Edge computing low-energy consumption task offloading method and system based on cellular vehicle network

By dividing tasks into sub-task blocks in the Internet of Vehicles and using improved simulated annealing algorithms to optimize the energy consumption distribution between the vehicle and the edge server, the driving vehicle and the stationary vehicle, the problem of high energy consumption in the Internet of Vehicles is solved. The goal of rational use of resources and energy conservation has been achieved, and the goal of green transportation has been achieved.

CN114980206BActive Publication Date: 2024-11-05SHANDONG ACAD OF SCI INST OF AUTOMATION
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202210493359.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-07
Publication Date
2024-11-05
Estimated Expiration
2042-05-07

Smart Images

  • Figure CN114980206B_ABST
    Figure CN114980206B_ABST
Patent Text Reader

Abstract

The present invention belongs to the field of intelligent network edge computing and green transportation, and provides a low-energy consumption task unloading method and system for edge computing based on cellular vehicle network, including dividing the tasks generated by the vehicle and needing to be processed into a plurality of unrelated subtask blocks; determining which server processes each subtask block according to the initial position of the vehicle when generating the task, the vehicle's driving speed, the computing power of the vehicle's own server, and the computing power of the edge server and other vehicle servers; the present invention uses an improved simulated annealing algorithm to obtain the optimal unloading power and the optimal task allocation ratio according to factors such as the vehicle's driving speed, the position when the demand is generated, the network access time, the task volume, the bandwidth, the number and computing power of the server of the vehicle and other surrounding vehicles, and the computing power of the edge server in the roadside unit, thereby reducing the energy consumption consumed by unloading the vehicle and processing tasks, and realizing reasonable resource allocation and effective energy conservation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of intelligent connected edge computing and green transportation technology, and specifically relates to an edge computing low-energy consumption task offloading method and system based on cellular vehicle network. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the widespread application of intelligent transportation systems and the rapid development of Internet of Vehicles technology, a large number of computing-intensive tasks are emerging, such as real-time monitoring, high-definition maps, and in-vehicle games. However, the computing power of the vehicle itself is limited, and the cloud server is far away from the vehicle. During the transmission of computing tasks, the vehicle has high latency and high energy consumption due to the poor communication environment. Therefore, the Mobile Edge Computing (MEC) technology is introduced into the Internet of Vehicles to sink the cloud server from the core of the network to the edge of the network, focusing on solving the timeliness, reliability, and cost issues of task offloading and processing. MEC servers are installed near the roadside unit (RSU) to make full use of the rich computing resources to process tasks, thereby reducing the computing pressure and energy consumption of the vehicle itself.

[0004] In recent years, energy conservation and consumption reduction has always been a top priority for the development of various fields in the country. The global energy crisis is just around the corner, and the situation facing energy consumption issues is very severe. The energy consumption issue in the Internet of Vehicles cannot be ignored. First, under limited energy conditions, low-energy unloading decisions can handle more tasks; second, low-energy unloading decisions reduce energy costs while reducing energy consumption; third, under the national policy of environmental protection first, energy conservation and consumption reduction and pollution reduction have become the common goals of the Chinese people. Therefore, the present invention focuses on the unloading method of reducing energy consumption.

[0005] In current research, cost minimization is mostly a joint consideration of latency and energy consumption, or focuses on minimizing the energy consumption of the total task. There is a lack of research from the user's perspective to minimize the energy consumption of the vehicle itself. At the same time, in current research on task offloading in the Internet of Vehicles, the allocation of computing resources considered is mostly offloading to vehicles in motion or to vehicles parked on the roadside. There is a lack of an allocation method that offloads tasks to both vehicles in motion and vehicles parked on the roadside. Therefore, the solutions to task offloading and resource management problems still need to be improved. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a low-energy task offloading method and system for edge computing based on cellular vehicle network. The present invention aims to reduce the energy consumption overhead of the vehicle's own task processing and reasonably allocate computing resources, so as to achieve the purpose of rational utilization of computing resources and effective reduction of unloading energy consumption, thereby achieving the goal of green transportation.

[0007] According to some embodiments, a first solution of the present invention provides an edge computing low-energy consumption task offloading method based on cellular vehicle networking, which adopts the following technical solutions:

[0008] The low-energy consumption task offloading method of edge computing based on cellular vehicle networking includes:

[0009] Divide the tasks that need to be processed by the vehicle into several unrelated subtask blocks;

[0010] Determine the transmission distance and transmission rate between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server based on the vehicle's initial position when the task is generated, the vehicle's driving speed, the vehicle's own server computing power, and the edge server and other vehicle servers' computing power;

[0011] Determine the transmission energy consumption between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server according to the transmission rates between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server;

[0012] According to the computing power of the vehicle's own server, determine the local computing energy consumption of the vehicle to process the vehicle subtask block;

[0013] Taking the minimum sum of local computing energy consumption and each server's transmission energy consumption as the goal, the total energy consumption determination objective function of the vehicle is constructed;

[0014] An improved simulated annealing algorithm is obtained by adding a random factor to the update of each iterative independent variable. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio when the total energy consumption of the vehicle is the lowest are obtained.

