosure of Invention
In order to solve the defects of the prior art, the present disclosure provides a method and a system for selecting a network access and service placement position of a task, which can consider two attributes of delay and energy consumption at the same time, so that the delay is lower, the energy consumption is smaller, the QoS requirement of a user is met, and the task unloading rate is improved.
In order to achieve the above purpose, the present disclosure adopts the following technical scheme:
the first aspect of the present disclosure provides a method for selecting a network access and service placement location of a task.
A method for selecting network access and service placement positions of tasks comprises the following steps:
obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
A second aspect of the present disclosure provides a network access and service placement location selection system for a task.
A network access and service placement location selection system for a task, comprising:
a data acquisition module configured to: obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
a random solution generation module configured to: generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
an optimal solution acquisition module configured to: obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
a location selection module configured to: and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
A third aspect of the present disclosure provides a medium having stored thereon a program which when executed by a processor performs the steps in a network access and service placement location selection method for the tasks as described in the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in the network access and service placement location selection method of the tasks according to the first aspect of the present disclosure when the program is executed.
Compared with the prior art, the beneficial effects of the present disclosure are:
1. the method, the system, the medium and the electronic equipment provided by the disclosure can consider two attributes of delay and energy consumption at the same time, so that the time delay is lower, the energy consumption is smaller, the QoS requirement of a user is met, and the task unloading rate is improved.
2. According to the method, the system, the medium and the electronic equipment provided by the disclosure, when the access point selection of the task and the service placement position can not be in the same cloud, the Dijkstra algorithm is used for calculating the optimal path from the network access base station a to the service placement base station b, so that the minimum communication delay from the network access base station to the service placement base station is ensured.
3. According to the method, the system, the medium and the electronic equipment provided by the disclosure, two attributes of delay and energy consumption are comprehensively considered, an effect function related to delay and energy consumption is designed, the function is minimized as a fitness function, repeated iterative optimization is performed through an improved particle swarm algorithm, and finally, the network access and service placement base station with the optimal task is obtained, and the accuracy of task unloading is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure, illustrate and explain the exemplary embodiments of the disclosure and together with the description serve to explain the disclosure, and do not constitute an undue limitation on the disclosure.
Fig. 1 is a schematic diagram of a mobile edge computing scenario provided in embodiment 1 of the present disclosure.
Fig. 2 is a flowchart of a network access and service placement location selection method for the task provided in embodiment 1 of the present disclosure.
Detailed Description
The disclosure is further described below with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments in accordance with the present disclosure. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
Example 1:
as shown in fig. 1, the mobile edge computing system contemplated by the present disclosure includes a number of mobile devices and a number of edge servers. The equipment uploads the task to an edge cloud which can serve the area where the task is located, so that a network is accessed; and (5) arbitrarily selecting one edge cloud placement service. The network access base station and the service placement base station of the task may be the same or different, but it should be noted that the task can only select the base station whose service scope includes the task as the network access point. After the completion of the edge execution, the task is transmitted back to the local device via the wireless link.
Like car networking, smart city, smart home, etc., are typical applications in mobile edge computing scenarios. In these typical applications, smartphones, ipads, etc. can be used as terminal devices, where tasks can be performed either locally or off-load to an edge cloud. The embodiment selects the optimal network access and service placement base station for the task, which not only can make up the deficiency of the computing and storage capacity of the terminal equipment, but also can effectively reduce the time delay and the energy consumption and meet the QoS requirement of the user.
As shown in fig. 2, embodiment 1 of the present disclosure provides a method for selecting a network access and service placement location for a task, including the following steps:
obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
The detailed steps are as follows:
s1: and initializing a system. The method comprises the steps of obtaining resource limitation of each edge cloud access point and service resource limitation.
S2: and acquiring real-time information of the current task. The real-time information of the task includes the geographical location information of the task executed in the time slot t, the required access point resource requirement, the service resource requirement, the data length required to be transmitted by the task and the CPU period required by the task execution, and the energy consumption required by the task execution.
