CN114710785A - Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm - Google Patents
Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm Download PDFInfo
- Publication number
- CN114710785A CN114710785A CN202210367435.4A CN202210367435A CN114710785A CN 114710785 A CN114710785 A CN 114710785A CN 202210367435 A CN202210367435 A CN 202210367435A CN 114710785 A CN114710785 A CN 114710785A
- Authority
- CN
- China
- Prior art keywords
- vehicles
- particle swarm
- optimization
- vehicle
- internet
- 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
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/02—Resource partitioning among network components, e.g. reuse partitioning
- H04W16/10—Dynamic resource partitioning
-
- 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]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
- H04W28/18—Negotiating wireless communication parameters
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a particle swarm algorithm-based vehicle networking cooperative computing resource scheduling design method, which reduces the overall delay by introducing vehicle cooperative computing auxiliary vehicle-mounted application. The method converts an actual problem into an optimization function solving problem, applies and designs a heuristic algorithm, and equivalently converts a complex mixed integer nonlinear programming problem into a variable in a particle swarm evolution mechanism; by utilizing the method, the dependence of designers on mathematical theory knowledge can be reduced, the method is more easily applied to other resource scheduling systems, and a resource scheduling method with a more complex structure and more excellent performance can be designed; meanwhile, compared with the traditional traversal method, the method greatly reduces the search complexity, reduces the average transmission power and saves the energy consumption.
Description
Technical Field
The invention belongs to the field of wireless communication network application in a new generation of information technology, and particularly relates to a particle swarm algorithm-based resource scheduling design method for Internet of vehicles cooperation calculation.
Background
With the advent of computing-intensive and delay-sensitive vehicle applications, such as Virtual Reality (VR), Augmented Vehicle Reality (AVR), and image recognition, have presented significant challenges for autonomous vehicles with limited computing resources. These applications require a large amount of computing resources to analyze large amounts of raw sensing data and require real-time processing. The vehicle auxiliary computing can reduce the problem of high delay caused by insufficient vehicle-mounted computing resources, and by unloading the vehicle-mounted application to an idle auxiliary vehicle, the application tasks of the vehicle with insufficient computing resources can be quickly processed, so that the overall delay performance is improved. However, similar offloading and resource scheduling problems are usually very complex, and different application scenarios may generate different optimization problems and corresponding solutions, and the traditional mathematical solution of such problems is complex and not beneficial to simplify design and large-scale application. Therefore, the resource scheduling design is realized by using an intelligent algorithm and an intelligent design mode, and the method has strong requirements.
As early as the 17 th century, European mathematician Fermat proposed the problem of solving the maximum or minimum values according to the derivative relation, but the system theory is not formed, and then in the following time, the optimization method is slowly developed until the second world war of 20 decades and forty, and some optimization algorithms such as linear programming and the like are generated due to the urgent need of military operational research. With the expansion of the fields of economy, military and science and technology after the second war, the optimization algorithm is developed rapidly.
Particle swarm optimization is a heuristic computational technique, originally proposed by Eberhar and Kennedy in 1995. Through continuous development, the method has the characteristics of fast convergence, low complexity and high precision, and is a practical method for solving the problem of complex optimization.
Shahin Gheitanchi et al use a particle swarm algorithm to solve the problem of resource allocation in wireless communication systems. (S.Gheitanchi, F.Ali and E.Stipidis, "Particle Swarm Optimization for Resource Allocation in OFDMA," 200715 th International Conference on Digital Signal Processing,2007, pp.383-386, doi: 10.1109/ICDSP.2007.4288599.). The article applies the method to subcarrier allocation in OFDMA, and the result shows that compared with the traditional technology, the method greatly reduces the computational complexity and increases the flexibility.
