CN113220364A - Task unloading method based on vehicle networking mobile edge computing system model - Google Patents

Task unloading method based on vehicle networking mobile edge computing system model Download PDF

Info

Publication number
CN113220364A
CN113220364A CN202110490591.5A CN202110490591A CN113220364A CN 113220364 A CN113220364 A CN 113220364A CN 202110490591 A CN202110490591 A CN 202110490591A CN 113220364 A CN113220364 A CN 113220364A
Authority
CN
China
Prior art keywords
mec
algorithm
server
intelligent transportation
task
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
CN202110490591.5A
Other languages
Chinese (zh)
Inventor
王振宇
王阳东
魏剑
陈严
李伟
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.)
Peking University
Original Assignee
Peking University
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 Peking University filed Critical Peking University
Priority to CN202110490591.5A priority Critical patent/CN113220364A/en
Publication of CN113220364A publication Critical patent/CN113220364A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/445—Program loading or initiating
    • G06F9/44594—Unloading
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
    • 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)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Evolutionary Biology (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Mathematical Physics (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the field of Internet of vehicles and the field of edge computing, and discloses a task unloading method based on an Internet of vehicles mobile edge computing system model. An MEC-intelligent transportation system, comprising: roadside units, base stations, core networks, the internet. On the basis, a task delay model and an MEC server energy consumption model in the MEC-intelligent transportation system are constructed, and accordingly, the problem of minimizing total energy consumption of the MEC server in the MEC-intelligent transportation system is defined. The solving method combines the thought of probability jump in the simulated annealing algorithm on the basis of the traditional particle swarm algorithm, overcomes the defect that the traditional particle swarm algorithm is easy to fall into the local optimal solution, is easy to obtain the global optimal solution, is further fused with the genetic algorithm, and improves the algorithm convergence and the algorithm global search.

