CN112689303B - Edge cloud cooperative resource joint allocation method, system and application - Google Patents

Edge cloud cooperative resource joint allocation method, system and application Download PDF

Info

Publication number
CN112689303B
CN112689303B CN202011584281.1A CN202011584281A CN112689303B CN 112689303 B CN112689303 B CN 112689303B CN 202011584281 A CN202011584281 A CN 202011584281A CN 112689303 B CN112689303 B CN 112689303B
Authority
CN
China
Prior art keywords
edge
user
task
cloud
unloading
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
Application number
CN202011584281.1A
Other languages
Chinese (zh)
Other versions
CN112689303A (en
Inventor
唐怀玉
周雨晨
陈健
郭兰图
杨龙
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.)
Xidian University
China Institute of Radio Wave Propagation CETC 22 Research Institute
Original Assignee
Xidian University
China Institute of Radio Wave Propagation CETC 22 Research Institute
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 Xidian University, China Institute of Radio Wave Propagation CETC 22 Research Institute filed Critical Xidian University
Priority to CN202011584281.1A priority Critical patent/CN112689303B/en
Publication of CN112689303A publication Critical patent/CN112689303A/en
Application granted granted Critical
Publication of CN112689303B publication Critical patent/CN112689303B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Mobile Radio Communication Systems (AREA)

Abstract

The invention belongs to the technical field of wireless communication, and discloses a method, a system and an application for edge cloud cooperative resource joint allocation, wherein a determined task unloading part is forwarded to selected assisting user equipment; the method comprises the steps that a cooperative communication mode is adopted, the assisting user equipment forwards a task unloading part to an edge server, and at the moment, in order to ensure the decoding success rate of edge service, the unloading user equipment simultaneously sends the task unloading part to the edge server in a frequency division multiple access mode; the edge server further splits the offloaded tasks to the cloud servers. The invention adopts the edge cloud cooperation technology and realizes the purpose of providing calculation unloading service for the user in a mode of user equipment assistance. Under the background of edge cloud cooperation, proper assisting equipment is selected for users needing to calculate and unload, the unloading task amount and communication resources are optimized, the time delay and energy consumption index requirements of different services are guaranteed, and the aim that the user calculation tasks are efficiently unloaded to edge clouds and even to clouds is achieved.