[0015] Further, the determining of the transmission distance and transmission rate between the vehicle and the edge server, the moving vehicle server and the stationary vehicle server includes:

[0016] Determine the transmission distance and transmission rate between the vehicle and the edge server based on the initial position of the vehicle when the task is generated, the driving speed of the vehicle, and the diameter of the edge server coverage area;

[0017] Determine the transmission distance and transmission rate between the vehicle and the driving vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle and the driving speed of the driving vehicle;

[0018] The transmission distance and transmission rate between the vehicle and the stopped vehicle server are determined according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the diameter of the coverage range of the stopped vehicle server and the position of the stopped vehicle.

[0019] Further, the determining of the transmission energy consumption between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server includes:

[0020] Determine the transmission delay of the subtask offloading to the edge server according to the transmission rate between the vehicle and the edge server, and further determine the transmission energy consumption between the vehicle and the edge server;

[0021] Determine the transmission delay of the subtask offloading to the traveling vehicle server according to the transmission rate between the vehicle and the traveling vehicle server, and further determine the transmission energy consumption between the vehicle and the traveling vehicle server;

[0022] The transmission delay of offloading the subtask to the stationary vehicle server is determined according to the transmission rate between the vehicle and the stopped vehicle server, and the transmission energy consumption between the vehicle and the stationary vehicle server is further determined.

[0023] Furthermore, the determination of the local computing energy consumption of the vehicle for processing the vehicle subtask block is specifically as follows:

[0024] During the entire process of task processing, in addition to offloading to other servers, some subtasks are calculated locally by the vehicle. The local computing energy consumption is determined based on the local processing task volume, the energy coefficient of the vehicle's server, the rotation speed of the vehicle's server, and the task computing density.

[0025] Furthermore, the total energy consumption of the vehicle is determined by the objective function:

[0026] minE S =E V2I +E V2V(M) +E V2V(p) +E0

[0027] Among them, the total energy consumed by processing tasks is E S , E V2I represents the transmission energy consumption between the vehicle and the edge server, E V2V(M) represents the transmission energy consumption between the vehicle and the moving vehicle server, E V2V(p) It represents the transmission energy consumption between the vehicle and the stationary vehicle server, and E0 represents the local computing energy consumption of the vehicle for processing the vehicle subtask block.

[0028] Furthermore, the constraints of the objective function for determining the total energy consumption of the vehicle include:

[0029] The sum of the rotation speeds of all subtasks is equal to the total rotation speed of the total task of this vehicle; the sum of the bandwidths allocated by all servers does not exceed the total bandwidth, that is, the maximum bandwidth; the time of the entire process is the maximum value of the four times: the total processing time of unloading subtasks to the edge server, the total processing time of unloading subtasks to the moving vehicle server, the total processing time of unloading subtasks to the stationary vehicle server, and the local calculation time; the total processing time of unloading subtasks to the moving vehicle server is the maximum value of the sum of transmission and calculation time among N moving vehicles; the total processing time of unloading subtasks to the edge server is the sum of transmission and calculation time; the total processing time of unloading subtasks to the stationary vehicle server is the maximum value of the sum of transmission and calculation time among M stationary vehicles; the sum of all transmission powers does not exceed the total transmission power; there are a total of N moving vehicle servers n other than this vehicle; there are a total of M roadside stationary vehicle servers m.

[0030] Furthermore, the improved independent variable updating simulated annealing algorithm is used to solve the objective function of determining the total energy consumption of the vehicle, and the optimal subtask unloading power and the optimal subtask allocation ratio when the total energy consumption of the vehicle is the lowest are obtained, including:

[0031] Step 1: Set the initial temperature for starting annealing according to the energy coefficient, rotation speed and task calculation density of the vehicle server, that is, the initial objective function value T = T0;

[0032] Step 2: Randomly generate an initial solution as the initial position of the iteration, substitute the initial solution into the total energy consumption of the vehicle to determine the objective function, and calculate the corresponding objective function value;

[0033] Step 3: Set the number of loop iterations;

[0034] Step 4: Use the improved independent variable update function to obtain a new solution from the initial solution:

[0035] x j+1 =θ·x j +(1-θ)Δx(j=1, 2, ...J)

[0036] Among them, x j+1 is the solution at the j+1th iteration, θ is a random factor selected from 0 to 1, and The j-th solution x j Substitute the above formula to calculate the next iterative solution x j+1 ;