Description

Task unloading method based on vehicle networking mobile edge computing system model
Technical Field
The invention relates to the field of Internet of vehicles and the field of edge computing, in particular to a task unloading method based on an Internet of vehicles mobile edge computing system model.
Background
With the continuous development of intelligent transportation systems and car networking technologies, a large number of tasks sensitive to time delay and large in calculation amount need to be processed in real time, and the traditional cloud computing cannot meet the requirement of low delay of the tasks. This is due to the fact that the deployed cloud server is generally far from the mobile terminal device, and therefore, a long delay is caused in the process of offloading the computing task. Mobile Edge Computing (MEC) has come and come, and sinks part of cloud servers to network Edge nodes, thereby effectively meeting the requirement of low delay of task processing. The mobile edge computing technology is applied to the Internet of vehicles, vehicles can process tasks with large computing amount and high real-time performance by using edge servers of roadside units, and the vehicles can select different task unloading strategies to unload the tasks according to different task requirements. Under the condition of meeting the time delay condition of a calculation task, a task unloading method for minimizing the total energy consumption of an edge server is the key point of the current discussion. The total energy consumption of the edge server directly influences the operation cost of an intelligent transportation system operator, and on the premise of ensuring timely and reliable completion of tasks, the analysis and discussion of a more economic and efficient task unloading strategy can be greatly beneficial to further development of the intelligent transportation system. Therefore, it is very necessary to research a new and efficient task offloading method based on the car networking mobile edge computing system model, so as to optimize the total energy consumption of the MEC server under the task delay constraint.
Disclosure of Invention
Therefore, the invention introduces a novel task unloading method based on a vehicle networking mobile edge computing system model. The method considers an MEC-intelligent traffic system consisting of roadside units, a base station, a core network and the Internet, and constructs a task delay model and an MEC server energy consumption model in the MEC-intelligent traffic system. The solving method combines the thought of probability jump in the simulated annealing algorithm on the basis of the traditional particle swarm algorithm, overcomes the defect that the traditional particle swarm algorithm is easy to fall into the local optimal solution, is easy to obtain the global optimal solution, is further fused with the genetic algorithm, and improves the algorithm convergence and the algorithm global search.
In order to achieve the above purpose, the invention provides the following technical scheme:
according to a first aspect of the invention, a model of a networked mobile edge computing system, comprises: roadside units (RSUs), Base Stations (BSs), core networks, the internet. Roadside units are deployed at the roadsides to provide assistance or services to vehicles on the roadways. Cellular base stations are part of a system of urban cellular network infrastructure that serves not only vehicles on the road, but also more users in a larger area. Fully configured servers can provide the computing resources and storage resources required by V2X applications, and these servers can be deployed: roadside units, cellular base stations, operator core networks, the internet (e.g., renting cloud servers from the cloud). In the internet of vehicles mobile edge computing system model, the MEC server is deployed on a roadside unit or base station.
Further, assume that the roadside unit generated V2X mission is generated based on information obtained from a large number of vehicles operating independently of each other. Therefore, we can consider the process of generating task f by each node (e.g., RSU) as a Poisson process according to the queuing theory. We use σifRepresenting the strength of the generation of task f by node i. If node i does not generate task f, then σif＝0。
Further, we use the array Z ═ { Z ═ ZifkDenotes the assignment of task flows to the servers. If task f, generated by node i, is executed remotely on the server of node k, then z ifk1. Otherwise, z ifk0. At the same time, we reintroduce the vector Y ═ Yk}. If the server of node k (remote server k) is used for task computation, then y k1. Otherwise, y k0. It follows that the mathematical relationship between the variables Z and Y is as follows:
Figure BDA0003052369500000031
since the task f generated by each given node can select a server for performing the unloading calculation according to the current information of the given node, the task flow of the task f generated by a specific node can be completely unloaded to a specific server for performing the calculation. Namely:
Figure BDA0003052369500000032
the computation time of task f is a random value that depends on the server used for the computation. For a particular server k, the computation time for task f consists of the average computation time value and the variance. To avoid overloading the servers for computation, the total incoming load for any server k should not exceed the maximum computation capacity μ of the serverkNamely:
Figure BDA0003052369500000033
further, the task f is generated by the node i and then is unloaded to the server k, and the total delay of returning to the node i after being processed by the server k is called difk(if k ═ i, then node i does not perform task offloading, but performs task computation independently). difkBy offload task transmission delay t between node i and server kikAnd a transmission delay t of returned result informationikAnd the sum T of the queuing time and the calculation time of the task calculation processing on the server kkComposition (if the option is to offload to a distant core network or internet cloud server, ignoring T due to its very powerful server computing powerk) I.e. difk＝2tik+Tk. We assume that the delay constraint for task f is DfThen the quality requirement of the V2X application is met. So that the total delay of task f does not exceed DfIs greater than or equal to q, expressed by a mathematical expression, i.e. P (d)ifk＜Df)≥q。
For poissonDistributed, we can view server processing computing tasks as M/G/1 queues. Therefore, we can know the average waiting time E [ W ] between the time when the task is unloaded to the server k and the time when the task is processed by the server k according to the Pollaczek-Khinchine formulak]：
Figure BDA0003052369500000034
Probability distribution function of latency F (x)k) The q-quantile of (a) is skln[1/(1-q)]. We will average the calculation time 1/μkPlus, then TkThe q-quantile of
Figure BDA0003052369500000041
Thus, the constraint equation can be rewritten as:
Figure BDA0003052369500000042
further, in an idle state, i.e. when the server is not performing any computational tasks, the server energy consumption is also not zero. Let us assume that the energy consumption of server k in idle state and working state is β respectivelykAnd gammak. If a task is unloaded to the server k, the utilization rate of the computing resource of the server k is hk/μk. Wherein the content of the first and second substances,
Figure BDA0003052369500000043
and the input intensity of the calculation task of the server k is shown, namely the density of the calculation task of the roadside unit unloaded to the server k. At this time, the average energy consumption S of the server kk：
Figure BDA0003052369500000044
Let alphak＝γk-βkThe above formula can be written as:
Figure BDA0003052369500000045
according to the second aspect of the invention, a new task unloading method based on a mobile edge computing system model of the Internet of vehicles-genetic simulation annealing particle swarm algorithm:
step 1: initializing parameters;
step 2: randomly generating an initial population;
and step 3: calculating the fitness value of the particle, wherein an objective function (fitness (x)) is a fitness function (f (x) for short);
and 4, step 4: calculating to obtain an initial temperature T of an annealing algorithm;
and 5: by fSA(x) The function is expressed as a function of the fitness of the annealing algorithm at the temperature T
Figure BDA0003052369500000046
Step 6: using the idea of roulette to place a bet at the individual's optimum position PidPick a substitute global corresponding optimum position PpdIs denoted by Prd；
And 7: by PrdIn place of PpdAnd updating the speed of each particle as follows:
Figure BDA0003052369500000051
and 8: calculating the fitness value of the particles again;
and step 9: updating the corresponding positions of the particles;
step 10: and (3) annealing operation: t ═ δ × T;
step 11: after annealing, sorting the particles in ascending order according to the fitness value from small to large;
step 12: deleting 1/4 the individuals with the highest fitness value, duplicating the remaining 1/3 individuals with intermediate fitness values;
step 13: randomly selecting i and j from particles with low fitness value, and calculating the positions of the i and jNumber cross over, if
Figure BDA0003052369500000052
Updating the position of the particle i, and j is the same;
Figure BDA0003052369500000053
step 14: randomly extracting particles with low fitness value to obtain particles i if
Figure BDA0003052369500000054
Generating a new position of the particle i;
Figure BDA0003052369500000055
step 15: making a selection according to the judgment result, and if the judgment result meets the condition, outputting the result and ending; otherwise, if the condition is not satisfied, the process returns to step 5, and goes down again until the condition is satisfied.
The model and the method have the following advantages:
the solving method is based on the traditional particle swarm algorithm and combines the thought of probability jump in the simulated annealing algorithm, overcomes the defect that the traditional particle swarm algorithm is easy to fall into the local optimal solution, is easy to obtain the global optimal solution, and is further fused with the genetic algorithm. According to the natural rule thought of 'win-loss and survival of suitable persons' of the genetic algorithm, high-quality genes in the population can be inherited, the convergence of the algorithm is improved, and the cross operator and the mutation operator are combined with each other, so that the diversity of the population is richer, and the global searching performance of the algorithm is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a schematic flow chart of a task offloading method based on a mobile edge computing system model of Internet of vehicles according to the present invention;
FIG. 2 is a schematic diagram of the MEC-intelligent transportation system model in the present invention;
