CN111818168A - Self-adaptive joint calculation unloading and resource allocation method in Internet of vehicles - Google Patents
Self-adaptive joint calculation unloading and resource allocation method in Internet of vehicles Download PDFInfo
- Publication number
- CN111818168A CN111818168A CN202010670745.4A CN202010670745A CN111818168A CN 111818168 A CN111818168 A CN 111818168A CN 202010670745 A CN202010670745 A CN 202010670745A CN 111818168 A CN111818168 A CN 111818168A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- unloading
- mec
- matrix
- vehicles
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 44
- 238000013468 resource allocation Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 56
- 239000002245 particle Substances 0.000 claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000005265 energy consumption Methods 0.000 claims description 25
- 230000005540 biological transmission Effects 0.000 claims description 16
- 230000003044 adaptive effect Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 239000013307 optical fiber Substances 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 230000006855 networking Effects 0.000 abstract description 4
- 239000000835 fiber Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
- H04B17/3912—Simulation models, e.g. distribution of spectral power density or received signal strength indicator [RSSI] for a given geographic region
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
- 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]
Abstract
The invention relates to a self-adaptive joint calculation unloading and resource allocation method in a vehicle networking, and belongs to the field of vehicle networking edge calculation. The method comprises the step of considering the condition of concurrent unloading of a plurality of vehicles under the combination of a local server, an MEC server, a remote cloud server and an idle vehicle multi-computing platform. Comprehensively considering the size of the vehicle task, the maximum tolerance time delay, the computing resource under RSU and the network bandwidth factor, and unloading the computing task of the vehicle to a plurality of computing platforms; automatically adjusting the unloading platform and the unloading proportion of the vehicle calculation task according to the number of tasks under the RSU, and distributing the calculation resources of the MEC when the vehicle obtains the optimal unloading proportion; modeling a calculation unloading decision and resource allocation as a multi-constraint optimization problem; and optimizing unloading decision and resource allocation by using a compressed particle swarm optimization algorithm and providing a particle matrix coding mode. Experimental results show that the method can meet the maximum tolerant time delay and minimize the total cost of the system.
Description
Technical Field
The invention belongs to the field of vehicle networking computing, and relates to a self-adaptive joint computing unloading and resource allocation method in the vehicle networking.
Background
As the number of autonomous vehicles in C-V2X increases, various computationally intensive and delay sensitive applications, such as image-assisted navigation and augmented reality driving, are emerging that require significant computing resources for real-time processing and analysis of large amounts of sensory data, which presents significant challenges to vehicles with limited computing resources.
By offloading the computing tasks to other computing nodes, the problem of limited vehicle computing resources can be effectively solved. The remote cloud server has abundant computing resources, but is far away from the vehicle, which can generate huge transmission delay and energy consumption. The MEC server sinks the calculation to the roadside equipment unit, and is closer to the vehicle, so that the time delay and the energy consumption are lower, however, the computing resource of the MEC server is limited, and if the vehicle is too many in the current RSU, the time delay is increased.
In the existing research, the task unloading of a single vehicle is mostly considered, and the simultaneous unloading of the calculation tasks of a plurality of vehicles is rarely researched; most of them only consider delay and not energy consumption. Offloading decisions also basically only considers offloading to one platform rather than multiple computing platforms, and does not allocate resources while offloading decisions. In fact, most vehicles are unloaded concurrently, it is difficult for the MEC server with limited computing resources to meet the maximum tolerance delay, so that the unloading of multiple computing platforms and the reasonable allocation of resources need to be considered, and it is necessary for the green internet of vehicles to consider energy consumption.
Disclosure of Invention
In view of the above, the present invention provides a method for adaptive joint computation offloading and resource allocation in an internet of vehicles.
In order to achieve the purpose, the invention provides the following technical scheme:
under the scene of concurrent unloading of a plurality of vehicles, according to the bandwidth, the size of tasks, the maximum tolerance time delay and the vehicle transmitting power of the vehicles, constructing a network model, a task model and a calculation model of the vehicles comprises the following steps:
(1) vehicle network model: the channel of the vehicle upload link is a Rayleigh channel model, vehicle viThe data rate of upload/download with the BS isVehicle viThe data rate of uploading/downloading between the idle vehicle and the MEC is
Wherein h is1,h2,B1,B2,Respectively representing the channel gain, channel bandwidth and transmitting power between the vehicle and the BS and between the vehicle and the MEC/idle vehicle; alpha is alpha2Representing the noise power, λ, ω ∈ (0,1) are bandwidth allocation factors。
(2) And (3) task model: vehicle viComputing task S requiring offloadingiIs divisible and definedThe calculation tasks of each vehicle are different, so the parameters are not completely the same. Herein IiDenotes SiThe workload size of (2); g represents the number of CPU cycles required for calculating 1bit data, and unit cycles/bit; f. ofiRepresents the computing power of the vehicle, in cycles/s;denotes SiMaximum tolerated delay of; the computing resource of the MEC is fmecIs assigned to the vehicle viIs a computing resource ofThe computing resource provided by the remote cloud server to the vehicle is fcloudWith free vehicles providing only certain computational resources fidle. The offload decision matrix is: d ═ D1,d2,…,dn]WhereinRespectively represent SiAnd unloading to the local, MEC server, remote cloud server, and idle vehicle.
