CN114679748A - Collaborative optimization method between MEC servers - Google Patents

Collaborative optimization method between MEC servers Download PDF

Info

Publication number
CN114679748A
CN114679748A CN202210189840.1A CN202210189840A CN114679748A CN 114679748 A CN114679748 A CN 114679748A CN 202210189840 A CN202210189840 A CN 202210189840A CN 114679748 A CN114679748 A CN 114679748A
Authority
CN
China
Prior art keywords
mec
mec server
server
local
energy consumption
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210189840.1A
Other languages
Chinese (zh)
Inventor
江凇
汪大洋
蔡昊
李沛
贾平
柳旭
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.)
Information and Telecommunication Branch of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
Information and Telecommunication Branch of State Grid Jiangsu Electric Power Co Ltd
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 Information and Telecommunication Branch of State Grid Jiangsu Electric Power Co Ltd filed Critical Information and Telecommunication Branch of State Grid Jiangsu Electric Power Co Ltd
Priority to CN202210189840.1A priority Critical patent/CN114679748A/en
Publication of CN114679748A publication Critical patent/CN114679748A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H04W28/086—Load balancing or load distribution among access entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/08—Load balancing or load distribution
    • H04W28/09—Management thereof
    • H04W28/0925—Management thereof using policies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
    • H04W52/02—Power saving arrangements
    • H04W52/0209—Power saving arrangements in terminal devices
    • 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)
  • Computer And Data Communications (AREA)

Abstract

The invention discloses a collaborative optimization method among MEC servers, which comprises the steps of determining the energy consumption of a local MEC server for executing tasks, the energy consumption of adjacent MEC servers for executing tasks and the energy consumption of the local MEC server for unloading partial tasks to the adjacent MEC servers; determining total energy consumption of the system based on the obtained energy consumptions; establishing a collaborative optimization model between MEC servers by taking the minimum total energy consumption of the system as an optimization target; and solving the collaborative optimization model among the MEC servers to obtain the unloading rate of the tasks. The invention also considers the decision making of the unloading rate in the unloading process to achieve the purpose of load balancing.

