CN112929412A - Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell - Google Patents

Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell Download PDF

Info

Publication number
CN112929412A
CN112929412A CN202110085210.5A CN202110085210A CN112929412A CN 112929412 A CN112929412 A CN 112929412A CN 202110085210 A CN202110085210 A CN 202110085210A CN 112929412 A CN112929412 A CN 112929412A
Authority
CN
China
Prior art keywords
bandwidth
vehicle
edge server
cell
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110085210.5A
Other languages
Chinese (zh)
Other versions
CN112929412B (en
Inventor
张海霞
夏阳
郭帅帅
袁东风
周晓天
薛彤
刘文杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong University
Original Assignee
Shandong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong University filed Critical Shandong University
Priority to CN202110085210.5A priority Critical patent/CN112929412B/en
Publication of CN112929412A publication Critical patent/CN112929412A/en
Application granted granted Critical
Publication of CN112929412B publication Critical patent/CN112929412B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/52—Network services specially adapted for the location of the user terminal

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本发明涉及一种基于MEC单车单小区的联合带宽分配与数据流卸载方法、设备及存储介质，是指：车辆在离开小区时，该小区内完成总的数据流时，计算出车辆总数据流的最低时延ts；由于处理的数据流过大，车辆在离开小区时，该小区内未完成总的数据流时，边缘服务器通过分配最优带宽方法，解决边缘服务器缓冲区拥堵问题和车辆发生小区切换时边缘服务器缓冲区数据流未处理完问题，并使车辆数据上传量最大。本发明解决边缘服务器缓冲区拥堵问题和车辆发生小区切换时边缘服务器缓冲区数据流未处理完问题。通过边缘服务器对车辆提供最优带宽分配方法，合理控制上传数据量，实现该小区内车辆总数据流计算时延最低或者上传数据量最大。

Figure 202110085210

The invention relates to a method, device and storage medium for joint bandwidth allocation and data flow unloading based on MEC single-vehicle and single-cell, which means: when a vehicle leaves a cell, when the total data flow in the cell is completed, the total data flow of the vehicle is calculated. The lowest delay t s is the minimum delay t s ; because the processed data flow is too large, when the vehicle leaves the cell, when the total data flow is not completed in the cell, the edge server solves the edge server buffer congestion problem and the vehicle by allocating the optimal bandwidth method. When a cell switch occurs, the edge server buffer data stream is not processed completely, and the vehicle data upload volume is maximized. The invention solves the problem of edge server buffer congestion and the problem that the edge server buffer data stream is not processed completely when the vehicle switches between cells. The edge server provides the optimal bandwidth allocation method for vehicles, reasonably controls the amount of uploaded data, and achieves the lowest calculation delay of the total data flow of vehicles in the cell or the largest amount of uploaded data.