FIG. 3 is a diagram of a MEC-intelligent transportation system network model in accordance with the present invention;
FIG. 4 is a flow chart of the genetic simulated annealing particle swarm algorithm of the present invention;
FIG. 5 is a diagram of variation of total energy consumption of an MEC server with vehicle load factors in a small-scale scene, taking an MEC-intelligent transportation system network model as an example;
fig. 6 is a diagram of the change of the total energy consumption of the MEC server along with the vehicle load factor in a large-scale scene taking the MEC-intelligent transportation system network model as an example.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a flow chart of a task offloading method based on a mobile edge computing system model of internet of vehicles;
referring to fig. 2 and fig. 3, the invention provides an MEC-intelligent transportation system composed of roadside units, a base station, a core network and the internet, and a task delay model and an MEC server energy consumption model in the MEC-intelligent transportation system are constructed.
Referring to fig. 4, the present invention proposes a new genetic simulated annealing particle swarm algorithm. In this embodiment, appropriate simulation parameters are selected to further explain the present invention in detail. Different V2X applications have different quality of service requirements and technical parameters. Three V2X applications discussed in this invention: the service quality requirements and technical parameters required to be met by vehicle continuous arrangement, crossroad safety and environmental information are shown in the following table.
V2X application type and data
Figure BDA0003052369500000071
Where the frequency represents the number of tasks generated per second and the E2E delay represents the one-way end-to-end delay constraint. If the round-trip delay of the wireless link between the vehicle and the roadside unit does not exceed 4ms, a task round-trip total delay constraint D can be obtainedfIs twice the one-way delay minus 4 ms. Roadside unit to core network tcoreAnd roadside units to the Internet tinternetSet to 5ms and 10ms, respectively.
Assuming that the length l of each RSU service section is 200m, all RSUs are deployed along the road edge at intervals of 200m, the load factor xi epsilon (0,1) of vehicles on the road, and the number n of lanes is 4. At this point, we can estimate the rate σ at which one RSU generates tasks per secondif：
Figure BDA0003052369500000072
Wherein if the vehicle on the RSU service road section generates the task F (F belongs to F)i) If I is 1; otherwise, I is 0. w is the sum of the length of each vehicle and the safety distance between the vehicles, and w is 6. Each roadside unit RSU has its own server for performing task calculations. Each base station has a 25% probability of having a type 1 server, a 25% probability of having a type 2 server, and a 50% probability of having no server. In a small-scale scene, a server is only deployed on a roadside unit and a base station; in a large-scale scenario, one server is deployed on the core network and the internet, respectively, in addition to servers deployed on roadside units and base stations. The parameters for each type of server are shown in the table below.
Server parameters
Figure BDA0003052369500000081
Model construction is completed, simulation is executed, two scenes, namely a large-scale scene and a small-scale scene, are considered:
(1) small-scale scenario: 12RSU, 3BS
(2) Large-scale scenario: 49RSU, 7BS
The iteration number of the GSAPSO algorithm is 400, the number of particles is 500, the dimension of a search space is 100, and other key parameters are set as follows:
(1) selecting an operator: the method comprises the steps of firstly calculating the fitness value of each particle in each iteration, sorting the particles from small to large according to the fitness value, eliminating 1/4 particles with high fitness, copying the particles with the middle fitness 1/3 in the rest particles to form a new population, keeping the population number unchanged, and then carrying out subsequent operations;
(2) and (3) a crossover operator: adopting a crossover operator of arithmetic crossover, selecting two individuals with good applicability as x respectivelyiAnd xjThen the new individuals after the arithmetic crossover:
Figure BDA0003052369500000091
(3) mutation operator: selecting individuals with good adaptability to perform Gaussian variation, and obtaining new individuals according to the formula 4-8.
Figure BDA0003052369500000092
Referring to fig. 5 and 6, the present example evaluates the performance of the genetic simulated annealing algorithm by setting appropriate simulation parameters. In a small-scale scene and a large-scale scene, the GSAPSO algorithm is better than the SAPSO algorithm and the traditional particle swarm algorithm, so that the total energy consumption of the MEC server is smaller. In a small-scale scene, when the vehicle load factor xi is 0.05, the GSAPSO algorithm saves the total energy consumption of the MEC server by 5W most compared with the SAPSO algorithm, namely, the total energy consumption of the MEC server is reduced by 11.6%. In a large-scale scene, when the vehicle load factor xi is 0.7, the GSAPSO algorithm saves the total energy consumption of the MEC server by the maximum amount and 104W compared with the SAPSO algorithm, namely, the total energy consumption of the MEC server is reduced by 20.8%.