Description

Edge cloud cooperative resource joint allocation method, system and application
Technical Field
The invention belongs to the technical field of wireless communication, and particularly relates to a method, a system and application for edge cloud cooperative resource joint allocation.
Background
At present: with the continuous development of big data and internet of things technology, more and more intelligent applications are popularized in the field of wireless communication, and users can obtain rich intelligent business services through a wireless network. Under the background, the cloud computing technology provides technical support for intelligent application and service, and big data flowing through a wireless network can be analyzed and optimized by a cloud computing server to make system decisions, so that services with higher service quality and experience quality are brought to users. However, with the continuous development of communication technology and cloud computing technology, people no longer satisfy the service quality brought by the prior art, and an edge computing technology is developed in response to further improve the end-to-end time delay when a user acquires a service or further reduce the energy consumption generated when the user acquires the service. The edge computing technology can enable cloud computing to be close to a user, deploy a small server for an access point close to the user, and really provide computing services of short distance, high speed and high reliability for the user.
Considering that the amount of resource that can be driven by edge computing is limited compared to cloud computing, when a user needs some large computing services, an edge computing server is not enough to meet the computing needs of the user. Under the background, the concept of edge cloud cooperation is developed in order to ensure that a user can obtain computing services in a short distance and also ensure that the user can obtain sufficient computing resources. Jinke Ren et al studied the cooperation between Cloud Computing and Edge Computing in "connectivity Cloud and Edge Computing" published by "IEEE Transactions on vehicle Technology" (international institute of electrical and electronics engineers, vehicle Technology journal of 2019, volume 68, 5, month 5), so that part of the tasks of the mobile device can be jointly processed on the Edge node and the Cloud server, thereby improving the Edge Cloud work efficiency under limited communication and Computing capabilities. Junhui Zhao et al in 2019 proposed a side Cloud coordination scheme specially For a vehicle network in "calculation off and Resource Allocation For Assisted Offloading and Resource Allocation" published in IEEE Transactions on Vehicular Technology of International society of Electrical and electronics Engineers "(vol. 8, 2019, vol. 68, 8), and guaranteed delay constraints during vehicle calculation Offloading by jointly optimizing calculation Offloading decisions and calculation Resource Allocation.
However, the above solution does not consider that there is differentiation between user service types in an actual network environment, and different service types have different requirements on transmission and computation time delay and energy consumption. In addition, the user equipment is easily perceived by other adjacent user equipment when unloading the computing task, and the collaborative forwarding of the computing task is realized by fully utilizing each user equipment, so that the task accessibility at the edge computing server can be further improved.
Through the above analysis, the problems and defects of the prior art are as follows: the prior art does not consider that the user service types in the actual network environment are different, and different service types have different requirements on transmission and calculation time delay and energy consumption. In addition, user devices are easily perceived by other user devices in the vicinity when offloading computing tasks, however, these nearby devices are not utilized by the prior art.
The difficulty in solving the above problems and defects is: the weight coefficient can well represent the requirements of different user services on transmission and calculation time delay and energy consumption indexes, but how to realize the balance between the time delay and the energy consumption through reasonable resource allocation and task segmentation based on the weight coefficient is one of the difficulties of the invention. In addition, by utilizing the cooperative communication technology, the adjacent user equipment can be utilized, on one hand, the unloading efficiency of the edge server can be enhanced, but the problem solving difficulty is further caused.
The significance for solving the problems and the defects is as follows: based on the requirements of the user task on the transmission and calculation time delay and the energy consumption index, a reasonable optimization scheme can be formulated to determine key performance parameters of the user such as local calculation amount, uploading task amount, local transmission power, local calculation time delay, cooperative transmission power, edge calculation task amount, edge calculation time delay, cloud calculation task amount and cloud calculation time delay, so that the performance balance of time delay and energy consumption is ensured.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method, a system and application for edge cloud cooperative resource joint allocation.
The invention is realized in such a way, the joint allocation method of the edge cloud cooperative resources is characterized in that an unloading user firstly determines time delay and energy consumption weight based on self service type; the method comprises the steps that an unloading user selects an assisting device according to a link state, and determines local calculation amount, uploading task amount, local transmission power and local calculation time delay according to weight, and notices that in order to avoid interference among users, users in the coverage range of an adjacent edge server adopt a frequency division multiple access mode; the method comprises the steps that a user firstly transmits an uploading task to selected assisting equipment, and then unloads the uploading task to an edge server in a cooperative communication mode under the assistance of the assisting equipment, so that the edge server is ensured to accurately receive the unloading task, and at the moment, the cooperative transmission power in the cooperative communication process needs to be determined; and the edge server determines the edge computing task amount, the edge computing time delay, the cloud computing task amount and the cloud computing time delay according to the weight indexes of the user on the computing time delay and the computing energy consumption, and further unloads the cloud computing task to the cloud server, so that the whole unloading process is completed.
Further, the edge cloud cooperative resource joint allocation method specifically includes:
(1) the uninstaller determines the time delay and the energy consumption weight based on the service type of the uninstaller, and orders
Figure BDA0002865158830000031
And
Figure BDA0002865158830000032
respectively representing the weight indexes of the user u for communication energy consumption, communication time delay, calculated energy consumption and calculated time delay, wherein
Figure BDA0002865158830000033
And is
Figure BDA0002865158830000034
The larger the weight value is, the more sensitive the unloading task of the user to the index is;
(2) the uninstaller selects the assisting equipment according to the link state, and determines the local calculation amount, the uploading task amount, the local transmission power and the local calculation time delay according to the weight:
(2.1) assume that the set of alternative assisting devices for user U is UuLet the alternative device u' be its assisting device, then
Figure BDA0002865158830000035
Wherein g isu,u'、
Figure BDA0002865158830000036
And
Figure BDA0002865158830000037
respectively representing the power gain of the user u to the alternative device u', the edge server n associated with the user u to the user uuAnd alternative device u' to the edge server n associated with user uuThe power gain of (d);
(2.2) user u can optimize the local calculation amount a according to the weight set in (1)uUpload task amount 1-auLocal transmission power pu,1And calculating the time delay locally
Figure BDA0002865158830000038
The optimization problem can be modeled as:
Figure BDA0002865158830000039
wherein, Iu、Bu、c、
Figure BDA0002865158830000041