S3: and (3) determining the fitness function of the system according to the information of the current task and the parameter information of the system obtained in the step (S2). The fitness function of this embodiment is a weighted value that minimizes the time delay and energy consumption of the system, and specifically includes the following steps:
s in t The switching time delay of executing the task in the time slot t; q (Q) t Queuing delay for executing tasks in time slot t; c (C) t The communication time delay of executing the task in the time slot t; p (P) t The calculation time delay of executing the task in the time slot t; e (E) j (t) is the energy consumption of executing tasks on compute node j; lambda (lambda) 1 t ，λ 2 t Belonging to [0,1 ]]A weighting coefficient representing the calculated time delay and energy in decision making; y is j k (t) represents the decision of the access point selection of user k at time t, if y j k (t) =1 means that at time t the task of user k is performed on access point j, otherwise means that the task is not performed on access point j; r is (r) j k (t) access point requirements for the task performed at access point j; p (P) j Is the access resource capacity of the edge cloud j; x is x i k (t) represents the service placement decision of user k in time slot t, if x i k (t) =1 means that the service of the task is placed on edge cloud i, otherwise means that the service is not placed on edge cloud i; s is(s) i k (t) is the service resource demand of the edge cloud of the task that user k places at edge cloud i at time t; r is R i Is the service resource capacity of edge cloud i.
Wherein constraint (2) ensures that each task can be executed on only one edge cloud.
Constraint (3) represents task network access decision variable y j k The value range of (t).
Constraint (4) indicates that the total amount of access tasks in each cloud cannot exceed the resource limit of the access point.
Constraint (5) ensures that each service is assigned and can only be assigned to one edge cloud.
Constraint (6) ensures that the total number of services in each cloud does not exceed the capacity limit.
Constraint (7) represents a user's service placement decision variable x i k The value range of (t).
Constraint (8) represents a weighting factor for time delay and energy consumption of the task at decision time. Lambda (lambda) 1 t ，λ 2 t Belonging to [0,1 ]]Under different schemes, the task has different sensitivity to time delay and energy consumption, and the task is more sensitive to delay like the Internet of vehicles, virtual reality, face recognition systems and the like; and when the power of the terminal equipment is low, the task is more sensitive to energy consumption. In this embodiment lambda 1 t ＝0.4，λ 2 t =0.6, i.e. the scheme is energy consumption sensitive.
The network access and service placement process of the specific task is as follows:
(1) Access point selection: at each time slot, the system makes AP selection decisions for each task. The task may be performed on the user's local device or off-load to other external nodes (i.e., edge servers or remote clouds). Designing a binary vector y j k (t) to represent dynamic access point decisions. If y j k (t) =1, then the task of user k at time t is performed on edge cloud j; otherwise, y j k (t) =0. Note that in a given time slot, there is and only one access point per task, i.e. the access point selects as follows:
wherein r is j k And (t) is the access point requirement of the task performed by user k at access point j for time slot tset. Constraint (11) indicates that at no time t, the task of accessing edge cloud j can exceed the access resource limit of edge cloud j.
(1) Service placement selection: at each time slot t, the system selects an access point access network for each task and then selects a service placement location for the task to provide service requirements for the task. In particular, for a single task, there is no necessary association of access point selection and service placement decisions. The services of a task may be placed on any edge cloud, but an access point can only select an access point that can serve the task. Similar to access point selection, service placement selection is:
s in i k (t) is the service resource demand of the edge cloud of the task that user k places at edge cloud i at time t. Constraint (12) indicates that the service must be allocated and exactly oneEdge clouds. Constraint (13) ensures that the total number of services in the cloud does not exceed its capacity limit. Constraint (14) is a service placement decision variable, if x i k (t) =1, then the service representing the task of user k at time t is placed on edge cloud i, otherwise, there is no.
The embodiment comprehensively considers the influence of delay and energy consumption on QoS of users, wherein the delay comprises switching delay, queuing delay, communication delay and calculation delay, and the specific calculation process is as follows:
(1) Switching delay: due to the mobility of the user, it may be necessary to switch to other access points to obtain good user awareness. In return, there is some handoff delay. Suppose S 0 Is the delay generated by a handoff, then the total handoff delay of the system at time slot t is:
(2) Queuing delay: since the number of users accessing each access point varies with time, the access point tasks may be too much when the access point is preferentially selected according to the location of the user, resulting in queuing problems. To better analyze delay performance, the present embodiment incorporates queuing delays into the model. Definition q 0 The waiting time when the task is queued is the previous waiting time, the queuing delay of the task executed in the time slot t is:
(3) Communication delay: in this embodiment, the task access point selection and service placement location may not be in the same cloud, and it is obvious that some hot point clouds may be relieved, but at the same time, an additional communication delay will be generated by accessing the service through the edge cloud, so when considering the service placement decision x i k (t) and access point selection decision y j k At (t), the total communication delay of the system at time slot t can be expressed as:
middle l ij (t) represents the communication delay from access point j to edge cloud i.