Description

Collaborative optimization method between MEC servers
Technical Field
The invention relates to the technical field of cloud computing, in particular to a collaborative optimization method among MEC servers.
Background
In the data transmission and processing process, the heterogeneity and difference of the communication, calculation and storage resources needed by the service in different network segments are strong, the bearing relationship between the service and the resources and the connection relationship between the resources in different network segments are complex, and the integrated management of the end-to-end resources cannot be realized. In a traditional centralized management mode, a mobile service is sent to a cloud computing platform for processing, so that great transmission delay and computing pressure are caused, and the service requirements of a large number of delay sensitive services cannot be met. On the other hand, while the moving edge calculation may reduce the delay caused by communication, it may cause excessive processing delay due to limited computational power.
Disclosure of Invention
The invention aims to solve the problems in the prior art, and provides a collaborative optimization method among MEC servers, which comprehensively analyzes the interaction between the unloading decision and the resource allocation of the MEC servers and performs combined optimization on the unloading decision and the resource allocation of the MEC servers.
In order to achieve the technical purpose, the invention adopts the following technical scheme.
A method for collaborative optimization among MEC servers comprises the following steps:
determining energy consumption of a local MEC server for executing tasks, energy consumption of an adjacent MEC server for executing tasks and energy consumption of the local MEC server for unloading part of tasks to the adjacent MEC server;
determining total energy consumption of the system based on the obtained energy consumptions;
establishing a collaborative optimization model between MEC servers by taking the minimum total energy consumption of the system as an optimization target;
and solving the collaborative optimization model among the MEC servers to obtain the unloading rate of the tasks.
Further, the inter-MEC server collaborative optimization model is represented as follows:
Etot，ij(t)＝max{ΔEi(t)，Ei，j(t)+ΔEj(t)+Ej，i(t)}
wherein Etot，ij(t) Total System energy consumption, Δ Ei(t) is a local MEC server niEnergy consumption for executing tasks; ei，j(t) Power consumption consumed to offload portions of the computational task, Δ Ej(t) is an adjacent MEC server njEnergy consumption for executing tasks, Ej，i(t) energy consumption required for the neighboring MEC server to transmit part of the computation result back to the local server.
Further, energy consumption Δ E of local MEC server i to execute taskiThe calculation method of (t) is as follows:
Figure BDA0003524146390000021
wherein muiAs an intermediate parameter of the local MEC server, lambdaiFor the arrival rate, δ, of neighboring MEC servers to local MEC serveriIn order to be the load factor,
μi＝1/Texe，i(t)，Texe，i(t) is a local MEC server niPerforming a computing task TkTime of (P)powerThe energy consumed for transferring data.
Still further, local MEC server niTime T for executing a computing taskexe，iThe calculation method of (t) is as follows:
Figure BDA0003524146390000031
wherein DiAmount of data calculated for local MEC Server, XiNumber of CPU cycles occupied for each task, fRIs the computing power of the MEC server.
Further, the offloading part of the computing task consumes power Ei，jThe expression of (t) is:
Figure BDA0003524146390000032
where α is the unload rate, DiFor locally calculated data quantity, Ri，j(t) is MEC Server niTo MEC server njThe transmission rate therebetween.
Further, energy consumption E required for the neighboring MEC server to transmit part of the calculation result back to the local serverj，iThe expression of (t) is:
Figure BDA0003524146390000041
where α is the unload rate, λjFor arrival rate of local MEC server to neighboring MEC server, DjAmount of data, R, calculated for local MEC serveri，j(t) is MEC Server niTo MEC server njTransmission rate of (P) powerThe energy consumed for transferring data.
Further, adjacent MEC servers njEnergy consumption Δ E for executing tasksjThe expression of (t) is:
Figure BDA0003524146390000042
wherein mujAs an intermediate parameter of the neighboring MEC server, δiAs a load factor, PpowerEnergy consumed for transmitting data, λjIs the arrival rate of the local MEC server to the neighboring MEC server.
Further, local MEC server niTo adjacent MEC servers njWith a transmission rate R betweeni，j(t) the expression is:
Figure BDA0003524146390000051
wherein B ismFor the channel bandwidth, Pi,j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njTransmission power of gi,j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njChannel gain, σ, betweeni,j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njThe noise variance of (2).
The invention has the following beneficial technical effects:
the invention considers that partial edge unloading can be carried out besides all local calculation and all edge unloading, namely partial unloading can be carried out to the edge node for auxiliary calculation when the terminal equipment can not carry out calculation by itself, thereby improving the calculation efficiency. Meanwhile, after the computing task is unloaded to the edge node, the edge node of the receiving party can select to process the whole computing task by itself or select another edge node to share the computing task. The selected edge node and the edge node of the receiving party cooperatively process tasks, when a calculation unloading decision is determined, a corresponding calculation model is determined mainly according to a situation and the calculation model at that time, and meanwhile, the decision making of the unloading rate in the unloading process is considered to achieve the purpose of load balancing.
Drawings
Fig. 1 is a schematic flowchart of a method for collaborative optimization of an MEC server according to an embodiment;
FIG. 2 is a diagram illustrating a comparison of system delays in an exemplary embodiment;
FIG. 3 is a diagram illustrating the comparison of the energy consumption of the system in the exemplary embodiment.
Detailed Description
Specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
An embodiment of a method for collaborative optimization between MEC servers, as shown in fig. 1, includes:
determining energy consumption of a local MEC server for executing tasks, energy consumption of an adjacent MEC server for executing tasks and energy consumption of the local MEC server for unloading part of tasks to the adjacent MEC server;
determining total energy consumption of the system based on the obtained energy consumptions;
establishing a collaborative optimization model between MEC servers by taking the minimum total energy consumption of the system as an optimization target;
and solving the collaborative optimization model among the MEC servers to obtain the unloading rate of the tasks.
In a specific embodiment, different offloading policies may be applied in the process of performing computation offloading on the service MEC server, and different offloading policies may bring different computation models, so that the computation models mainly depend on offloading decisions, and the service terminal performs offloading on the service MEC serverA binary offload policy is usually followed at this time, i.e. each task can be offloaded either at the local MEC server or remotely at the edge MEC server. Herein with a iE {0, 1} indicates that the ith task is local (a)i0) or at the edge server (a)i1) is performed.
For the local MEC server, let the frequency of the CPU, which is the processing power allocated to the service terminal itself for computation, be denoted fi localThen, the power consumption of the service terminal for locally processing data may be expressed as:
Figure BDA0003524146390000061
wherein k is1Representing the effective switched capacitance associated with the chip architecture in the service terminal. As can be seen from the above, the energy consumption calculated locally by the service terminal can be expressed as:
Figure BDA0003524146390000062
therefore, the data amount processed by the service terminal in local computation is represented as:
Figure BDA0003524146390000063
where c is the data processing density.
For edge server node computation, when a local MEC server (service terminal) generates a computation task, the local MEC server may select an edge MEC server node within its communication range and offload the computation data of the task to the edge node for computation. We assume the processing power of the edge server to be
Figure BDA0003524146390000071
The power consumption of the MEC server (edge node) to process the data is:
Figure BDA0003524146390000072
wherein k is2Representing the effective switched capacitance associated with the edge server chip architecture. Therefore, the edge node k has an energy consumption of processing data in one calculation as
Figure BDA0003524146390000073
The edge node thus computes the amount of data processed as
Figure BDA0003524146390000074
For the communication model between the local MEC server and the neighboring MEC server (or traffic terminal and edge node), the communication involves offloading data to the edge node. In a network architecture, data may involve communication in the process of being offloaded to an edge node. To model the offloading process, we note the path loss as d and θ, where d and θ represent the transmitter-to-receiver distance and path loss exponent, respectively. The channel fading coefficient is represented by h, which is modeled as a circularly symmetric complex gaussian random variable. When data is transmitted and unloaded on the channel, the transmission rate is as follows:
Figure BDA0003524146390000075
wherein
Figure BDA0003524146390000076
For transmission power of service terminals, omega0Is the power of white gaussian noise and is,
Figure BDA0003524146390000077
the distance from the service terminal to the edge node k in the t time slot. However, when the service terminal performs data transmission, the calculation is carried out by unloading the service terminal to a plurality of edge nodesAnd thus the energy consumed in the communication may be related to the unloaded path.
In the communication transmission process, each service terminal has a communication range, and we can assume that the coverage range of each service terminal is R, and in the communication process, an edge node capable of unloading is found in a three-dimensional space with a radius of R, in which case a single service terminal may cover multiple edge nodes for unloading, so that the cooperative unloading in the case of multiple edge nodes may involve the design written in a model, in which the use of a communication model may be involved many times.
The resources of the edge nodes are still very limited compared to the cloud center. With the increase of the number of service terminals, it is difficult for a single MEC server to simultaneously satisfy different requirements of the service terminals for offloading services. The load status of MEC servers in a cluster varies. For example, in an emergency, a large amount of data is uploaded by the information acquisition terminal for processing, so that some MEC servers need to process a large amount of service requests, the load rate is high, and part of the MEC servers are relatively idle and in a low-load state.
Therefore, in the specific embodiment, a mode of dispersing the task of a single service terminal to adjacent MEC servers for performing cooperative computing is provided, so as to optimize the resource utilization rate and further reduce the time delay of the system.
In local offload computation, task TkBy local MEC server niAnd (4) directly calculating. By Lt(CPU calculation frequency) representation task TkMay be defined as:
Lt＝DtXt。
wherein DtIs the amount of data processed, XtIs the frequency required to complete the task.
Let Q betIndicating the number of CPU cycles required by the MEC server to process a single computational task, which is determined by the type of application and can be obtained by off-line measurements. f. ofRIs the computing power of the MEC server, satisfies f R≤fmax. Therefore, the calculation rate R of the local MEC serverl(t) can be expressed as:
Figure BDA0003524146390000091
assuming that tasks generated by the mobile service terminal are subject to Poisson distribution, the tasks are represented by lambdaiReaches MEC server niThe scheduler of (2). Modeling MEC servers of access points as M/M/1 queues to MEC server niThe task of calculation follows the Poisson process, and the arrival rate is lambdai. Therefore, the average time delay Δ T of the local MEC server to complete the taskl(t) can be expressed as:
Figure BDA0003524146390000092
wherein, mul＝1/Texe,l(t)。Texe,l(T) performing a computing task T for the local MEC serverkCan be expressed as:
Figure BDA0003524146390000093