[0037] Step 5: Substitute the initial solution x0 into the above formula to calculate the new solution x1, and calculate the corresponding objective function value E(x1);

[0038] Step 6: Determine whether to accept the independent variable that increases the value of the objective function:

[0039] If E(x1)≤E(x0), then assign x1 to x0, that is, x0=x1; if not, then The probability of accepting a new solution is is the probability, which is obviously less than 1, k is a positive physical constant; T is the temperature during the annealing process, that is, the value of the objective function, which is a positive number, so ΔE is negative, ΔE = -|E(x1)-E(x0)|;

[0040] Step 7: The number of iterations increases continuously, and steps 4 to 6 are repeated once for each iteration. At temperature T, it is determined whether the termination condition is met. If so, the iteration is stopped. At this time, x0 is the global optimal solution, where the independent variable x is the transmission power and the task allocation ratio, and the dependent variable E(x) is the energy consumption.

[0041] According to some embodiments, a second solution of the present invention provides an edge computing low-energy consumption task offloading system based on cellular vehicle networking, which adopts the following technical solutions:

[0042] The edge computing low-energy task offloading system based on cellular vehicle networking includes:

[0043] The task block module is configured to divide the task generated by the vehicle and needing to be processed into a number of unrelated sub-task blocks;

[0044] The transmission distance and transmission rate determination module is configured to determine the transmission distance and transmission rate between the vehicle and the edge server, the moving vehicle server and the stationary vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the computing capacity of the vehicle's own server, and the computing capacity of the edge server and other vehicle servers;

[0045] a transmission energy consumption determination module, configured to determine the transmission energy consumption between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server according to the transmission rates between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server;

[0046] A local computing energy consumption determination module is configured to determine the local computing energy consumption of the vehicle for processing the vehicle subtask block according to the computing capacity of the vehicle's own server;

[0047] The objective function determination module is configured to construct an objective function for determining the total energy consumption of the vehicle by taking the sum of the local computing energy consumption and the transmission energy consumption of each server as the minimum;

[0048] The objective function solving module is configured to obtain an improved simulated annealing algorithm by adding a random factor to the update of each iterative independent variable on the basis of the traditional simulated annealing algorithm. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio are obtained when the total energy consumption of the vehicle is the lowest.

[0049] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0050] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the edge computing low-energy task offloading method based on cellular vehicle network as described in the first aspect above.

[0051] According to some embodiments, a fourth aspect of the present invention provides a computer device.

[0052] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for offloading low-energy tasks in edge computing based on cellular vehicle network as described in the first aspect above are implemented.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The present invention selects a public road section with multiple vehicles in a single cell. When a vehicle is driving, it generates a task unloading demand. In addition to the calculation by the vehicle itself, it is sent to the servers of surrounding vehicles traveling in the same direction, the servers of vehicles parked on the roadside, and the edge servers of the roadside units for processing. According to factors such as the vehicle's driving speed, the location when the demand is generated, the network access time, the task volume, the bandwidth, the number and computing power of the servers of the vehicle and other surrounding vehicles, and the computing power of the edge servers in the roadside units, the improved simulated annealing algorithm is used to obtain the optimal unloading power and the optimal task allocation ratio, thereby reducing the energy consumption of the vehicle unloading and processing tasks, and realizing reasonable resource allocation and effective energy conservation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0056] Figure 1 It is a flow chart of a low-energy consumption task offloading method for edge computing based on cellular vehicle networking according to an embodiment of the present invention;

[0057] Figure 2 is a model diagram of the cellular vehicle network described in an embodiment of the present invention;

[0058] In the figure:

[0059] MEC-edge server; RSU-roadside unit; L1-edge server coverage diameter; L2-roadside stationary vehicle server coverage; D1-the distance from the vehicle to the roadside unit perpendicular to the road; D2-the distance from the vehicle to the roadside parked vehicle perpendicular to the road; H-roadside unit height; a-the initial position of the vehicle relative to the edge server when the unloading request is issued; b-the initial position of the vehicle relative to the roadside stationary vehicle when the unloading request is issued; d V2I -The distance between the vehicle and the edge server; d V2V(M) - The distance between the vehicle and the moving vehicle server; d V2V(p) -The distance between the vehicle and the roadside stationary vehicle server; v-the vehicle's speed. DETAILED DESCRIPTION

[0060] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0061] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0062] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0063] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0064] Embodiment 1

[0065] like Figure 1As shown, this embodiment provides a low-energy task offloading method for edge computing based on cellular vehicle networking. This embodiment uses the method applied to a server as an example. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communications, middleware services, domain name services, security services CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application is not limited here.

