CN116405569A - Task unloading matching method and system based on vehicle and edge computing server - Google Patents
Task unloading matching method and system based on vehicle and edge computing server Download PDFInfo
- Publication number
- CN116405569A CN116405569A CN202211612847.6A CN202211612847A CN116405569A CN 116405569 A CN116405569 A CN 116405569A CN 202211612847 A CN202211612847 A CN 202211612847A CN 116405569 A CN116405569 A CN 116405569A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- server
- vehicles
- steps
- task
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000005265 energy consumption Methods 0.000 claims abstract description 54
- 230000005540 biological transmission Effects 0.000 claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims abstract description 47
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000001174 ascending effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000001133 acceleration Effects 0.000 claims description 6
- 239000000654 additive Substances 0.000 claims description 3
- 230000000996 additive effect Effects 0.000 claims description 3
- 238000009954 braiding Methods 0.000 claims description 3
- 238000003825 pressing Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/509—Offload
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of information and communication engineering, and particularly relates to a task unloading matching method and system based on a vehicle and an edge computing server. The method comprises the following steps: s1, an initialization stage: the central control center MBS collects basic information of vehicles and roadside units RSU; s2, calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by considering random movement of the vehicles and various uploading rate calculation methods; s3, establishing an optimization model taking joint optimization task unloading time delay and energy consumption as targets and taking task unloading decision and random movement of a vehicle as constraints; and S4, solving the model established in the step S3 by adopting a matching algorithm based on cost minimization, and obtaining the final matching condition of the vehicle server. The invention has the characteristics of being capable of jointly optimizing time delay and energy consumption and considering mobility and transmission reliability of vehicles.
Description
Technical Field
The invention belongs to the technical field of information and communication engineering, and particularly relates to a task unloading matching method and system based on a vehicle and an edge computing server.
Background
With the rapid development of vehicle networks, how to process massive data of computationally intensive tasks in time is urgent. Because of the limited computing and battery resources of the vehicle, the vehicle cannot meet all computing demands. Traditional solutions are to upload tasks to the cloud to aid in computation, but due to the huge delay, it is impractical to require all vehicles to interact directly with the cloud. Transmitting large amounts of data to the cloud will put tremendous strain on the network bandwidth. Meanwhile, the security of user privacy data is difficult to ensure by traditional cloud computing. Mobile edge computing (MEC, mobile edge computing) is a new promising solution to the vehicle resource constraint challenges that can deploy edge computing infrastructure in roadside units (RSUs) and offload computing tasks from the vehicle to edge servers. The Mobile Edge Computing (MEC) enables computing resources to be closer to the Internet of vehicles, and has the characteristics of low time delay, large bandwidth, high reliability and the like.
Task offloading is a very important problem in moving edge computing. The prior art investigated the impact of vehicle mobility on computational offloading. However, these works mostly only consider constant movement of the vehicle speed, which is not a true vehicle running mode. In addition, the mobility of the vehicle also affects the wireless channel, requiring consideration of various uplink transmission rates. However, most efforts only assume that the uplink transmission rate is constant within the coverage of one roadside unit RSU. Previous studies only consider time delays or energy consumption in vehicle edge calculations and do not jointly optimize both for better performance. Therefore, how to combine the above matters is a urgent problem to be solved.
For example, a task offloading method based on mobile edge calculation in the internet of vehicles described in chinese patent document with application number of cn202210242936.X, the method includes: constructing a multi-edge server joint unloading model; acquiring an unloading task of a vehicle, and constructing an unloading base station selection vector according to the unloading task of the vehicle; calculating the load and energy consumption for task unloading by adopting a resource allocation method based on the equivalent maximum tolerant delay according to the unloading base station selection vector; taking energy consumption as an adaptive function, and adopting a genetic algorithm to carry out iterative optimization on an unloading task of the vehicle to obtain an unloading base station selection scheme; optimizing a task unloading strategy by using reinforcement learning according to an unloading base station selection scheme to obtain a task unloading ratio and unloading power; according to the selected unloading base station, the formulated unloading ratio and the unloading power, task unloading is completed, while the total energy consumption expenditure of the system is effectively reduced, and the effectiveness of the task unloading and resource allocation of the internet of vehicles is realized, the method has the disadvantage that the problem of jointly optimizing the random movement and various uploading rates of the vehicles to obtain better performance is not considered because only the time delay or the energy consumption in the calculation of the edges of the vehicles is still considered.