(3) Local vehicle calculation model: siThe amount of computational tasks performed at the local vehicle isDefining local vehicle execution time delay asThe energy consumption isSince the vehicle calculates only the calculation delay locally, there is no communication delay.
Wherein, PiIndicating a vehicle viThe device power of (1).
(4) MEC calculation model: siThe amount of computational tasks performed at the MEC isDefining the execution delay at MEC as A transmission delay ofThe return delay isFrom vehicle viTotal time delay to offload to MEC isTotal energy consumption of
Wherein, PmecIs the device power of the MEC server,is a vehicle viThe upload power of (1) is an output data amount coefficient, which represents a relationship between an output data amount and an input data amount.
(5) A remote cloud server computing model: offloading to the remote cloud server requires offloading to the BS and then to the remote cloud server by the fiber. Defining an execution latency at a remote cloud server asA transmission delay ofThe calculated result returns to the transmission delay ofCalculating task average transmission waiting time delay t on optical fiber linecloudFrom vehicle viTotal time delay for offloading to the remote cloud server isTotal energy consumption of
Wherein, PcloudDevice Power, P, representing remote cloud ServerBSRepresenting the transmit power of the base station.
(6) Idle vehicle calculation model: the time delay of the unloading to the idle vehicle isA transmission delay ofThe return time of the calculation result isAverage relay time delay between vehicles is twFrom vehicle viTotal time delay for unloading to an idle vehicle isTotal energy consumption of
Wherein, PidleIndicating the device power of the idle vehicle.
Further, the time delay and the energy consumption of all vehicles are weighted to obtain the total system cost, and a constraint optimization problem and a resource allocation model which meet the maximum time delay tolerance and minimize the total system cost are established:
the total time delay T and the total energy consumption E of the combined unloading of the vehicles define the cost of the combined unloading system as H.
H=γ·T+(1-γ)·E
Wherein, gamma is a time delay weight coefficient, and 1-gamma is an energy consumption weight coefficient.
In meeting task SiMaximum tolerated delayAnd under the resource limit, minimizing the total cost of the combined unloading system, and modeling the task unloading and resource allocation of the system as follows:
wherein D is an unloading decision matrix, F is a calculation resource allocation vector of the MEC server and is expressed as
In order to perform resource allocation while making an unloading decision, obtain a task proportion of each vehicle unloaded to each computing platform, and obtain computing resources allocated to the vehicle by the MEC, the particle matrix coding method is provided and comprises the following steps:
the optimized parameters of each vehicle are 5, respectivelyAndif there are n vehicles under the RSU that need to be unloaded, then the encoding matrix M of a particle is an n × 5 matrix. The first 4 columns of the matrix are the offload decision matrix D for the vehicle and the 5 th column of the matrix is the computational resource allocation vector F for the MEC server. The whole particle group is stored by a matrix A, each particle encoding matrix M is firstly converted into a rowAnd stored in the matrix a. The matrix a is a matrix of N rows (N × 5) columns, where N is the particle group size.
In order to solve the integer constraint of the above model, the proposed particle correction algorithm comprises:
taking out each row of the matrix A, reducing the matrix into a particle coding matrix M, taking out each row of the particle coding matrix, and correcting the matrix so that the task of each vehicle meets the requirement
In order to solve the equality and inequality constraints in the task unloading and resource allocation model of the system, the constraint processing method by utilizing the compression particle swarm optimization and combining the penalty function method comprises the following steps:
the penalty function is:
P(q)=θ(q)·qγ(q)
where q is a relative constraint penalty function, θ (q) is a piecewise assignment function, and γ (q) is a penalty index. The fitness function is the target function plus a penalty function:
the invention has the beneficial effects that: the invention comprehensively considers the size of each vehicle task, the maximum tolerant time delay, the computing resource under RSU and the network bandwidth. And the unloading platform and the optimal unloading proportion can be automatically adjusted according to the task number of the current RSU, and the computing resources of the MEC are distributed while the unloading proportion is obtained. Through experimental simulation, the invention is verified to be capable of effectively reducing the total cost of the system.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a system model of the present invention;
FIG. 2 is a flow chart of the solution of the present invention;
FIG. 3 is a schematic diagram of a particle encoding matrix according to the present invention;
FIG. 4 is a flow chart of the particle swarm algorithm improved by the present invention;
FIG. 5 is a graph of total system cost versus calculated task load per vehicle for different algorithms;
FIG. 6 is a graph of total system cost versus number of vehicles under different algorithms;
FIG. 7 is a graph of the total system cost versus the output data volume factor for different algorithms.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not an indication or suggestion that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes, and are not to be construed as limiting the present invention, and the specific meaning of the terms may be understood by those skilled in the art according to specific situations.