[0066] In this embodiment, the method includes the following steps:

[0067] Divide the tasks that need to be processed by the vehicle into several unrelated subtask blocks;

[0068] Calculate the transmission distance and transmission rate between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server respectively;

[0069] Calculate the transmission energy consumption between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server respectively;

[0070] Calculate the local computing energy consumption of the vehicle to process the vehicle subtask block;

[0071] Taking the minimum sum of local computing energy consumption and each server's transmission energy consumption as the goal, the total energy consumption determination objective function of the vehicle is constructed;

[0072] Based on the traditional simulated annealing algorithm, a random factor is added to the update of the independent variable in each iteration to obtain an improved simulated annealing algorithm. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio when the total energy consumption of the vehicle is the lowest are obtained.

[0073] The tasks generated by vehicle i that need to be processed are divided into blocks. The total task volume is S, and the tasks are divided into several independent small blocks, which are subtask blocks. The server that processes each subtask block is determined based on the initial position of the vehicle when it generates the task, the vehicle's driving speed, the computing power of the vehicle's own server, and the computing power of the edge server and other vehicle servers. nThe proportion of tasks that are offloaded to the nth vehicle server traveling in the same direction as the vehicle in the vehicle-to-vehicle (V2V) communication mode to the total task volume, is the total amount of tasks unloaded to N vehicles traveling in the same direction by V2V communication; m The proportion of tasks that are unloaded to the mth vehicle server stopped on the roadside by V2V communication to the total tasks, is the total amount of tasks unloaded to M roadside vehicles by V2V communication; β is the proportion of tasks that some subtasks are unloaded to the edge server by Vehicle-To-Infrastructure (V2I) communication to the total amount of tasks, and βS is the total amount of tasks that some subtasks are unloaded by V2I communication. To handle the workload locally.

[0074] Vehicle i offloads tasks to the edge server and other N vehicles traveling in the same direction and M vehicles parked on the roadside. The optimal offloading power and optimal task splitting ratio are allocated to vehicle i by the edge server and the other N vehicles traveling and M vehicles parked. Finally, the energy consumed by the vehicle to complete the total task is calculated. S .

[0075] Specifically, Figure 1 , Figure 2 As shown, this embodiment provides a low-energy consumption task offloading method for edge computing based on cellular vehicle networking, and the main implementation steps are as follows:

[0076] Step 1: Calculate the transmission distance and transmission rate

[0077] (1) Calculate the transmission efficiency between edge servers and vehicles:

[0078] like Figure 2 As shown in the figure, the spectrum resources used by the two communication modes of V2V and V2I are in different frequency bands and do not interfere with each other. First, the distance d between the edge server and vehicle i is calculated by the following formula: V2I :

[0079]

[0080] Where D1 is the distance from the vehicle to the roadside unit perpendicular to the road; H is the height of the roadside unit; L1 is the diameter of the edge server coverage; a is the initial position of vehicle i relative to the edge server when the unloading request is issued; v is the driving speed of vehicle i, assuming that vehicle i is driving at a constant speed on this section of road; t V2I is the upload delay of vehicle i sending part of the subtask to the edge server.

[0081] Secondly, calculate the uplink transmission rate R of vehicle i sending part of the subtask to the edge server V2I :

[0082]

[0083] Among them, B V2I Allocate bandwidth to edge servers; V2I is the unloading power sent to the edge server; h is the Rayleigh channel coefficient of the complex Gaussian distribution; γ is the path loss exponent, which is a constant and usually ranges from 2.5 to 4; N0 is the noise power spectral density at the edge server receiving end, and v is the vehicle speed.

[0084] Calculate the transmission efficiency between vehicles traveling in the same direction:

[0085] First, the distance d between vehicle i and other vehicles n traveling in the same direction n This is d in the system model diagram. V2V(M) , assuming that vehicle i and vehicle n traveling in the same direction are both traveling at a constant speed and have the same speed v, so d n is a constant and has a fixed value.

[0086] Secondly, calculate the uplink transmission rate R of vehicle i sending multiple subtasks to the moving vehicle server V2V(M) :

[0087]

[0088] Among them, B n Allocate bandwidth to the vehicle n server; p n is the unloading power; h is the Rayleigh channel coefficient of the complex Gaussian distribution; γ is the path loss exponent, which is a constant and usually ranges from 2.5 to 4; N0 is the noise power spectral density at the receiving end of the vehicle server.

[0089] Calculate the transmission efficiency between the vehicle and the roadside stopped vehicle:

[0090] First, calculate the distance between vehicle i and the roadside stopped vehicle, which is d in the system model diagram. V2V(p) :

[0091]

[0092] Where D2 is the distance perpendicular to the road from the vehicle to the roadside vehicle; L2 is the diameter of the roadside vehicle server coverage; b is the initial position of vehicle i relative to the roadside vehicle when the unloading request is issued; v is the speed of vehicle i, assuming that vehicle i is traveling at a constant speed on this section of road; t V2V(p) is the upload delay of vehicle i sending part of the subtask to the roadside stop vehicle server.