ξUserRespectively representing the total task load and the offload bandwidth (, calculating per bit) of user uThe number of CPUs (central processing units) required to be consumed by the task, local computation time delay and user equipment computation energy coefficient; in addition, the optimization variable pu,1And
Figure BDA0002865158830000042
if the boundary value is exceeded, the boundary value is directly set;
(2.3) the uninstalled user u determines the variable a in an alternating iteration modeu、pu,1And
Figure BDA0002865158830000043
(3) offload user u will first offload 1-a of the taskuPartly with transmission power pu,1Sending the data to the selected assisting device u', and then unloading 1-a of the task in a cooperative communication mode with the assistance of the assisting deviceuPartial offload to edge server nuAt this time, the cooperative transmission power of the offloaded user u and the assisting device u' is pu,2And pu'，pu,2And pu'Is obtained by the following optimization problem:
Figure BDA0002865158830000044
where the variable p is optimizedu,2And pu'If the limit value is exceeded, the limit value is directly set as the limit value; the first two terms of the objective function of the optimization problem OP3 are for pu,2And pu'The last two terms are with respect to p, respectivelyu,2And pu'The first two terms therefore need to be successive convex approximated, when the variable p isu,2And pu'The solution of (c) can be obtained by the following optimization problem:
Figure BDA0002865158830000045
wherein, the corner mark i represents the iteration number;
Figure BDA0002865158830000046
Figure BDA0002865158830000047
representing the function h (p)u,2,pu') At p isu,2First derivative of (1)
Figure BDA0002865158830000048
Figure BDA0002865158830000049
Representing p from the ith iterationu,2A value;
Figure BDA00028651588300000410
represents the function h (p)u,2,pu') At p isu'And substitution of the first derivative of (1)
Figure BDA00028651588300000411
Figure BDA00028651588300000412
Denotes p obtained from the ith iterationu'A value; the optimization problem OP4 is for pu,2And pu'By searching for H' (p)u,2) 0 and H' (p)u') The root of 0 can get p in the optimization problem OP3u,2And pu'The solution of (2); repeatedly updated p based on the idea of successive convex approximationu,2And pu'Up to p adjacent to two iterationsu,2And pu'Are respectively less than a certain precision, namely the algorithm is considered to be converged, and p is obtained during convergenceu,2And pu'Namely, the cooperative transmission power p of the user u and the assisting device u' in (3) is unloadedu,2And pu'The final solution of (2);
(4) edge server nuDetermining the edge calculation task amount b according to the weight index of the uninstaller u on the calculation time delay and the calculation energy consumptionuEdge calculated time delay
Figure BDA0002865158830000051
And cloud computing workload 1-buCloud computing latency
Figure BDA0002865158830000052
And will cloud computing task 1-buFurther unloading to a cloud server, and completing the whole unloading process:
(4.1) edge Server nuOptimizing the edge calculation task b according to the weight set in (1)uEdge calculated time delay
Figure BDA0002865158830000053
And cloud computing task volume 1-buCloud computing latency
Figure BDA0002865158830000054
The optimization problem can be modeled as:
Figure BDA0002865158830000055
xi thereinMECAnd xiCloudRepresenting an edge server computing energy coefficient and a cloud server computing energy coefficient; where variables are optimized
Figure BDA0002865158830000056
And
Figure BDA0002865158830000057
if the boundary value is exceeded, the boundary value is directly set;
(4.2) edge Server nuDetermining variable b by means of alternate iterationu、
Figure BDA0002865158830000058
And
Figure BDA0002865158830000059
(5) offload user u, edge server nuAnd the cloud server respectively calculates the rates based on the optimization results
Figure BDA00028651588300000510
And
Figure BDA00028651588300000511
handling task of uninstalling user uuMoiety, bu(1-au) Moiety and (1-b)u)(1-au) And partially, after the calculation is finished, the unloading user u collects all the calculation results and generates a final calculation result of the unloading task.
Further, the step (2.3) is carried out according to the following steps:
(2.3a) initialize a set of p for each offload user uu,1And
Figure BDA00028651588300000512
a value of (d);
(2.3b) based on the resulting pu,1And
Figure BDA00028651588300000513
optimizing variable auThe optimization problem constructed at this time is converted to auThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (a) is:
Figure BDA00028651588300000514
if a is obtainedu *If the value is more than 1, the value is 1;
(2.3c) based on a obtaineduOptimizing variables
Figure BDA00028651588300000515
The optimization problem constructed at this time is converted into one about
Figure BDA00028651588300000516
The convex optimization problem can be obtained based on a convex optimization theory
Figure BDA00028651588300000517
Is solved as
Figure BDA00028651588300000518
(2.3d) based on a obtaineduOptimizing variable pu,1When the first term of the objective function is with respect to pu,1With the second term relating to pu,1The first term, when the variable p is a continuous convex approximationu,1Can be obtained from the following optimization problem:
Figure BDA0002865158830000061
wherein, the corner mark i represents the iteration number;
Figure BDA0002865158830000062
Figure BDA0002865158830000063
representing the function f (p)u,1) At p isu,1And substitution of the first derivative of (1)
Figure BDA0002865158830000064
Figure BDA0002865158830000065
Representing p from the ith iterationu,1A value; the optimization problem OP2 is about pu,1By searching for F' (p)u,1) The root of 0 can get p in the optimization problem OP2u,1The solution of (1); repeatedly updated p based on the idea of successive convex approximationu,1Up to p adjacent to two iterationsu,1If the difference is less than a certain precision, the algorithm can be considered to be converged, and the newly obtained pu,1Value of p in optimization problem OP1u,1The solution of (2);
(2.3e) based on the results obtained in steps (2.3c) and (2.3d)
Figure BDA0002865158830000066
And
Figure BDA0002865158830000067
update auBased on the obtained auRefreshing
Figure BDA0002865158830000068
And
Figure BDA0002865158830000069
continuously circulating until the algorithm is converged, and obtaining a during convergenceu、pu,1And
Figure BDA00028651588300000610
namely the local calculated quantity a in the step (2.2)uLocal transmission power pu,1And local computing
Figure BDA00028651588300000611
The final solution of (c).
Further, the step (4.2) is carried out according to the following steps:
(4.2a) to edge Server nuInitializing a group
Figure BDA00028651588300000612
And
Figure BDA00028651588300000613
a value of (d);
(4.2b) based on the obtained
Figure BDA00028651588300000614
And
Figure BDA00028651588300000615
optimization variable buThe optimization problem constructed at this time is converted into one about buThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (A) is as follows:
Figure BDA00028651588300000616
(4.2c) based on obtainingB of (a)uOptimizing variables
Figure BDA00028651588300000617
And
Figure BDA00028651588300000618
the optimization problem constructed at this time is converted into one about
Figure BDA00028651588300000619
And
Figure BDA00028651588300000620
the convex optimization problem can be obtained based on a convex optimization theory
Figure BDA00028651588300000621
And
Figure BDA00028651588300000622
the solution of (2) is as follows:
Figure BDA00028651588300000623
and
Figure BDA00028651588300000624
(4.2d) based on that obtained in step (4.2c)
Figure BDA00028651588300000625
And
Figure BDA00028651588300000626
update buBased on b obtaineduRefreshing
Figure BDA00028651588300000627
And
Figure BDA00028651588300000628
continuously circulating until the algorithm is converged, and b obtained during convergenceu、
Figure BDA00028651588300000629
And
Figure BDA00028651588300000630
namely the task amount b of edge calculation in the step (4.1)uEdge calculated time delay
Figure BDA00028651588300000631
And cloud computing time delay
Figure BDA00028651588300000632
The final solution of (c).