(4) Calculating the delay: in this embodiment, the tasks may be performed at the user's local device or may be offloaded to other computing nodes for execution. Since the calculation demand of a task is affected by various factors such as the location of a user, the condition of a network, and the like. The present embodiment therefore represents the calculated demand as a time-varying quantity λ (t), C j (t) represents the computing power of the computing node j to perform tasks at time slot t (i.e., CPU cycles per second), and thus the computation delay can be expressed as:
(5) Energy consumption: at time slot t, the energy consumption of task execution includes the energy consumption of the user transmitting data to the MEC server and the energy consumption of the user in an idle state. O is used in this embodiment j (t) represents the energy consumption of performing a task at the computing node j at time slot t, so the energy consumption at time slot t can be expressed as:
furthermore, the access point selection and service placement location of the task may not be in the same cloud. Obviously, this relieves some of the hotspot cloud from being stressed, but at the same time, access to the service via the edge cloud will create additional communication delays. The present embodiment calculates the best path from the network access base station a to the service placement base station b using Dijkstra's algorithm, which is a typical single-source shortest path algorithm. Network access and service placement may be on the same base station or may be achieved by switching to other base stations via n (n > =0) base stations. If the distance from a to b is shortest directly, the middle does not need to be switched to other base stations, otherwise, the middle may pass through 1 or n base stations. This embodiment can thereby ensure that the communication delay from the network access base station to the service placement base station is minimal.
S4: a plurality of random solutions for network access and service placement are generated, each solution should contain network access and service placement base stations for several tasks. In the specific embodiment, the number of the base stations is N, and the number of the users is K. Each solution may be defined as a matrix X of 2n×k, where the first N rows represent network access locations of users, the last N rows represent service placement locations of users, i.e., X [ a ] [ b ] =1 (0 < a < N) represents that mobile user b access point selects as edge cloud a, X [ a ] [ b ] =1 (N < a < 2N) represents that mobile user b services are placed in edge cloud a, X [ a ] [ b ] =0 represents that user b does not select edge cloud a as network access or service placement location.
And S5, respectively calculating the fitness value of each random solution in S4 according to the fitness function in the Step 3. Finding out the solution with the highest adaptability in each solution, namely the local optimal solution, wherein the network access and service placement base station corresponding to the solution is the optimal network access and service placement base station in the current solution, and is marked as P id The method comprises the steps of carrying out a first treatment on the surface of the Finding the solution with the highest fitness value in all solutions of the iteration and the previous iteration, taking the network access and service placement base station of the solution as the global optimal solution, and marking as P gd 。
S6: optimizing by using a particle swarm algorithm to obtain the predicted optimal network access and service placement position of the iteration; and respectively selecting the most suitable network access and service placement base station for each task according to the designed transition probability according to the obtained predicted optimal network access and service placement positions to carry out task unloading.
The specific implementation process is as follows:
the locally optimal solution P obtained by S5 id And a globally optimal solution P gd The three-dimensional coordinates of each base station corresponding to the global optimal solution and the local optimal solution can be obtained respectively.
The system updates each solution according to the three-dimensional coordinates and the following update formula:
V id ＝w×V id +c 1 ×r 1 ×(P id -X id )+c 2 ×r 2 ×(P gd -X id ) (20)
X id ＝X id +V id (21)
v in id Is the speed of solving the update of the i-th dimension; x is X id Network access or service placement coordinates of the solution; w is the inertial weight, p id Historical best coordinates of network access or service placement, p gd Global best coordinates for network access or service placement, c 1 And c 2 Is a learning factor, also called acceleration constant, r 1 And r 2 Is [0,1 ]]Uniform random numbers within the range.
The three parts in the formula (20) respectively represent the trend of maintaining the previous speed of the user, the trend of approaching the historical optimal position of the user and the trend of approaching the optimal position of the group, and the setting of c 1 ＝c 2 That is, the effect of local and global optima on the solution update is considered to be the same. Equation (21) updates the solved network access or service placement coordinates.
Whereby optimized network access and service placement coordinates for each solution can be obtained. Obviously, the calculated optimal coordinates are not necessarily the same as the coordinates of the base station in the actual scene. To solve this problem, the present embodiment designs a transition probability as a criterion for further selecting network access and service placement base stations.
