CN112084025A - Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method - Google Patents

Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method Download PDF

Info

Publication number
CN112084025A
CN112084025A CN202010902490.XA CN202010902490A CN112084025A CN 112084025 A CN112084025 A CN 112084025A CN 202010902490 A CN202010902490 A CN 202010902490A CN 112084025 A CN112084025 A CN 112084025A
Authority
CN
China
Prior art keywords
fog
node
particle
time delay
particle swarm
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010902490.XA
Other languages
Chinese (zh)
Other versions
CN112084025B (en
Inventor
李旭杰
张光照
孙颖
辛元雪
胡居荣
顾燕
张云飞
李建霓
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.)
Hohai University HHU
Original Assignee
Hohai University HHU
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 Hohai University HHU filed Critical Hohai University HHU
Priority to CN202010902490.XA priority Critical patent/CN112084025B/en
Publication of CN112084025A publication Critical patent/CN112084025A/en
Application granted granted Critical
Publication of CN112084025B publication Critical patent/CN112084025B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
    • 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a fog computing task unloading time delay optimization method based on an improved particle swarm algorithm. The method comprises the steps of initializing system parameters and an initial population, and setting the speed and the position of each particle; then, taking the unloading time delay of the minimized system as a target, and taking the unloading time delay value corresponding to each particle as a fitness function value of the particle swarm algorithm; then, iteratively calculating the individual optimal value of each particle and the global optimal value of the whole population, evolving the speed and the position of the particle, and carrying out boundary condition processing; and finally, stopping the algorithm when the evolution algebra iterates to meet the termination condition, and obtaining the optimal unloading time delay of the task unloading. The invention can effectively reduce the task unloading time delay and improve the task unloading efficiency of the system fog computing on the premise of meeting the user service quality.