Claims (7)

1. An MEC-intelligent transportation system, comprising: roadside units, base stations, core networks, the internet. On the basis, a task delay model and an MEC server energy consumption model in the MEC-intelligent transportation system are constructed, and accordingly, the problem of minimizing total energy consumption of the MEC server in the MEC-intelligent transportation system is defined.
2. The MEC-intelligent transportation system of claim 1, wherein roadside units are deployed at roadsides to provide assistance or services to vehicles on the roadways. Cellular base stations are part of a system of urban cellular network infrastructure that serves not only vehicles on the road, but also more users in a larger area. Fully configured servers can provide the computing resources and storage resources required by V2X applications, and these servers can be deployed: roadside units, cellular base stations, operator core networks, the internet (e.g., renting cloud servers from the cloud). In the internet of vehicles mobile edge computing system model, the MEC server is deployed on a roadside unit or base station.
3. The MEC-intelligent transportation system of claim 1, wherein the MEC servers in the MEC-intelligent transportation system total energy consumption minimization problem: under the time delay constraint, the total energy consumption of the MEC server in the MEC-intelligent transportation system is minimized. The energy consumption of each server depends on its own computing resource utilization (h)k/μk) Then the V2X task offload energy consumption optimization problem can be expressed as follows.
Figure FDA0003052369490000011
Figure FDA0003052369490000012
。
4. A new task unloading method based on a mobile edge computing system model of the Internet of vehicles, namely a genetic simulation annealing particle swarm algorithm, is characterized by comprising the following steps:
step 1: initializing parameters;
step 2: randomly generating an initial population;
and step 3: calculating the fitness value of the particle, wherein an objective function (fitness (x)) is a fitness function (f (x) for short);
and 4, step 4: calculating to obtain an initial temperature T of an annealing algorithm;
and 5: by fSA(x) The function is expressed as a function of the fitness of the annealing algorithm at the temperature T
Figure FDA0003052369490000021
Step 6: using the idea of roulette to place a bet at the individual's optimum position PidPick a substitute global corresponding optimum position PpdIs denoted by Prd；
And 7: by PrdIn place of PrdAnd updating the speed of each particle as follows:
Figure FDA0003052369490000022
and 8: calculating the fitness value of the particles again;
and step 9: updating the corresponding positions of the particles;
step 10: and (3) annealing operation: t ═ δ × T;
step 11: after annealing, sorting the particles in ascending order according to the fitness value from small to large;
step 12: deleting 1/4 the individuals with the highest fitness value, duplicating the remaining 1/3 individuals with intermediate fitness values;
step 13: randomly selecting i and j from particles with low fitness value, and performing arithmetic crossing on positions of i and j, if the positions are low
Figure FDA0003052369490000023
Updating the position of the particle i, and j is the same;
Figure FDA0003052369490000024
step 14: randomly extracting particles with low fitness value to obtain particles i if
Figure FDA0003052369490000025
Generating a new position of the particle i;
Figure FDA0003052369490000026
step 15: making a selection according to the judgment result, and if the judgment result meets the condition, outputting the result and ending; otherwise, if the condition is not satisfied, the process returns to step 5, and goes down again until the condition is satisfied.
5. The genetic simulated annealing particle swarm algorithm according to claim 4, wherein the concept of probability jump in the simulated annealing particle swarm algorithm is combined, so that the defect that the traditional particle swarm algorithm is easy to fall into the local optimal solution is overcome, the global optimal solution is easy to obtain, and the genetic algorithm is further fused. According to the natural rule thought of 'win-loss and survival of suitable persons' of the genetic algorithm, high-quality genes in the population can be inherited, the convergence of the algorithm is improved, and the cross operator and the mutation operator are combined with each other, so that the diversity of the population is richer, and the global searching performance of the algorithm is further improved.
6. The gene of claim 4The simulated annealing particle swarm algorithm is characterized in that the crossover operator adopts an arithmetic crossover operator, and two individuals with good applicability are selected to be x respectivelyiAnd xjThen the new individuals after the arithmetic crossover.
Figure FDA0003052369490000031
。
7. The genetic simulated annealing particle swarm algorithm of claim 4, wherein the mutation operator selects individuals with good applicability to perform Gaussian mutation to obtain new individuals according to the following formula.
Figure FDA0003052369490000032
。
CN202110490591.5A 2021-05-06 2021-05-06 Task unloading method based on vehicle networking mobile edge computing system model Pending CN113220364A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110490591.5A CN113220364A (en) 2021-05-06 2021-05-06 Task unloading method based on vehicle networking mobile edge computing system model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110490591.5A CN113220364A (en) 2021-05-06 2021-05-06 Task unloading method based on vehicle networking mobile edge computing system model

Publications (1)

Publication Number Publication Date
CN113220364A true CN113220364A (en) 2021-08-06

Family

ID=77091451

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110490591.5A Pending CN113220364A (en) 2021-05-06 2021-05-06 Task unloading method based on vehicle networking mobile edge computing system model

Country Status (1)

Country Link
CN (1) CN113220364A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113918240A (en) * 2021-10-15 2022-01-11 全球能源互联网研究院有限公司 Task unloading method and device
CN114615264A (en) * 2022-02-22 2022-06-10 东南大学 Urban traffic network data transmission and distribution method under edge cloud cooperative computing environment
CN115098115A (en) * 2022-06-17 2022-09-23 西安邮电大学 Edge calculation task unloading method and device, electronic equipment and storage medium
CN115866626A (en) * 2023-02-23 2023-03-28 安徽思高智能科技有限公司 NSGA-II and simulated annealing based service deployment method under edge environment
CN116955354A (en) * 2023-06-30 2023-10-27 国家电网有限公司大数据中心 Identification analysis method and device for energy digital networking
CN117336697A (en) * 2023-08-08 2024-01-02 广东工业大学 Internet of vehicles task unloading optimization method and system based on hybrid coverage scene