The invention provides a self-adaptive joint calculation unloading and resource allocation method in an internet of vehicles, which comprises the following steps:
step 1: as shown in FIG. 1, the calculation task of the unloading vehicle can be calculated locally, and can be unloaded to the idle vehicle V under the current RSUidleThe computing can be unloaded to an RSU equipped with an MEC server, and can also be unloaded to a remote cloud server through a cellular network. FIG. 2 is a flow chart of the solution of the present invention; thus, a network model of the vehicle is constructed as follows:
the method comprises the steps that a plurality of vehicles unload tasks simultaneously, and a set of vehicles which have calculation tasks and need to unload under the coverage of a current RSU is defined as V ═ V1,v2,…,vnEach vehicle has a calculation task to be unloaded, and the corresponding task set is S ═ S1,S2,…,SnThe set of free vehicles is C ═ C1,c2,…,ck}. The channel of the vehicle upload link is a Rayleigh channel model, vehicle viThe data rate of upload/download with the BS isVehicle viThe data rate of uploading/downloading between the idle vehicle and the MEC is
Wherein h is1,h2,B1,B2,Respectively representing the channel gain, channel bandwidth and transmitting power between the vehicle and the BS and between the vehicle and the MEC/idle vehicle; alpha is alpha2Representing the noise power, λ, ω ∈ (0,1) are bandwidth allocation factors.
Step 2: constructing a task model of the vehicle as follows:
vehicle viComputing task S requiring offloadingiIs divisible and definedThe calculation tasks of all vehicles are different, and the parameters are not completely the same. Herein IiDenotes SiThe workload size of (2); g represents the number of CPU cycles required for calculating 1bit data, and unit cycles/bit; f. ofiRepresents the computing power of the vehicle, in cycles/s;denotes SiMaximum tolerated delay of; the computing resource of the MEC is fmecIs assigned to the vehicle viIs a computing resource ofThe computing resource provided by the remote cloud server to the vehicle is fcloudWith free vehicles providing only certain computational resources fidle。
Since tasks can be computed locally, at the MEC server, at the remote cloud server, at the idle vehicle, the tasks need to be divided, andit is determined which platforms to offload to, and how much to offload. Defining an offload decision matrix as: d ═ D1,d2,…,dn]WhereinRespectively represent SiAnd unloading to the local, MEC server, remote cloud server, and idle vehicle.
And step 3: according to the network model and the task model, the calculation models of the four calculation platforms are established as follows:
(1) local vehicle calculation model: siThe amount of computational tasks performed at the local vehicle isDefining local vehicle execution time delay asThe energy consumption isSince the vehicle calculates only the calculation delay locally, there is no communication delay.
Wherein, PiIndicating a vehicle viThe device power of (1).
(2) MEC calculation model: siThe amount of computational tasks performed at the MEC isDefining the execution delay at MEC as A transmission delay ofThe return delay isFrom vehicle viTotal time delay to offload to MEC isThe total energy consumption is e.
Wherein, PmecIs the device power of the MEC server,is a vehicle viThe upload power of (1) is an output data amount coefficient, which represents a relationship between an output data amount and an input data amount.
(3) A remote cloud server computing model: offloading to the remote cloud server requires offloading to the BS and then to the remote cloud server by the fiber. Is defined at the far endExecution time delay of cloud server isA transmission delay ofThe calculated result returns to the transmission delay ofCalculating task average transmission waiting time delay t on optical fiber linecloudFrom vehicle viTotal time delay for offloading to the remote cloud server isTotal energy consumption of
Wherein, PcloudDevice Power, P, representing remote cloud ServerBSRepresenting the transmit power of the base station.
(4) Idle vehicle calculation model: the time delay of the unloading to the idle vehicle isA transmission delay ofThe return time of the calculation result isAverage relay time delay between vehicles is twFrom vehicle viTotal time delay for unloading to an idle vehicle isTotal energy consumption of
Wherein, PidleIndicating the device power of the idle vehicle.
And 4, step 4: through the steps, the time delay and the energy consumption of all vehicles are further weighted to obtain the total system cost, and a constraint optimization problem and a resource allocation model which meet the maximum time delay tolerance and minimize the total system cost are established:
the total time delay T and the total energy consumption E of the combined unloading of the vehicles define the cost of the combined unloading system as H.
H=γ·T+(1-γ)·E
Wherein, gamma is a time delay weight coefficient, and 1-gamma is an energy consumption weight coefficient.
In meeting task SiMaximum tolerated delayAnd under the resource limit, minimizing the total cost of the combined unloading system, and modeling the task unloading and resource allocation of the system as follows:
wherein D is an unloading decision matrix, F is a calculation resource allocation vector of the MEC server and is expressed as
C1 denotes a vehicle viDetermining task SiAdding the task proportions of the idle vehicles into the whole task by the MEC server, the remote cloud server and the local vehicle; c2 indicates that the time to complete each vehicle's mission should not exceed the maximum tolerated delay; c3 represents the maximum number of vehicles that can be unloaded to spare; c4 indicates that the computational resources allocated for each vehicle cannot exceed the total resources of the MEC server; c5 indicates that the total sum of computing resources allocated for vehicle tasks cannot exceed the total resources of the MEC server.
And 5: in order to perform resource allocation while making an unloading decision, obtain a task proportion of each vehicle unloaded to each computing platform, and obtain computing resources allocated to the vehicle by the MEC, a particle matrix coding mode is proposed as follows:
the optimized parameters of each vehicle are 5, respectivelyAndassuming that there are n vehicles under one RSU that need to be task unloaded, the encoding matrix M for one particle is an n × 5 matrix. As shown in fig. 3, the first 4 columns of the matrix are the vehicle offload decision matrix D, and the 5 th column of the matrix is the computing resource allocation vector F of the MEC server. The whole particle swarm is stored by using a matrix A, and each particle encoding matrix M is converted into a row and stored in the matrix A. The matrix a is a matrix of N rows (N × 5) columns, where N is the particle group size.