Description

Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method
Technical Field
The invention relates to the field of task unloading of fog computing, in particular to a time delay optimization method for the task unloading of the fog computing based on an Improved Particle Swarm Optimization (IPSO).
Background
With the rapid development of communication technology, the global information age characterized by networking has gradually started. Due to the mature development of the fifth generation mobile communication technology (5G) and the comprehensive development of the 5G base station deployment, novel applications such as smart cities, smart homes, smart car road systems and unmanned vehicles are continuously generated. The access of more and more mobile devices and internet of things devices inevitably makes data traffic present a explosive growth situation. Therefore, in order to meet the huge demand for data traffic by the increasing global users and user equipments, new network technologies are emerging in a large number. The development of cloud computing technology has come, and in a cloud computing architecture, computing and processing of all network resources are placed in a cloud data center. Due to the fact that processing resources of single terminal equipment are limited, tasks of the terminal equipment can be unloaded to a cloud data center for processing through a communication link through a cloud computing architecture. However, there are also problems with the development of cloud processing technology. Firstly, the cloud data center has a high aggregation level and is usually far from an end user, and the task offloading to the operation center computing process inevitably brings high network delay. Secondly, more and more terminal devices upload various generated data tasks to the cloud, so that congestion is generated on a transmission link from the terminal devices to the cloud computing center. In order to solve the defects of low time delay, huge data volume and the like of cloud computing in the internet, a fog computing network architecture is produced. The fog computing network does not have the characteristic of a network center like cloud computing, but adopts a distributed computing architecture, is positioned in the middle layers of the cloud data center and the terminal equipment of the Internet of things, and can also provide the capabilities of computing, caching, communication, control and the like.
However, the introduction of the fog calculation also brings a series of challenges, the amount of tasks generated by the terminal equipment may be large, and the distribution to fewer fog nodes for calculation causes a large time delay. Therefore, a reasonable task unloading delay optimization algorithm needs to be designed, and task unloading is effectively performed on the premise that the user service quality is met.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to solve the problem of task unloading of a fog computing network, and provides a fog computing task unloading time delay optimization method based on an improved particle swarm algorithm, which can efficiently optimize a task unloading process, reduce time delay and improve computing capacity of the fog computing network.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the following technical scheme:
a fog computing task unloading time delay optimization method based on an improved particle swarm algorithm is disclosed, wherein a fog computing system comprises a task unloading terminal node and a fog node for receiving task processing, one terminal node can unload tasks to a plurality of fog nodes for carrying out task processing, and the method comprises the following steps:
(1) initializing system parameters including a signal-to-noise ratio threshold, the number of fog nodes, the total amount of tasks, the CPU period and frequency of the fog nodes, a computing capacity coefficient, a transmitting power threshold, a transmitting total power, a channel bandwidth, noise power, a path loss factor and the distance between a terminal node and the fog nodes;
(2) randomly generating a two-dimensional array with the size of P rows and N columns as an initial population, and limiting the position and the speed of each particle in the initial population; wherein P is the number of particles in the population, and N is the number of fog nodes;
(3) taking the unloading time delay of a minimized system as a target, and taking the unloading time delay value corresponding to each particle as a fitness function value of a particle swarm algorithm;
(4) calculating an individual optimal value of each particle and a global optimal value of the whole population; for each particle jUsing its fitness function value fit (j) and individual optimum value pbest(j) Comparison, if fit (j)<pbest(j) Then replace p with fit (j)best(j) (ii) a Furthermore, the fitness function value fit (j) and the global optimum value g for each particle are usedbestComparison, if fit (j)<gbestThen replace g with fit (j)best；
(5) Evolving the speed and position of the particle, and processing boundary conditions;
(6) and repeating the evolution process until an iteration termination condition is met, and obtaining the optimal unloading time delay of the fog calculation task unloading under different iteration times.
Preferably, the calculation formula of the unloading delay d in the step (3) is as follows:
Figure BDA0002660239670000021
wherein M is the total amount of tasks, CPCalculating a rate, F, for a terminal nodeiFor the optimal equivalent calculation capacity of the ith fog node, the calculation formula is as follows:
Figure BDA0002660239670000022
wherein the content of the first and second substances,iis the CPU cycle of the ith fog node, fiIs the CPU frequency, λ, of the ith fog nodeiIs the calculated power coefficient, r, of the ith fog nodeiThe channel capacity between the terminal node and the ith fog node is calculated by the following formula:
Figure BDA0002660239670000023
where B is the wireless link channel bandwidth, SNRiSignal-to-noise ratio for data transmission from the terminal node to the ith fog node, alpha represents the path loss factor, DiRepresenting the distance between the terminal node and the ith fog node, N0Is the noise power, piFor the terminal node toAnd the ith fog node transmits the transmitting power of the data.
Preferably, the transmission power and the signal-to-noise ratio of the terminal node for transmitting data satisfy the following constraints:
0＜pi≤pth
Figure BDA0002660239670000031
SNRi≥SNRth