[0093] Secondly, calculate the uplink transmission rate R of vehicle i sending multiple subtasks to the stopped vehicle server V2V(p) :

[0094]

[0095] Among them, B m Allocate bandwidth to the vehicle m server; p m is the unloading power; h is the Rayleigh channel coefficient of the complex Gaussian distribution; γ is the path loss exponent, which is a constant and usually ranges from 2.5 to 4; N0 is the noise power spectral density at the receiving end of the vehicle server.

[0096] Step 2: Calculate transmission energy consumption

[0097] Vehicle i offloads part of its subtasks to the edge server, N moving vehicle servers, and M stationary vehicle servers. The corresponding transmission energy consumption is calculated below.

[0098] First, calculate the transmission energy consumption caused by vehicle i offloading part of the subtask to the edge server:

[0099] E V2I =p V2I t V2I (6)

[0100] Among them, t V2I The transmission delay of the subtask to the edge server is offloaded. V2I The expression is:

[0101]

[0102] Secondly, calculate the total transmission energy consumption E generated by vehicle i offloading multiple subtasks to N vehicle servers traveling in the same direction V2V(M) :

[0103]

[0104] Among them, t n is the transmission delay of the subtask offloading to the nth vehicle server. n The expression is:

[0105]

[0106] Next, calculate the total transmission energy consumption E generated by vehicle i offloading multiple subtasks to M stationary vehicle servers on the roadside V2V(p) :

[0107]

[0108] Among them, t mis the transmission delay of the subtask offloading to the mth stationary vehicle server. m The expression is:

[0109]

[0110] Step 3: Calculate local computing energy consumption

[0111] During the entire task processing process, in addition to offloading to other servers, some subtasks are calculated locally by vehicle i. The energy consumption E0 of local calculation is calculated as follows:

[0112]

[0113] Where η is the energy coefficient, which depends on the chip structure of the server and can be 10 -26 J / Hz 2 ;f i is the rotation speed of the local server, indicating the computing power of the server; K is the task computing density (cycles / bit).

[0114] Step 4: Calculate the total energy consumption of the vehicle to determine the objective function and constraints

[0115] The total energy E consumed by minimizing the unloading and processing tasks of vehicle i is calculated as follows: S :

[0116] E S =E V2I +E V2V(M) +E V2V(p) +E0(13)

[0117] Then, the optimal unloading power and optimal unloading ratio with the lowest energy consumption are obtained by solving the objective function shown in the following formula:

[0118]

[0119]

[0120]

[0121] C3:t=max{t1,t2,t3,t0}

[0122]

[0123] C5:t2=t V2I +t c

[0124]

[0125] C7:p1+p2+...+pn +p'1+p'2+...p m +p V2I ≤p

[0126] C8: n = 1, 2, ... N

[0127] C9:m=1、2、...M (14)

[0128] Among them, ω n is the speed of the subtask unloaded to the driving vehicle server; ω m is the speed of the subtask unloaded to the stationary vehicle server; ω V2I is the speed of the subtask unloaded to the edge server; ω0 is the task speed calculated by the vehicle; ω is the total speed of the task i of the vehicle; B n The bandwidth allocated to the nth vehicle; B m The bandwidth allocated to the mth stationary vehicle; B V2I Bandwidth allocated to edge servers; B max is the total bandwidth; t is the total time for task offloading and processing to be completed; t1 is the total time for subtasks to be processed by the driving vehicle server; is the calculation time of the nth driving vehicle for the subtask; t c is the computing time of the subtask by the edge server; t2 is the total time of the subtask processed by the edge server; t3 is the total time of the subtask processed by the stationary vehicle server; is the calculation time of the mth stationary vehicle for the subtask; t0 is the time for the subtask to be calculated by the vehicle server; p1, p2, ...p n is the transmission power of the subtask unloaded to the moving vehicle; p'1, ​​p'2, ... p m The transmission power offloaded to the stationary vehicle for the subtask; p V2I is the transmission power of the subtask offloaded to the edge server; p is the total transmission power.

[0129] The above constraints, C1 means that the sum of the rotation speeds of all subtasks is equal to the total rotation speed of the total task of the vehicle; C2 means that the sum of the bandwidths allocated by all servers does not exceed the total bandwidth, i.e., the maximum bandwidth; C3 means that the time of the entire process is the maximum value of the four times, namely, the total processing time of unloading subtasks to the edge server, the total processing time of unloading subtasks to the moving vehicle server, the total processing time of unloading subtasks to the stationary vehicle server, and the local computing time; C4 means that the total processing time of unloading subtasks to the moving vehicle server is the maximum value of the sum of the transmission and computing time among N moving vehicles; C5 means that the total processing time of unloading subtasks to the edge server is the sum of the transmission and computing time; C6 means that the total processing time of unloading subtasks to the stationary vehicle server is the maximum value of the sum of the transmission and computing time among M stationary vehicles; C7 means that the sum of all transmission powers does not exceed the total transmission power; C8 means that there are a total of N moving vehicle servers n except this vehicle; C9 means that there are a total of M roadside stationary vehicle servers m.