Step 6: in order to solve the integer constraint in the task unloading and resource allocation model of the system established in step 4, the proposed particle correction algorithm is as follows:
(1) and taking out each row of the matrix A and reducing the matrix A into a particle coding matrix M.
(3) The idealcar largest numbers are selected from the fourth column of M, and the rest are assigned values of 0.
(6) The 2 nd column of the matrix M is added to obtain all the task volumes sum offloaded to the MEC server.
(8) The matrix M is then converted into 1 row and placed in the corresponding row in the matrix a.
Among them, the number of idle vehicles in the ideal.
And 7: in order to solve the equality and inequality constraints in the task unloading and resource allocation model of the system, the constraint is processed by utilizing a compression particle swarm algorithm and combining a penalty function method as follows:
the penalty function is:
P(q)=θ(q)·qγ(q)
where q is a relative constraint penalty function, θ (q) is a piecewise assignment function, and γ (q) is a penalty index. The fitness function is the target function plus a penalty function:
and finally, obtaining an improved particle swarm algorithm flow chart as shown in the figure 4.
As can be seen from fig. 5, as the amount of computing tasks increases, the total system cost of the five algorithms also increases. However, the magnitude of the increase of the algorithm proposed by the present invention is minimal, and the total cost of the system is significantly lower than the other four algorithms. Approximately 22.09% of the total local offload algorithm, 38.66% of the total MEC offload algorithm, 27.8% of the random offload algorithm, and 68.80% of the conventional joint offload algorithm.
As can be seen from fig. 6, the total system cost of the five algorithms all show an upward trend as the number of vehicles increases. Compared with other algorithms, the algorithm provided by the invention has the minimum total system cost. Where all MEC offload algorithms are spiked at a vehicle count of 20, this is higher than the total system cost for local computation, since when the vehicle count exceeds a certain value, the resulting computing resources allocated by the MEC to each vehicle are not yet locally high.
As can be seen from fig. 7, as the amount of output data increases, the total system cost increases for all algorithms except for all local offload algorithms. Since the local computation has no return time delay of the computation result, the total system cost of all local unloading algorithms remains unchanged. And the influence of other algorithms is small because the result return time delay is only realized when the result is unloaded to the MEC, the remote cloud server and the idle vehicle, and the return quantity of the calculation result is relatively small, so that the influence on the system cost is small.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (6)
1. A self-adaptive joint calculation unloading and resource allocation method in the Internet of vehicles is characterized in that: the method comprises the following steps:
s1: under the scene of concurrent unloading of a plurality of vehicles, a vehicle network model, a task model and a calculation model are constructed according to the bandwidth, the size of a task, the maximum tolerance time delay and the vehicle transmitting power of the vehicles;
s2: weighting the time delay and the energy consumption of all vehicles to obtain the total system cost, and establishing a constraint optimization problem and a resource allocation model which meet the maximum time delay tolerance and minimize the total system cost;
s3: providing a particle matrix coding mode on the basis of a compressed particle swarm algorithm serving as a basic algorithm, performing resource allocation while making an unloading decision, obtaining a task proportion of each vehicle unloaded to each computing platform, and obtaining computing resources allocated to the vehicles by an MEC;
s4: the proposed particle correction algorithm utilizes a compressed particle swarm algorithm in combination with a penalty function method to solve the problem of constraint optimization.
2. The method for adaptive joint computation offload and resource allocation in the internet of vehicles according to claim 1, wherein: the method for constructing the network model, the task model and the calculation model of the vehicle comprises the following steps:
s21: vehicle network model: the channel of the vehicle upload link is a Rayleigh channel model, vehicle viThe data rate of uploading/downloading with BS is Ri 1V. vehicleiThe data rate of uploading/downloading between the idle vehicle and the MEC is Ri 2;
Wherein h is1,h2,B1,B2,Respectively representing the channel gain, channel bandwidth and transmitting power between the vehicle and the BS and between the vehicle and the MEC/idle vehicle; alpha is alpha2Representing the noise power, and lambda, omega epsilon (0,1) is a bandwidth allocation factor;
s22: and (3) task model: vehicle viComputing task S requiring offloadingiIs divisible and definedWherein the calculation tasks of all vehicles are different, and the parameters are not completely the same; i isiDenotes SiThe workload size of (2); g represents the number of CPU cycles required for calculating 1bit data, and unit cycles/bit; f. ofiRepresents the computing power of the vehicle, in cycles/s;denotes SiMaximum tolerated delay of; the computing resource of the MEC is fmecIs assigned to the vehicle viIs a computing resource ofThe computing resource provided by the remote cloud server to the vehicle is fcloudWith free vehicles providing only certain computational resources fidle(ii) a The offload decision matrix is: d ═ D1,d2,…,dn]Wherein d isi=[ai 1,ai 2,ai 3,ai 4],ai 1、ai 2、ai 3、ai 4Respectively represent SiThe proportion of the vehicle load to local, MEC server, remote cloud server and idle vehicle; a isi 1,ai 2,ai 3,ai 4∈[0,1],ai 1+ai 2+ai 3+ai 4=1;
S23: local vehicle calculation model: siThe amount of calculation task performed at the local vehicle is ai 1×IiDefining local vehicle execution time delay asThe energy consumption isBecause the vehicle only has calculation time delay in local calculation and no communication time delay;
wherein, PiIndicating a vehicle viThe device power of (1);
s24: MEC calculation model: siThe amount of computational tasks performed at the MEC is ai 2×IiDefining the execution delay at MEC asA transmission delay ofThe return delay isFrom vehicle viTotal time delay to offload to MEC isTotal energy consumption of
Wherein, PmecIs the device power of the MEC server,is a vehicle viThe upload power of (1) is an output data volume coefficient representing a relationship between an output data volume and an input data volume;
s25: a remote cloud server computing model: the unloading to the remote cloud server needs to be carried out to the BS firstly and then to the remote cloud server by the optical fiber; defining an execution latency at a remote cloud server asA transmission delay ofThe calculated result returns to the transmission delay ofCalculating task average transmission waiting time delay t on optical fiber linecloudFrom vehicle viTotal time delay for offloading to the remote cloud server isTotal energy consumption of
Wherein, PcloudDevice Power, P, representing remote cloud ServerBSRepresents the transmit power of the base station;
s26: idle vehicle calculation model: the time delay of the unloading to the idle vehicle isA transmission delay ofThe return time of the calculation result isAverage relay time delay between vehicles is twFrom vehicle viThe total time delay for unloading to an idle vehicle is t and the total energy consumption is
Wherein, PidleIndicating the device power of the idle vehicle.