Figure 202110085210

Description

Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell
Technical Field
The invention belongs to the technical field of vehicle networking and edge computing, and relates to a method, equipment and a storage medium for joint bandwidth allocation and data flow unloading based on an MEC single vehicle single cell, which can be used for communication resource allocation and task unloading in vehicle networking edge computing.
Background
The Mobile Edge Computing (MEC) is used as a key technology of 5G, has the characteristics of short distance, high bandwidth, ultralow time delay, geographical position perception and the like, and solves some key technical problems of scenes such as high capacity, low time delay, high reliability and the like in the Internet of vehicles. In the internet of vehicles MEC-based vehicle mobility research, key factors related to task offloading and resource allocation problems include mobility, handover, multi-rate and backhaul links, etc.
When a vehicle user is in a mobility state, handover and task migration between cells are the subject of important research. The continuity of task unloading calculation is guaranteed, the system resources of the edge server are fully utilized, the time delay and the communication cost of a vehicle user are reduced, and the user experience is improved. In the aspect of researching vehicle mobility management, time delay and communication cost are optimized from the aspects of task unloading and resource allocation.
In the aspect of task unloading for researching vehicle mobility, the current research situation of vehicle networking edge computing is to consider the influence of vehicle mobility on task completion delay, energy consumption and total cost of task unloading and resource allocation. A document, Mobility-Aware routing in MEC-Based contextual Wireless Networks, proposes an expected cost analysis model, determines the average total cost of remote task execution by adopting an energy consumption average cost analysis and average task processing delay analysis method, and considers the switching situation of random Mobility of vehicles and the task size possibly occurring in the unloading process. In the second document, considered in a single-cell scene, an effect Mobility-Aware Task Offloading scheme is proposed; in a multi-cell cooperation scene, an unloading scheme based on position is provided. In the two scenarios, the communication and computing resource cost required by task completion and the maximum unloading delay combined optimization are balanced, and the optimal unloading scheme of the task is computed. However, both the first and second documents ignore the problem that too many tasks in a single cell are offloaded, which may result in incomplete tasks in the cell during cell handover, which may result in increased communication backhaul cost and lost tasks during backhaul. The problem of buffer congestion of an edge server is not considered in the current Internet of vehicles edge calculation research, and task loss and performance reduction of an edge server system can be caused by the buffer congestion. In the aspect of calculating the total time delay of the task, the second document mentions that the total time delay of completing the task is the maximum value of the local calculation time delay and the total time delay of unloading the edge server, and the total time delay of completing the task is the minimum only when the local time delay is equal to the total time delay of unloading the edge server. Document three, Joint Task Assignment, Transmission, and Computing Resource Allocation in multilayered Mobile Edge Computing Systems, proposes a multilayered Edge stream system for static users, fully utilizes cloud Edge Computing capability, and alleviates the problem of Edge server buffer congestion. However, the problem of buffer congestion is not completely solved in the document, the optimal bandwidth allocation provided by the edge server is neglected, the uploading task amount is reasonably controlled, and the problem of buffer congestion of the edge server can be avoided.
Disclosure of Invention
Aiming at the problems of edge server buffer congestion caused by excessive task uploading and buffer task incomplete processing during cell switching, the invention provides a method for joint bandwidth allocation and data stream unloading based on an MEC single-vehicle single-cell under a single-vehicle single-cell scene.
The invention also provides a computer device and a storage medium;
the invention researches that in a single-vehicle single-cell scene, a vehicle sends a data stream unloading calculation request to an edge server at a certain position, the edge server is determined to allocate the optimal bandwidth for the vehicle according to the speed, the initial position and the size of the data stream of the vehicle, the limited calculation capacity of a vehicle-mounted unit, the calculation capacity of the edge server, the maximum storage capacity of a buffer area and other factors, the problem of buffer area congestion of the edge server and the problem that the data stream of the buffer area of the edge server is not processed completely when the vehicle cell is switched are solved, and the minimum time delay of the calculation of the total data stream of the vehicle in the cell or the maximum uploading data quantity are realized.
The invention solves the problem of edge server buffer area congestion and the problem that the data stream of the edge server buffer area is not processed completely when the vehicles are switched in the cell. The edge server provides an optimal bandwidth allocation method for the vehicles, the uploaded data volume is reasonably controlled, and the minimum time delay of total vehicle data flow calculation or the maximum uploaded data volume in the cell is realized.
The technical scheme of the invention is as follows:
a method for joint bandwidth allocation and data flow unloading based on an MEC single-vehicle single-cell is characterized in that: when the vehicle leaves the cell and the total data flow is completed in the cell, the lowest time delay t of the total data flow of the vehicle is calculateds(ii) a Because the processed data flow is too large, when the vehicle leaves the cell and the total data flow is not finished in the cell, the edge server solves the problem of buffer area congestion of the edge server and the problem that the data flow of the buffer area of the edge server is not finished when the vehicle is switched between the cells by a method for distributing optimal bandwidth, and the data uploading quantity of the vehicle is maximum.
According to the optimization of the invention, the vehicle i completes the total data stream in the cell, and the lowest total time delay t of the processed vehicle total data stream is calculated according to the method of distributing the optimal bandwidth of the vehicle i by the edge server jsThe method comprises the following steps:
A. according to equation (1), an initial bandwidth b is given0Under the condition of meeting the maximum capacity of the buffer area of the edge server j, the maximum bandwidth b provided by the edge server j for the vehicle i is calculated by adopting a PID algorithmij，bij＝b1The bandwidth b of the vehicle i provided by the edge server j satisfies b ═ b0,b1](ii) a The data volume uploaded by the vehicle i can be reasonably controlled, and the problem of congestion of the buffer area of the edge server j is solved.
Figure BDA0002910551660000031
In the formula (1), N edge servers provide communication, storage and calculation resources for vehicles on a suburb or a highway, M vehicles run in a cell served by an edge server j, j is { 1.·, N }, a certain vehicle i runs at a constant speed in a straight line in the cell served by the edge server j, and i is { 1.·, M }, and a task unloading request is sent to the edge server at a certain position in the cell;
vehicle i is traveling at velocity v in the cell served by edge server jijStraight-line running at a constant speed at a certain initial position aijThe time required for the vehicle i to travel in the cell is t until the vehicle i leaves the cell after starting to transmit the data stream to the edge server j4：
Figure BDA0002910551660000032
When the vehicle leaves the cell, the total data flow is completed in the cell, which means that: t is more than or equal to 0 and less than or equal to t of the vehicle4Completing data flow unloading calculation in a time period;
Pijis the uplink transmission power, h, of vehicle i at edge server jijIs the small-scale fading path loss, N, of vehicle i at edge server j0Is the noise power spectral density of the edge server j receive segment; height of edge server j service is HjRice, horizontal distance to road surface DjRice, diameter of radiation range LCMeter, k is the number of revolutions of the CPU required by each bit, and epsilon refers to the maximum storage capacity of the buffer area;
t1is the moment when the first upload rate equals the computed rate of the edge server, t2Is the moment when the second upload rate equals the calculated rate of the edge server, t3Is the time when the data stream in the buffer of the edge server is processed, tsIs the total time delay for completing the vehicle data flow in the cell, xi is the integral parameter of the uploading rate integral with time, fjIs the number of revolutions per second, R, of the j CPU of the edge serverij(0) Vehicle i upload rate when t is 0;
B. according to the step AOut of the bandwidth b range, b ∈ [ b [ ]0,b1]B, under the condition of finishing calculating the data stream of the buffer zone when the vehicle i leaves the cell, bijCalculating the maximum bandwidth b provided by the edge server j for the vehicle i by adopting a PID algorithm to the formula (2)ij，bij＝b2(ii) a The bandwidth b range of the vehicle i provided by the edge server j satisfies b E [ b ∈0,b2],b2∈[b0,b1](ii) a The data flow uploaded by the vehicle i can be reasonably controlled, and the problem that when the vehicle i leaves the cell, the data flow of the buffer area of the edge server is not processed completely is solved.
Figure BDA0002910551660000041
C. And B, calculating a bandwidth B range B epsilon [ B ] meeting the constraint condition according to the step A and the step B0,b2]Considering the factors of the size and initial position of the data stream, the uploading rate when t is 0
Figure BDA0002910551660000042
If vehicle i data stream SiSatisfies SiWhen S is less than or equal to S, the maximum bandwidth b is solved by a PID algorithm adjusting bandwidth method under the condition that no data stream is stored in a j buffer area of the edge serverijSo that the total time delay t of the objective functionsMinimum, i.e. ts＝t1Calculating the total time delay as shown in the formula (3); if vehicle i data stream SiSatisfies SiWhen the bandwidth is larger than S, the bandwidth is adjusted through a PID algorithm, and the maximum bandwidth b is solved under the condition that the data stream stored in the buffer area is not larger than the maximum capacity of the buffer areaijIn the known bandwidth range, the bandwidth method is adjusted through a PID algorithm to solve the optimal bandwidth bijSo that the total time delay t of the objective functionsLowest and satisfies the total delay tsAt t2＜t3≤ts≤t4In the range, formula (3) is as follows:
Figure BDA0002910551660000043
in the formula (3), R (xi) is xi ranging from 0 to tsUpload rate at any time in time, SiIs the size of the data stream that vehicle i needs to compute, in bits. Expanding the uploading rate R (xi) to know, the edge server j provides the optimal bandwidth b of the vehicle iijThe above two problems can be solved and the total task S is calculatediThe lowest delay.