wherein p isthTransmission power threshold, p, for transmitting data from terminal node to fog nodemaxTransmitting a total power threshold, SNR, for a terminal nodethRepresenting a signal-to-noise threshold for the end node to transmit data.
Preferably, in the step (5), the velocity of the particle is evolved by using an improved compression factor, and the velocity update expression is as follows:
vid(t+1)＝λ·vid(t)+c1r1(t)[pbest(t)-xid(t)]+c2r2(t)[gbest(t)-xid(t)]
wherein, c1And c2Is a learning factor; t marks the iteration times; r is1(t) and r2(t) is [0 to 1]A uniform random number within a range; v. ofid(t) and xid(t) velocity and position of the particles, respectively; p is a radical ofbest(t) is an individual optimum value representing the optimum position of the particle searched so far; gbest(t) is a global optimum value representing the optimum position searched so far by the whole particle swarm; λ is a compression factor, and its expression is:
Figure BDA0002660239670000032
wherein the content of the first and second substances,
Figure BDA0002660239670000033
has the advantages that: compared with the prior art, the fog computing task unloading time delay optimization method based on the improved particle swarm algorithm aims at the problems that the basic particle swarm algorithm is poor in local search capability and low in convergence speed, the compression factor of the improved particle swarm algorithm can control the final convergence of the system behavior, the overall search capability is high, and the like, so that the time delay of the fog computing task unloading can be effectively reduced, the system performance and the service quality are improved, the advantages are obvious, and the method is easy to achieve.
Drawings
FIG. 1 is a detailed flow chart of an implementation of a fog computing task unloading delay optimization method based on an improved particle swarm optimization algorithm;
FIG. 2 is a diagram of an application scenario for fog computing task offloading;
FIG. 3 is a graph of optimal offloading delays for offloading of tasks under different algorithms;
FIG. 4 is a graph of cumulative distribution of optimal unloading delays under different algorithms;
fig. 5 is a graph comparing the optimal unloading delay at different task sizes.
Detailed Description
The present invention is further illustrated by the following figures and specific examples, which are to be understood as illustrative only and not as limiting the scope of the invention, which is to be given the full breadth of the appended claims and any and all equivalent modifications thereof which may occur to those skilled in the art upon reading the present specification.
The selection of the scene directly affects the time delay optimization performance of the unloading of the fog calculation task, and the setting of the scene and the setting of the parameters are analyzed in detail below.
1. Function and number of fog nodes
In the fog computing task unloading system, a Terminal Node (TN) is a node generating various data tasks, the terminal node can compute a small amount of data tasks, more data tasks are unloaded to a plurality of Fog Nodes (FN) for computation, and the fog nodes receive the tasks of the terminal node and then compute. One terminal node can unload the tasks to a plurality of fog nodes for calculation according to the size of the task quantity, and the quantity of the fog nodes is correspondingly set to be N.
2. Offloading latency of tasks
After a task is generated by the terminal node, the computing system of the terminal node processes part of data, the rest is unloaded to the fog node for processing, and the local computing rate of the terminal node is represented as CPChannel capacity r off-loaded to the ith fog nodeiCan be expressed by the formula:
Figure BDA0002660239670000041
where B is the wireless link channel bandwidth, SNRiSignal-to-noise ratio for data transmission from the terminal node to the ith fog node, alpha represents the path loss factor, DiRepresenting the distance between the terminal node and the ith fog node, N0Is the noise power, piAnd transmitting the transmission power of the data to the ith fog node for the terminal node. Thus, the offload delay for a task is the sum of the local computation delay and the transfer delay offloaded to the node, and is formulated as:
Figure BDA0002660239670000042
wherein M is the total amount of tasks, FiFor the optimal equivalent calculation capacity of the ith fog node, the calculation formulas are respectively as follows:
Figure BDA0002660239670000043
wherein the content of the first and second substances,ithe CPU cycle of the ith fog node, which is related to the CPU performance, fiIs the CPU frequency, λ, of the ith fog nodeiThe power factor is calculated according to the performance of the CPU processor.
3. Setting of system boundary conditions
A plurality of fog nodes with different computing capacities exist in the system, and the transmitting power and the transmitting total power of each fog node are limited. Furthermore, to ensure the communication quality requirements of the data transmission link, the signal-to-noise ratio needs to meet its threshold. The constraints are as follows: 0 < pi≤pth，
Figure BDA0002660239670000051
Wherein p isthTransmission power threshold, p, for transmitting data from a Terminal Node (TN) to a fog nodemaxA threshold of total power is transmitted for the N fog nodes. The signal-to-noise ratio constraint conditions are as follows: SNRi≥SNRth，SNRthRepresenting the signal-to-noise threshold of the TN transmission data.
Based on the theoretical basis, the improved particle swarm algorithm-based fog calculation task unloading time delay optimization method is designed.
The symbols or parameters used in the present invention are first described as follows:
TN terminal node
FN mist node
N is the number of fog nodes
M task amount
Bandwidth of channel
N0Noise power
CPTerminal node calculates rate
FiOptimal equivalent computing power of ith fog node
riChannel capacity between terminal node and ith fog node
Alpha path loss factor
DiDistance between terminal node and ith fog node
piTransmitting power of data transmitted by terminal node to ith fog node
pmaxTotal emission power transmitted by terminal node to fog node
SNRiSignal-to-noise ratio of data transmitted by terminal node to ith fog node
SNRthThreshold value of signal-to-noise ratio
iCPU cycle of ith fog node
λiCPU computing power coefficient of ith fog node
fiCPU frequency of ith fog node
c1Learning factor 1
c2Learning factor 2
As shown in fig. 1, the method for optimizing the unloading delay of the fog computing task based on the improved particle swarm optimization disclosed by the embodiment of the invention comprises the following steps:
(1) initializing system parameters including signal-to-noise ratio threshold SNRthThe number N of fog nodes, the total number M of tasks and the period of the ith fog node CPUiAnd frequency fiAnd calculating the coefficient of power λiPower threshold p of the fog nodethTotal power of transmission pmaxChannel bandwidth B, noise power N0Path loss factor α, distance D of terminal node to ith fog nodei(ii) a The wireless transmission links between the Terminal Nodes (TN) and the Fog Nodes (FN) are assumed to distribute orthogonal spectrum resources, each fog node occupies an independent sub-channel, and the link interference between the terminal nodes and different fog nodes can be ignored;
(2) randomly generating a two-dimensional array with the size of P rows and N columns as an initial population, and limiting the position and the speed of each particle in the initial population; wherein P is the number of particles in the population, N is the number of individuals contained in each particle and is also the number of nodes in the fog;
(3) taking the unloading time delay of a minimized system as a target, taking the unloading time delay value corresponding to each particle as a fitness function value fit (i) of the particle swarm algorithm, and taking the unloading time delay d according to a formula
Figure BDA0002660239670000061
Wherein
Figure BDA0002660239670000062
Carrying out time delay solution on the fog calculation task unloading system;
(4) calculating an individual optimal value of each particle and a global optimal value of the whole population; for each particle, using its fitness function value fit (j) and the individual optimum value pbest(j) Comparison, if fit (j)<pbest(j) Then replace p with fit (j)best(j) (ii) a Furthermore, the fitness function fit (j) and global optimum g for each particle are usedbestComparison, if fit (j)<gbestThen replace g with fit (j)bestWherein j is 1,2, … P, P is the number of particles;
(5) and evolving the speed and the position of the particle according to the calculated optimal value, wherein the speed updating expression is as follows: v. ofid(t)＝λ·vid(t)+c1r1(t)[pbest(t)-xid(t)]+c2r2(t)[gbest(t)-xid(t)]Wherein T is 1,2, … T, T represents the maximum number of iterations; λ is the improved compression factor, and the improved expression is:
Figure BDA0002660239670000071
the position update expression is x (j,:) + v (j,: where j is 1,2, … P, P is the number of particles; judging the constraint condition after the position and speed are updated, and according to the boundary constraint condition that 0 < pi≤pth，
Figure BDA0002660239670000072
Constraining, wherein the transmission power transmitted by the terminal node to the fog node does not exceed pthTotal power of transmission not exceeding pmax. In addition, another constraint is to constrain the SNR for the signal-to-noise ratio of the transmissioni≥SNRthWherein SNR isthRepresenting the signal-to-noise threshold of the TN transmission data.
(6) And stopping the algorithm when the evolutionary algebra iterates to a set maximum number T or meets other convergence conditions of finding an optimal value of the fitness function, gradually stabilizing the task unloading delay and the like. And finally, calculating a final objective function value and calculating the optimal task unloading time delay.
Fig. 2 is a scene diagram of a fog computing task unloading delay optimization method based on an improved particle swarm optimization, according to a specific example of an embodiment of the present invention, N Fog Nodes (FN) with different computing capabilities coordinate to complete a task generated by a Terminal Node (TN).
Fig. 3 compares the optimal offloading time delay of the task of fog computing obtained by using the Improved Particle Swarm Optimization (IPSO) and other algorithms in detail. In order to verify the advantages of the method of the invention over the prior art, it can be seen from the figure that the optimal offloading time delay of the Genetic Algorithm (GA), the differential evolution algorithm (DE) and the basic particle swarm algorithm (PSO) is always higher than that of the improved particle swarm algorithm (IPSO) along with the continuous increase of the iteration times, so the optimization of the genetic algorithm, the differential evolution algorithm and the basic particle swarm algorithm on the optimal offloading time delay is not as good as that of the improved particle swarm algorithm. With the continuous increase of the iteration times, the optimal unloading time delay of the improved particle swarm algorithm is continuously reduced, which shows that the optimization result is continuously optimized and the time delay is continuously shortened with the increase of the iteration times of the algorithm. In summary, the improved particle swarm algorithm-based fog calculation task unloading time delay optimization method adopted in the invention has the advantages of small calculated amount, short optimal unloading time delay and fast convergence, and can greatly improve the task unloading performance and quality of the system.
Fig. 4 illustrates the Cumulative Distribution Function (CDF) of the optimal unloading delay under different algorithms by using a monte carlo simulation method. It can be seen that the time delay optimization performance of the genetic algorithm and the basic particle swarm algorithm is the worst, the performance of the improved particle swarm algorithm is the best, and the obtained optimal solution is approximately distributed in the range of 1.5 seconds to 5.3 seconds. Compared with a Genetic Algorithm (GA), a differential evolution algorithm (DE) and a basic particle swarm algorithm (PSO), the optimal unloading time delay obtained by improving the particle swarm algorithm (IPSO) is respectively reduced by 1 to 1.5 seconds, and the effectiveness of the algorithm is further verified.
Fig. 5 shows the optimal unloading delay of different task sizes under different algorithms. It can be seen that, as the amount of tasks increases, the optimal offload delay using Genetic Algorithm (GA) increases most, and the optimal offload delay using improved particle swarm algorithm (IPSO) is the second to particle swarm algorithm (PSO) and differential evolution algorithm (DE) is the smallest. Thereby indicating. When the task amount is increased, the optimization capability of the particle swarm optimization is still strong, and the universality and the effectiveness of the particle swarm optimization are further verified.