It is a further object of the invention to provide a computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of: firstly, determining time delay and energy consumption weight based on self service type; the method comprises the steps that an unloading user selects an assisting device according to a link state, determines local calculated amount, uploading task amount, local transmission power and local calculation time delay according to weight, and notices that in order to avoid interference among users, users in a coverage range of an adjacent edge server adopt a frequency division multiple access mode; the method comprises the steps that a user firstly transmits an uploading task to selected assisting equipment, and then unloads the uploading task to an edge server in a cooperative communication mode under the assistance of the assisting equipment, so that the edge server is ensured to accurately receive the unloading task, and at the moment, the cooperative transmission power in the cooperative communication process needs to be determined; and the edge server determines the edge computing task quantity, the edge computing time delay, the cloud computing task quantity and the cloud computing time delay according to the weight index of the user on the computing time delay and the computing energy consumption, and further unloads the cloud computing task to the cloud server, so that the whole unloading process is completed.
It is another object of the present invention to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of: firstly, determining time delay and energy consumption weight based on self service type; the method comprises the steps that an unloading user selects an assisting device according to a link state, and determines local calculation amount, uploading task amount, local transmission power and local calculation time delay according to weight, and notices that in order to avoid interference among users, users in the coverage range of an adjacent edge server adopt a frequency division multiple access mode; the method comprises the steps that a user firstly transmits an uploading task to selected assisting equipment, and then unloads the uploading task to an edge server in a cooperative communication mode under the assistance of the assisting equipment, so that the edge server is ensured to accurately receive the unloading task, and at the moment, the cooperative transmission power in the cooperative communication process needs to be determined; and the edge server determines the edge computing task amount, the edge computing time delay, the cloud computing task amount and the cloud computing time delay according to the weight indexes of the user on the computing time delay and the computing energy consumption, and further unloads the cloud computing task to the cloud server, so that the whole unloading process is completed.
Another objective of the present invention is to provide an information data processing terminal, where the information data processing terminal is configured to implement the edge cloud cooperative resource joint allocation method.
Another objective of the present invention is to provide an edge computing server, where the edge computing server is configured to implement the edge cloud cooperative resource joint allocation method.
The invention also aims to provide a cloud computing server, which is used for realizing the edge cloud cooperative resource joint allocation method.
Another objective of the present invention is to provide a wireless communication system, where the wireless communication system is configured to implement the edge cloud cooperative resource joint allocation method.
By combining all the technical schemes, the invention has the advantages and positive effects that: according to the invention, the user assists in unloading the cloud task, the accessibility of the unloaded task can be improved, and meanwhile, the minimization of the weighted sum of the time delay and the energy efficiency in the two aspects of communication and calculation is realized based on the weight index requirements of the unloaded user on the time delay and the energy consumption. The invention adopts the edge cloud cooperation technology and realizes the purpose of providing calculation unloading service for the user in a mode of user equipment assistance. Under the background of edge cloud cooperation, proper assisting equipment is selected for users needing computing and unloading, unloading task quantity and communication resources are optimized, time delay and energy consumption index requirements of different services are guaranteed, and the aim of efficiently unloading computing tasks of the users to edge clouds and even clouds is fulfilled.
The invention specifically describes the application of a side cloud cooperation technology in a multi-user computing task unloading and wireless communication scene, and guarantees the time delay and energy consumption index requirements of different unloading services in the communication and computing aspects by means of jointly allocating computing resources and communication resources (including assisting device selection, computing task splitting proportion, transmission power and computing time delay), so that the aim of efficiently unloading user computing tasks to edge clouds and even clouds is fulfilled.
The invention provides a user-assistance-based edge cloud cooperative resource joint allocation method, which particularly describes the application of an edge cloud cooperative technology in a multi-user computing task unloading and wireless communication scene, ensures the time delay and energy consumption index requirements of different unloading services in two aspects of communication and computing by a mode of joint allocation of computing resources and communication resources (including assisting equipment selection, computing task splitting proportion, transmission power and computing time delay), and achieves the aim of efficiently unloading user computing tasks to edge clouds and even clouds.
The invention provides a user-assistance-based edge cloud cooperative resource joint allocation method, which considers that the user service types in the actual network environment are different, and the requirements of different service types on transmission and calculation time delay and energy consumption are different. In addition, the user equipment is easily perceived by other adjacent user equipment when unloading the computing task, and the user equipment is fully utilized to realize the cooperative forwarding of the computing task, so that the task accessibility at the edge computing server can be further improved.
The invention adopts the edge cloud cooperation technology and realizes the purpose of providing calculation unloading service for the user in a mode of user equipment assistance. Under the background of edge cloud cooperation, proper assisting equipment is selected for users needing to calculate and unload, the unloading task amount and communication resources are optimized, the time delay and energy consumption index requirements of different services are guaranteed, and the aim that the user calculation tasks are efficiently unloaded to edge clouds and even to clouds is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a method for jointly allocating edge cloud cooperative resources according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an edge cloud cooperative resource joint allocation system according to an embodiment of the present invention;
in fig. 2: 1. a time delay and energy consumption weight determining module; 2. a parameter determination module; 3. a cooperative communication transmission module; 4. unloading the processing module; 5. and a calculation result output module.
Fig. 3 is a diagram of a user equipment assisted side cloud collaborative model provided by an embodiment of the present invention.
Fig. 4 is a general flowchart of an implementation of the edge cloud cooperative resource joint allocation method provided in the embodiment of the present invention.
Fig. 5 is a diagram of exemplary performance under different energy consumption and delay weights provided by an embodiment of the present invention.
Fig. 6 is a comparison graph of performance of different technologies provided by the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Aiming at the problems in the prior art, the invention provides a method, a system and application for edge cloud cooperative resource joint allocation. The invention relates to edge cloud cooperation, which relates to two aspects of resource cooperation and service management cooperation: 1. the resource cooperation refers to the calculation resource cooperation, and can call the resources of the cloud center to supplement under the condition that the local resources and the edge resources of the user are insufficient, so as to meet the requirements of the user side application on the resources. 2. The service management cooperation can provide related network services for clients according to the requirements of energy consumption and time delay indexes through the service quality of the value-added network services of the cloud server. The present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the edge cloud cooperative resource joint allocation method provided by the present invention includes the following steps:
s101: the method comprises the steps that an unloading user determines time delay and energy consumption weight based on the service type of the unloading user;