The transition probability is:
where, since the service range of each base station is limited, we define n' to be the set of base stations that can serve the current task. The transition probability takes into account the following two properties: one is the distance d between each base station i and the calculated optimal coordinates i The other is the number of tasks queued on base station i, denoted path i Then according to probability P i Selecting the most appropriate from all base stationsAnd selecting a network and serving the base station to perform task unloading.
S: and judging whether the iteration meets a termination condition. If the termination condition is not satisfied, repeating S5-S7; if the iteration number reaches a given maximum value or the optimal solution does not change for a period of time, the iteration is terminated; and recording the highest fitness value, outputting a network access and service placement base station corresponding to the fitness value, and unloading the task.
Example 2:
embodiment 2 of the present disclosure provides a network access and service placement location selection system for a task, including:
a data acquisition module configured to: obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
a random solution generation module configured to: generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
an optimal solution acquisition module configured to: obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
a location selection module configured to: and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
The working method of the system is the same as the network access and service placement location selection method of the task provided in embodiment 1, and will not be described here again.
Example 3:
embodiment 3 of the present disclosure provides a medium having a program stored thereon, which when executed by a processor, performs the steps in the network access and service placement location selection method for the task described in embodiment 1 of the present disclosure, the steps being:
obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
The detailed steps are the same as the network access and service placement location selection method of the task provided in embodiment 1, and will not be repeated here.
Example 4:
embodiment 4 of the present disclosure provides an electronic device, including a memory, a processor, and a program stored on the memory and executable on the processor, where the processor executes the program to implement steps in a network access and service placement location selection method for tasks as described in embodiment 1 of the present disclosure, and the steps are:
obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
and optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and the global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities.
The detailed steps are the same as the network access and service placement location selection method of the task provided in embodiment 1, and will not be repeated here.
It will be apparent to those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The foregoing description of the preferred embodiments of the present disclosure is provided only and not intended to limit the disclosure so that various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (10)
1. A method for selecting a network access and service placement location for a task, comprising the steps of:
obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities;
the fitness function is a weighted value for minimizing the time delay and the energy consumption of the system, and specifically comprises the following steps:
s in t The switching time delay of executing the task in the time slot t; q (Q) t Queuing delay for executing tasks in time slot t; c (C) t The communication time delay of executing the task in the time slot t; p (P) t The calculation time delay of executing the task in the time slot t; e (E) j (t) is the energy consumption of executing tasks on compute node j; lambda (lambda) 1 t ，λ 2 t Belonging to [0,1 ]]A weighting coefficient representing the calculated time delay and energy in decision making; y is j k (t) represents the decision of the access point selection of user k at time t, if y j k (t) =1 means that at time t the task of user k is performed on access point j, otherwise means that the task is not performed on access point j; r is (r) j k (t) access point requirements for the task performed at access point j; p (P) j Is the access resource capacity of the edge cloud j; x is x i k (t) represents the service placement decision of user k in time slot t, if x i k (t) =1 means that the service of the task is placed on edge cloud i, otherwise means that the service is not placed on edge cloud i; s is(s) i k (t) is the service resource demand of the edge cloud of the task that user k places at edge cloud i at time t; r is R i Is the service resource capacity of edge cloud i.
2. The method for selecting a network access and service placement location for a task according to claim 1, wherein the fitness value of each random solution is calculated according to a fitness function, the solution with the highest fitness in each solution is taken as a locally optimal solution, and the solution with the highest fitness in all solutions in the current iteration and the previous iteration is taken as a globally optimal solution.
3. The method for selecting a network access and service placement location of a task according to claim 1, wherein the real-time status data of the current task includes at least geographical location information of the task to be executed in a certain time slot, a required access point resource requirement, a service resource requirement, a data length required to be transmitted by the task, a CPU cycle required for the task to be executed, and energy consumption required for the task to be executed;
alternatively, the parameter data of the edge computing system includes at least individual edge cloud access point resource limitations and service resource limitations.
4. The method for selecting a network access and service placement location for a task according to claim 1, wherein the fitness function is a minimum value of a weighted value of a time delay and an energy consumption for executing the task in a preset time slot, and the time delay includes a handover time delay, a queuing time delay, a communication time delay and a calculation time delay.