In addition, Sandra Scott-Hayward et al developed a multi-user wireless network resource scheduling method using a particle swarm algorithm. (S.Scott-Hayward and E.Garcia-Palactios, "A PSO approach to resource allocation in wireless networks," 201235 th International Conference on Telecommunications and Signal Processing (TSP),2012, pp.151-155, doi: 10.1109/TSP.2012.6256271.). The capability of the particle swarm algorithm to reach the optimal solution shows that the method has the potential of resource allocation in a heterogeneous application program network which is not suitable for the convex optimization method.
Hanan Al-Tous et Al studied the problem of resource scheduling in multiuser cooperative communication by particle swarm optimization in 2016. (H.Al-Tous and I.Barhuni, "Distributed resource allocation for multi-user multi-relay AF collaborative Communication," 20148 th International Conference on Signal Processing and Communication Systems (ICSPCS),2014, pp.1-6, doi: 10.1109/ICSPCS.2014.7021077.). A method for distributing distributed resources based on fitness function is provided.
Qiang Wang et al published 2017 a method for resource allocation using particle swarm optimization in CIS. (Q.Wang, T.Chen and H. -L.Liu, "Resource Allocation for D2D underline Communication Systems Using PSO," 201713 th International Conference on Computational Integration and Security (CIS),2017, pp.202-206, doi: 10.1109/CIS.2017.00051.). The method adopts a particle swarm algorithm to design a frequency spectrum sharing method, aims at optimizing the system speed, and improves the frequency spectrum utilization rate.
The process of solving the problem of complex communication resource allocation by the traditional optimization algorithm is complex, and sometimes even a corresponding solution cannot be obtained. In practical application, due to a complex space-time scene, the final effect of the method often cannot meet the index requirement. In addition, when a communication scene changes, due to the change of a system model, a designed optimization algorithm generally cannot be applied to a new system, and a modeling extraction optimization problem needs to be re-established and then solved, so that the method is not beneficial to large-scale application. Therefore, the method for resource scheduling design based on particle swarm can greatly save labor cost and reduce design time. By using the resource scheduling design method, a designer only needs to input the acquired vehicle and road channel information to realize the automatic generation of the unloading target and the resource scheduling. With the continuous development of the intelligent optimization algorithm, a resource scheduling scheme meeting the requirements can be more conveniently designed by means of the mutual combination of the optimization algorithm and simulation software, and the method also becomes an effective way for designing a resource scheduling system.
Disclosure of Invention
In order to solve the problems in the vehicle auxiliary computing unloading and resource scheduling design, the invention provides a vehicle networking cooperative computing resource scheduling design method based on a particle swarm algorithm, in order to achieve the aim, the invention designs vehicle auxiliary computing unloading and resource scheduling design steps based on the particle swarm algorithm, and the unloading and resource scheduling design steps are as follows:
the method comprises the following steps: dividing an actual road into even sub-regions according to distance, adopting frequency reuse among the spaced regions, and enabling each sub-region to have a vehicle auxiliary calculation; and selecting the idle vehicle with the highest computing resource as an auxiliary vehicle, and taking the rest vehicles as potential unloading requesting vehicles.
Step two: and establishing a system mathematical model according to the specific vehicle network environment and the task type, and calculating to generate an optimization target. The optimization target is the total time delay for all vehicles to complete the task, including the local computation time delay and the auxiliary computation time delay (transmission time delay and auxiliary computation time delay). The optimization variables include the unloaded vehicle selection, and the transmit power allocation of the unloaded vehicle. The constraint condition is determined according to the environmental parameters.
Step three: and encoding the unloading vehicles with the optional optimized variables and the corresponding transmitting power by aiming at a particle swarm algorithm, setting particle variable boundaries according to constraint conditions, and selecting proper particle population quantity, iteration times and internal parameters.
Step four: selecting the unloading vehicle number of the initial particle by adopting a roulette wheel method according to the channel condition, and selecting the corresponding transmitting power by adopting a given function, wherein the step corresponds to the establishment of the initial population in the particle swarm optimization.