s102: the unloading user selects the assisting equipment according to the link state, and determines local calculated amount, uploading task amount, local transmission power and local calculation time delay according to the weight;
s103: the method comprises the steps that a user firstly transmits an uploading task to selected assisting equipment, and then unloads the uploading task to an edge server in a cooperative communication mode under the assistance of the assisting equipment, so that the edge server is ensured to accurately receive the unloading task, and at the moment, the cooperative transmission power in the cooperative communication process needs to be determined;
s104: the edge server determines the edge computing task quantity, the edge computing time delay, the cloud computing task quantity and the cloud computing time delay according to the weight indexes of the user on the computing time delay and the computing energy consumption, and further unloads the cloud computing task to the cloud server, so that the whole unloading process is completed;
s105: and the unloading user, the edge server and the cloud server respectively process the divided unloading tasks at respective calculation rates based on the optimization results, and the unloading user summarizes all the calculation results after the calculation is finished and generates a final calculation result.
Persons of ordinary skill in the art of the edge cloud cooperative resource joint allocation method provided by the present invention may also use other steps to implement, and the edge cloud cooperative resource joint allocation method provided by the present invention in fig. 1 is only a specific embodiment.
As shown in fig. 2, the edge cloud cooperative resource joint allocation system provided by the present invention includes:
the time delay and energy consumption weight determining module 1 is used for determining time delay and energy consumption weight based on self service type by an unloading user;
the parameter determination module 2 is used for enabling the unloading user to select the assisting equipment according to the link state and determining local calculated amount, uploading task amount, local transmission power and local calculation time delay according to the weight;
the cooperative communication transmission module 3 is used for transmitting the uploading task to the selected assisting equipment by the user and unloading the uploading task to the edge server by adopting a cooperative communication mode under the assistance of the assisting equipment;
the unloading processing module 4 is used for determining the edge computing task amount, the edge computing time delay, the cloud computing task amount and the cloud computing time delay by the edge server according to the weight indexes of the user on the computing time delay and the computing energy consumption, and further unloading the cloud computing task to the cloud server to complete the whole unloading process;
and the calculation result output module 5 is used for processing the divided unloading tasks at the respective calculation rates based on the optimization results by the unloading users, the edge server and the cloud server, summarizing the calculation results of all parts by the unloading users after the calculation is finished, and generating a final calculation result.
The technical scheme of the invention is further described in the following with reference to the attached drawings.
As shown in fig. 3, the present invention uses a user equipment assisted edge cloud cooperation model diagram, in which a base station integrates a cloud server, and an access point at the edge of a network integrates an edge server. Three steps are required for the unloading user to complete task unloading: firstly, forwarding the determined task unloading part to the selected assisting user equipment; then, assisting the user equipment to forward the task unloading part to the edge server in a cooperative communication mode, and simultaneously sending the task unloading part to the edge server by the unloading user equipment in a frequency division multiple access mode in order to ensure the decoding success rate of the edge service; finally, the edge server further splits the offloaded task to the cloud server, and since the edge server is usually connected to the cloud server in a wired manner, this part of communication resources can be assumed to be sufficient, and only the computation energy consumption and the computation latency are considered.
As shown in fig. 4, the specific implementation steps of the present invention are as follows:
the method comprises the following steps: and the unloading user determines the time delay and the energy consumption weight based on the service type of the unloading user. Order to
Figure BDA0002865158830000111
Figure BDA0002865158830000112
And
Figure BDA0002865158830000113
respectively representing the weight indexes of the user u on communication energy consumption, communication time delay, calculated energy consumption and calculated time delay, wherein
Figure BDA0002865158830000114
And is
Figure BDA0002865158830000115
The larger the weight value is, the more sensitive the user's unloading task is to the index.
Step two: the uninstaller selects the assisting equipment according to the link state, and determines the local calculation amount, the uploading task amount, the local transmission power and the local calculation time delay according to the weight:
2.1) assume that the set of alternative assisting devices for user U is UuLet the alternative device u' be its assisting device, then
Figure BDA0002865158830000116
Wherein g isu,u'、
Figure BDA0002865158830000117
And
Figure BDA0002865158830000118
respectively representing the power gain of the user u to the alternative device u', the edge server n associated with the user u to the user uuAnd alternative device u' to user u associationEdge server n ofuThe power gain of (c).
2.2) the user u can optimize the local calculated amount a according to the weight set in step 1uUpload task amount 1-auLocal transmission power pu,1And locally calculating the time delay
Figure BDA0002865158830000121
The optimization problem can be modeled as:
Figure BDA0002865158830000122
wherein, Iu、Bu、c、
Figure BDA0002865158830000123
ξUserRespectively representing the total task amount (unit: bits) of a user u, the unloading frequency bandwidth (unit: Hz), the number of CPUs (unit: CPU/bit) required to be consumed by calculating each bit of task, the local calculation time delay (unit: s), and the user equipment calculation energy coefficient (which can be represented by multiplying the CPU utilization rate by the energy efficiency coefficient); in addition, the optimization variable pu,1And
Figure BDA0002865158830000124
if the upper and lower limits are present, the boundary value is set as it is if the limit value is exceeded.
2.3) the uninstalled user u determines the variable a in an alternative iteration modeu、pu,1And
Figure BDA0002865158830000125
2.3.1) initialize a set of p for each offload user uu,1And
Figure BDA0002865158830000126
a value of (d);
2.3.2) based on p obtainedu,1And
Figure BDA0002865158830000127
optimizing variablesauThe optimization problem constructed at this time is converted to one about auThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (a) is:
Figure BDA0002865158830000128
wherein
Figure BDA0002865158830000129
It means that if x is greater than 1, the value is 1, and if x is less than 0, the value is 0.
2.3.3) based on a obtaineduOptimizing variables
Figure BDA00028651588300001210
The optimization problem constructed at this time is converted into one about
Figure BDA00028651588300001211
The convex optimization problem can be obtained based on a convex optimization theory
Figure BDA00028651588300001212
Is solved as
Figure BDA00028651588300001213
2.3.4) based on a obtaineduOptimizing variable pu,1When the first term of the objective function is with respect to pu,1With a second term relating to pu,1The first term, thus requiring a continuous convex approximation of the first term, when the variable p isu,1Can be obtained from the following optimization problem:
Figure BDA00028651588300001214
wherein the content of the first and second substances,
Figure BDA0002865158830000131
Figure BDA0002865158830000132
representing the function f (p)u,1) At pu,1First derivative of (1)
Figure BDA0002865158830000133
Figure BDA0002865158830000134
Representing p from the ith iterationu,1A value; the optimization problem OP2 is about pu,1By searching for F' (p)u,1) The root of 0 can get p in the optimization problem OP2u,1The solution of (2); repeatedly updated p based on the idea of successive convex approximationu,1Up to p of two adjacent iterationsu,1If the difference is less than a certain precision, the algorithm can be considered to be converged, and the newly obtained pu,1Value of p in optimization problem OP1u,1The solution of (c).