According to the invention, when the vehicle leaves the cell and the total data stream is not completed in the cell, the edge server solves the problem of edge server buffer area congestion and the problem that the data stream of the edge server buffer area is not completed when the vehicle is switched over, and the vehicle data uploading amount is maximum by the method for distributing the optimal bandwidth, and the method comprises the following steps:
D. according to equation (1), an initial bandwidth b is given0Under the condition of meeting the maximum capacity of the buffer area of the edge server j, the maximum bandwidth b provided by the edge server j for the vehicle i is calculated by adopting a PID algorithmij，bij＝b1The bandwidth range of the vehicle i provided at the edge server j satisfies b ═ b0,b1](ii) a The data volume uploaded by the vehicle i can be reasonably controlled, and the problem of congestion of the buffer area of the edge server j is solved.
E. According to the bandwidth b range calculated in the step D, b belongs to [ b ∈ [)0,b1]B, under the condition of finishing calculating the data stream of the buffer zone when the vehicle i leaves the cell, bijCalculating the maximum bandwidth b provided by the edge server j for the vehicle i by adopting a PID algorithm to the formula (2)ij，bij＝b2(ii) a The bandwidth b range of the vehicle i provided by the edge server j satisfies b E [ b ∈0,b2],b2∈[b0,b1](ii) a The data flow uploaded by the vehicle i can be reasonably controlled, and the problem that when the vehicle i leaves the cell, the data flow of the buffer area of the edge server is not processed completely is solved.
F. According to the bandwidth b range which is calculated in the step D and the step E and meets the constraint condition, b belongs to [ b ]0,b2]. Within the known bandwidth range, the optimal band is solved by a bandwidth adjusting methodWidth bij，bij＝b2According to the time t when the vehicle i runs in the cell of the edge server j, t is t4Solving the maximum data quantity S of the objective functionijAs shown in formula (4):
Figure BDA0002910551660000051
in the formula (4), R (xi) is xi ranging from 0 to tsUpload rate S at any time within timeijIs the amount of data uploaded by vehicle i in cell of edge server j, and the unit is bit. Expanding the uploading rate R (xi) to know, the edge server j provides the optimal bandwidth b of the vehicle iijThe two problems can be solved, and the vehicle i uploads the maximum data volume S in the cell of the edge server jij。
According to the invention, the following steps are preferably executed before the step A and the step D, and the steps comprise:
a. calculating an initial bandwidth b0: when in use
Figure BDA0002910551660000061
When t is equal to 0, the sum of the values,
Figure BDA0002910551660000062
solving the initial bandwidth b0，b0≤Bj；
a0Refers to the radius of the communication range of the edge server j, i.e.
Figure BDA0002910551660000063
Wherein L isCIs the edge server communication diameter; when in use
Figure BDA0002910551660000064
And when t is 0, Rij(0) The uploading rate of the vehicle i at the nearest position of the edge server j when t is 0;
b. judging the initial position aijAnd
Figure BDA0002910551660000065
in a relation of
Figure BDA0002910551660000066
Then, calculate Rij(0)：
Figure BDA0002910551660000067
Namely at
Figure BDA0002910551660000068
Then, the sum S of the data stream uploaded and calculated at the time point and the data stream calculated by the vehicle-mounted terminal is as shown in formula (5):
Figure BDA0002910551660000069
c. the sum S of the data streams is compared with the total data stream S of the vehicle iiMaking a comparison, if SiLess than or equal to S, adopting PID algorithm to convert the initial bandwidth b0Substituting equation (6) calculates the difference e:
Figure BDA00029105516600000610
when the difference e is greater than or equal to the set threshold, increasing the initial bandwidth b0The coefficient of increase is c; bandwidth bij＝b0+ce，bij≤BjCalculating
Figure BDA00029105516600000611
To obtain a time point t1，t1The time point when the first uploading rate is equal to the computing rate of the edge server is obtained;
then the new bandwidth b is addedijSubstituting the formula (6), calculating a new difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and obtaining the bandwidth b meeting the minimum total time delay calculated by the total data of the vehicleij(ii) a Data stream no store bufferZone, not necessarily at t2Releasing the computing power after a point in time to process the buffer data stream, t2For the time point when the second upload rate is equal to the calculated rate of the edge server, the lowest total delay is ts＝t1；
If S isiS, enter step A or step D.
According to a preferred embodiment of the invention, an initial bandwidth b is given in step A or step D0And calculating the optimal bandwidth provided by the edge server j for the vehicle i by adopting a PID algorithm: when in use
Figure BDA0002910551660000071
When the step (d) is performed, step (d) is performed
Figure BDA0002910551660000072
If yes, entering the step e;
step d is as follows:
using PID algorithm, the calculation is performed at time t1And t2The memory capacity of the data stream uploading buffer is less than or equal to the maximum buffer memory capacity epsilon:
first, an initial bandwidth b is defined0Substituting into formula
Figure BDA0002910551660000073
To obtain a time point t1And t2；
Then, the initial bandwidth b0Substituting equation (7) to calculate the target value ε and t1And t2Data flow difference value e of the buffer area between:
Figure BDA0002910551660000074
when the difference e is larger than or equal to the set value c, the bandwidth b is adjustedij＝b0+ce，bij≤Bj；
Then the new bandwidth b is addedijSubstituting the formula (7) to recalculate the difference e, iterating for multiple times until the difference e is smaller than the set threshold value, jumping out of the loop, and calculating a satisfaction stripOptimum bandwidth of the element bij(ii) a By means of Matlab simulation, considering the influence of different initial positions and vehicle speeds on the bandwidth requirement, the problem of buffer congestion is solved by a bandwidth adjusting method to obtain a simulation diagram, as shown in FIG. 5.
Step e is as follows:
satisfy the requirement of
Figure BDA0002910551660000075
When the condition is met, firstly, the initial bandwidth b0Substituting into formula
Figure BDA0002910551660000076
To obtain a time point t1And t2At the time point t of solution1Is a negative number, take t 10; then, the initial bandwidth b0Substituting equation (8) to calculate the target value ε and t1And t2The data flow difference e of the buffer areas between;
Figure BDA0002910551660000081
when the difference e is larger than or equal to the set value c, the bandwidth b is adjustedij＝b0+ce，bij≤Bj(ii) a Then the new bandwidth b is addedijSubstituting the formula (8) to recalculate the difference e, iterating for multiple times until the difference e is smaller than the set threshold value, jumping out of the loop, and calculating the optimal bandwidth b meeting the conditionij。
Preferably, in step B or E, the optimal bandwidth satisfying time t is calculated by using a PID algorithm to formula (2)3At t2≤t3≤t4Calculating the optimal bandwidth provided by the edge server j for the vehicle i within the range; when in use
Figure BDA0002910551660000082
When the step f is performed, go to step f
Figure BDA0002910551660000083
Entering step g;
step f is as follows:
and the bandwidth is adjusted by adopting a PID algorithm, so that the problem that the data stream of the buffer area is processed when the vehicle leaves the cell is solved:
under the condition of satisfying the above-mentioned solution bandwidth range, firstly, the initial bandwidth b is set0Substituting equation (9) to calculate the time t for finishing processing the buffer3：
Figure BDA0002910551660000084
Then, the target value t is determined4And time t3When the difference e is larger than or equal to a set value d, adjusting the bandwidth
Figure BDA0002910551660000085
Then the new bandwidth is added
Figure BDA0002910551660000086
Substituting equation (9) to calculate the new time t3；
Recalculating the difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and calculating the time t3Bandwidth of
Figure BDA0002910551660000087
To meet the required optimal bandwidth, when time t3＝t4When the vehicle just leaves the cell, the buffer zone is processed, and the bandwidth at the moment
Figure BDA0002910551660000088
Maximum bandwidth to meet the requirements;
step g is as follows:
and the PID algorithm is adopted to adjust the bandwidth, so that the problem of processing the data stream of the buffer area when the vehicle leaves the cell is solved. Under the condition of satisfying the above-mentioned solution bandwidth range, firstly, the initial bandwidth b is set0Substituting equation (10) to calculate the time t for finishing processing the buffer3；
Figure BDA0002910551660000091
Then, the target value t is determined4And time t3When the difference e is larger than or equal to a set value d, adjusting the bandwidth
Figure BDA0002910551660000092
Then the new bandwidth is added
Figure BDA0002910551660000093
Substituting equation (10) to calculate the new time t3；
Recalculating the difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and calculating the time t3Bandwidth of
Figure BDA0002910551660000094
To meet the required optimal bandwidth, when time t3＝t4When the vehicle just leaves the cell, the buffer zone is processed, and the bandwidth at the moment
Figure BDA0002910551660000095
To meet the required maximum bandwidth.
A computer arrangement comprising a memory storing a computer program and a processor implementing the steps of a MEC-single cell based joint bandwidth allocation and data flow offloading method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the MEC-single-cell based joint bandwidth allocation and data flow offloading method.
The invention has the beneficial effects that:
the invention researches a method for providing optimal bandwidth allocation for vehicles through the edge server under a single-vehicle single-cell scene, reasonably controls the data flow uploaded by the vehicles, and solves the problems of edge server buffer congestion and unprocessed data of the edge server buffer during vehicle cell switching. According to the dataThe size of the stream and the limited edge server computing power, as well as the vehicle's own computing power, take into account two scenarios. The first case is the case where the total data flow is completed in the cell, where the lowest time delay t of the total data flow of the vehicles can be calculateds. The second case is that the edge server solves the above two problems by allocating the optimal bandwidth and simultaneously maximizes the vehicle data upload amount because the processed data flow is too large and the vehicle does not complete the total data flow when leaving the cell. The invention provides a method for distributing optimal bandwidth by an edge server, which solves the problems of data stream loss and reduced system performance of the edge server caused by the congestion of a buffer area of the edge server. The problem that data streams in a buffer area are not processed completely when a vehicle is subjected to cell switching is solved, so that the cost of return communication is increased and tasks are lost in the return process.
Drawings
FIG. 1 is a schematic diagram of single-vehicle single-cell communication based on MEC in the present invention;