[0130] Step 5: Solve using the improved simulated annealing algorithm

[0131] Under the above constraints, the improved simulated annealing algorithm is used to optimize the objective function to obtain the optimal transmission power and task allocation ratio. Based on the traditional simulated annealing algorithm, the present invention adds a random factor to the update of each iterative independent variable to increase the robustness of the algorithm.

[0132] (1) Set the initial temperature:

[0133] Calculate the initial temperature T = T0 for starting annealing, which is the initial objective function value:

[0134] T=ηf i 2 KS(14)

[0135] Where η is the energy coefficient, which depends on the chip structure of the vehicle server and can be 10 -26 J / Hz 2 ;f i 2 is the rotation speed of the local server, indicating the computing power of the server; K is the task computing density.

[0136] (2) Generate the initial solution and calculate the corresponding function value:

[0137] Randomly generate the initial solution x0 = {p n(0) ,p m(0) ,p V2I(0) ,α n(0) ,δ m(0) ,β (0)} is the initial position of the iteration, where p n(0)={p 1(0) ,p 2(0) ,...p N(0)}、p m(0) = {p1' (0) ,p' 2(0) ,...p M(0)}、α n(0) ={α 1(0) ,α 2(0) ,...α N(0)}、δ m(0) ={δ 1(0) ,δ 2(0) ,...δ M(0)}. p n(0) represents the transmission power transmitted to the moving vehicle n, p m(0) represents the transmission power transmitted to the stationary vehicle m, p V2I(0) represents the transmission power to the edge server, α n(0) represents the unloading ratio transferred to the moving vehicle n, δ m(0) represents the unloading ratio transferred to the stationary vehicle m, β (0) represents the offload ratio transmitted to the edge server. Substitute into the objective function Calculate the corresponding objective function value E S (x0).

[0138] (3) Set the number of iterations:

[0139] Suppose the number of loop iterations is j, and the number of iterations increases gradually, with a maximum of J, j=1, 2, ...J.

[0140] (4) Improve the independent variable update formula:

[0141] Compared with the traditional simulated annealing algorithm that randomly perturbs the initial solution, the present invention uses an improved independent variable update function to obtain a new solution from the initial solution:

[0142] x j+1 =θ·x j +(1-θ)Δx(j=1, 2,...J) (15)

[0143] Among them, x j+1 is the solution at the j+1th iteration, θ is a random factor selected from 0 to 1, and The j-th solution x j Substitute into the above formula (15) to calculate the next iterative solution x j+1 .

[0144] (5) Calculate the new solution and the corresponding function value:

[0145] Substitute the initial solution x0 into the above formula (15) to calculate x1, and x1={pn(1) ,p m(1) ,p V2I(1) ,α n(1) ,δ n(1) ,β (1)}, where p n(1) ={p 1(1) ,p 2(1) ,...p N(1)}、p m(1) = {p' 1(1) ,p' 2(1) ,...p M(1)}、α n(1) ={α 1(1) ,α 2(1) ,...α N(1)}、δ m(1) ={δ 1(1) ,δ 2(1) ,...δ M(1)}, and calculate the corresponding objective function value E(x1).

[0146] (6) Decide whether to accept a worse outcome:

[0147] Since the purpose of this patent is to reduce energy consumption, the lower the energy consumption, the closer to the optimal solution. If E(x1)≤E(x0), then assign x1 to x0, that is, x0=x1; if not, then The probability of accepting a new solution. is a probability, which is obviously less than 1. k is a positive physical constant; T is the temperature during the annealing process, which is the objective function value of the present invention, and is a positive number. Therefore, ΔE is negative, ΔE = -|E(x1) - E(x0)|.

[0148] Determine whether to accept the independent variable that increases the objective function value. Here, the better result is the independent variable with a smaller objective function value, so the worse result is the independent variable that increases the objective function value.

[0149] (7) Determine whether to end the iteration:

[0150] The number of iterations increases continuously, and steps (4) to (6) are repeated once for each iteration. At temperature T, it is determined whether the termination condition is met. If so, the iteration is stopped. At this time, x0 is the global optimal solution. The independent variable x is the transmission power and the task allocation ratio, and the dependent variable E(x) is the energy consumption.

[0151] Step 6: Get the optimization result

[0152] The optimal transmission power p that minimizes the vehicle's own energy consumption is obtained by the improved simulated annealing algorithm. n(0) ,p m(0) ,p V2I(0)And the optimal task allocation ratio α n(0) ,δ m(0) ,β (0) To achieve rational use of resources and achieve the goal of green transportation with energy conservation and emission reduction.