3. The method of claim 1, wherein the establishing a constrained optimization problem and resource allocation model that minimizes the total system cost and satisfies the maximum delay tolerance comprises:
the total time delay T and the total energy consumption E of the combined unloading of the vehicles define the cost of the combined unloading system as H;
H=γ·T+(1-γ)·E
wherein gamma is a time delay weight coefficient, and (1-gamma) is an energy consumption weight coefficient;
in meeting task SiMaximum tolerated delayAnd under the resource limit, minimizing the total cost of the combined unloading system, and modeling the task unloading and resource allocation of the system as follows:
wherein D is an unloading decision matrix, F is a calculation resource allocation vector of the MEC server and is expressed as
4. The method for adaptive joint computation offload and resource allocation in the internet of vehicles according to claim 1, wherein: the particle matrix encoding method comprises the following steps:
the optimized parameters of each vehicle are 5, and are respectively ai 1,ai 2,ai 3,ai 4Andif n vehicles need to unload tasks under the RSU, the encoding matrix M of one particle is an n multiplied by 5 matrix; the first 4 columns of the matrix are unloading decision matrixes D of the vehicles, and the 5 th column of the matrix is a calculation resource allocation vector F of the MEC server; the whole particle swarm is stored by a matrix A, each particle coding matrix M is firstly converted into a row and stored in the matrix A; the matrix a is a matrix of N rows (N × 5) columns, where N is the particle group size.
5. The method for adaptive joint computation offload and resource allocation in the internet of vehicles according to claim 1, wherein: the proposed particle correction algorithm comprises:
taking out each row of the matrix A, reducing the matrix into a particle coding matrix M, taking out each row of the particle coding matrix, and correcting to enable the task of each vehicle to meet ai 1,ai 2,ai 3,ai 4∈[0,1],ai 1+ai 2+ai 3+ai 4=1。
6. The method for adaptive joint computation offload and resource allocation in the internet of vehicles according to claim 1, wherein: the method for solving the constraint optimization problem by using the compression particle swarm algorithm and combining the penalty function method specifically comprises the following steps:
the penalty function is:
P(q)=θ(q)·qγ(q)
wherein q is a relative constraint penalty function, θ (q) is a piecewise assignment function, and γ (q) is a penalty index; the fitness function is the target function plus a penalty function:
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2020105665558 | 2020-06-19 | ||
CN202010566555 | 2020-06-19 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111818168A true CN111818168A (en) | 2020-10-23 |
CN111818168B CN111818168B (en) | 2022-05-03 |
Family
ID=72841864
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010670745.4A Active CN111818168B (en) | 2020-06-19 | 2020-07-13 | Self-adaptive joint calculation unloading and resource allocation method in Internet of vehicles |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111818168B (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112367640A (en) * | 2020-11-09 | 2021-02-12 | 中科怡海高新技术发展江苏股份公司 | V2V mode multitask unloading method and system based on mobile edge calculation |
CN112492626A (en) * | 2020-12-07 | 2021-03-12 | 南京邮电大学 | Method for unloading computing task of mobile user |
CN112638005A (en) * | 2020-12-29 | 2021-04-09 | 张晓益 | Distributed street lamp control device and system based on Internet of vehicles |
CN112685163A (en) * | 2021-01-06 | 2021-04-20 | 北京信息科技大学 | Computing unloading method based on mobile edge computing and mobile edge computing server |
CN112714178A (en) * | 2020-12-25 | 2021-04-27 | 北京信息科技大学 | Task unloading method and device based on vehicle-mounted edge calculation |
CN112737842A (en) * | 2020-12-29 | 2021-04-30 | 西北工业大学深圳研究院 | Task safety unloading method based on minimized time delay in air-ground integrated Internet of vehicles |
CN112860350A (en) * | 2021-03-15 | 2021-05-28 | 广西师范大学 | Task cache-based computation unloading method in edge computation |
CN112888021A (en) * | 2021-01-29 | 2021-06-01 | 重庆邮电大学 | Task unloading method for avoiding interruption in Internet of vehicles |
CN112929850A (en) * | 2021-02-02 | 2021-06-08 | 天津理工大学 | Internet of vehicles data returning method facing edge computing environment |
CN112969163A (en) * | 2021-02-22 | 2021-06-15 | 安徽大学 | Cellular network computing resource allocation method based on self-adaptive task unloading |