FIG. 2 is a schematic diagram of the calculation of a single vehicle and a single cell based on MEC in the present invention;
FIG. 3(a) is a view showing the driving direction of a vehicle toward an edge server according to the present invention and t1The uploading rate change process greater than 0 influences the situation of data stream stored in the buffer area;
FIG. 3(b) is a view showing that the vehicle of the present invention is driven toward the edge server and t1The uploading rate change process of 0 affects the situation that the data flow is stored in the buffer area;
FIG. 3(c) is a diagram of a vehicle driving off an edge server and t of the present invention1The uploading rate change process of 0 affects the situation that the data flow is stored in the buffer area;
FIG. 4(a) shows the bandwidth allocation method of the present invention having calculated t1～t2The data flow condition of the buffer area with the shaded area is shown schematically;
FIG. 4(b) is the bandwidth allocation method of the present invention, which has been calculated from 0 to t2A schematic diagram of the data flow condition of the buffer area with the shaded area;
FIG. 4(c) is the bandwidth allocation method of the present invention, which has been calculated from 0 to t2Buffer data flow condition of shaded areaAn intent;
FIG. 5 is a schematic diagram of the maximum bandwidth that meets the capacity of the buffer calculated by the PID algorithm in the present invention;
FIG. 6(a) is a schematic diagram showing the effect of a vehicle speed of 20m/s and different initial positions on bandwidth allocation in the present invention;
FIG. 6(b) is a schematic diagram showing the effect of a vehicle speed of 25m/s and different initial positions on bandwidth allocation in the present invention.
Detailed Description
The invention is further defined in the following, but not limited to, the figures and examples in the description.
Example 1
A method for joint bandwidth allocation and data flow unloading based on an MEC single-vehicle single-cell is characterized in that: when the vehicle leaves the cell and the total data flow is completed in the cell, the lowest time delay t of the total data flow of the vehicle is calculateds(ii) a Because the processed data flow is too large, when the vehicle leaves the cell and the total data flow is not finished in the cell, the edge server solves the problem of buffer area congestion of the edge server and the problem that the data flow of the buffer area of the edge server is not finished when the vehicle is switched between the cells by a method for distributing optimal bandwidth, and the data uploading quantity of the vehicle is maximum.
Example 2
The method for joint bandwidth allocation and data flow offloading based on MEC single-vehicle single-cell in embodiment 1 is characterized in that:
the vehicle i completes the total data stream in the cell, and the lowest total time delay t for processing the total data stream of the vehicle is calculated according to the method for distributing the optimal bandwidth of the vehicle i by the edge server jsThe method comprises the following steps:
A. according to equation (1), an initial bandwidth b is given0Under the condition of meeting the maximum capacity of the buffer area of the edge server j, the maximum bandwidth b provided by the edge server j for the vehicle i is calculated by adopting a PID algorithmij，bij＝b1The bandwidth b of the vehicle i provided by the edge server j satisfies b ═ b0,b1](ii) a The data volume uploaded by the vehicle i can be reasonably controlled, and the problem of congestion of the buffer area of the edge server j is solved.
Figure BDA0002910551660000111
In the formula (1), N edge servers provide communication, storage and calculation resources for vehicles on a suburb or a highway, M vehicles run in a cell served by an edge server j, j is { 1.·, N }, a certain vehicle i runs at a constant speed in a straight line in the cell served by the edge server j, and i is { 1.·, M }, and a task unloading request is sent to the edge server at a certain position in the cell;
vehicle i is traveling at velocity v in the cell served by edge server jijStraight-line running at a constant speed at a certain initial position aijThe time required for the vehicle i to travel in the cell is t until the vehicle i leaves the cell after starting to transmit the data stream to the edge server j4：
Figure BDA0002910551660000112
When the vehicle leaves the cell, the total data flow is completed in the cell, which means that: t is more than or equal to 0 and less than or equal to t of the vehicle4Completing data flow unloading calculation in a time period;
Pijis the uplink transmission power, h, of vehicle i at edge server jijIs the small-scale fading path loss, N, of vehicle i at edge server j0Is the noise power spectral density of the edge server j receive segment; height of edge server j service is HjRice, horizontal distance to road surface DjRice, diameter of radiation range LCMeter, as shown in fig. 1, k is the number of revolutions per bit of the CPU required, and epsilon refers to the maximum storage capacity of the buffer;
as in FIG. 3(a), t1Is the moment when the first upload rate equals the computed rate of the edge server, t2Is the moment when the second upload rate equals the calculated rate of the edge server, t3Is the time when the data stream in the buffer of the edge server is processed, tsIs the total time delay for completing the vehicle data flow in the cell, xi is the integral parameter of the uploading rate integral with time, fjIs the number of revolutions per second of the j CPU of the edge server，Rij(0) Vehicle i upload rate when t is 0;
B. according to the bandwidth b range calculated in the step A, b belongs to [ b ∈ [ ]0,b1]B, under the condition of finishing calculating the data stream of the buffer zone when the vehicle i leaves the cell, bijCalculating the maximum bandwidth b provided by the edge server j for the vehicle i by adopting a PID algorithm to the formula (2)ij，bij＝b2(ii) a The bandwidth b range of the vehicle i provided by the edge server j satisfies b E [ b ∈0,b2],b2∈[b0,b1](ii) a The data flow uploaded by the vehicle i can be reasonably controlled, and the problem that when the vehicle i leaves the cell, the data flow of the buffer area of the edge server is not processed completely is solved.
Figure BDA0002910551660000121
C. And B, calculating a bandwidth B range B epsilon [ B ] meeting the constraint condition according to the step A and the step B0,b2]Considering the factors such as the size and initial position of the data stream, it can be seen from fig. 3(a) and equation (5) that the upload rate is 0 when t is equal to t
Figure BDA0002910551660000122
As shown in fig. 2, when the first byte arrives at the edge server, it is assumed that the edge server can calculate after receiving the first byte, and therefore, the upload start time is equal to the calculation start time. Because the calculated result is generally small, the return delay is approximately ignored, the queue delay of the buffer area is considered, and the data stream of the buffer area is processed when the vehicle leaves the cell, the total delay of the edge server for processing the data stream is equal to the uploading delay of the vehicle in the cell. If vehicle i data stream SiSatisfies SiWhen S is less than or equal to S, the maximum bandwidth b is solved by a PID algorithm adjusting bandwidth method under the condition that no data stream is stored in a j buffer area of the edge serverijSo that the total time delay t of the objective functionsMinimum, i.e. ts＝t1Calculating the total time delay as shown in the formula (3); if vehicle i data stream SiSatisfies SiWhen > S, through PID calculationAdjusting bandwidth, and solving the maximum bandwidth b when the data stream stored in the buffer is not greater than the maximum capacity of the bufferijIn the known bandwidth range, the bandwidth method is adjusted through a PID algorithm to solve the optimal bandwidth bijSo that the total time delay t of the objective functionsLowest and satisfies the total delay tsAt t2＜t3≤ts≤t4In the range, formula (3) is as follows:
Figure BDA0002910551660000131
in the formula (3), R (xi) is xi ranging from 0 to tsUpload rate at any time in time, SiIs the size of the data stream that vehicle i needs to compute, in bits. Expanding the uploading rate R (xi) to know, the edge server j provides the optimal bandwidth b of the vehicle iijThe above two problems can be solved and the total task S is calculatediThe lowest delay.
The reasoning process of equation (1) is as follows:
and the edge server j solves the problem of buffer congestion through a bandwidth allocation method, and when the uploading rate is greater than the calculation rate of the edge server, unprocessed data in unit time are stored in the buffer. There are three cases where the uploading rate change process affects the buffer storage data stream, as shown in fig. 3(a) to 3(c), where the edge server j calculates the rate as:
Figure BDA0002910551660000132
t in FIG. 3(a)1And t2The upload rate at that time is equal to the edge server computation rate, as in fig. 3(b) and 3(c)
Figure BDA0002910551660000133
That is, when t is 0, the uploading rate is greater than the calculation rate, so that the unprocessed data is stored in the buffer area when t is 0, that is, t is t 10. The area of the shaded part in the calculated graph isThe memory capacity of the buffer area can be ensured as long as the memory capacity of the buffer area is not more than the maximum memory capacity epsilon of the buffer area. t is t4Is that the vehicle i is from a certain initial position a in the edge server j cellijThe time required to start sending a data stream until leaving the cell, wherein,
Figure BDA0002910551660000134
Figure BDA0002910551660000135
k is the number of revolutions per bit required by the CPU.
For the uplink transmission rate R in the above formulaijAnd xi, the edge server j can avoid the problem of buffer congestion through bandwidth allocation, as shown in formula (1).
The reasoning process of equation (2) is as follows:
the edge server j provides bandwidth allocation to solve the problem that the task is not finished when the cell is switched. As shown in fig. 4(a) to 4(c), the edge server j causes t to be a bandwidth allocation method2And t3The area of the shaded portion in between is equal to t1And t2The shaded area therebetween, wherein, fig. 4(a) is the bandwidth allocation method having calculated t1～t2The data flow condition of the buffer area with the shaded area is shown schematically; t in FIGS. 4(b) and 4(c)1＝0、t3The time is the time when the data in the buffer area is processed and is not processed, as long as t is satisfied3≤t4This condition solves the problem of unprocessed data streams in the buffer of the edge server j when the vehicle i leaves the cell. When t is3＝t4And meanwhile, the edge server j allocates the maximum bandwidth for the vehicle i, so that the problems of increase of return communication cost and task loss when the vehicle i runs to the next cell are solved.
Figure BDA0002910551660000141
Simplifying to obtain:
Figure BDA0002910551660000142
for the uplink transmission rate R in the above formulaijAnd xi, the problem that the data stream of the buffer area of the edge server j is not processed completely when the vehicle i leaves the cell is solved by the edge server j through a bandwidth allocation method, as shown in a formula (2).
Example 3
The method for joint bandwidth allocation and data flow offloading based on MEC single-vehicle single-cell in embodiment 1 is characterized in that:
when a vehicle leaves a cell and the total data flow is not completed in the cell, the edge server solves the problem of edge server buffer area congestion and the problem that the data flow of the edge server buffer area is not processed when the vehicle is switched between the cells by a method for distributing optimal bandwidth, and the vehicle data uploading quantity is maximum, and the method comprises the following steps:
D. according to equation (1), an initial bandwidth b is given0Under the condition of meeting the maximum capacity of the buffer area of the edge server j, the maximum bandwidth b provided by the edge server j for the vehicle i is calculated by adopting a PID algorithmij，bij＝b1The bandwidth range of the vehicle i provided at the edge server j satisfies b ═ b0,b1](ii) a The data volume uploaded by the vehicle i can be reasonably controlled, and the problem of congestion of the buffer area of the edge server j is solved.
E. According to the bandwidth b range calculated in the step D, b belongs to [ b ∈ [)0,b1]B, under the condition of finishing calculating the data stream of the buffer zone when the vehicle i leaves the cell, bijCalculating the maximum bandwidth b provided by the edge server j for the vehicle i by adopting a PID algorithm to the formula (2)ij，bij＝b2(ii) a The bandwidth b range of the vehicle i provided by the edge server j satisfies b E [ b ∈0,b2],b2∈[b0,b1](ii) a The uploading data flow of the vehicle i can be reasonably controlled, and the problem of the vehicle i leaving is solvedWhen the cell is opened, the data flow of the buffer area of the edge server is not processed.
F. According to the bandwidth b range which is calculated in the step D and the step E and meets the constraint condition, b belongs to [ b ]0,b2]. Within the known bandwidth range, the optimal bandwidth b is solved by a bandwidth adjusting methodij，bij＝b2According to the time t when the vehicle i runs in the cell of the edge server j, t is t4Solving the maximum data quantity S of the objective functionijAs shown in formula (4):
Figure BDA0002910551660000151
in the formula (4), R (xi) is xi ranging from 0 to tsUpload rate S at any time within timeijIs the amount of data uploaded by vehicle i in cell of edge server j, and the unit is bit. Expanding the uploading rate R (xi) to know, the edge server j provides the optimal bandwidth b of the vehicle iijThe two problems can be solved, and the vehicle i uploads the maximum data volume S in the cell of the edge server jij。
Example 4
The method for joint bandwidth allocation and data flow unloading based on the MEC single-vehicle single-cell in the embodiment 2 or 3 is characterized in that:
the following steps are executed before the step A and the step D, and the steps comprise:
a. calculating an initial bandwidth b0: when in use
Figure BDA0002910551660000161
When t is equal to 0, the sum of the values,
Figure BDA0002910551660000162
solving the initial bandwidth b0，b0≤Bj；
a0Refers to the radius of the communication range of the edge server j, i.e.
Figure BDA0002910551660000163
Wherein L isCIs the edge server communication diameter; when in use
Figure BDA0002910551660000164
And when t is 0, Rij(0) The uploading rate of the vehicle i at the nearest position of the edge server j when t is 0;
b. judging the initial position aijAnd
Figure BDA0002910551660000165
in a relation of
Figure BDA0002910551660000166
Then, calculate Rij(0)：
Figure BDA0002910551660000167
Namely at
Figure BDA0002910551660000168
Then, the sum S of the data stream uploaded and calculated at the time point and the data stream calculated by the vehicle-mounted terminal is as shown in formula (5):
Figure BDA0002910551660000169
c. the sum S of the data streams is compared with the total data stream S of the vehicle iiMaking a comparison, if SiLess than or equal to S, adopting PID algorithm to convert the initial bandwidth b0Substituting equation (6) calculates the difference e:
Figure BDA00029105516600001610
when the difference e is greater than or equal to the set threshold, increasing the initial bandwidth b0The coefficient of increase is c; bandwidth bij＝b0+ce，bij≤BjCalculating
Figure BDA00029105516600001611
To obtain a time point t1，t1The time point when the first uploading rate is equal to the computing rate of the edge server is obtained;
then the new bandwidth b is addedijSubstituting the formula (6), calculating a new difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and obtaining the bandwidth b meeting the minimum total time delay calculated by the total data of the vehicleij(ii) a The data stream has no storage buffer and does not need to be at t2Releasing the computing power after a point in time to process the buffer data stream, t2For the time point when the second upload rate is equal to the calculated rate of the edge server, the lowest total delay is ts＝t1；
If S isiS, enter step A or step D.
Example 5
The method for joint bandwidth allocation and data flow unloading based on the MEC single-vehicle single-cell in the embodiment 2 or 3 is characterized in that:
in step A or step D, an initial bandwidth b is given0And calculating the optimal bandwidth provided by the edge server j for the vehicle i by adopting a PID algorithm: when in use
Figure BDA0002910551660000171
When the step (d) is performed, step (d) is performed
Figure BDA0002910551660000172
If yes, entering the step e;
step d is as follows:
using PID algorithm, the calculation is performed at time t1And t2The memory capacity of the data stream uploading buffer is less than or equal to the maximum buffer memory capacity epsilon:
first, an initial bandwidth b is defined0Substituting into formula
Figure BDA0002910551660000173
To obtain a time point t1And t2；
Then, the initial bandwidth b0Substituting equation (7) to calculate the target value ε and t1And t2Data flow difference value e of the buffer area between:
Figure BDA0002910551660000174
when the difference e is larger than or equal to the set value c, the bandwidth b is adjustedij＝b0+ce，bij≤Bj；
Then the new bandwidth b is addedijSubstituting the formula (7) to recalculate the difference e, iterating for multiple times until the difference e is smaller than the set threshold value, jumping out of the loop, and calculating the optimal bandwidth b meeting the conditionij(ii) a By means of Matlab simulation, considering the influence of different initial positions and vehicle speeds on the bandwidth requirement, the problem of buffer congestion is solved by a bandwidth adjusting method to obtain a simulation diagram, as shown in FIG. 5.
Step e is as follows:
satisfy the requirement of
Figure BDA0002910551660000175
When the condition is met, firstly, the initial bandwidth b0Substituting into formula
Figure BDA0002910551660000176
To obtain a time point t1And t2At the time point t of solution1Is a negative number, take t 10; then, the initial bandwidth b0Substituting equation (8) to calculate the target value ε and t1And t2The data flow difference e of the buffer areas between;
Figure BDA0002910551660000181
when the difference e is larger than or equal to the set value c, the bandwidth b is adjustedij＝b0+ce，bij≤Bj(ii) a Then the new bandwidth b is addedijSubstituting the formula (8) to recalculate the difference e, iterating for multiple times until the difference e is smaller than the set threshold value, jumping out of the loop, and calculating to meet the requirementOptimum bandwidth of condition bij. By means of Matlab simulation, considering the influence of different initial positions and vehicle speeds on the bandwidth requirement, the problem of buffer congestion is solved by a bandwidth adjusting method to obtain a simulation diagram, as shown in FIG. 5.
Example 6
The method for joint bandwidth allocation and data flow unloading based on the MEC single-vehicle single-cell in the embodiment 2 or 3 is characterized in that:
in the step B or E, the optimal bandwidth satisfying time t is calculated by adopting a PID algorithm to the formula (2)3At t2≤t3≤t4Calculating the optimal bandwidth provided by the edge server j for the vehicle i within the range; when in use
Figure BDA0002910551660000182
When the step f is performed, go to step f
Figure BDA0002910551660000183
Entering step g;
step f is as follows:
and the bandwidth is adjusted by adopting a PID algorithm, so that the problem that the data stream of the buffer area is processed when the vehicle leaves the cell is solved:
under the condition of satisfying the above-mentioned solution bandwidth range, firstly, the initial bandwidth b is set0Substituting equation (9) to calculate the time t for finishing processing the buffer3：
Figure BDA0002910551660000184
Then, the target value t is determined4And time t3When the difference e is larger than or equal to a set value d, adjusting the bandwidth
Figure BDA0002910551660000185
Then the new bandwidth is added
Figure BDA0002910551660000186
Substituting equation (9) to calculate the new time t3；
Recalculating the difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and calculating the time t3Bandwidth of
Figure BDA0002910551660000187
To meet the required optimal bandwidth, when time t3＝t4When the vehicle just leaves the cell, the buffer zone is processed, and the bandwidth at the moment
Figure BDA0002910551660000191
Maximum bandwidth to meet the requirements; by Matlab simulation, a simulation diagram is obtained by solving the problem that buffer zone data is not processed when a vehicle leaves a cell by a bandwidth allocation method in consideration of the influence of different initial positions and vehicle speeds on bandwidth allocation, as shown in FIG. 6(a) and FIG. 6 (b). As can be seen from the simulation diagrams of fig. 6(a) and 6(b), the bandwidth allocation is independent of the speed size, and is only related to the initial position.
Step g is as follows:
and the PID algorithm is adopted to adjust the bandwidth, so that the problem of processing the data stream of the buffer area when the vehicle leaves the cell is solved. Under the condition of satisfying the above-mentioned solution bandwidth range, firstly, the initial bandwidth b is set0Substituting equation (10) to calculate the time t for finishing processing the buffer3；
Figure BDA0002910551660000192
Then, the target value t is determined4And time t3When the difference e is larger than or equal to a set value d, adjusting the bandwidth
Figure BDA0002910551660000193
Then the new bandwidth is added
Figure BDA0002910551660000194
Substituting equation (10) to calculate the new time t3；
Recalculating the difference e, iterating for multiple times until the difference e is smaller than a set threshold value, jumping out of the loop, and calculating the time t3Bandwidth of
Figure BDA0002910551660000195
To meet the required optimal bandwidth, when time t3＝t4When the vehicle just leaves the cell, the buffer zone is processed, and the bandwidth at the moment
Figure BDA0002910551660000196
To meet the required maximum bandwidth. By Matlab simulation, a simulation diagram is obtained by solving the problem that buffer zone data is not processed when a vehicle leaves a cell by a bandwidth allocation method in consideration of the influence of different initial positions and vehicle speeds on bandwidth allocation, as shown in FIG. 6(a) and FIG. 6 (b).
Example 7
A computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method for joint bandwidth allocation and data stream offloading based on MEC single-vehicle single-cell according to any of embodiments 1-6 when executing the computer program.
Example 8
A computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of any of the MEC single car cell based joint bandwidth allocation and data stream offloading methods of embodiments 1-6.