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107766135A (en) * 2017-09-29 2018-03-06 东南大学 Method for allocating tasks based on population and simulated annealing optimization in mobile cloudlet

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107766135A (en) * 2017-09-29 2018-03-06 东南大学 Method for allocating tasks based on population and simulated annealing optimization in mobile cloudlet

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
肖尧: ""面向5G低时延高可靠车载业务的计算卸载策略研究"", 《中国优秀硕士学位论文全文数据库》 *

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113918240A (en) * 2021-10-15 2022-01-11 全球能源互联网研究院有限公司 Task unloading method and device
CN113918240B (en) * 2021-10-15 2024-05-28 全球能源互联网研究院有限公司 Task unloading method and device
CN114615264A (en) * 2022-02-22 2022-06-10 东南大学 Urban traffic network data transmission and distribution method under edge cloud cooperative computing environment
CN114615264B (en) * 2022-02-22 2024-02-09 东南大学 Urban traffic network data transmission distribution method under Bian Yun cooperative computing environment
CN115098115A (en) * 2022-06-17 2022-09-23 西安邮电大学 Edge calculation task unloading method and device, electronic equipment and storage medium
CN115866626A (en) * 2023-02-23 2023-03-28 安徽思高智能科技有限公司 NSGA-II and simulated annealing based service deployment method under edge environment
CN115866626B (en) * 2023-02-23 2023-05-12 安徽思高智能科技有限公司 Service deployment method based on NSGA-II and simulated annealing in edge environment
CN116955354A (en) * 2023-06-30 2023-10-27 国家电网有限公司大数据中心 Identification analysis method and device for energy digital networking
CN117336697A (en) * 2023-08-08 2024-01-02 广东工业大学 Internet of vehicles task unloading optimization method and system based on hybrid coverage scene
CN117336697B (en) * 2023-08-08 2024-06-04 广东工业大学 Internet of vehicles task unloading optimization method and system based on hybrid coverage scene

Similar Documents

Publication Publication Date Title
CN113220364A (en) Task unloading method based on vehicle networking mobile edge computing system model
Zhang et al. Deep learning empowered task offloading for mobile edge computing in urban informatics
Ning et al. Deep reinforcement learning for intelligent internet of vehicles: An energy-efficient computational offloading scheme
CN113296845B (en) Multi-cell task unloading algorithm based on deep reinforcement learning in edge computing environment
Hameed et al. Energy-and performance-aware load-balancing in vehicular fog computing
Li et al. NOMA-enabled cooperative computation offloading for blockchain-empowered Internet of Things: A learning approach
CN111475274B (en) Cloud collaborative multi-task scheduling method and device
CN110717300B (en) Edge calculation task allocation method for real-time online monitoring service of power internet of things
WO2023040022A1 (en) Computing and network collaboration-based distributed computation offloading method in random network
CN111339554B (en) User data privacy protection method based on mobile edge calculation
CN114143346B (en) Joint optimization method and system for task unloading and service caching of Internet of vehicles
He et al. QoE-based cooperative task offloading with deep reinforcement learning in mobile edge networks
CN110851277A (en) Task scheduling strategy based on edge cloud cooperation in augmented reality scene
CN111885493B (en) Micro-cloud deployment method based on improved cuckoo search algorithm
CN115297171A (en) Edge calculation unloading method and system for cellular Internet of vehicles hierarchical decision
Ouyang Task offloading algorithm of vehicle edge computing environment based on Dueling-DQN
CN116185523A (en) Task unloading and deployment method
Manalastas et al. Where to go next?: A realistic evaluation of AI-assisted mobility predictors for HetNets
Gill et al. On the capacity bounds for bumblebee-inspired connected vehicle networks via queuing theory
CN113747450A (en) Service deployment method and device in mobile network and electronic equipment
Wang et al. Multi-objective joint optimization of communication-computation-caching resources in mobile edge computing
Zhang et al. On-device intelligence for 5g ran: Knowledge transfer and federated learning enabled ue-centric traffic steering
CN116567651A (en) Decision method and system for MEC task unloading and migration based on particle swarm
CN114615705B (en) Single-user resource allocation strategy method based on 5G network
CN114980127B (en) Computing and unloading method based on federal reinforcement learning in fog wireless access network

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20210806

WD01 Invention patent application deemed withdrawn after publication