CN112995289A (en) * | 2021-02-04 | 2021-06-18 | 天津理工大学 | Internet of vehicles multi-target computing task unloading scheduling method based on non-dominated sorting genetic strategy |
CN113051003A (en) * | 2021-03-22 | 2021-06-29 | 中国科学院上海微系统与信息技术研究所 | Method, system and storage medium for processing calculation task unloading of satellite communication network |
CN113179296A (en) * | 2021-04-08 | 2021-07-27 | 中国科学院计算技术研究所 | Task unloading method for vehicle-mounted edge computing system |
CN113364860A (en) * | 2021-06-03 | 2021-09-07 | 吉林大学 | Method and system for joint calculation resource allocation and unloading decision in MEC |
CN113535397A (en) * | 2021-07-14 | 2021-10-22 | 南通大学 | Resource allocation method for intelligent vehicle edge computing network |
CN113676519A (en) * | 2021-07-28 | 2021-11-19 | 北京信息科技大学 | Joint optimization method and device for vehicle content pre-caching and broadband distribution |
CN113709694A (en) * | 2021-07-28 | 2021-11-26 | 南京邮电大学 | Calculation task unloading method for edge Internet of vehicles system |
CN113783959A (en) * | 2021-09-13 | 2021-12-10 | 吉林大学 | Internet of vehicles joint optimization calculation task unloading rate and resource allocation method |
CN114189521A (en) * | 2021-12-15 | 2022-03-15 | 福州大学 | Method for cooperative computing offload in F-RAN architecture |
CN114637608A (en) * | 2022-05-17 | 2022-06-17 | 之江实验室 | Calculation task allocation and updating method, terminal and network equipment |
CN114928611A (en) * | 2022-05-16 | 2022-08-19 | 重庆邮电大学 | Internet of vehicles energy-saving calculation unloading optimization method based on IEEE802.11p protocol |
CN114928612A (en) * | 2022-06-01 | 2022-08-19 | 重庆邮电大学 | Excitation mechanism and resource allocation method for cooperative unloading in mobile edge computing |
CN115373856A (en) * | 2022-10-21 | 2022-11-22 | 南京理工大学 | Unloading task allocation method for intelligent vehicle in end edge cloud network framework |
CN115412607A (en) * | 2022-09-15 | 2022-11-29 | 桂林理工大学 | Task unloading method based on roadside parking cooperative edge calculation |
WO2023236391A1 (en) * | 2022-06-08 | 2023-12-14 | 厦门雅迅网络股份有限公司 | In-vehicle computing task unloading method and system |
CN117499999A (en) * | 2023-12-29 | 2024-02-02 | 四川华鲲振宇智能科技有限责任公司 | Task unloading method based on edge calculation |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013123445A1 (en) * | 2012-02-17 | 2013-08-22 | Interdigital Patent Holdings, Inc. | Smart internet of things services |
WO2016057885A1 (en) * | 2014-10-10 | 2016-04-14 | DimensionalMechanics, Inc. | System and methods for generating interactive virtual environments |
CN109814951A (en) * | 2019-01-22 | 2019-05-28 | 南京邮电大学 | The combined optimization method of task unloading and resource allocation in mobile edge calculations network |
CN110035410A (en) * | 2019-03-07 | 2019-07-19 | 中南大学 | Federated resource distribution and the method and system of unloading are calculated in a kind of vehicle-mounted edge network of software definition |
CN110856259A (en) * | 2019-11-12 | 2020-02-28 | 郑州轻工业学院 | Resource allocation and offloading method for adaptive data block size in mobile edge computing environment |
CN111124531A (en) * | 2019-11-25 | 2020-05-08 | 哈尔滨工业大学 | Dynamic unloading method for calculation tasks based on energy consumption and delay balance in vehicle fog calculation |
-
2020
- 2020-07-13 CN CN202010670745.4A patent/CN111818168B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013123445A1 (en) * | 2012-02-17 | 2013-08-22 | Interdigital Patent Holdings, Inc. | Smart internet of things services |
WO2016057885A1 (en) * | 2014-10-10 | 2016-04-14 | DimensionalMechanics, Inc. | System and methods for generating interactive virtual environments |
CN109814951A (en) * | 2019-01-22 | 2019-05-28 | 南京邮电大学 | The combined optimization method of task unloading and resource allocation in mobile edge calculations network |
CN110035410A (en) * | 2019-03-07 | 2019-07-19 | 中南大学 | Federated resource distribution and the method and system of unloading are calculated in a kind of vehicle-mounted edge network of software definition |
CN110856259A (en) * | 2019-11-12 | 2020-02-28 | 郑州轻工业学院 | Resource allocation and offloading method for adaptive data block size in mobile edge computing environment |
CN111124531A (en) * | 2019-11-25 | 2020-05-08 | 哈尔滨工业大学 | Dynamic unloading method for calculation tasks based on energy consumption and delay balance in vehicle fog calculation |
Non-Patent Citations (3)
Title |
---|
CHUNHUI LIU等: ""Adaptive Offloading for Time-Critical Tasks in Heterogeneous Internet of Vehicles"", 《IEEE INTERNET OF THINGS JOURNAL》 * |
栾秋季: ""车联网系统中基于MEC的任务卸载优化研究"", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
秦笙: ""面向车载自组织网络中紧急消息传输机制研究"", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