5. The method for task network access and service placement location selection according to claim 1, wherein Dijkstra algorithm is used to calculate the best path from network access base station to service placement base station when task access point selection and service placement location may not be in the same cloud.
6. The method for selecting the network access and service placement location for the task according to claim 1, wherein the three-dimensional coordinates of each base station corresponding to the global optimal solution and the local optimal solution are obtained according to the local optimal solution and the global optimal solution, respectively, and the three-dimensional coordinates of each base station after optimization are obtained according to the obtained three-dimensional coordinates of each base station.
7. The method for selecting network access and service placement locations for tasks according to claim 1, wherein the preset transition probabilities are constructed according to the distance between each base station and the obtained optimized coordinates and the number of tasks queued on the corresponding base station, and the most appropriate network option and service placement base station are selected from all base stations according to the preset transition probabilities to perform task offloading;
or judging whether the iteration meets the termination condition, and if not, repeatedly acquiring a local optimal solution and a global optimal solution; if the iteration number reaches a given maximum value or the optimal solution does not change for a period of time, the iteration is terminated; and recording the highest fitness value, outputting a network access and service placement base station corresponding to the fitness value, and unloading the task.
8. A system for selecting a network access and service placement location for a task, comprising:
a data acquisition module configured to: obtaining an adaptability function according to the acquired real-time state data of the current task and the acquired parameter data of the edge computing system;
a random solution generation module configured to: generating a plurality of random solutions of network access and service placement, wherein each random solution comprises a plurality of network access and service placement base stations of at least one task;
an optimal solution acquisition module configured to: obtaining a local optimal solution and a global optimal solution in each random solution according to the fitness function;
a location selection module configured to: optimizing by utilizing a particle swarm algorithm according to the obtained local optimal solution and global optimal solution to obtain optimal network access and service placement position coordinates, and obtaining real network access and service placement positions according to preset transition probabilities;
the fitness function is a weighted value for minimizing the time delay and the energy consumption of the system, and specifically comprises the following steps:
s in t The switching time delay of executing the task in the time slot t; q (Q) t Queuing delay for executing tasks in time slot t; c (C) t The communication time delay of executing the task in the time slot t; p (P) t The calculation time delay of executing the task in the time slot t; e (E) j (t) is the energy consumption of executing tasks on compute node j; lambda (lambda) 1 t ，λ 2 t Belonging to [0,1 ]]A weighting coefficient representing the calculated time delay and energy in decision making; y is j k (t) represents the decision of the access point selection of user k at time t, if y j k (t) =1 means that at time t the task of user k is performed on access point j, otherwise means that the task is not performed on access point j; r is (r) j k (t) access point requirements for the task performed at access point j; p (P) j Is the access resource capacity of the edge cloud j; x is x i k (t) represents the service placement decision of user k in time slot t, if x i k (t) =1 means that the service of the task is placed on edge cloud i, otherwise means that the service is not placed on edge cloud i; s is(s) i k (t) is the service resource demand of the edge cloud of the task that user k places at edge cloud i at time t; r is R i Is the service resource capacity of edge cloud i.
9. A medium having stored thereon a program, which when executed by a processor performs the steps of the network access and service placement location selection method of the task of any one of claims 1-7.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor performs the steps in the network access and service placement location selection method for performing the tasks of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010733646.6A CN111988787B (en) | 2020-07-27 | 2020-07-27 | Task network access and service placement position selection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010733646.6A CN111988787B (en) | 2020-07-27 | 2020-07-27 | Task network access and service placement position selection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111988787A CN111988787A (en) | 2020-11-24 |
| CN111988787B true CN111988787B (en) | 2023-04-28 |
Family