Step five: and importing the calculation result into a particle swarm algorithm learning mechanism, and realizing the optimization of data through a generation mechanism and a movement mechanism of the particle swarm algorithm. And according to the multi-objective optimization strategy, each particle is moved to the optimal solution direction in iteration through a series of optimization mechanisms. By means of the random movement of parts in each particle, a new solution space can be explored in the optimization process, and the joint action of a plurality of factors is considered.
Step six: and judging whether the newly generated particles exceed the constraint condition, and correcting the exceeded part to enable the newly generated particles to meet the constraint condition.
Step seven: and according to the convergence condition of the calculation result, performing iterative calculation judgment: and judging whether the convergence condition is met or not according to a preset maximum iteration step number or a preset convergence condition. If the convergence condition is met, stopping calculation, and exporting an unloading target and a corresponding transmission power distribution parameter result; otherwise, returning to the step five to continue the calculation.
Step eight: and importing the calculated unloading target and the transmission power parameter result into a total time delay calculation model to generate the unloading target of the vehicle and obtain a cooperative calculation resource scheduling result of the Internet of vehicles.
More specifically, in step one of the present disclosure, a road is divided into M sub-regions according to distance, and each N sub-regions use the same frequency for auxiliary computation transmission. Suppose there are K vehicles in total, denoted VU, on a roadkK is K, K ∈ K, K {1,2, …, K }. The idle vehicle with the largest computing resource in each subarea is taken as an auxiliary vehicle and is marked as AUiI e {1,2, …, M }, with other vehicles in each sub-zone as optional requestsUnloading vehicles, and recording the number set as RU according to the sub-aream,m∈{1,2,…,M}。
For step two of the disclosure, there may be one vehicle unloaded to the auxiliary vehicle calculation for each sub-area, and the unloading decision of all K vehicles may be described as: a ═ a1,a2,…,aK},
k∈K，
When a isk1 indicates that a vehicle VU is selectedkOffloading tasks to AU as request offload vehiclemPerforming auxiliary calculation, otherwise
Indicating VUkLocal calculations are performed. Further obtain VUkTask delay of (2):
wherein
In order to calculate the time delay locally,
time delays calculated for offloading to an auxiliary vehicle, including vehicle VUkTo auxiliary vehicles AUiIs delayed
And assisting the calculated time delay of the vehicle
Let the transmission power of each vehicle be P ═ P1,P2,…,PKA constraint condition of 0 ≦ Pk≤Pk max，Pk maxIs the maximum transmit power. Further obtaining the task minimization time delay optimization of all vehiclesThe target is as follows:
aiming at the third step of the invention, the vehicle number is used for representing the unloading request vehicle in each subarea, and corresponding transmission power is applied to generate the particle code with the dimension of 2M: x ═ r1,r2,…,rM,P1,P2,…,PM]＝[xr,xP]Wherein r ismK stands for selecting vehicle VUkAs a request to unload the vehicle, PmIs its corresponding transmit power.
Aiming at the fourth step of the invention, the initial population is selected by adopting a roulette wheel method according to the initial channel condition of each vehicle, the better the initial channel condition between the vehicles is, the higher the probability of selecting the vehicle as the initial population is:
wherein p isk,iFor selecting vehicles VUkAs probability of requesting to unload the vehicle, gk,iIs VUkAnd auxiliary vehicles AUmChannel information between.
The initial transmission power is selected to be any value of the maximum power and half of the maximum power:
Pk,i＝rand(Pmax)
where rand is a random function between 0.5 and 1.
Aiming at the fifth step of the invention content, according to a particle swarm evolution mechanism, aiming at the particle swarm coding, in the optimization process, the weight value position x of the l-dimension particle is adjustedlAnd velocity vlTo implement the change of each particle parameter to obtain a new solution.