Disclosure of Invention
The invention provides a task unloading matching method and a task unloading matching system based on a vehicle and an edge computing server, which can jointly optimize time delay and energy consumption and consider the mobility and transmission reliability of the vehicle, and solve the problem that the method has certain limitation because the prior task unloading method in the mobile edge computing only considers that the speed of the vehicle is constant and the uplink transmission rate is constant in the coverage area of a roadside unit RSU and does not consider the random movement and various uploading rates of the vehicle.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the task unloading matching method based on the vehicle and the edge computing server comprises the following steps:
s1, an initialization stage:
the central control center MBS collects basic information of vehicles and roadside units RSU;
s2, calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by considering random movement of the vehicles and various uploading rate calculation methods;
s3, establishing an optimization model taking joint optimization task unloading time delay and energy consumption as targets and taking task unloading decision and random movement of a vehicle as constraints;
and S4, solving the model established in the step S3 by adopting a matching algorithm based on cost minimization, and obtaining the final matching condition of the vehicle server.
Preferably, in step S1, the basic information of the vehicle and the roadside unit RSU includes a task data size of the vehicle, a calculation capability of the vehicle, an upper and lower limit of a moving speed and an acceleration, and a calculation capability of the roadside unit RSU.
Preferably, step S2 includes the steps of:
s21, set in the VEC server layer, deployRSU of different coverage areas, the set of RSUs is recorded as ,Representing the braiding of different RSUs within the coverage area;is expressed as the coverage radius of (2);For each ofThe computing resources provided by the vehicle are noted asThe method comprises the steps of carrying out a first treatment on the surface of the Network layer of vehicleVehicle composition, representing a collection of vehiclesThe method comprises the steps of carrying out a first treatment on the surface of the Binary group for vehicle taskTo represent;the data size representing the task is represented by a size of the data,representing the required CPU cycles;
s22, settingFor the length of time slot, the firstThe time slots are semi-closed intervals; dividing the coverage area of each into the same length by adopting a discretization methodIs defined between cells of (a); obtainingThe right boundary index of coverage of (c) isThe method comprises the steps of carrying out a first treatment on the surface of the Position index of roadThe method comprises the steps of carrying out a first treatment on the surface of the Vehicle with a vehicle body having a vehicle body supportFirst, thePosition of each time slotTracking through indexes corresponding to the positions of the time slots; vehicle with a vehicle body having a vehicle body supportIs the position of (2)Sum speed ofEvery time according to the following formulaUpdating once per second:
wherein,,andminimum and maximum speeds of vehicle movement, respectively;for vehiclesThe amount of speed change of the first time slot,for vehiclesFirst, theAcceleration of each time slot, subject to truncationStandard gaussian distribution on;andrespectively vehiclesA maximum deceleration value and a maximum acceleration value of (a);
s23, if the vehicleSelecting to offload to VEC server, vehicleIs composed of four parts: latency of waitingTransmission delay timeCalculating time delayTime delay of switchingThe method comprises the steps of carrying out a first treatment on the surface of the If the vehicle isSelecting a locally calculated vehicleIs the calculated time delay;
the transmission signal-to-noise ratio calculating method comprises the following steps:
wherein,,for the transmission power of the vehicle,is thatTo the point ofThe distance between the two plates is set to be equal,in order to be a path loss index,for the reference channel gain at the reference distance,is additive white noise power;
s24, uplink transmission rateDifferent transmission models and coding rate calculations are selected by signal-to-noise ratio:
vehicle with a vehicle body having a vehicle body supportIs the first of (2)Data volume transmitted in each time slotIs approximately atThe average uplink transmission rate over the time slot interval:
Transmission delay timeFor vehiclesUploading tasks to a serverThe time required satisfies the following formula:
the transmission delay must be such that the transmission is completed within the coverage of the server, i.e. the transmission delay cannot exceed the maximum transmission delay that can be uploaded at the corresponding server:
Maximum transmission delayIs the time required from the vehicle entering the server coverage to leaving the server coverage:
s25, calculating time delay as time required by processing tasks; if the vehicle isAt the local computing task, the time delay is calculatedThe method comprises the following steps:
wherein,,the frequency is calculated for the local area of the vehicle,representing the CPU cycles required for the computing task;
if the vehicle isSelective offloading to a serverCalculating, then calculating the time delayThe method comprises the following steps:
S26, at the serverWhen a vehicle moves out of the coverage range of a server during processing tasks, switching is needed, and a calculation result needs to be transmitted from a current server to a server in a range to which the position of the vehicle belongs after calculation is completed and then transmitted to the vehicle; the data quantity of the calculation result is smaller, and the feedback delay is ignored; obtaining the switching time delayThe method comprises the following steps:
wherein the method comprises the steps ofTo unload the server index of the range to which the vehicle position belongs after completion,indexing the transmitted server;the time required for completing one-time switching for two adjacent servers;
wherein,,representing a vehicleFrom entering the road to the task at the serverCalculating the number of time slots required by completion;
s27, if the vehicle selects to calculate locally, the energy consumption of the vehicleTo calculate the energy consumption:
wherein,,for a vehicleThe energy consumption cost factor of the vehicle is calculated,for the energy coefficients specified in the vehicle CPU model,for vehiclesIs a local calculation frequency of (2);
if the vehicle isSelecting to unload toCalculating the energy consumption of the vehicleThe energy consumption required for transmission:
s28, finally obtaining the vehicleIs of (2)And energy consumptionThe following expression is present:
preferably, step S3 includes the steps of:
s31, setting the optimization variable definition of task unloading asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
s32, converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the total time delay and the total energy consumption are jointly optimized, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the vehicle is occupied;
s33, modeling the total optimization problem is finally obtained as follows:
preferably, step S4 includes the steps of:
s41, adopting an algorithm based on cost minimization, firstly calculating the vehicleSelective offloading to a serverCost of (2)If the constraint condition in step S33 is not satisfied, thenIs infinite;
s42, calculating the priority of each server by the following formula:
wherein,,=1 indicates a vehicleMay be offloaded to the server, if the constraints are not met,the method comprises the steps of carrying out a first treatment on the surface of the Pressing on serverAnd (5) ascending order arrangement is carried out to obtain a server priority list.
Preferably, the step S4 further includes the steps of:
s43, setting cost values which are unloaded to different servers according to selection for each vehicle, and arranging the cost values in ascending order to be used as a preference list of the vehicles;
s44, each vehicle selects the first server in the preference list, sends a matching request, and temporarily divides the vehicles into vehicle sets of the corresponding serversNeutralizing;
processing the matching request according to the order of the server priority list; for each server, if the received matching request exceedsThe requests are arranged in an ascending order according to the cost value, and the front is arrangedThe vehicles corresponding to the matching requests are reserved; for each of the remaining vehicles, continuing to send a matching request to the next server in the preference list until a server is found that does not exceed the capacity limit, and classifying the corresponding vehicle intoNeutralizing; when all of the servers have been processed,the final vehicle server match.
The invention also provides a task unloading matching system based on the vehicle and the edge computing server, which comprises the following steps:
the initialization stage module is used for enabling the centralized control center MBS to collect basic information of vehicles and roadside units RSU;
the time delay and energy consumption calculation module is used for calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by taking into consideration random movement of the vehicles and various uploading rate calculation methods;
the model building module is used for building an optimization model which aims at jointly optimizing task unloading time delay and energy consumption and aims at task unloading decision and random movement of the vehicle as constraints;
and the model solving module is used for solving the established model by adopting a matching algorithm based on cost minimization to obtain the final matching condition of the vehicle server.