Claims (5)

1. A fog computing task unloading time delay optimization method based on an improved particle swarm algorithm is characterized in that a fog computing system comprises a task unloading terminal node and a fog node for receiving task processing, and one terminal node can unload tasks to a plurality of fog nodes for carrying out task processing, and the method comprises the following steps:
(1) initializing system parameters including a signal-to-noise ratio threshold, the number of fog nodes, the total amount of tasks, the CPU period and frequency of the fog nodes, a computing capacity coefficient, a transmitting power threshold, a transmitting total power, a channel bandwidth, noise power, a path loss factor and the distance between a terminal node and the fog nodes;
(2) randomly generating a two-dimensional array with the size of P rows and N columns as an initial population, and limiting the position and the speed of each particle in the initial population; wherein P is the number of particles in the population, and N is the number of fog nodes;
(3) taking the unloading time delay of a minimized system as a target, and taking the unloading time delay value corresponding to each particle as a fitness function value of a particle swarm algorithm;
(4) calculating an individual optimal value of each particle and a global optimal value of the whole population; for each particle j, use its fitness function value fit (j) and the individual optimum value pbest(j) Comparison, if fit (j)<pbest(j) Then replace p with fit (j)best(j) (ii) a Furthermore, the fitness function value fit (j) and the global optimum value g for each particle are usedbestComparison, if fit (j)<gbestThen replace g with fit (j)best；
(5) Evolving the speed and position of the particle, and processing boundary conditions;
(6) and repeating the evolution process until an iteration termination condition is met, and obtaining the optimal unloading time delay of the fog calculation task unloading under different iteration times.
2. The improved particle swarm optimization-based task unloading delay optimization method according to claim 1, wherein the unloading delay d in the step (3) is calculated by the following formula:
Figure FDA0002660239660000011
wherein M is the total amount of tasks, CPCalculating rates for terminal nodes，FiThe optimal equivalent computing power of the ith fog node.
3. The improved particle swarm optimization-based fog calculation task unloading delay optimization method as claimed in claim 2, wherein the optimal equivalent calculation capacity F of the ith fog nodeiThe calculation formula of (2) is as follows:
Figure FDA0002660239660000012
wherein the content of the first and second substances,iis the CPU cycle of the ith fog node, fiIs the CPU frequency, λ, of the ith fog nodeiIs the calculated power coefficient, r, of the ith fog nodeiThe channel capacity between the terminal node and the ith fog node is calculated by the following formula:
Figure FDA0002660239660000021
where B is the wireless link channel bandwidth, SNRiSignal-to-noise ratio for data transmission from the terminal node to the ith fog node, alpha represents the path loss factor, DiRepresenting the distance between the terminal node and the ith fog node, N0Is the noise power, piAnd transmitting the transmission power of the data to the ith fog node for the terminal node.
4. The improved particle swarm optimization-based fog calculation task unloading delay optimization method according to claim 3, wherein the transmission power and signal-to-noise ratio of the terminal node for transmitting data satisfy the following constraints:
0＜pi≤pth
Figure FDA0002660239660000022
SNRi≥SNRth
wherein p isthTransmission power threshold, p, for transmitting data from terminal node to fog nodemaxTransmitting a total power threshold, SNR, for a terminal nodethRepresenting a signal-to-noise threshold for the end node to transmit data.
5. The improved particle swarm algorithm-based fog computing task unloading delay optimization method according to claim 1, wherein in the step (5), the velocity of the particle is evolved by using an improved compression factor, and a velocity update expression is as follows:
vid(t+1)＝λ·vid(t)+c1r1(t)[pbest(t)-xid(t)]+c2r2(t)[gbest(t)-xid(t)]
wherein, c1And c2Is a learning factor; t marks the iteration times; r is1(t) and r2(t) is [0 to 1]A uniform random number within a range; v. ofid(t) and xid(t) velocity and position of the particles, respectively; p is a radical ofbest(t) is an individual optimum value representing the optimum position of the particle searched so far; gbest(t) is a global optimum value representing the optimum position searched so far by the whole particle swarm; λ is a compression factor, and its expression is:
Figure FDA0002660239660000023
wherein the content of the first and second substances,
Figure FDA0002660239660000024
CN202010902490.XA 2020-09-01 2020-09-01 Improved particle swarm optimization based time delay optimization method for unloading of fog calculation task Active CN112084025B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010902490.XA CN112084025B (en) 2020-09-01 2020-09-01 Improved particle swarm optimization based time delay optimization method for unloading of fog calculation task