In particular, by pbestlAnd the optimal position of the particle for obtaining the optimal time delay at the current iteration time is represented, and the global optimal position obtained from all the particles until the current iteration time is represented by the gbest. By combining the velocity vector and the position vector, the particle swarm optimization algorithm approaches to the optimal position, and searches for new position one by oneAnd (4) solving the space. The following equations describe the update plan details for each particle as follows:
vl[t+1]＝w[t]vl[t]+ccog·rand1(pbestl[t]-xl[t])+csoc·rand2(gbest[t]-xl[t])
xl[t+1]＝xl[t]+vl[t+1]；
where t is the number of iterations, ccogAnd csocRespectively a predetermined cognitive parameter and a predetermined social parameter, rand1And rand2Is a random function for generating parameters between 0 and 1 to provide a new exploration direction. Using a weighting coefficient w t]To calculate the step size controlling the particle velocity, w t as the number of iterations t increases]And decreases. Normally the weighting factors may be as follows: w [ t ]]＝wmax-(wmax-wmin)·t/Tpso；
Wherein T ispsoIs the maximum number of iteration steps, w, of the particle swarmmaxAnd wminGiven a weighting factor.
Aiming at the sixth step of the invention content, because the number of the vehicle requesting to unload is a real number, the front M dimension of the obtained new particle is rounded, the exceeding part is corrected according to the constraint condition as follows, the number of the vehicle in the exceeding sub-area is the nearest number of the vehicle in the atomic area,
given boundary values for the transmit power outside the power range,
and as described in the seventh step, when the calculation result reaches the maximum iteration step number, ending the particle swarm calculation. At this time, the gbest result of the last step is derived as the final optimization solution.
And step eight, importing the calculated unloading target and the transmission power parameter result into a total time delay calculation model to obtain the task time delays of all vehicles. And the vehicle carrying out the auxiliary unloading transmits the task to the auxiliary vehicle for calculation by adopting the corresponding transmitting power, the transmitting power of the vehicle not carrying out the auxiliary unloading is 0, the local calculation is carried out, and finally the scheduling result of the cooperative calculation resources of the Internet of vehicles is obtained.
Drawings
FIG. 1 is a flow chart of resource allocation design based on particle swarm optimization;
FIG. 2 is a schematic diagram of road Internet of vehicles cooperative computing resource scheduling;
FIG. 3 is a diagram illustrating sub-region division and frequency reuse;
FIG. 4 is a schematic diagram of an initial population selection roulette wheel of a particle swarm algorithm;
FIG. 5 is a time delay comparison diagram of methods such as resource allocation and exhaustion based on particle swarm optimization;
fig. 6 is a comparison graph of average transmission power of methods such as resource allocation and exhaustion based on particle swarm optimization.
Detailed Description
In order to further illustrate the technical means and effects of the present invention, the following description is given with reference to the embodiments and the performances of the present invention.
The embodiment discloses a design method for scheduling cooperative computing resources of the Internet of vehicles based on a particle swarm algorithm. Illustrative embodiments of the invention are shown in the drawings, by which aspects of the invention are practiced. The following concepts and embodiments may be implemented in any of a variety of ways and are not limited to the embodiments described below.
The sub-area size is set according to the road environment, in this example, a single-row road with a length of 200 meters is used, the sub-area1-sub-area4 is equally divided into 4 sub-areas, the sub-areas with different frequencies use the same frequency band (N2, freq1-freq2), as shown in fig. 2, and the arrows in the figure respectively represent the local calculation of the vehicle, the unloading auxiliary calculation and the generated transmission interference. The number of vehicles in each subarea is 3 to 8, and the positions are randomly distributed. Task size of each vehicle is [5-20 ]]Mbit, randomly generated. The idle vehicle generation probability is 0.3. Channel bandwidth BvIs 2MHz, maximum transmission power Pmax30dBm, noise power σ2Is-114 dBm. The transmission rate R of auxiliary unloading in frequency reuse can be obtainedk,iFor calculating transmission time delay
Where k ∈ RUmJ is the number of the vehicles requested to be unloaded in the interval subarea, and j belongs to RUm+2. Channel information adoption model | gk,i|2＝αk,i|hk,i|2In which α isk,i＝63.3+17.7log10(dk,i) Is large scale fading, dk,iIs the distance between the two vehicles,
is a small scale fading.