[0153] Embodiment 2

[0154] This embodiment provides an edge computing low-energy consumption task offloading system based on cellular vehicle networking, including:

[0155] The task block module is configured to divide the task generated by the vehicle and needing to be processed into a number of unrelated sub-task blocks;

[0156] The transmission distance and transmission rate determination module is configured to determine the transmission distance and transmission rate between the vehicle and the edge server, the moving vehicle server and the stationary vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the computing capacity of the vehicle's own server, and the computing capacity of the edge server and other vehicle servers;

[0157] a transmission energy consumption determination module, configured to determine the transmission energy consumption between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server according to the transmission rates between the vehicle and the edge server, the moving vehicle server, and the stationary vehicle server;

[0158] A local computing energy consumption determination module is configured to determine the local computing energy consumption of the vehicle for processing the vehicle subtask block according to the computing capacity of the vehicle's own server;

[0159] The objective function determination module is configured to construct an objective function for determining the total energy consumption of the vehicle by taking the sum of the local computing energy consumption and the transmission energy consumption of each server as the minimum;

[0160] The objective function solving module is configured to obtain an improved simulated annealing algorithm by adding a random factor to the update of each iterative independent variable on the basis of the traditional simulated annealing algorithm. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio are obtained when the total energy consumption of the vehicle is the lowest.

[0161] The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment 1. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0162] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0163] The proposed system can be implemented in other ways. For example, the system embodiment described above is only illustrative, and the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0164] Embodiment 3

[0165] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the edge computing low-energy task offloading method based on cellular vehicle network as described in the above-mentioned embodiment 1 are implemented.

[0166] Embodiment 4

[0167] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the edge computing low-energy task offloading method based on cellular vehicle network as described in the first embodiment above are implemented.

[0168] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0169] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0172] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0173] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A low-energy task offloading method for edge computing based on cellular vehicle networking, characterized in that: include: Divide the tasks that need to be processed by the vehicle into several unrelated subtask blocks; Determine the transmission distance and transmission rate between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the computing power of the vehicle's own server, and the computing power of the edge server and other vehicle servers; Determine the transmission energy consumption between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server according to the transmission rates between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server; According to the computing power of the vehicle's own server, determine the local computing energy consumption of the vehicle to process the vehicle subtask block; Taking the minimum sum of local computing energy consumption and each server's transmission energy consumption as the goal, the total energy consumption determination objective function of the vehicle is constructed; An improved simulated annealing algorithm is obtained by adding a random factor to the update of each iterative independent variable. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio when the total energy consumption of the vehicle is the lowest are obtained; The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio when the total energy consumption of the vehicle is the lowest are obtained, including: Step 1: Set the initial temperature for annealing based on the energy coefficient, speed, and task calculation density of the vehicle server T = T 0, which is the initial objective function value; Step 2: Randomly generate an initial solution as the initial position of the iteration, substitute the initial solution into the total energy consumption of the vehicle to determine the objective function, and calculate the corresponding objective function value; Step 3: Set the number of loop iterations; Step 4: Use the improved independent variable update function to obtain a new solution from the initial solution: , in, is the solution at the j+1th iteration, is a random factor selected from 0 to 1, and ; The j-th solution Substitute the above formula to calculate the next iterative solution ; J is the maximum number of iterations; Step 5: Convert the initial solution Substitute the above formula to calculate the new solution , and calculate the corresponding objective function value ; Step 6: Determine whether to accept the independent variable that increases the value of the objective function: like , then Assign to ,Right now If the opposite is true, The probability of accepting a new solution is is the probability, then it is obviously less than 1, is a positive physical constant; is the temperature during annealing, which is the objective function value and is a positive number, so is negative, ; Step 7: The number of iterations increases continuously, and steps 4 to 6 are repeated once for each iteration. , determine whether the termination condition is met, and if so, stop the iteration; at this time is the global optimal solution, where the independent variable That is, the transmission power and the task allocation ratio, the dependent variable That is energy consumption.

2. The low-energy consumption task offloading method for edge computing based on cellular vehicle networking as claimed in claim 1 is characterized in that: The determining of the transmission distance and the transmission rate between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server includes: Determine the transmission distance and transmission rate between the vehicle and the edge server based on the initial position of the vehicle when the task is generated, the driving speed of the vehicle, and the diameter of the edge server coverage area; Determine the transmission distance and transmission rate between the vehicle and the driving vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle and the driving speed of the driving vehicle; The transmission distance and transmission rate between the vehicle and the stopped vehicle server are determined according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the diameter of the coverage range of the stopped vehicle server and the position of the stopped vehicle.