Claims (8)

1.一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，是指：车辆在离开小区时，该小区内完成总的数据流时，计算出车辆总数据流的最低时延ts；车辆在离开小区时，该小区内未完成总的数据流时，边缘服务器通过分配最优带宽方法，解决边缘服务器缓冲区拥堵问题和车辆发生小区切换时边缘服务器缓冲区数据流未处理完问题，并使车辆数据上传量最大。1. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single cell, it is characterized in that: refer to: when vehicle leaves cell, when completing total data flow in this cell, calculates the minimum value of vehicle total data flow. Time delay t s ; when the vehicle leaves the cell, when the total data flow is not completed in the cell, the edge server solves the edge server buffer congestion problem by assigning the optimal bandwidth method and the edge server buffer data flow when the vehicle switches between cells Unfinished issues and maximized vehicle data uploads. 2.根据权利要求1所述的一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，车辆i在该小区内完成总数据流，根据边缘服务器j分配车辆i最优带宽方法，计算出处理完车辆总数据流的最低总时延ts，包括步骤如下：2. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single cell according to claim 1, it is characterized in that, vehicle i completes total data flow in this cell, according to edge server j allocating vehicle i optimal The bandwidth method calculates the minimum total delay ts after processing the total data flow of the vehicle, including the following steps: A、根据式(1)，给定一个初始带宽b0，在满足边缘服务器j缓冲区最大容量的条件下，采用PID算法计算出边缘服务器j为车辆i提供的最大带宽bij，bij＝b1，在边缘服务器j提供车辆i的带宽b范围满足b＝[b0,b1]；A. According to formula (1), given an initial bandwidth b 0 , under the condition that the maximum buffer capacity of edge server j is satisfied, the PID algorithm is used to calculate the maximum bandwidth b ij provided by edge server j for vehicle i, b ij = b 1 , the bandwidth b of the vehicle i provided by the edge server j satisfies b=[b 0 , b 1 ];
Figure FDA0002910551650000011
Figure FDA0002910551650000011
 式(1)中，在城郊或者高速公路上有N个边缘服务器为车辆提供通信、存储、计算资源，边缘服务器j服务的小区内有M辆车行驶，j＝{1,...,N}，边缘服务器j服务的小区内某辆车i匀速直线行驶，i＝{1,...,M}，在小区内某个位置向边缘服务器发送任务卸载请求；In formula (1), there are N edge servers on the suburbs or highways to provide communication, storage, and computing resources for vehicles, and there are M vehicles running in the cell served by edge server j, j={1,...,N }, a vehicle i in the cell served by the edge server j runs in a straight line at a constant speed, i={1,...,M}, and sends a task offloading request to the edge server at a certain position in the cell; 车辆i在边缘服务器j服务的小区内以速度vij匀速直线行驶，在某个初始位置aij开始向边缘服务器j发送数据流直到离开该小区，车辆i在小区内行驶所需要的时间为t4：
Figure FDA0002910551650000012
车辆在离开小区时该小区内完成总的数据流，是指：车辆在0≤t≤t4时间段内完成了数据流卸载计算；Vehicle i travels in a straight line at a constant speed v ij in the cell served by edge server j, and starts to send data stream to edge server j at a certain initial position a ij until it leaves the cell, the time required for vehicle i to travel in the cell is t 4 :
Figure FDA0002910551650000012
When the vehicle leaves the cell, the total data flow is completed in the cell, which means: the vehicle completes the data flow unloading calculation within the time period of 0≤t≤t4 ; Pij是车辆i在边缘服务器j的上行传输功率，hij是车辆i在边缘服务器j的小尺度衰落路径损耗，N0是边缘服务器j接收段的噪声功率谱密度；边缘服务器j服务的高度为Hj米，到路面的水平距离为Dj米，辐射的范围直径为LC米，k是每比特需要CPU的转数，ε是指缓冲区最大存储量；P ij is the uplink transmission power of vehicle i at edge server j, h ij is the small-scale fading path loss of vehicle i at edge server j, N 0 is the noise power spectral density of the receiving section of edge server j; the height served by edge server j is H j meters, the horizontal distance to the road is D j meters, the diameter of the radiation range is L C meters, k is the number of CPU revolutions required per bit, and ε refers to the maximum storage capacity of the buffer; t1是第一次上传速率等于边缘服务器计算速率的时刻，t2是第二次上传速率等于边缘服务器计算速率的时刻，t3是处理完边缘服务器缓冲区数据流的时刻，ts是在该小区内完成车辆数据流的总时延，ξ是上传速率随时间积分的积分参数，fj是边缘服务器j CPU每秒的转数，Rij(0)是t＝0时的车辆i上传速率；t 1 is the moment when the first upload rate is equal to the computing rate of the edge server, t 2 is the moment when the second upload rate is equal to the computing rate of the edge server, t 3 is the moment when the buffer data stream of the edge server is processed, and t s is The total delay of completing the vehicle data flow in the cell, ξ is the integral parameter of the upload rate integrated over time, f j is the number of revolutions per second of the CPU of the edge server j, and R ij (0) is the upload of the vehicle i at t=0 rate; B、根据步骤A计算出的带宽b范围，b∈[b0,b1]，在满足车辆i离开小区时计算完缓冲区数据流的条件下，bij采用PID算法对公式(2)计算出边缘服务器j为车辆i提供的最大带宽bij，bij＝b2；在边缘服务器j提供车辆i的带宽b范围满足b∈[b0,b2],b2∈[b0,b1]；B. According to the range of bandwidth b calculated in step A, b∈[b 0 ,b 1 ], under the condition that the buffer data flow is calculated when vehicle i leaves the cell, b ij is calculated by PID algorithm to formula (2) The maximum bandwidth b ij provided by edge server j for vehicle i, b ij =b 2 ; the range of bandwidth b provided by edge server j for vehicle i satisfies b∈[b 0 ,b 2 ],b 2 ∈[b 0 ,b 1 ];
Figure FDA0002910551650000021
Figure FDA0002910551650000021
 C、根据步骤A及步骤B计算出的满足约束条件的带宽b范围b∈[b0,b2]，如果车辆i数据流Si满足Si≤S时，通过PID算法调整带宽方法，在没有边缘服务器j缓冲区存储数据流情况下求解出最大带宽bij，使得目标函数总时延ts最低，即ts＝t1，计算总时延如式(3)所示；如果车辆i数据流Si满足Si＞S时，通过PID算法调整带宽，在缓冲区存储数据流不大于缓冲区最大容量情况下求解出最大带宽bij，在已知的带宽范围内，通过PID算法调整带宽方法，求解出最优带宽bij，使得目标函数总时延ts最低，并且满足总时延ts在t2＜t3≤ts≤t4范围内，式(3)如下所示：C. According to the bandwidth b range b∈[b 0 ,b 2 ] that satisfies the constraint conditions calculated in step A and step B, if the data stream Si of vehicle i satisfies Si ≤S , adjust the bandwidth method by PID algorithm, in The maximum bandwidth b ij is obtained without the edge server j buffer storing the data stream, so that the total delay ts of the objective function is the lowest, that is, ts = t 1 , and the total delay is shown in equation (3). When the data stream Si satisfies Si > S , the bandwidth is adjusted by the PID algorithm, and the maximum bandwidth b ij is obtained when the data stream stored in the buffer is not greater than the maximum capacity of the buffer. Within the known bandwidth range, the PID algorithm is used to adjust Using the bandwidth method, the optimal bandwidth b ij is obtained, so that the total time delay t s of the objective function is the lowest, and the total time delay t s is within the range of t 2 <t 3 ≤ t s ≤ t 4 , formula (3) is as follows :
Figure FDA0002910551650000031
Figure FDA0002910551650000031
 式(3)中，R(ξ)是ξ在0～ts时间内任意时刻的上传速率，Si是车辆i需要计算的数据流的大小，单位是比特。In Equation (3), R(ξ) is the upload rate of ξ at any time between 0 and t s , and S i is the size of the data stream that vehicle i needs to calculate, in bits. 3.根据权利要求2所述的一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，车辆在离开小区时，该小区内未完成总的数据流时，边缘服务器通过分配最优带宽方法，解决边缘服务器缓冲区拥堵问题和车辆发生小区切换时边缘服务器缓冲区数据流未处理完问题，并使车辆数据上传量最大，包括步骤如下：3. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single-cell according to claim 2, it is characterized in that, when the vehicle leaves the cell, when the total data flow is not completed in the cell, the edge server passes through. The optimal bandwidth allocation method solves the problem of edge server buffer congestion and the problem that the edge server buffer data stream is not processed when the vehicle is switched between cells, and maximizes the amount of vehicle data upload, including the following steps: D、根据式(1)，给定一个初始带宽b0，在满足边缘服务器j缓冲区最大容量的条件下，采用PID算法计算出边缘服务器j为车辆i提供的最大带宽bij，bij＝b1，在边缘服务器j提供车辆i的带宽范围满足b＝[b0,b1]；D. According to formula (1), given an initial bandwidth b 0 , under the condition that the maximum buffer capacity of edge server j is satisfied, the PID algorithm is used to calculate the maximum bandwidth b ij provided by edge server j for vehicle i, b ij = b 1 , the bandwidth range of the vehicle i provided by the edge server j satisfies b=[b 0 , b 1 ]; E、根据步骤D计算出的带宽b范围，b∈[b0,b1]，在满足车辆i离开小区时计算完缓冲区数据流的条件下，bij采用PID算法对公式(2)计算出边缘服务器j为车辆i提供的最大带宽bij，bij＝b2；在边缘服务器j提供车辆i的带宽b范围满足b∈[b0,b2],b2∈[b0,b1]；E. According to the range of bandwidth b calculated in step D, b∈[b 0 ,b 1 ], under the condition that the buffer data stream is calculated when vehicle i leaves the cell, b ij is calculated by PID algorithm to formula (2) The maximum bandwidth b ij provided by edge server j for vehicle i, b ij =b 2 ; the range of bandwidth b provided by edge server j for vehicle i satisfies b∈[b 0 ,b 2 ],b 2 ∈[b 0 ,b 1 ]; F、根据步骤D及步骤E计算出的满足约束条件的带宽b范围，b∈[b0,b2]，在已知的带宽范围内，通过带宽调整的方法，求解出最优带宽bij，bij＝b2，根据车辆i在边缘服务器j小区内行驶的时间t，t＝t4，求解出目标函数最大的数据量Sij，如式(4)所示：F. According to the range of bandwidth b that satisfies the constraints calculated in step D and step E, b∈[b 0 ,b 2 ], within the known bandwidth range, the optimal bandwidth b ij is obtained by the method of bandwidth adjustment , b ij =b 2 , according to the time t, t=t 4 that the vehicle i travels in the edge server j cell, the maximum data amount S ij of the objective function is obtained, as shown in formula (4):
Figure FDA0002910551650000041
Figure FDA0002910551650000041
 式(4)中，R(ξ)是ξ在0～ts时间内任意时刻的上传速率Sij是车辆i在边缘服务器j小区内上传的数据量，单位是比特。In formula (4), R(ξ) is the upload rate of ξ at any time between 0 and t s . S ij is the amount of data uploaded by vehicle i in the cell of edge server j, and the unit is bits. 4.根据权利要求3所述的一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，步骤A、步骤D之前均执行以下步骤，包括：4. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single cell according to claim 3, is characterized in that, before step A, step D, all execute the following steps, comprising: a、计算初始带宽b0：当
Figure FDA0002910551650000042
和t＝0时，
Figure FDA0002910551650000043
求解出初始带宽b0，b0≤Bj；a. Calculate the initial bandwidth b 0 : when
Figure FDA0002910551650000042
and t=0,
Figure FDA0002910551650000043
Solve the initial bandwidth b 0 , b 0 ≤B j ; a0是指边缘服务器j通信范围的半径，即
Figure FDA0002910551650000044
其中LC是边缘服务器通信直径；当
Figure FDA0002910551650000045
和t＝0时，Rij(0)是t＝0时的车辆i在边缘服务器j最近的位置的上传速率；a 0 refers to the radius of the communication range of the edge server j, that is
Figure FDA0002910551650000044
where L C is the edge server communication diameter; when
Figure FDA0002910551650000045