The corresponding initial particle population is generated in the top M dimension using the roulette wheel algorithm, and fig. 4 shows the probability of a selected vehicle number for unload assist calculation. In FIG. 4 r1-r6 are represented as the first M-dimensional vector x in the population of particlesrAnd correspondingly carrying out unloading auxiliary calculation on the vehicle number. Last M-dimensional transmit power vector xPGenerated by the rand function in step four.
Performing iterative computation by adopting a particle swarm algorithm, wherein the specific weight coefficient is respectively set as 256 times of population, 128 times of iteration, and ccogAnd csocRespectively take 2.03, wmaxAnd wminTake 0.9 and 0.5, respectively.
And combining the obtained result with the original optimization problem, calculating the overall time delay performance, randomly generating vehicle environment information according to the second step, performing 1000 times of calculation and solving, averaging to obtain the average performance result of the vehicle networking cooperative computing resource scheduling design based on the particle swarm optimization of the method, and recording the average performance result as V2V-PSO.
An exhaustive method is adopted to obtain an optimal solution, wherein the number of the selectable transmission power combinations of the vehicles is set to be 5, and a comparison with the method is made in figure 5 and is marked as V2V-optimal-exceeded. In addition, the method for requesting unloading of vehicles by randomly selecting the maximum transmission power and the method for requesting unloading of vehicles by optimally selecting the maximum transmission power are compared with the method only by adopting a Local calculation method and are respectively marked as V2V-random-fixed, V2V-optimal-fixed and Local-fixed. As can be seen from fig. 5, as the number of vehicles in each sub-area increases, the total time delay increases, and the method can achieve performance close to the optimal solution and reduce the task time delay over local computation and other offloading methods. In fig. 6, the average transmit power for the method taken and the method of exhaustive to get the optimal solution and the fixed maximum transmit power are denoted by P-PSO, P-optimal and P-fixed, respectively. It can be found that the method can reduce the average transmission power and save energy while achieving the approximate optimal solution.
Through analysis, when the number of vehicles existing in each cell is 8, the search complexity of the method is 256 multiplied by 128, and the search complexity of the optimal solution obtained by the exhaustion method is 84×54. Therefore, the method can greatly reduce the algorithm complexity and improve the application efficiency. Particularly, as the number of vehicles increases, in order to better improve the auxiliary calculation efficiency, the number M of sub-regions should also increase, and the search complexity of the exhaustive method increases exponentially and is not suitable for solving the optimization problem any more.
Claims (7)
1. A design method for scheduling cooperative computing resources in Internet of vehicles based on a particle swarm algorithm is characterized in that the automatic design step of cooperative computing resource scheduling is as follows:
the method comprises the following steps: dividing an actual road into a plurality of sub-areas according to distance, selecting an idle vehicle with the highest computing resource in each area as an auxiliary computing vehicle, performing networking auxiliary computing in the plurality of sub-areas simultaneously, and performing local computing on the other vehicles;
step two: according to the specific vehicle network environment and the task type, a system mathematical model is established, and the total time delay of completing tasks of all vehicles is optimized; setting parameters of the algorithm according to actual conditions, wherein the parameters comprise the number of variables, the variation range of the variables and the size of a population;
step three: encoding optimization variable selectable unloading vehicles and corresponding transmitting power by aiming at a particle swarm algorithm: establishing an initial population in a particle swarm algorithm, selecting the unloading vehicle number of an initial particle by adopting a roulette plate method, selecting corresponding transmitting power by adopting a given function, and setting a particle variable boundary according to a constraint condition;
step four: importing the calculation result into a particle swarm algorithm learning mechanism, and realizing the optimization of data through a generation mechanism and a movement mechanism of the particle swarm algorithm; according to a multi-objective optimization strategy, each particle is moved to the optimal solution direction in iteration through a series of optimization mechanisms; by means of random movement of parts of particles, a new solution space can be explored in the optimization process, and new variables are adjusted according to constraints;
step five: and importing the calculated unloading target and the transmission power parameter result into a total time delay calculation model to generate the unloading target of the vehicle, and obtaining the cooperative calculation resource scheduling result of the Internet of vehicles.