ID=73444409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010733646.6A Active CN111988787B (en) | 2020-07-27 | 2020-07-27 | Task network access and service placement position selection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111988787B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113472844B (en) * | 2021-05-26 | 2023-06-16 | 北京邮电大学 | Edge computing server deployment method, device and equipment for Internet of vehicles |
| CN114040438B (en) * | 2021-10-29 | 2024-07-09 | 华润数字科技有限公司 | Networking method of cooperative network, terminal equipment and computer readable storage medium |
| CN114978794B (en) * | 2022-05-19 | 2023-06-23 | 北京有竹居网络技术有限公司 | Network access method, device, storage medium and electronic equipment |
| CN115134366B (en) * | 2022-06-28 | 2024-03-15 | 山东海量信息技术研究院 | Mobile edge distribution network server placement method and system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109218414A (en) * | 2018-08-27 | 2019-01-15 | 杭州中恒云能源互联网技术有限公司 | A kind of distributed computing method of smart grid-oriented hybrid network framework |
| CN109548031A (en) * | 2018-03-01 | 2019-03-29 | 重庆大学 | A kind of non-equilibrium edge cloud network access and resource allocation mechanism |
| CN110602633A (en) * | 2019-08-02 | 2019-12-20 | 广东工业大学 | Explosive flow-oriented mobile edge computing unmanned aerial vehicle cluster auxiliary communication method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11546361B2 (en) * | 2019-01-04 | 2023-01-03 | Samsung Electronics Co., Ltd. | Method and apparatus for organizing and detecting swarms in a network |
-
2020
- 2020-07-27 CN CN202010733646.6A patent/CN111988787B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109548031A (en) * | 2018-03-01 | 2019-03-29 | 重庆大学 | A kind of non-equilibrium edge cloud network access and resource allocation mechanism |
| CN109218414A (en) * | 2018-08-27 | 2019-01-15 | 杭州中恒云能源互联网技术有限公司 | A kind of distributed computing method of smart grid-oriented hybrid network framework |
| CN110602633A (en) * | 2019-08-02 | 2019-12-20 | 广东工业大学 | Explosive flow-oriented mobile edge computing unmanned aerial vehicle cluster auxiliary communication method |
Non-Patent Citations (2)
| Title |
|---|
| Jun-Qing Li et. al."Hybrid Artificial Bee Colony Algorithm for a Parallel Batching Distributed Flow-Shop Problem With Deteriorating Jobs".《IEEE Transactions on Cybernetics》.2019,全文. * |
| Lei Yang et. al."Joint Computation Partitioning and Resource Allocation for Latency Sensitive Applications in Mobile Edge Clouds".《Joint Computation Partitioning and Resource Allocation for Latency Sensitive Applications in Mobile Edge Clouds》.2017,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111988787A (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111988787B (en) | Task network access and service placement position selection method and system | |
| Chen et al. | Energy-efficient task offloading and resource allocation via deep reinforcement learning for augmented reality in mobile edge networks | |
| Mohammed et al. | Distributed inference acceleration with adaptive DNN partitioning and offloading | |
| CN113708972B (en) | Service function chain deployment method and device, electronic equipment and storage medium | |
| CN111414252A (en) | Task unloading method based on deep reinforcement learning | |
| CN113867843B (en) | Mobile edge computing task unloading method based on deep reinforcement learning | |
| CN110662238A (en) | Reinforced learning scheduling method and device for burst request under edge network | |
| CN108600299B (en) | Distributed multi-user computing task unloading method and system | |
| CN113076177B (en) | Dynamic migration method of virtual machine in edge computing environment | |
| CN113687875B (en) | Method and device for unloading vehicle tasks in Internet of vehicles | |
| CN113220356A (en) | User computing task unloading method in mobile edge computing | |
| CN113993218A (en) | Multi-agent DRL-based cooperative unloading and resource allocation method under MEC architecture | |
| Yang et al. | Cooperative task offloading for mobile edge computing based on multi-agent deep reinforcement learning | |
| CN114205353B (en) | Calculation unloading method based on hybrid action space reinforcement learning algorithm | |
| Ren et al. | Vehicular network edge intelligent management: A deep deterministic policy gradient approach for service offloading decision | |
| CN113645637B (en) | Method and device for unloading tasks of ultra-dense network, computer equipment and storage medium | |
| CN111511028A (en) | Multi-user resource allocation method, device, system and storage medium | |
| Bista et al. | Probabilistic computation offloading for mobile edge computing in dynamic network environment | |
| EP4024212A1 (en) | Method for scheduling interference workloads on edge network resources | |
| Henna et al. | Distributed and collaborative high-speed inference deep learning for mobile edge with topological dependencies | |
| CN115499875B (en) | Satellite internet task unloading method, system and readable storage medium | |
| Wang et al. | On Jointly optimizing partial offloading and SFC mapping: a cooperative dual-agent deep reinforcement learning approach | |
| CN111158893A (en) | Task unloading method, system, equipment and medium applied to fog computing network | |
| CN114615705B (en) | Single-user resource allocation strategy method based on 5G network | |
| CN111930435A (en) | Task unloading decision method based on PD-BPSO technology |
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 |