and when t=0, R ij (0) is the upload rate of vehicle i at the nearest position of edge server j at t=0; b、判断初始位置aij与
Figure FDA0002910551650000046
的关系，当
Figure FDA0002910551650000047
时，计算Rij(0)：b. Determine the initial position a ij and
Figure FDA0002910551650000046
relationship, when
Figure FDA0002910551650000047
When , compute R ij (0):
Figure FDA0002910551650000048
Figure FDA0002910551650000048
 即在
Figure FDA0002910551650000049
时，该时间点上传并计算的数据流加上车载终端计算的数据流总和S如式(5)所示：that is
Figure FDA0002910551650000049
, the sum S of the data stream uploaded and calculated at this time point plus the data stream calculated by the vehicle terminal is shown in formula (5):
Figure FDA00029105516500000410
Figure FDA00029105516500000410
 c、将数据流总和S与车辆i的总数据流Si进行比对，如果Si≤S，采用PID算法将初始带宽b0带入公式(6)计算出差值e：c. Compare the total data flow S i with the total data flow S i of the vehicle i, if S i ≤ S, use the PID algorithm to bring the initial bandwidth b 0 into formula (6) to calculate the difference e:
Figure FDA0002910551650000051
Figure FDA0002910551650000051
 当差值e大于等于设定阈值时，增加初始带宽b0，增加的系数为c；带宽bij＝b0+ce，bij≤Bj，计算
Figure FDA0002910551650000052
得出时间点t1，t1为第一次上传速率等于边缘服务器计算速率的时间点；When the difference e is greater than or equal to the set threshold, increase the initial bandwidth b 0 , and the increased coefficient is c; the bandwidth b ij =b 0 +ce, b ij ≤B j , calculate
Figure FDA0002910551650000052
The time point t 1 is obtained, and t 1 is the time point when the first upload rate is equal to the computing rate of the edge server; 再将新的带宽bij带入公式(6)，计算出新的差值e，多次迭代，直到差值e小于设定的阈值跳出循环，即求出满足车辆总数据量计算最低总时延的带宽bij；数据流没有存储缓冲区，不需要在t2时间点之后释放计算能力处理缓冲区数据流，t2为第二次上传速率等于边缘服务器计算速率的时间点因此最低总时延为ts＝t1；Then bring the new bandwidth b ij into the formula (6), calculate the new difference e, and iterate multiple times until the difference e is less than the set threshold and jump out of the loop, that is, to find the minimum total time that satisfies the calculation of the total data volume of the vehicle. The extended bandwidth b ij ; the data stream has no storage buffer, and it is not necessary to release the computing power to process the buffer data stream after the time point t 2 , t 2 is the time point when the second upload rate is equal to the computing rate of the edge server, so the minimum total time Extend as t s =t 1 ; 如果Si＞S，进入步骤A或步骤D。If S i > S, go to step A or step D. 5.根据权利要求3所述的一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，步骤A或步骤D中，给定一个初始带宽b0，采用PID算法计算出边缘服务器j为车辆i提供的最优带宽：当
Figure FDA0002910551650000053
时，进入步骤d，当
Figure FDA0002910551650000054
时，进入步骤e；5. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single cell according to claim 3, is characterized in that, in step A or step D, given an initial bandwidth b 0 , adopt PID algorithm to calculate The optimal bandwidth provided by edge server j for vehicle i: when
Figure FDA0002910551650000053
, go to step d, when
Figure FDA0002910551650000054
, enter step e; 步骤d是指：Step d means: 采用PID算法，计算在时间t1和t2之间的数据流上传缓冲区存储量小于等于最大缓冲区存储量ε：Using the PID algorithm, calculate that the upload buffer storage capacity of the data stream between time t 1 and t 2 is less than or equal to the maximum buffer storage capacity ε: 首先，将初始带宽b0带入公式
Figure FDA0002910551650000055
得出时间点t1和t2；First, bring the initial bandwidth b 0 into the formula
Figure FDA0002910551650000055
obtain time points t 1 and t 2 ; 然后，将初始带宽b0带入公式(7)计算出目标值ε与在时间t1和t2之间的缓冲区的数据流差值e：Then, the initial bandwidth b 0 is brought into formula (7) to calculate the target value ε and the data flow difference e of the buffer between times t 1 and t 2 :
Figure FDA0002910551650000056
Figure FDA0002910551650000056
 当差值e大于等于设定值c，调整带宽bij＝b0+ce，bij≤Bj；When the difference e is greater than or equal to the set value c, adjust the bandwidth b ij =b 0 +ce, b ij ≤B j ; 再将新的带宽bij带入公式(7)重新计算差值e，多次迭代，直到差值e小于设定的阈值跳出循环，计算出满足条件的最优带宽bij；Then bring the new bandwidth b ij into formula (7) to recalculate the difference e, and iterate multiple times until the difference e is less than the set threshold and jump out of the loop, and calculate the optimal bandwidth b ij that satisfies the condition; 步骤e是指：Step e means: 满足
Figure FDA0002910551650000061
条件时，首先，将初始带宽b0带入公式
Figure FDA0002910551650000062
得出时间点t1和t2，此时求解的时间点t1是负数，取t1＝0；然后，将初始带宽b0带入公式(8)计算出目标值ε与在时间t1和t2之间的缓冲区的数据流差值e；Satisfy
Figure FDA0002910551650000061
condition, first, bring the initial bandwidth b 0 into the formula
Figure FDA0002910551650000062
The time points t 1 and t 2 are obtained. At this time, the time point t 1 to be solved is a negative number, and t 1 = 0 is taken; then, the initial bandwidth b 0 is brought into formula (8) to calculate the target value ε and the and the data flow difference e of the buffer between t 2 ;
Figure FDA0002910551650000063
Figure FDA0002910551650000063
 当差值e大于等于设定值c，调整带宽bij＝b0+ce，bij≤Bj；再将新的带宽bij带入公式(8)重新计算差值e，多次迭代，直到差值e小于设定的阈值跳出循环，计算出满足条件的最优带宽bij。When the difference e is greater than or equal to the set value c, adjust the bandwidth b ij =b 0 +ce, b ij ≤B j ; then bring the new bandwidth b ij into formula (8) to recalculate the difference e, and iterate several times, Until the difference e is smaller than the set threshold, the loop is jumped out, and the optimal bandwidth b ij that satisfies the condition is calculated. 6.根据权利要求3所述的一种基于MEC单车单小区的联合带宽分配与数据流卸载方法，其特征在于，步骤B或E中，采用PID算法对公式(2)计算出最优带宽满足时间t3在t2≤t3≤t4范围内计算出边缘服务器j为车辆i提供的最优带宽；当
Figure FDA0002910551650000064
时，进入步骤f，当
Figure FDA0002910551650000065
时，进入步骤g；6. a kind of joint bandwidth allocation and data stream unloading method based on MEC single-vehicle single cell according to claim 3, is characterized in that, in step B or E, adopt PID algorithm to calculate optimal bandwidth to formula (2) and satisfy At time t 3 , the optimal bandwidth provided by edge server j for vehicle i is calculated within the range of t 2 ≤ t 3 ≤ t 4 ; when
Figure FDA0002910551650000064
, go to step f, when
Figure FDA0002910551650000065
, enter step g; 步骤f是指：Step f means: 采用PID算法调整带宽，解决车辆离开小区时处理完缓冲区的数据流问题：The PID algorithm is used to adjust the bandwidth to solve the data flow problem after the buffer is processed when the vehicle leaves the cell: 首先，将初始带宽b0带入公式(9)计算出处理完缓冲区的时间t3：First, bring the initial bandwidth b 0 into formula (9) to calculate the time t 3 when the buffer is processed:
Figure FDA0002910551650000066
Figure FDA0002910551650000066
 然后，判断目标值t4与时间t3差值e，当差值e大于等于设定值d，调整带宽
Figure FDA0002910551650000067
bij≤Bj，再将新的带宽
Figure FDA0002910551650000071
带入公式(9)计算出新的时间t3；Then, determine the difference e between the target value t 4 and the time t 3 , when the difference e is greater than or equal to the set value d, adjust the bandwidth
Figure FDA0002910551650000067
b ij ≤B j , then use the new bandwidth
Figure FDA0002910551650000071
Bring into formula (9) to calculate the new time t 3 ; 重新计算差值e，多次迭代，直到差值e小于设定的阈值跳出循环，计算出时间t3的带宽
Figure FDA0002910551650000072
为满足要求的最优带宽，当时间t3＝t4时，车辆在刚离开小区时处理完缓冲区，此时的带宽
Figure FDA0002910551650000073
为满足要求的最大值带宽；Recalculate the difference e, and iterate multiple times until the difference e is less than the set threshold to jump out of the loop, and calculate the bandwidth at time t 3
Figure FDA0002910551650000072
In order to meet the required optimal bandwidth, when the time t 3 =t 4 , the vehicle has finished processing the buffer when it just left the cell, and the bandwidth at this time is
Figure FDA0002910551650000073
To meet the maximum bandwidth required; 步骤g是指：Step g means: 首先，将初始带宽b0带入公式(10)计算出处理完缓冲区的时间t3；First, bring the initial bandwidth b 0 into formula (10) to calculate the time t 3 when the buffer is processed;
Figure FDA0002910551650000074
Figure FDA0002910551650000074
 然后，判断目标值t4与时间t3差值e，当差值e大于等于设定值d，调整带宽
Figure FDA0002910551650000075
bij≤Bj，再将新的带宽
Figure FDA0002910551650000076
带入公式(10)计算出新的时间t3；Then, determine the difference e between the target value t 4 and the time t 3 , when the difference e is greater than or equal to the set value d, adjust the bandwidth
Figure FDA0002910551650000075
b ij ≤B j , then use the new bandwidth
Figure FDA0002910551650000076
Bring into formula (10) to calculate the new time t 3 ; 重新计算差值e，多次迭代，直到差值e小于设定的阈值跳出循环，计算出时间t3的带宽
Figure FDA0002910551650000077
为满足要求的最优带宽，当时间t3＝t4时，车辆在刚离开小区时处理完缓冲区，此时的带宽
Figure FDA0002910551650000078
为满足要求的最大值带宽。Recalculate the difference e, and iterate multiple times until the difference e is less than the set threshold to jump out of the loop, and calculate the bandwidth at time t 3
Figure FDA0002910551650000077
In order to meet the required optimal bandwidth, when the time t 3 =t 4 , the vehicle has finished processing the buffer when it just left the cell, and the bandwidth at this time is
Figure FDA0002910551650000078
to meet the required maximum bandwidth. 7.一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1-6任一所述基于MEC单车单小区的联合带宽分配与数据流卸载方法的步骤。7. A computer device comprising a memory and a processor, wherein the memory is stored with a computer program, wherein, when the processor executes the computer program, any one of claims 1-6 is realized based on the MEC single-vehicle single cell The steps of the joint bandwidth allocation and data flow offloading method. 8.一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1-6任一所述基于MEC单车单小区的联合带宽分配与数据流卸载方法的步骤。8. A computer-readable storage medium having a computer program stored thereon, is characterized in that, when the computer program is executed by the processor, the joint bandwidth allocation based on the MEC single-vehicle single-cell described in any of claims 1-6 and The steps of the data flow offloading method.
CN202110085210.5A 2021-01-22 2021-01-22 Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell Active CN112929412B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110085210.5A CN112929412B (en) 2021-01-22 2021-01-22 Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110085210.5A CN112929412B (en) 2021-01-22 2021-01-22 Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell

Publications (2)

Publication Number Publication Date
CN112929412A true CN112929412A (en) 2021-06-08
CN112929412B CN112929412B (en) 2022-03-11

Family

ID=76164412

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110085210.5A Active CN112929412B (en) 2021-01-22 2021-01-22 Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell

Country Status (1)

Country Link
CN (1) CN112929412B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115242649A (en) * 2022-07-26 2022-10-25 白犀牛智达(北京)科技有限公司 Data returning method and system
CN116249142A (en) * 2023-05-06 2023-06-09 南京邮电大学 Joint optimization method for perception task offloading and resource allocation and related devices

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109041130A (en) * 2018-08-09 2018-12-18 北京邮电大学 Resource allocation methods based on mobile edge calculations
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 A joint optimization method for task offloading and resource allocation in mobile edge computing networks
US20190335520A1 (en) * 2018-04-27 2019-10-31 Nokia Solutions And Networks Oy Traffic steering for stateless packets over multipath networks
CN111010684A (en) * 2019-12-17 2020-04-14 重庆邮电大学 Internet of vehicles resource allocation method based on MEC cache service
JP2020072278A (en) * 2018-10-29 2020-05-07 三菱電機株式会社 Vehicle communication system and communication method of the same
CN111918245A (en) * 2020-07-07 2020-11-10 西安交通大学 Computing task offloading and resource allocation method based on multi-agent vehicle speed perception
CN112188442A (en) * 2020-11-16 2021-01-05 西南交通大学 Vehicle networking data-driven task unloading system and method based on mobile edge calculation

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190335520A1 (en) * 2018-04-27 2019-10-31 Nokia Solutions And Networks Oy Traffic steering for stateless packets over multipath networks
CN109041130A (en) * 2018-08-09 2018-12-18 北京邮电大学 Resource allocation methods based on mobile edge calculations
JP2020072278A (en) * 2018-10-29 2020-05-07 三菱電機株式会社 Vehicle communication system and communication method of the same
CN109814951A (en) * 2019-01-22 2019-05-28 南京邮电大学 A joint optimization method for task offloading and resource allocation in mobile edge computing networks
CN111010684A (en) * 2019-12-17 2020-04-14 重庆邮电大学 Internet of vehicles resource allocation method based on MEC cache service
CN111918245A (en) * 2020-07-07 2020-11-10 西安交通大学 Computing task offloading and resource allocation method based on multi-agent vehicle speed perception
CN112188442A (en) * 2020-11-16 2021-01-05 西南交通大学 Vehicle networking data-driven task unloading system and method based on mobile edge calculation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王寒松: "车联网中基于MEC的计算任务卸载策略研究", 《中国优秀硕士学位论文全文数据库》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115242649A (en) * 2022-07-26 2022-10-25 白犀牛智达(北京)科技有限公司 Data returning method and system
CN115242649B (en) * 2022-07-26 2023-10-31 白犀牛智达(北京)科技有限公司 Data return method and system
CN116249142A (en) * 2023-05-06 2023-06-09 南京邮电大学 Joint optimization method for perception task offloading and resource allocation and related devices

Also Published As

Publication number Publication date
CN112929412B (en) 2022-03-11

Similar Documents

Publication Publication Date Title
CN111132077B (en) D2D-based multi-access edge computing task offloading method in the Internet of Vehicles environment
CN109391681B (en) MEC-based V2X mobility prediction and content cache offloading scheme
CN110035410B (en) A method for joint resource allocation and computational offloading in software-defined in-vehicle edge networks
CN110650457B (en) Joint optimization method for task unloading calculation cost and time delay in Internet of vehicles
CN115277845B (en) Internet of vehicles distributed edge cache decision method based on multi-agent near-end strategy
CN110012039B (en) ADMM-based task allocation and power control method in Internet of vehicles
CN112512013B (en) Learning pruning-based vehicle networking mobile edge computing task unloading method and system
Li et al. Compound model of task arrivals and load-aware offloading for vehicular mobile edge computing networks
CN111935303B (en) Task unloading method based on intention perception in air-ground integrated Internet of vehicles
CN111339554A (en) User data privacy protection method based on mobile edge computing
CN111010684A (en) Internet of vehicles resource allocation method based on MEC cache service
CN112929412B (en) Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell
CN115052262B (en) A method for computing offloading and power optimization in Internet of Vehicles based on potential game
CN115209426A (en) Dynamic deployment method of digital twin servers in edge internet of vehicles
CN116030623A (en) Collaborative path planning and scheduling method based on blockchain in cognitive Internet of vehicles scene
CN113709249B (en) Safe balanced unloading method and system for driving assisting service
CN108093443B (en) Multi-service vehicle-ground communication bandwidth distribution system and method
CN114449477A (en) Internet of vehicles content distribution method based on edge cache and immune clone strategy
CN114189869A (en) Collaborative path planning and resource allocation method for unmanned vehicles based on edge computing
CN113691956B (en) Internet of vehicles mobility management method based on SDN and MEC
CN116634396A (en) Graph attention-based content caching decision method for multi-agent edge computing in Internet of Vehicles
CN116405569A (en) Task unloading matching method and system based on vehicle and edge computing server
CN114928611B (en) IEEE802.11p protocol-based energy-saving calculation unloading optimization method for Internet of vehicles
Mensah et al. A game-theoretic approach to computation offloading in software-defined D2D-enabled vehicular networks
Hong et al. An optimal resource allocation mechanism in vehicular MEC systems

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