2. The Internet of vehicles cooperative computing resource scheduling design method based on particle swarm optimization according to claim 1, wherein in the first step, roads are equally divided into even number of sub-areas, frequency reuse technology is adopted, and non-adjacent areas reuse the same frequency spectrum.
3. The Internet of vehicles cooperative computing resource scheduling design method based on particle swarm optimization according to claim 1, wherein in step two, parameters to be optimized in a system mathematical model are converted into variables in the mathematical model, and specifically, the parameters include vehicle selection for unloading auxiliary computing and corresponding transmission power; in the actual engineering optimization process, the total calculation time delay of all vehicles is set as an optimization target, and the relation is established with the optimized parameters through calculation and transmission time delay.
4. The design method for scheduling cooperative computing resources in internet of vehicles based on particle swarm optimization according to claim 1, wherein in the third step, each factor affecting the optimization goal can be represented as a variable parameter, the number of variables and the type of variables are determined by the factors affecting the optimization goal in the practical problem, and the set x is [ r ],1,r2,…,rM,P1,P2,…,PM]＝[xr,xP]encoding a population, wherein xrInteger variable representing the number of the selected unloaded vehicles, xPIs a continuous variable and represents the corresponding transmission power, and M represents the number of sub-regions; and generating corresponding variables by adopting the method in the third step, and generating an initial population according to the population parameters set in the second step.
5. The Internet of vehicles cooperative computing resource scheduling design method based on particle swarm optimization according to claim 4, wherein in the fifth step, the computing result is imported into a learning mechanism of particle swarm optimization, and the optimization of data is realized through a generation mechanism and a movement mechanism of the particle swarm optimization; adjusting the particle variables exceeding the constraint condition: for new variable xrRounding and ensuring to be in the same sub-region for x exceeding the transmission power boundaryPTaking boundary values.
6. The method for designing scheduling of cooperative computing resources in Internet of vehicles based on particle swarm optimization according to claim 5, wherein the vehicles for auxiliary unloading and non-auxiliary unloading are subjected to auxiliary computing and local computing respectively according to the time delay condition of each node in the system mathematical model, so that an optimized scheduling result of cooperative computing resources in Internet of vehicles is realized.
7. The Internet of vehicles cooperative computing resource scheduling design method based on the particle swarm optimization is characterized in that in the fifth step, the optimized population in each step is introduced into a total time delay calculation model to generate an unloading target of the vehicle, and the value of the optimized parameter variable is obtained according to the final optimized calculation result to obtain the final Internet of vehicles cooperative computing resource scheduling method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210367435.4A CN114710785B (en) | 2022-04-08 | 2022-04-08 | Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210367435.4A CN114710785B (en) | 2022-04-08 | 2022-04-08 | Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114710785A true CN114710785A (en) | 2022-07-05 |
| CN114710785B CN114710785B (en) | 2022-11-29 |
Family
ID=82173532
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210367435.4A Active CN114710785B (en) | 2022-04-08 | 2022-04-08 | Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114710785B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980470A (en) * | 2010-10-03 | 2011-02-23 | 鲁东大学 | Chaotic particle swarm optimization-based OFDM system resource allocation algorithm |
| US9015093B1 (en) * | 2010-10-26 | 2015-04-21 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| CN111314889A (en) * | 2020-02-26 | 2020-06-19 | 华南理工大学 | Task unloading and resource allocation method based on mobile edge calculation in Internet of vehicles |