Cited By (43)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112367640A (en) * | 2020-11-09 | 2021-02-12 | 中科怡海高新技术发展江苏股份公司 | V2V mode multitask unloading method and system based on mobile edge calculation |
CN112367640B (en) * | 2020-11-09 | 2022-10-28 | 中科怡海高新技术发展江苏股份公司 | V2V mode multi-task unloading method and system based on mobile edge calculation |
CN112492626B (en) * | 2020-12-07 | 2022-04-12 | 南京邮电大学 | Method for unloading computing task of mobile user |
CN112492626A (en) * | 2020-12-07 | 2021-03-12 | 南京邮电大学 | Method for unloading computing task of mobile user |
CN112714178A (en) * | 2020-12-25 | 2021-04-27 | 北京信息科技大学 | Task unloading method and device based on vehicle-mounted edge calculation |
CN112714178B (en) * | 2020-12-25 | 2023-05-12 | 北京信息科技大学 | Task unloading method and device based on vehicle-mounted edge calculation |
CN112638005B (en) * | 2020-12-29 | 2023-11-03 | 张晓益 | Distributed street lamp control device and system based on Internet of vehicles |
CN112737842A (en) * | 2020-12-29 | 2021-04-30 | 西北工业大学深圳研究院 | Task safety unloading method based on minimized time delay in air-ground integrated Internet of vehicles |
CN112737842B (en) * | 2020-12-29 | 2022-12-09 | 西北工业大学深圳研究院 | Task safety unloading method based on minimized time delay in air-ground integrated Internet of vehicles |
CN112638005A (en) * | 2020-12-29 | 2021-04-09 | 张晓益 | Distributed street lamp control device and system based on Internet of vehicles |
CN112685163B (en) * | 2021-01-06 | 2023-05-02 | 北京信息科技大学 | Calculation unloading method based on mobile edge calculation and mobile edge calculation server |
CN112685163A (en) * | 2021-01-06 | 2021-04-20 | 北京信息科技大学 | Computing unloading method based on mobile edge computing and mobile edge computing server |
CN112888021A (en) * | 2021-01-29 | 2021-06-01 | 重庆邮电大学 | Task unloading method for avoiding interruption in Internet of vehicles |
CN112888021B (en) * | 2021-01-29 | 2022-08-23 | 重庆邮电大学 | Task unloading method for avoiding interruption in Internet of vehicles |
CN112929850A (en) * | 2021-02-02 | 2021-06-08 | 天津理工大学 | Internet of vehicles data returning method facing edge computing environment |
CN112995289B (en) * | 2021-02-04 | 2022-05-17 | 天津理工大学 | Internet of vehicles multi-target computing task unloading scheduling method based on non-dominated sorting genetic strategy |
CN112995289A (en) * | 2021-02-04 | 2021-06-18 | 天津理工大学 | Internet of vehicles multi-target computing task unloading scheduling method based on non-dominated sorting genetic strategy |
CN112969163A (en) * | 2021-02-22 | 2021-06-15 | 安徽大学 | Cellular network computing resource allocation method based on self-adaptive task unloading |
CN112969163B (en) * | 2021-02-22 | 2022-06-21 | 安徽大学 | Cellular network computing resource allocation method based on self-adaptive task unloading |
CN112860350A (en) * | 2021-03-15 | 2021-05-28 | 广西师范大学 | Task cache-based computation unloading method in edge computation |
CN112860350B (en) * | 2021-03-15 | 2022-06-03 | 广西师范大学 | Task cache-based computation unloading method in edge computation |
CN113051003A (en) * | 2021-03-22 | 2021-06-29 | 中国科学院上海微系统与信息技术研究所 | Method, system and storage medium for processing calculation task unloading of satellite communication network |
CN113179296A (en) * | 2021-04-08 | 2021-07-27 | 中国科学院计算技术研究所 | Task unloading method for vehicle-mounted edge computing system |
CN113364860A (en) * | 2021-06-03 | 2021-09-07 | 吉林大学 | Method and system for joint calculation resource allocation and unloading decision in MEC |
CN113535397A (en) * | 2021-07-14 | 2021-10-22 | 南通大学 | Resource allocation method for intelligent vehicle edge computing network |
CN113676519B (en) * | 2021-07-28 | 2023-06-06 | 北京信息科技大学 | Combined optimization method and device for vehicle content pre-caching and broadband distribution |
CN113676519A (en) * | 2021-07-28 | 2021-11-19 | 北京信息科技大学 | Joint optimization method and device for vehicle content pre-caching and broadband distribution |
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 |
CN113783959B (en) * | 2021-09-13 | 2022-06-03 | 吉林大学 | Internet of vehicles joint optimization calculation task unloading rate and resource allocation method |
CN113783959A (en) * | 2021-09-13 | 2021-12-10 | 吉林大学 | Internet of vehicles joint optimization calculation task unloading rate and resource allocation method |
CN114189521B (en) * | 2021-12-15 | 2024-01-26 | 福州大学 | Method for collaborative computing offloading in F-RAN architecture |
CN114189521A (en) * | 2021-12-15 | 2022-03-15 | 福州大学 | Method for cooperative computing offload in F-RAN architecture |
CN114928611A (en) * | 2022-05-16 | 2022-08-19 | 重庆邮电大学 | Internet of vehicles energy-saving calculation unloading optimization method based on IEEE802.11p protocol |