2.3.5) based on the products obtained in steps 2.3.3) and 2.3.4)
Figure BDA0002865158830000135
And
Figure BDA0002865158830000136
update auBased on the obtained auRefreshing
Figure BDA0002865158830000137
And
Figure BDA0002865158830000138
continuously circulating until the algorithm is converged, and obtaining a during convergenceu、pu,1And
Figure BDA0002865158830000139
namely the local calculated quantity a in the step 2.2)uLocal transmission power pu,1And local computing
Figure BDA00028651588300001310
The final solution of (c).
Step three:offload user u will first offload 1-a of the taskuPartly at transmission power pu,1Sending the data to the selected assisting equipment u', and then unloading 1-a of the task in a cooperative communication mode with the assistance of the assisting equipmentuPartial offload to edge server nuAt this time, the cooperative transmission power of the offloaded user u and the assisting device u' is pu,2And pu'，pu,2And pu'The solution of (c) can be obtained by the following optimization problem:
Figure BDA00028651588300001311
where the variable p is optimizedu,2And pu'If the boundary value is exceeded, the boundary value is directly set; the first two terms of the objective function of the optimization problem OP3 are for pu,2And pu'The last two terms are with respect to p, respectivelyu,2And pu'The first two terms therefore need to be successive convex approximated, when the variable p isu,2And pu'The solution of (c) can be obtained by the following optimization problem:
Figure BDA00028651588300001312
wherein, the first and the second end of the pipe are connected with each other,
Figure BDA00028651588300001313
Figure BDA00028651588300001314
represents the function h (p)u,2,pu') At pu,2First derivative of (1)
Figure BDA00028651588300001315
Figure BDA00028651588300001316
Denotes p obtained from the ith iterationu,2The value of the sum of the values,
Figure BDA00028651588300001317
representing the function h (p)u,2,pu') At pu'First derivative of (1)
Figure BDA00028651588300001318
Figure BDA00028651588300001319
Representing p from the ith iterationu'A value; the optimization problem OP4 is for pu,2And pu'By searching for H' (p)u,2) 0 and H' (p)u') The root of 0 can get p in the optimization problem OP3u,2And pu'The solution of (1); repeatedly updated p based on the idea of successive convex approximationu,2And pu'Up to p adjacent to two iterationsu,2And pu'Are respectively less than a certain precision, namely the algorithm is considered to be converged, and p is obtained during convergenceu,2And pu'I.e. the cooperative transmission power p of the offloaded user u and the assisting device u' in step 3u,2And pu'The final solution of (c).
Step four: edge server nuDetermining the edge calculation task amount b according to the weight index of the uninstaller u to the calculation time delay and the calculation energy consumptionuEdge calculated time delay
Figure BDA0002865158830000141
And cloud computing task volume 1-buCloud computing latency
Figure BDA0002865158830000142
And will cloud computing task 1-buFurther unloading to the cloud server, thereby completing the whole unloading process:
4.1) edge Server nuOptimizing the edge calculation task b according to the weight set in the step 1uEdge calculated time delay
Figure BDA0002865158830000143
And cloud computing task volume 1-buCloud computing latency
Figure BDA0002865158830000144
The optimization problem can be modeled as:
Figure BDA0002865158830000145
in which ξMECAnd xiCloudRepresenting an edge server computing energy coefficient and a cloud server computing energy coefficient (the computing energy coefficient can be represented by multiplying the CPU utilization rate by an energy efficiency coefficient); where variables are optimized
Figure BDA0002865158830000146
And
Figure BDA0002865158830000147
if the upper and lower limits are present, the boundary value is set as it is if the limit value is exceeded.
4.2) edge Server nuDetermining variable b in an alternating iterative manneru、
Figure BDA0002865158830000148
And
Figure BDA0002865158830000149
4.2.1) to edge Server nuInitializing a group
Figure BDA00028651588300001410
And
Figure BDA00028651588300001411
a value of (d);
4.2.2) based on the results
Figure BDA00028651588300001412
And
Figure BDA00028651588300001413
optimization variable buOptimization of the structure at this timeQuestions are converted to about buThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (A) is as follows:
Figure BDA00028651588300001414
wherein
Figure BDA00028651588300001415
Meaning that if x is greater than 1, the value is 1, and if x is less than 0, the value is 0.
4.2.3) based on b obtaineduOptimizing variables
Figure BDA00028651588300001416
And
Figure BDA00028651588300001417
the optimization problem constructed at this time is converted into one about
Figure BDA00028651588300001418
And
Figure BDA00028651588300001419
the convex optimization problem can be obtained based on a convex optimization theory
Figure BDA00028651588300001420
And
Figure BDA00028651588300001421
the solution of (A) is as follows:
Figure BDA00028651588300001422
and
Figure BDA00028651588300001423
4.2.4) based on that obtained in step 4.2.3)
Figure BDA0002865158830000151
And
Figure BDA0002865158830000152
update buBased on b obtaineduRefreshing
Figure BDA0002865158830000153
And
Figure BDA0002865158830000154
continuously circulating until the algorithm is converged, and obtaining b during convergenceu、
Figure BDA0002865158830000155
And
Figure BDA0002865158830000156
namely the task amount b of edge calculation in the step 4.1)uEdge calculation time delay
Figure BDA0002865158830000157
And cloud computing latency
Figure BDA0002865158830000158
The final solution of (2).
Step five: offload user u, edge server nuAnd the cloud server respectively calculates the rates based on the optimization results
Figure BDA0002865158830000159
And
Figure BDA00028651588300001510
handling task of uninstalling user uuMoiety, bu(1-au) Moiety and (1-b)u)(1-au) And after the calculation is finished, the unloading user u collects the calculation results of all the parts and generates a final calculation result of the unloading task.
The technical effects of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 5, a diagram illustrating the present invention compared to conventional strategies is presented. Legend horizontal seatMarking as the total task amount of the uninstalled user; (a) comparing user unloading time delays under different energy consumption weights, (b) comparing user unloading energy consumption under different energy consumption weights, wherein the energy consumption weights represented by a dotted solid line and a round solid line are respectively
Figure BDA00028651588300001511
And
Figure BDA00028651588300001512
the corresponding delay weights are
Figure BDA00028651588300001513
And
Figure BDA00028651588300001514
the legend assumes spectral resource normalization with each unit energy coefficient being 1. As can be seen from the figure, as the total task amount increases, the total time delay and total energy consumption for unloading users cannot avoid generating an ascending trend; however, according to the different types of the unloading tasks or the different index requirements of the unloading tasks, the energy consumption and delay weight factors are adjusted, when the energy consumption weight is larger, a certain unloading delay can be sacrificed to obtain lower unloading energy consumption, and vice versa. Therefore, the time delay energy consumption weight represents the requirements of the unloading task on time delay and energy consumption, the time delay energy consumption weight is reasonably set, and the performance compromise of unloading time delay and unloading energy consumption can be realized.
As shown in fig. 6, a graph comparing the performance of the present invention with other technical effects is presented; (a) comparing user unloading time delay under different technologies, and (b) comparing user unloading energy consumption of different technologies. The contrast scheme is that the edge computing server provides business service for the user, and the cooperation of cloud center resources and business management is not considered. It can be seen that the system performance can be further improved in two aspects of time delay and reliability through edge cooperation and reasonable division of computing resources and task split ratios.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the present invention and the appended claims are not to be construed as limiting the scope of the invention, which is intended to cover all modifications, equivalents and improvements that are within the spirit and scope of the invention as defined by the appended claims.