| CN112084025A (en) * | 2020-09-01 | 2020-12-15 | 河海大学 | Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method |
| CN112512056A (en) * | 2020-11-14 | 2021-03-16 | 北京工业大学 | Multi-objective optimization calculation unloading method in mobile edge calculation network |
-
2022
- 2022-04-08 CN CN202210367435.4A patent/CN114710785B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101980470A (en) * | 2010-10-03 | 2011-02-23 | 鲁东大学 | Chaotic particle swarm optimization-based OFDM system resource allocation algorithm |
| US9015093B1 (en) * | 2010-10-26 | 2015-04-21 | Michael Lamport Commons | Intelligent control with hierarchical stacked neural networks |
| CN111314889A (en) * | 2020-02-26 | 2020-06-19 | 华南理工大学 | Task unloading and resource allocation method based on mobile edge calculation in Internet of vehicles |
| CN112084025A (en) * | 2020-09-01 | 2020-12-15 | 河海大学 | Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method |
| CN112512056A (en) * | 2020-11-14 | 2021-03-16 | 北京工业大学 | Multi-objective optimization calculation unloading method in mobile edge calculation network |
Non-Patent Citations (2)
| Title |
|---|
| 徐佳等: "移动边缘计算中能耗优化的多重资源计算卸载策略", 《计算机集成制造系统》 * |
| 胡应鑫: "基于多目标粒子群的边缘云资源调度策略", 《电信技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114710785B (en) | 2022-11-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766135B (en) | Task allocation method based on particle swarm optimization and simulated annealing optimization in moving cloud | |
| CN111586762B (en) | Task unloading and resource allocation joint optimization method based on edge cooperation | |
| CN112512056B (en) | Multi-objective optimization calculation unloading method in mobile edge calculation network | |
| CN111586720B (en) | Task unloading and resource allocation combined optimization method in multi-cell scene | |
| CN113904947B (en) | Vehicle-road cooperative distributed edge computing task unloading and resource allocation method and system | |
| CN111010684B (en) | Internet of vehicles resource allocation method based on MEC cache service | |
| CN110798849A (en) | Computing resource allocation and task unloading method for ultra-dense network edge computing | |
| CN110650457B (en) | Joint optimization method for task unloading calculation cost and time delay in Internet of vehicles | |
| CN110233755B (en) | Computing resource and frequency spectrum resource allocation method for fog computing in Internet of things | |
| Yuan et al. | Edge-enabled wbans for efficient qos provisioning healthcare monitoring: A two-stage potential game-based computation offloading strategy | |
| CN109068391A (en) | Car networking communication optimization algorithm based on edge calculations and Actor-Critic algorithm | |
| CN113132943A (en) | Task unloading scheduling and resource allocation method for vehicle-side cooperation in Internet of vehicles | |
| CN113364860B (en) | Method and system for joint calculation resource allocation and unloading decision in MEC | |
| CN115297171B (en) | Edge computing and unloading method and system for hierarchical decision of cellular Internet of vehicles | |
| Ma et al. | Joint allocation on communication and computing resources for fog radio access networks | |
| CN114745383A (en) | Mobile edge calculation assisted multilayer federal learning method | |
| Zheng et al. | Digital twin empowered heterogeneous network selection in vehicular networks with knowledge transfer | |
| Hu et al. | Deep reinforcement learning for task offloading in edge computing assisted power IoT | |
| CN114189521B (en) | Method for collaborative computing offloading in F-RAN architecture | |
| CN114885422A (en) | Dynamic edge computing unloading method based on hybrid access mode in ultra-dense network | |
| CN114710785B (en) | Internet of vehicles cooperative computing resource scheduling design method based on particle swarm algorithm | |
| CN110602718B (en) | Heterogeneous cellular network power distribution method and system based on alternative direction multiplier method | |
| Shaodong et al. | Multi-step reinforcement learning-based offloading for vehicle edge computing | |
| CN111930435A (en) | Task unloading decision method based on PD-BPSO technology | |
| CN116112981A (en) | Unmanned aerial vehicle task unloading method based on edge calculation |
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 |