CN114928611B (en) * | 2022-05-16 | 2023-07-25 | 重庆邮电大学 | IEEE802.11p protocol-based energy-saving calculation unloading optimization method for Internet of vehicles |
CN114637608A (en) * | 2022-05-17 | 2022-06-17 | 之江实验室 | Calculation task allocation and updating method, terminal and network equipment |
CN114928612A (en) * | 2022-06-01 | 2022-08-19 | 重庆邮电大学 | Excitation mechanism and resource allocation method for cooperative unloading in mobile edge computing |
CN114928612B (en) * | 2022-06-01 | 2024-04-12 | 南京浮点智算数字科技有限公司 | Excitation mechanism and resource allocation method for collaborative offloading in mobile edge computing |
WO2023236391A1 (en) * | 2022-06-08 | 2023-12-14 | 厦门雅迅网络股份有限公司 | In-vehicle computing task unloading method and system |
CN115412607A (en) * | 2022-09-15 | 2022-11-29 | 桂林理工大学 | Task unloading method based on roadside parking cooperative edge calculation |
CN115373856A (en) * | 2022-10-21 | 2022-11-22 | 南京理工大学 | Unloading task allocation method for intelligent vehicle in end edge cloud network framework |
CN117499999A (en) * | 2023-12-29 | 2024-02-02 | 四川华鲲振宇智能科技有限责任公司 | Task unloading method based on edge calculation |
CN117499999B (en) * | 2023-12-29 | 2024-04-12 | 四川华鲲振宇智能科技有限责任公司 | Task unloading method based on edge calculation |
Also Published As
Publication number | Publication date |
---|---|
CN111818168B (en) | 2022-05-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111818168B (en) | Self-adaptive joint calculation unloading and resource allocation method in Internet of vehicles | |
CN111918311B (en) | Vehicle networking task unloading and resource allocation method based on 5G mobile edge computing | |
CN107766135B (en) | Task allocation method based on particle swarm optimization and simulated annealing optimization in moving cloud | |
CN111586696B (en) | Resource allocation and unloading decision method based on multi-agent architecture reinforcement learning | |
CN109656703B (en) | Method for assisting vehicle task unloading through mobile edge calculation | |
CN111930436A (en) | Random task queuing and unloading optimization method based on edge calculation | |
CN112512056A (en) | Multi-objective optimization calculation unloading method in mobile edge calculation network | |
CN111694655A (en) | Multitask-oriented edge computing resource allocation method | |
CN111401744B (en) | Dynamic task unloading method in uncertainty environment in mobile edge calculation | |
CN111262944B (en) | Method and system for hierarchical task offloading in heterogeneous mobile edge computing network | |
CN109947574A (en) | A kind of vehicle big data calculating discharging method based on mist network | |
CN110928691A (en) | Traffic data-oriented edge collaborative computing unloading method | |
CN111010684A (en) | Internet of vehicles resource allocation method based on MEC cache service | |
CN112860429B (en) | Cost-effective optimization system and method for task offloading in mobile edge computing system | |
CN113286329B (en) | Communication and computing resource joint optimization method based on mobile edge computing | |
CN113873660A (en) | Unmanned aerial vehicle-assisted optimal computation unloading decision and resource allocation method for service cache edge computation | |
CN110809291B (en) | Double-layer load balancing method of mobile edge computing system based on energy acquisition equipment | |
CN112118312A (en) | Network burst load evacuation method facing edge server | |
CN113364860B (en) | Method and system for joint calculation resource allocation and unloading decision in MEC | |
CN111711962A (en) | Cooperative scheduling method for subtasks of mobile edge computing system | |
CN113992678A (en) | Calculation migration method for offshore MEC load balancing and resource allocation joint optimization | |
CN115629873A (en) | System and method for controlling unloading of vehicle-road cloud cooperative tasks and stability of task queue | |
CN113573363A (en) | MEC calculation unloading and resource allocation method based on deep reinforcement learning | |
CN110996390A (en) | Wireless access network computing resource allocation method and network system | |
CN111526526B (en) | Task unloading method in mobile edge calculation based on service mashup |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240122 Address after: No. 10-20, Building 4, No. 170 Keyuan Fourth Road, Jiulongpo District, Chongqing, 400041 Patentee after: Chongqing Mouyi Technology Co.,Ltd. Country or region after: China Address before: 400065 Chongqing Nan'an District huangjuezhen pass Chongwen Road No. 2 Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS Country or region before: China |