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010902490.XA CN112084025B (en) 2020-09-01 2020-09-01 Improved particle swarm optimization based time delay optimization method for unloading of fog calculation task

Publications (2)

Publication Number Publication Date
CN112084025A true CN112084025A (en) 2020-12-15
CN112084025B CN112084025B (en) 2022-09-23

Family

ID=73731279

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010902490.XA Active CN112084025B (en) 2020-09-01 2020-09-01 Improved particle swarm optimization based time delay optimization method for unloading of fog calculation task

Country Status (1)

Country Link
CN (1) CN112084025B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112738263A (en) * 2020-12-31 2021-04-30 杭州电子科技大学 Genetic algorithm-based Fog-RAN network cache placement problem decision method
CN113590211A (en) * 2021-05-14 2021-11-02 南京航空航天大学 Calculation unloading method based on PSO-DE algorithm
CN113660325A (en) * 2021-08-10 2021-11-16 克拉玛依和中云网技术发展有限公司 Industrial Internet task unloading strategy based on edge calculation
CN113709694A (en) * 2021-07-28 2021-11-26 南京邮电大学 Calculation task unloading method for edge Internet of vehicles system
CN114143814A (en) * 2021-12-13 2022-03-04 华北电力大学（保定） Multitask unloading method and system based on heterogeneous edge cloud architecture
CN114710785A (en) * 2022-04-08 2022-07-05 浙江金乙昌科技股份有限公司 Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm
CN114756557A (en) * 2022-06-15 2022-07-15 广州晨安网络科技有限公司 Data processing method of improved computer algorithm model

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170337091A1 (en) * 2016-05-17 2017-11-23 International Business Machines Corporation Allocating compute offload resources
US20190190789A1 (en) * 2017-12-18 2019-06-20 Shanghai Research Center For Wireless Communications Computing capability description method, interaction method and node device for fog computing
CN110569128A (en) * 2019-09-12 2019-12-13 曲阜师范大学 scheduling method and system for fog computing resources
CN111510477A (en) * 2020-04-07 2020-08-07 河海大学 Fog computing network task unloading method based on improved contract network agreement and BAS