in the specific embodiment, a local computation model is optimized, the model is designed through cooperative unloading between edge nodes, and a task T is calculatedkCan be divided into two parts: (1-. alpha.) DtFor local MEC servers niCalculation of α DtFor adjacent MEC servers njCalculation, where α is the unload rate, the processed results are eventually merged to the local MEC server niIn (1). Suppose arriving at MEC Server niThe task of (1) follows the Poisson process, niTask scheduler by load factor deltaiIs determined by the value of (1-delta) and the arrival rate isi)λiAverage task execution time of Texe,i(t) of (d). At the same time, local MEC server niAverage time delay delta T for completing task i(t) can be expressed as: wherein mui＝1/Texe,i(t)，Texe,i(t) can be defined as:
Figure BDA0003524146390000101
wherein D istFor local MEC servers niThe data amount processed by local calculation can be obtained by the above formula
Figure BDA0003524146390000102
To be determined.
And, reach the neighboring MEC server njThe unloading task of (2) also follows the poisson process, and the arrival rate is deltaiλi. Similarly, adjacent MEC servers njAverage delay delta T for completion of a taskj(t) can be expressed as:
Figure BDA0003524146390000103
wherein muj＝1/Texe,j(t)，Texe,j(t) can be defined as:
Figure BDA0003524146390000104
wherein D istFor adjacent edge servers njThe amount of data to be processed can be calculated by the above formula
Figure BDA0003524146390000105
To be determined.
When selecting adjacent MEC server n in time slot tjThen, MEC server niTo njThe transmission rate of (d) may be expressed as:
Figure BDA0003524146390000106
wherein B ismIs the channel bandwidth, Pi,j(t) is n in time slot tiTo njTransmission power of gi,j(t) is n in time slot tiTo njChannel gain, σ, betweeni,j(t) is n in time slot tiTo njThe noise variance of (2). Therefore, in this mode, the communication delay T of part of the calculation task is unloadedi,j(t) can be defined as:
Figure BDA0003524146390000107
due to adjacent MEC server njMerging results to local MEC server n after executing partial computation taskiIn, therefore, MEC server njTransmitting partial calculation results to niTime delay T ofj,i(t) can be defined as:
Figure BDA0003524146390000111
in this mode, all computation tasks T are only offloaded and completed kThen, the total delay T can be measuredtot,ij(t), which can be expressed as:
Figure BDA0003524146390000112
combining the above analysis of the two computation patterns, the total time delay for the system to perform the computation task can be expressed as:
Ttot(t)＝(1-an(t))ΔTl(t)+an(t)Ttot,ij(t)
the service delay model is used above, and for the system energy consumption model, the transmission rate of the unmanned aerial vehicle terminal uploaded to the edge nodes and the transmission rate of the edge nodes in cooperative cooperation can be known according to a formula. Model one is for the local MEC server to perform the offload computation, in which the task T is performedkBy local MEC server niAnd (4) directly calculating.
Figure BDA0003524146390000113
In another modelThe design of a model is carried out through cooperative unloading between edge nodes, and a task T is calculated similarly to a time delay modelkThe method is divided into two parts: (1-. alpha.) DtFor local MEC servers niCalculation of α DtFor adjacent MEC servers njCalculating, where α is the unload rate, α is unloaded to the edge, 1- α is local;
the processed results are finally merged to the local MEC server niIn (1). In this mode, all computation tasks T are only offloaded and completedkThen, the total energy consumption E can be measuredtot,ij(t), which can be expressed as:
Figure BDA0003524146390000121
aiming at the problems of low self computing efficiency of a user equipment terminal, overlarge cloud platform transmission delay and the like, the invention provides an MEC server cooperative computing model, which can set the computing unloading rate between the terminal user equipment and the MEC server in the training process, and roughly divides the unloading process into three stages: the method comprises the following steps that a local MEC server unloads data to adjacent MEC servers, collaborative calculation unloading is carried out between the adjacent MEC servers, the adjacent MEC servers deliver calculation unloading results to the local MEC server, in the unloading process, experiment simulation needs to be carried out on unloading rate, service delay and system consumption, a simulation graph is analyzed and compared, and a relatively optimal result is obtained; in the process of achieving the calculation load balance, the invention coordinates the unloading rate among different devices to minimize the time delay and the energy consumption of the system.
Fig. 2 shows the simulation of unloading delay, the abscissa is unloading rate, and the ordinate is average unloading delay. With the change of the unloading rate, the system delay is seen to firstly decrease and then increase according to the image curve. As can be seen from the following figure, when the unloading rate is 0.65, the time delay is minimum, the system is reliable, and the efficiency is highest.
Fig. 3 shows the simulation of unloading energy consumption, in which the abscissa of the simulation graph is the unloading rate, and the ordinate is the overall energy consumption of the system, and as the unloading rate changes, it can be seen from the graph that the energy consumption of the system first decreases and then increases. As can be seen from fig. 2, when the unloading rate is 0.85, the overall energy consumption of the system is minimal.
In practical application, loads among different nodes need to be balanced, that is, a node with an overweight load unloads to a node with a light load, and the load rate acts as time delay and energy consumption of the whole balance system, so that the whole consumption of the system is reduced to the minimum. In the two unloading processes, the unloading rate is established. For the time delay aspect, the establishment of the proper unloading rate can effectively reduce the total transmission time delay and improve the reliability of the system. In the process of achieving the calculation load balance, the invention coordinates the unloading rate among different devices to minimize the time delay and the energy consumption of the system.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the modules and the system described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow of the flowcharts and/or figures, and combinations of flow 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.
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.
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.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.