3. The low-energy consumption task offloading method for edge computing based on cellular vehicle networking as claimed in claim 1 is characterized in that: The determining of the transmission energy consumption between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server includes: Determine the transmission delay of the subtask offloading to the edge server according to the transmission rate between the vehicle and the edge server, and further determine the transmission energy consumption between the vehicle and the edge server; Determine the transmission delay of the subtask offloading to the traveling vehicle server according to the transmission rate between the vehicle and the traveling vehicle server, and further determine the transmission energy consumption between the vehicle and the traveling vehicle server; The transmission delay of offloading the subtask to the stationary vehicle server is determined according to the transmission rate between the vehicle and the stopped vehicle server, and the transmission energy consumption between the vehicle and the stationary vehicle server is further determined.

4. The low-energy consumption task offloading method for edge computing based on cellular vehicle networking as claimed in claim 1 is characterized in that: The determination of the local computing energy consumption of the vehicle for processing the vehicle subtask block is specifically as follows: During the entire process of task processing, in addition to offloading to other servers, some subtasks are calculated locally by the vehicle. The local computing energy consumption is determined based on the local processing task volume, the energy coefficient of the vehicle's server, the rotation speed of the vehicle's server, and the task computing density.

5. The low-energy consumption task offloading method for edge computing based on cellular vehicle networking as claimed in claim 1 is characterized in that: The objective function for determining the total energy consumption of the vehicle is: in, represents the total energy consumed by processing tasks, represents the transmission energy consumption between the vehicle and the edge server, represents the transmission energy consumption between the vehicle and the moving vehicle server, represents the transmission energy consumption between the vehicle and the stationary vehicle server, Represents the local computing energy consumption of the vehicle in processing the vehicle subtask block.

6. The low-energy consumption task offloading method for edge computing based on cellular vehicle networking as claimed in claim 5 is characterized in that: The constraints of the objective function for determining the total energy consumption of the vehicle include: The sum of the rotation speeds of all subtasks is equal to the total rotation speed of the total task of this vehicle; the sum of the bandwidths allocated by all servers does not exceed the total bandwidth, that is, the maximum bandwidth; the time of the entire process is the maximum value of the four times: the total processing time of unloading subtasks to the edge server, the total processing time of unloading subtasks to the moving vehicle server, the total processing time of unloading subtasks to the stationary vehicle server, and the local calculation time; the total processing time of unloading subtasks to the moving vehicle server is the maximum value of the sum of transmission and calculation time among N moving vehicles; the total processing time of unloading subtasks to the edge server is the sum of transmission and calculation time; the total processing time of unloading subtasks to the stationary vehicle server is the maximum value of the sum of transmission and calculation time among M stationary vehicles; the sum of all transmission powers does not exceed the total transmission power; there are a total of N moving vehicle servers n other than this vehicle; there are a total of M roadside stationary vehicle servers m.

7. An edge computing low-energy consumption task offloading system based on cellular vehicle networking, used to implement an edge computing low-energy consumption task offloading method based on cellular vehicle networking as described in any one of claims 1 to 6, characterized in that: include: The task block module is configured to divide the task generated by the vehicle and needing to be processed into a number of unrelated sub-task blocks; The transmission distance and transmission rate determination module is configured to determine the transmission distance and transmission rate between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server according to the initial position of the vehicle when the task is generated, the driving speed of the vehicle, the computing capacity of the vehicle's own server, and the computing capacity of the edge server and other vehicle servers; a transmission energy consumption determination module, configured to determine the transmission energy consumption between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server according to the transmission rates between the vehicle and the edge server, the vehicle and the moving vehicle server, and the vehicle and the stationary vehicle server; A local computing energy consumption determination module is configured to determine the local computing energy consumption of the vehicle for processing the vehicle subtask block according to the computing capacity of the vehicle's own server; The objective function determination module is configured to construct an objective function for determining the total energy consumption of the vehicle by taking the sum of the local computing energy consumption and the transmission energy consumption of each server as the minimum; The objective function solving module is configured to obtain an improved simulated annealing algorithm by adding a random factor to the update of each iterative independent variable on the basis of the traditional simulated annealing algorithm. The improved simulated annealing algorithm is used to solve the total energy consumption of the vehicle to determine the objective function, and the optimal subtask unloading power and the optimal subtask allocation ratio are obtained when the total energy consumption of the vehicle is the lowest.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the edge computing low-energy task offloading method based on cellular vehicle network are implemented as described in any one of claims 1-6.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the steps in the edge computing low-energy task offloading method based on cellular vehicle network as described in any one of claims 1-6.

Citation Information

Patent Citations

  • Vehicle security risk warning and accident reconstruction system and method of big data processing

    CN106790367A

  • Task unloading and resource allocation joint optimization method based on edge cooperation

    CN111586762A

  • Computing unloading method and system for energy efficiency optimization in in-vehicle edge computing network

    WO2022011755A1