Claims (9)

1. A side cloud cooperative resource joint distribution method is characterized in that an unloading user of the side cloud cooperative resource joint distribution method firstly determines time delay and energy consumption weight based on self service type; the method comprises the steps that an unloading user selects an assisting device according to a link state, determines local calculated amount, uploading task amount, local transmission power and local calculation time delay according to weight, and notices that in order to avoid interference among users, users in a coverage range of an adjacent edge server adopt a frequency division multiple access mode; the method comprises the steps that a user firstly transmits an uploading task to selected assisting equipment, and then unloads the uploading task to an edge server in a cooperative communication mode under the assistance of the assisting equipment, so that the edge server is ensured to accurately receive the unloading task, and at the moment, the cooperative transmission power in the cooperative communication process needs to be determined; the edge server determines the edge computing task quantity, the edge computing time delay, the cloud computing task quantity and the cloud computing time delay according to the weight indexes of the user on the computing time delay and the computing energy consumption, and further unloads the cloud computing task to the cloud server, so that the whole unloading process is completed;
the edge cloud cooperative resource joint allocation method specifically comprises the following steps:
(1) the uninstaller determines the time delay and the energy consumption weight based on the service type of the uninstaller, and orders
Figure FDA0003677033200000011
And
Figure FDA0003677033200000012
respectively representing the weight indexes of the user u on communication energy consumption, communication time delay, calculated energy consumption and calculated time delay, wherein
Figure FDA0003677033200000013
And is provided with
Figure FDA0003677033200000014
The larger the weight value is, the more sensitive the unloading task of the user to the index is;
(2) the unloading user selects the assisting equipment according to the link state, and determines the local calculated amount, the uploading task amount, the local transmission power and the local calculation time delay according to the weight:
(2.1) assume that the set of alternative assisting devices for user U is UuLet the alternative device u' be its assisting device, then
Figure FDA0003677033200000015
Wherein g isu,u'、
Figure FDA0003677033200000016
And
Figure FDA0003677033200000017
respectively representing users u to standbySelecting power gain of device u', user u to user u associated edge server nuAnd alternative device u' to the edge server n associated with user uuThe power gain of (d);
(2.2) user u can optimize the local calculation amount a according to the weight set in (1)uUpload task volume 1-auLocal transmission power pu,1And calculating the time delay locally
Figure FDA0003677033200000018
The optimization problem can be modeled as:
Figure FDA0003677033200000019
wherein, Iu、Bu、c、
Figure FDA00036770332000000110
ξUserRespectively representing the total task amount of user u, the unloading frequency bandwidth (, the number of CPUs (central processing units) required to be consumed for calculating each bit of task, the local calculation time delay, the user equipment calculation energy coefficient, and in addition, an optimization variable pu,1And
Figure FDA0003677033200000021
if the boundary value is exceeded, the boundary value is directly set;
(2.3) the unloading user u determines the variable a in an alternate iteration modeu、pu,1And
Figure FDA0003677033200000022
(3) offload user u will first offload 1-a of the taskuPartly with transmission power pu,1Sending the data to the selected assisting device u', and then unloading 1-a of the task in a cooperative communication mode with the assistance of the assisting deviceuPartial offload to edge server nuAt this time, the cooperative transmission power of the user u and the assisting device u' are respectively unloadedIs pu,2And pu'，pu,2And pu'The solution of (c) is obtained by the following optimization problem:
Figure FDA0003677033200000023
where the variable p is optimizedu,2And pu'If the limit value is exceeded, the limit value is directly set as the limit value; the first two terms of the objective function of the optimization problem OP3 are about pu,2And pu'The last two terms are with respect to p, respectivelyu,2And pu'The concave function of (a), thus requiring a continuous convex approximation of the first two terms, when the variable p isu,2And pu'The solution of (c) can be obtained by the following optimization problem:
Figure FDA0003677033200000024
wherein, the corner mark i represents the iteration number;
Figure FDA0003677033200000025
Figure FDA0003677033200000026
representing the function h (p)u,2,pu') At pu,2First derivative of (1)
Figure FDA0003677033200000027
Figure FDA0003677033200000028
Representing p from the ith iterationu,2A value;
Figure FDA0003677033200000029
represents the function h (p)u,2,pu') At p isu'And substitution of the first derivative of
Figure FDA00036770332000000210
Figure FDA00036770332000000211
Representing p from the ith iterationu'A value; the optimization problem OP4 is for pu,2And pu'By searching for H' (p)u,2) 0 and H' (p)u') The root of 0 can get p in the optimization problem OP3u,2And pu'The solution of (1); repeatedly updated p based on the idea of successive convex approximationu,2And pu'Up to p adjacent to two iterationsu,2And pu'The difference values of (A) and (B) are respectively less than a certain precision, namely the algorithm is considered to be converged, and p is obtained during convergenceu,2And pu'Namely, the cooperative transmission power p of the user u and the assisting device u' in (3) is unloadedu,2And pu'The final solution of (2);
(4) edge server nuDetermining the edge calculation task amount b according to the weight index of the uninstaller u to the calculation time delay and the calculation energy consumptionuEdge calculated time delay
Figure FDA0003677033200000031
And cloud computing workload 1-buCloud computing latency
Figure FDA0003677033200000032
And will cloud computing task 1-buFurther unloading to a cloud server, and completing the whole unloading process:
(4.1) edge Server nuOptimizing the task amount b of edge calculation according to the weight set in (1)uEdge calculation time delay
Figure FDA0003677033200000033
And cloud computing task volume 1-buCloud computing latency
Figure FDA0003677033200000034
The optimization problem can be modeled as:
Figure FDA0003677033200000035
in which ξMECAnd xiCloudRepresenting an edge server computing energy coefficient and a cloud server computing energy coefficient; where variables are optimized
Figure FDA0003677033200000036
And
Figure FDA0003677033200000037
if the boundary value is exceeded, the boundary value is directly set;
(4.2) edge Server nuDetermining variable b by means of alternate iterationu、
Figure FDA0003677033200000038
And
Figure FDA0003677033200000039
(5) offload user u, edge server nuAnd the cloud server respectively calculates the rates based on the optimization results
Figure FDA00036770332000000310
Handling a in task of uninstalling user uuMoiety, bu(1-au) Moiety and (1-b)u)(1-au) And after the calculation is finished, the unloading user u collects the calculation results of all the parts and generates a final calculation result of the unloading task.
2. The edge cloud cooperative resource joint allocation method according to claim 1, wherein the step (2.3) is performed as follows:
(2.3a) initialize a set of p for each offload user uu,1And
Figure FDA00036770332000000311
a value of (d);
(2.3b) based on p obtainedu,1And
Figure FDA00036770332000000312
optimizing variable auThe optimization problem constructed at this time is converted to one about auThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (a) is:
Figure FDA00036770332000000313
if a is obtainedu *If the value is more than 1, the value is 1;
(2.3c) based on a obtaineduOptimizing variables
Figure FDA00036770332000000314
The optimization problem constructed at this time is converted into one about
Figure FDA00036770332000000315
The convex optimization problem can be obtained based on a convex optimization theory
Figure FDA00036770332000000316
Is solved as
Figure FDA00036770332000000317
(2.3d) based on a obtaineduOptimizing variable pu,1When the first term of the objective function is about pu,1With the second term relating to pu,1The first term, thus requiring a continuous convex approximation of the first term, when the variable p isu,1The solution of (c) can be obtained by the following optimization problem:
Figure FDA0003677033200000041
wherein, the corner mark i represents the iteration number;
Figure FDA0003677033200000042
Figure FDA0003677033200000043
representing the function f (p)u,1) At p isu,1And substitution of the first derivative of
Figure FDA0003677033200000044
Figure FDA0003677033200000045
Denotes p obtained from the ith iterationu,1A value; the optimization problem OP2 is about pu,1By searching for F' (p)u,1) The root of 0 can get p in the optimization problem OP2u,1The solution of (1); repeatedly updated p based on the idea of successive convex approximationu,1Up to p adjacent to two iterationsu,1If the difference is less than a certain precision, the algorithm can be considered to be converged, and the newly obtained pu,1Value of p in optimization problem OP1u,1The solution of (2);
(2.3e) based on the results obtained in steps (2.3c) and (2.3d)
Figure FDA0003677033200000046
And
Figure FDA0003677033200000047
update auBased on the obtained auRefreshing
Figure FDA0003677033200000048
And
Figure FDA0003677033200000049
continuously circulating until the algorithm is converged, and obtaining a during convergenceu、pu,1And
Figure FDA00036770332000000410
i.e. the local calculated quantity a in step (2.2)uLocal transmission power pu,1And local computing
Figure FDA00036770332000000411
The final solution of (c).
3. The edge cloud cooperative resource joint allocation method according to claim 1, wherein the step (4.2) is performed as follows:
(4.2a) to edge Server nuInitializing a group
Figure FDA00036770332000000412
And
Figure FDA00036770332000000413
a value of (d);
(4.2b) based on the obtained
Figure FDA00036770332000000414
And
Figure FDA00036770332000000415
optimization variable buThe optimization problem constructed at this time is converted to one relating to buThe convex optimization problem of (a) can be obtained based on a convex optimization theoryuThe solution of (a) is:
Figure FDA00036770332000000416
(4.2c) based on b obtaineduOptimizing variables
Figure FDA00036770332000000417
And
Figure FDA00036770332000000418
the optimization problem constructed at this time is converted into one about
Figure FDA00036770332000000419
And
Figure FDA00036770332000000420
the convex optimization problem can be obtained based on a convex optimization theory
Figure FDA00036770332000000421
And
Figure FDA00036770332000000422
the solution of (2) is as follows:
Figure FDA00036770332000000423
and
Figure FDA00036770332000000424
(4.2d) based on that obtained in step (4.2c)
Figure FDA00036770332000000425
And
Figure FDA00036770332000000426
update buBased on b obtaineduRefreshing
Figure FDA00036770332000000427
And
Figure FDA00036770332000000428
continuously circulating until the algorithm is converged, and b obtained during convergenceu、
Figure FDA00036770332000000429
And
Figure FDA00036770332000000430
namely the task amount b of edge calculation in the step (4.1)uEdge calculated time delay
Figure FDA00036770332000000431
And cloud computing latency
Figure FDA00036770332000000432
The final solution of (c).
4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the computer program, when executed by the processor, causes the processor to perform the steps of the edge cloud co-resource joint allocation method according to any one of claims 1 to 3.
5. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to execute the steps of the edge cloud cooperative resource joint allocation method according to any one of claims 1 to 3.
6. An information data processing terminal, characterized in that the information data processing terminal is configured to implement the edge cloud cooperative resource joint allocation method according to any one of claims 1 to 3.
7. An edge computing server, wherein the edge computing server is configured to implement the edge cloud cooperative resource joint allocation method according to any one of claims 1 to 3.
8. A cloud computing server is used for realizing the edge cloud cooperative resource joint allocation method of any one of claims 1 to 3.
9. A wireless communication system, wherein the wireless communication system is configured to implement the edge cloud cooperative resource joint allocation method according to any one of claims 1 to 3.
CN202011584281.1A 2020-12-28 2020-12-28 Edge cloud cooperative resource joint allocation method, system and application Active CN112689303B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011584281.1A CN112689303B (en) 2020-12-28 2020-12-28 Edge cloud cooperative resource joint allocation method, system and application