Claims (8)

1. A method for collaborative optimization between MEC servers is characterized by comprising the following steps:
determining energy consumption of a local MEC server for executing tasks, energy consumption of an adjacent MEC server for executing tasks and energy consumption of the local MEC server for unloading part of tasks to the adjacent MEC server;
determining total energy consumption of the system based on the obtained energy consumptions;
establishing a collaborative optimization model between MEC servers by taking the minimum total energy consumption of the system as an optimization target;
and solving the collaborative optimization model among the MEC servers to obtain the unloading rate of the tasks.
2. The method of claim 1, wherein the inter-MEC collaborative optimization model is expressed as follows:
Etot，ij(t)＝max{ΔEi(t)，Ei，j(t)+ΔEj(t)+Ej，i(t)}
wherein Etot，ij(t) Total System energy consumption, Δ Ei(t) is a local MEC server niEnergy consumption for executing tasks; ei，j(t) Power consumption consumed to offload portions of the computational task, Δ Ej(t) is an adjacent MEC server njEnergy consumption for executing tasks, Ej，i(t) energy consumption required for the neighboring MEC server to transmit part of the computation result back to the local server.
3. The method of claim 2, wherein energy consumption Δ E of local MEC server i to execute task isiThe calculation method of (t) is as follows:
Figure FDA0003524146380000021
Wherein muiAs an intermediate parameter of the local MEC server, lambdaiFor the arrival rate, δ, of neighboring MEC servers to the local MEC serveriIn order to be the load factor,
μi＝1/Texe，i(t)，Texe，i(t) is a local MEC server niPerforming a computing task TkTime of (P)powerThe energy consumed for transferring data.
4. The method of claim 3, wherein the local MEC server n is a server n of the MECiTime T for executing a computing taskexe，iThe calculation method of (t) is as follows:
Figure FDA0003524146380000022
wherein DiAmount of data calculated for local MEC Server, XiNumber of CPU cycles occupied for each task, fRIs the computing power of the MEC server.
5. The method of claim 2, wherein the offloading part of the computing tasks consumes power Ei，jThe expression of (t) is:
Figure FDA0003524146380000031
where α is the unload rate, DiFor locally calculated data quantity, Ri，j(t) is MEC Server niTo MEC server njThe transmission rate therebetween.
6. The method of claim 2, wherein the MEC inter-server cooperation optimization method,
energy consumption E required by neighboring MEC servers to transmit partial computation results back to local serverj，iThe expression of (t) is:
Figure FDA0003524146380000032
where α is the unload rate, λjFor arrival rate of local MEC server to neighboring MEC server, D jAmount of data, R, computed for local MEC serveri，j(t) is MEC Server niTo MEC server njTransmission rate of (P)powerThe energy consumed for transferring data.
7. The method of claim 2, wherein the neighboring MEC servers n are co-optimized with each otherjEnergy consumption Δ E for executing tasksjThe expression of (t) is:
Figure FDA0003524146380000041
wherein mujAs an intermediate parameter of the neighboring MEC server, δiAs a load factor, PpowerEnergy consumed for transmitting data, λjIs the arrival rate of the local MEC server to the neighboring MEC server.
8. The method of any one of claims 5 and 6, wherein the MEC server n is a server niTo MEC server njWith a transmission rate R betweeni，j(t) the expression is:
Figure FDA0003524146380000042
wherein B ismFor the channel bandwidth, Pi，j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njTransmission power of gi，j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njChannel gain, σ, betweeni，j(t) is the local MEC server n in time slot tiTo adjacent MEC servers njThe noise variance of (2).
CN202210189840.1A 2022-02-28 2022-02-28 Collaborative optimization method between MEC servers Pending CN114679748A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210189840.1A CN114679748A (en) 2022-02-28 2022-02-28 Collaborative optimization method between MEC servers