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170337091A1 (en) * 2016-05-17 2017-11-23 International Business Machines Corporation Allocating compute offload resources
US20190190789A1 (en) * 2017-12-18 2019-06-20 Shanghai Research Center For Wireless Communications Computing capability description method, interaction method and node device for fog computing
CN110569128A (en) * 2019-09-12 2019-12-13 曲阜师范大学 scheduling method and system for fog computing resources
CN111510477A (en) * 2020-04-07 2020-08-07 河海大学 Fog computing network task unloading method based on improved contract network agreement and BAS

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112738263A (en) * 2020-12-31 2021-04-30 杭州电子科技大学 Genetic algorithm-based Fog-RAN network cache placement problem decision method
CN113590211A (en) * 2021-05-14 2021-11-02 南京航空航天大学 Calculation unloading method based on PSO-DE algorithm
CN113709694A (en) * 2021-07-28 2021-11-26 南京邮电大学 Calculation task unloading method for edge Internet of vehicles system
CN113709694B (en) * 2021-07-28 2023-09-29 南京邮电大学 Computing task unloading method for edge internet of vehicles system
CN113660325A (en) * 2021-08-10 2021-11-16 克拉玛依和中云网技术发展有限公司 Industrial Internet task unloading strategy based on edge calculation
CN113660325B (en) * 2021-08-10 2023-11-07 克拉玛依和中云网技术发展有限公司 Industrial Internet task unloading strategy based on edge calculation
CN114143814A (en) * 2021-12-13 2022-03-04 华北电力大学（保定） Multitask unloading method and system based on heterogeneous edge cloud architecture
CN114143814B (en) * 2021-12-13 2024-01-23 华北电力大学（保定） Multi-task unloading method and system based on heterogeneous edge cloud architecture
CN114710785A (en) * 2022-04-08 2022-07-05 浙江金乙昌科技股份有限公司 Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm
CN114756557A (en) * 2022-06-15 2022-07-15 广州晨安网络科技有限公司 Data processing method of improved computer algorithm model

Also Published As

Publication number Publication date
CN112084025B (en) 2022-09-23

Similar Documents

Publication Publication Date Title
CN112084025B (en) Improved particle swarm optimization based time delay optimization method for unloading of fog calculation task
CN109413724B (en) MEC-based task unloading and resource allocation scheme
CN111314889A (en) Task unloading and resource allocation method based on mobile edge calculation in Internet of vehicles
CN113242568A (en) Task unloading and resource allocation method in uncertain network environment
CN109951869B (en) Internet of vehicles resource allocation method based on cloud and mist mixed calculation
CN111372314A (en) Task unloading method and task unloading device based on mobile edge computing scene
CN110233755B (en) Computing resource and frequency spectrum resource allocation method for fog computing in Internet of things
CN111556572B (en) Spectrum resource and computing resource joint allocation method based on reinforcement learning
CN110928654A (en) Distributed online task unloading scheduling method in edge computing system
CN111586720A (en) Task unloading and resource allocation combined optimization method in multi-cell scene
CN110167176B (en) Wireless network resource allocation method based on distributed machine learning
Hou et al. Joint allocation of wireless resource and computing capability in MEC-enabled vehicular network
CN110856259A (en) Resource allocation and offloading method for adaptive data block size in mobile edge computing environment
CN113115339B (en) Task unloading and resource allocation joint optimization method based on mobility awareness
CN112737842A (en) Task safety unloading method based on minimized time delay in air-ground integrated Internet of vehicles
CN113727362B (en) Unloading strategy method of wireless power supply system based on deep reinforcement learning
CN112491957B (en) Distributed computing unloading method and system under edge network environment
CN111182509B (en) Ubiquitous power Internet of things access method based on context-aware learning
WO2023020502A1 (en) Data processing method and apparatus
CN111556576B (en) Time delay optimization method based on D2D _ MEC system
CN112860429A (en) Cost-efficiency optimization system and method for task unloading in mobile edge computing system
CN116405569A (en) Task unloading matching method and system based on vehicle and edge computing server
CN113783959B (en) Internet of vehicles joint optimization calculation task unloading rate and resource allocation method
CN113709728A (en) NOMA (non-oriented multi-agent) and unmanned aerial vehicle-assisted two-stage mobile edge computing communication method
CN110602718B (en) Heterogeneous cellular network power distribution method and system based on alternative direction multiplier method

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