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011584281.1A CN112689303B (en) 2020-12-28 2020-12-28 Edge cloud cooperative resource joint allocation method, system and application

Publications (2)

Publication Number Publication Date
CN112689303A CN112689303A (en) 2021-04-20
CN112689303B true CN112689303B (en) 2022-07-22

Family

ID=75453989

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011584281.1A Active CN112689303B (en) 2020-12-28 2020-12-28 Edge cloud cooperative resource joint allocation method, system and application

Country Status (1)

Country Link
CN (1) CN112689303B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113191654A (en) * 2021-05-12 2021-07-30 余绍祥 Distributed resource scheduling system and method based on multi-objective optimization
CN113660625B (en) * 2021-07-06 2024-02-02 山东师范大学 Resource cooperation method and system for multi-access edge computing node and CDN node
CN113419867B (en) * 2021-08-23 2022-01-18 浙大城市学院 Energy-saving service supply method in edge-oriented cloud collaborative computing environment
CN113784373B (en) * 2021-08-24 2022-11-25 苏州大学 Combined optimization method and system for time delay and frequency spectrum occupation in cloud edge cooperative network
CN113923223B (en) * 2021-11-15 2024-02-06 安徽大学 User allocation method with low time cost in edge environment
CN114448991B (en) * 2021-12-28 2022-10-21 西安电子科技大学 Multi-edge server selection method, system, medium, device and terminal
CN114844900B (en) * 2022-05-05 2022-12-13 中南大学 Edge cloud resource cooperation method based on uncertain demand
CN116506877B (en) * 2023-06-26 2023-09-26 北京航空航天大学 Distributed collaborative computing method for mobile crowd sensing

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106900011A (en) * 2017-02-28 2017-06-27 重庆邮电大学 Task discharging method between a kind of cellular basestation based on MEC
CN107241767A (en) * 2017-06-14 2017-10-10 广东工业大学 The method and device that a kind of mobile collaboration is calculated
WO2017196249A1 (en) * 2016-05-13 2017-11-16 Telefonaktiebolaget Lm Ericsson (Publ) Network architecture, methods, and devices for a wireless communications network
CN108804227A (en) * 2018-05-23 2018-11-13 大连理工大学 The method of the unloading of computation-intensive task and best resource configuration based on mobile cloud computing
CN109474681A (en) * 2018-11-05 2019-03-15 安徽大学 Resource allocation methods, system and the server system of mobile edge calculations server
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 The combined optimization method of task unloading and resource allocation in mobile edge calculations network
CN111464983A (en) * 2020-03-10 2020-07-28 深圳大学 Calculation and communication cooperation method and system in passive edge calculation network
CN111585916A (en) * 2019-12-26 2020-08-25 国网辽宁省电力有限公司电力科学研究院 LTE electric power wireless private network task unloading and resource allocation method based on cloud edge cooperation
CN111586762A (en) * 2020-04-29 2020-08-25 重庆邮电大学 Task unloading and resource allocation joint optimization method based on edge cooperation
CN111913723A (en) * 2020-06-15 2020-11-10 合肥工业大学 Cloud-edge-end cooperative unloading method and system based on assembly line

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3358510A1 (en) * 2017-02-01 2018-08-08 Deutsche Telekom AG Network resources brokering system and brokering entity for accessing a network resource with preferential treatment

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017196249A1 (en) * 2016-05-13 2017-11-16 Telefonaktiebolaget Lm Ericsson (Publ) Network architecture, methods, and devices for a wireless communications network
CN106900011A (en) * 2017-02-28 2017-06-27 重庆邮电大学 Task discharging method between a kind of cellular basestation based on MEC
CN107241767A (en) * 2017-06-14 2017-10-10 广东工业大学 The method and device that a kind of mobile collaboration is calculated
CN108804227A (en) * 2018-05-23 2018-11-13 大连理工大学 The method of the unloading of computation-intensive task and best resource configuration based on mobile cloud computing
CN109474681A (en) * 2018-11-05 2019-03-15 安徽大学 Resource allocation methods, system and the server system of mobile edge calculations server
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 The combined optimization method of task unloading and resource allocation in mobile edge calculations network
CN111585916A (en) * 2019-12-26 2020-08-25 国网辽宁省电力有限公司电力科学研究院 LTE electric power wireless private network task unloading and resource allocation method based on cloud edge cooperation
CN111464983A (en) * 2020-03-10 2020-07-28 深圳大学 Calculation and communication cooperation method and system in passive edge calculation network
CN111586762A (en) * 2020-04-29 2020-08-25 重庆邮电大学 Task unloading and resource allocation joint optimization method based on edge cooperation
CN111913723A (en) * 2020-06-15 2020-11-10 合肥工业大学 Cloud-edge-end cooperative unloading method and system based on assembly line

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"Design and Performance Analysis of Cooperative NOMA With Coordinated Direct and Relay Transmission";MENGQI YANG, JIAN CHEN, LONG YANG,LU LV ,BINGTAO HE, AND BOYANG;《IEEE ACCESS》;20190528;全文 *
"一种基于非正交多址接入技术的协作多播传输方法";杨龙，陈健;《科技成果登记表》;20190501;全文 *

Also Published As

Publication number Publication date
CN112689303A (en) 2021-04-20

Similar Documents

Publication Publication Date Title
CN112689303B (en) Edge cloud cooperative resource joint allocation method, system and application
CN111586696B (en) Resource allocation and unloading decision method based on multi-agent architecture reinforcement learning
CN107995660B (en) Joint task scheduling and resource allocation method supporting D2D-edge server unloading
CN110351754B (en) Industrial Internet machine equipment user data calculation unloading decision method based on Q-learning
Cui et al. A novel offloading scheduling method for mobile application in mobile edge computing
US11831708B2 (en) Distributed computation offloading method based on computation-network collaboration in stochastic network
CN112105062B (en) Mobile edge computing network energy consumption minimization strategy method under time-sensitive condition
CN111163519A (en) Wireless body area network resource allocation and task unloading algorithm with maximized system benefits
CN105656999B (en) A kind of cooperation task immigration method of energy optimization in mobile cloud computing environment
CN112015545B (en) Task unloading method and system in vehicle edge computing network
CN111949409B (en) Method and system for unloading computing task in power wireless heterogeneous network
CN113918240B (en) Task unloading method and device
CN111163143B (en) Low-delay task unloading method for mobile edge calculation
CN111885147A (en) Dynamic resource pricing method in edge calculation
CN111836284B (en) Energy consumption optimization calculation and unloading method and system based on mobile edge calculation
CN112822707B (en) Task unloading and resource allocation method in computing resource limited MEC
CN112612553B (en) Edge computing task unloading method based on container technology
CN111796880B (en) Unloading scheduling method for edge cloud computing task
CN113992677A (en) MEC calculation unloading method for delay and energy consumption joint optimization
CN113573363A (en) MEC calculation unloading and resource allocation method based on deep reinforcement learning
CN111158893B (en) Task unloading method, system, equipment and medium applied to fog computing network
CN117579701A (en) Mobile edge network computing and unloading method and system
CN114615705B (en) Single-user resource allocation strategy method based on 5G network
CN116347522A (en) Task unloading method and device based on approximate computation multiplexing under cloud edge cooperation
CN114650568A (en) Distributed unloading method based on energy collection in mobile Ad Hoc cloud

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