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210189840.1A CN114679748A (en) 2022-02-28 2022-02-28 Collaborative optimization method between MEC servers

Publications (1)

Publication Number Publication Date
CN114679748A true CN114679748A (en) 2022-06-28

Family

ID=82071585

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210189840.1A Pending CN114679748A (en) 2022-02-28 2022-02-28 Collaborative optimization method between MEC servers

Country Status (1)

Country Link
CN (1) CN114679748A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112235387A (en) * 2020-10-10 2021-01-15 华北电力大学（保定） Multi-node cooperative computing unloading method based on energy consumption minimization
CN112235803A (en) * 2020-08-27 2021-01-15 华北电力大学（保定） Resource allocation joint optimization method for user cooperation in WPT-MEC system
CN113597013A (en) * 2021-08-05 2021-11-02 哈尔滨工业大学 Cooperative task scheduling method in mobile edge computing under user mobile scene
CN113709249A (en) * 2021-08-30 2021-11-26 北京邮电大学 Safe balanced unloading method and system for driving assisting service
CN113810908A (en) * 2021-08-24 2021-12-17 华北电力大学（保定） MEC system safety unloading method, equipment and MEC system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112235803A (en) * 2020-08-27 2021-01-15 华北电力大学（保定） Resource allocation joint optimization method for user cooperation in WPT-MEC system
CN112235387A (en) * 2020-10-10 2021-01-15 华北电力大学（保定） Multi-node cooperative computing unloading method based on energy consumption minimization
CN113597013A (en) * 2021-08-05 2021-11-02 哈尔滨工业大学 Cooperative task scheduling method in mobile edge computing under user mobile scene
CN113810908A (en) * 2021-08-24 2021-12-17 华北电力大学（保定） MEC system safety unloading method, equipment and MEC system
CN113709249A (en) * 2021-08-30 2021-11-26 北京邮电大学 Safe balanced unloading method and system for driving assisting service

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
FEI HAO: "2L-MC3：A Two-Layer Multi-Community-Cloud/Cloudlet Social Collaborative Paradigm for Mobile Edge Computing", IEEE INTERNET OF THINGS JOURNAL（VOLUME：6，JUNE 2019）, 26 August 2018 (2018-08-26) *
李智勇: "车辆边缘计算环境下任务卸载研究综述", 计算机学报第44卷第5期, 15 May 2021 (2021-05-15) *

Similar Documents

Publication Publication Date Title
CN112689303B (en) Edge cloud cooperative resource joint allocation method, system and application
Chen et al. Efficiency and fairness oriented dynamic task offloading in internet of vehicles
CN113950066A (en) Single server part calculation unloading method, system and equipment under mobile edge environment
CN107295109A (en) Task unloading and power distribution joint decision method in self-organizing network cloud computing
CN109951873B (en) Task unloading mechanism under asymmetric and uncertain information in fog computing of Internet of things
CN112148492B (en) Service deployment and resource allocation method considering multi-user mobility
CN113918240B (en) Task unloading method and device
CN111711962B (en) Cooperative scheduling method for subtasks of mobile edge computing system
CN113810233A (en) Distributed computation unloading method based on computation network cooperation in random network
CN112860429B (en) Cost-effective optimization system and method for task offloading in mobile edge computing system
CN111836284B (en) Energy consumption optimization calculation and unloading method and system based on mobile edge calculation
CN112231085A (en) Mobile terminal task migration method based on time perception in collaborative environment
CN114585006B (en) Edge computing task unloading and resource allocation method based on deep learning
CN112988347B (en) Edge computing unloading method and system for reducing energy consumption and cost sum of system
Tang et al. Research on heterogeneous computation resource allocation based on data-driven method
CN113573363A (en) MEC calculation unloading and resource allocation method based on deep reinforcement learning
CN115955479A (en) Task rapid scheduling and resource management method in cloud edge cooperation system
CN111158893B (en) Task unloading method, system, equipment and medium applied to fog computing network
CN115150893A (en) MEC task unloading strategy method based on task division and D2D
Chen et al. A game theoretic approach to task offloading for multi-data-source tasks in mobile edge computing
CN117579701A (en) Mobile edge network computing and unloading method and system
CN111611069B (en) Multi-type task migration method among multiple data centers
CN114615705B (en) Single-user resource allocation strategy method based on 5G network
CN114980216B (en) Dependency task unloading system and method based on mobile edge calculation
CN114679748A (en) Collaborative optimization method between MEC servers

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