Preferably, the model building module specifically comprises:
setting the optimization variables of task offloading to be defined asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the total time delay and the total energy consumption are jointly optimized, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the occupied;
The final overall optimization problem is modeled as:
compared with the prior art, the invention has the beneficial effects that: (1) According to the method, the edge computing server is deployed on the roadside unit, and the computing task of the vehicle can be selected to be computed locally or uploaded to the server for computing; under the condition that the vehicle randomly runs, from the matching angle, optimizing an unloading scheme between the vehicle and a server to jointly optimize the time delay and the energy consumption of the system; (2) The invention is different from the previous research that the uplink transmission rate is assumed to be constant, and the invention selects different transmission models and encoding rates according to the signal to noise ratio to calculate the uplink transmission rate, thereby ensuring the reliability of transmission; (3) The matching algorithm based on the cost minimization can effectively reduce time delay and energy consumption.
Drawings
FIG. 1 is a flow chart of a method for matching task offloading based on a vehicle and an edge computing server in accordance with the present invention;
FIG. 2 is a model architecture diagram of a vehicle and edge computing server based task offload matching system of the present invention;
fig. 3 is a cost simulation diagram of different unloading algorithms for different numbers of vehicles according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention, specific embodiments of the present invention will be described below with reference to the accompanying drawings. It is evident that the drawings in the following description are only examples of the invention, from which other drawings and other embodiments can be obtained by a person skilled in the art without inventive effort.
Examples:
as shown in fig. 1, the present invention provides a task offload matching method based on a vehicle and an edge computing server, comprising the steps of:
s1, an initialization stage:
the central control center MBS collects basic information of vehicles and roadside units RSU;
s2, calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by considering random movement of the vehicles and various uploading rate calculation methods;
s3, establishing an optimization model taking joint optimization task unloading time delay and energy consumption as targets and taking task unloading decision and random movement of a vehicle as constraints;
and S4, solving the model established in the step S3 by adopting a matching algorithm based on cost minimization, and obtaining the final matching condition of the vehicle server.
The present invention contemplates a three-tier network consisting of a VEC server tier, a vehicle network tier, and a centralized control tier as shown in FIG. 1. The centralized control center gathers the required data and solves the offloading policies. In step S1, the basic information of the vehicle and the roadside unit RSU includes the task data size of the vehicle, the computing power of the vehicle, the upper and lower limits of the moving speed and the acceleration, and the computing power of the roadside unit RSU.
Step S2 further comprises the steps of:
s21, set in the VEC server layer, deployRSU of different coverage areas, the set of RSUs is recorded as ,Representing the braiding of different RSUs within the coverage area;is expressed as the coverage radius of (2);The computing resources provided for each vehicle are noted asThe method comprises the steps of carrying out a first treatment on the surface of the Network layer of vehicleVehicle composition, representing a collection of vehiclesThe method comprises the steps of carrying out a first treatment on the surface of the Binary group for vehicle taskTo represent;the data size (in bits) representing the task represents the required CPU cycles;
for simplicity, local computing may be considered to be offloaded on one server, noted as. The tasks of the vehicle can be selected to be calculated locally or can be offloaded to a server for calculation.
The vehicle in the invention adopts a random moving mode. The invention adopts a time slot base to study the system, and specifically comprises the following steps:
s22, settingFor the length of time slot, the firstThe time slots are semi-closed intervalsThe method comprises the steps of carrying out a first treatment on the surface of the Each is discretized by adopting a discretization methodThe coverage area is divided into the same lengthAs shown in fig. 2; obtainingThe right boundary index of coverage of (c) isThe method comprises the steps of carrying out a first treatment on the surface of the Position index of roadThe method comprises the steps of carrying out a first treatment on the surface of the Vehicle with a vehicle body having a vehicle body supportFirst, thePosition of each time slotTracking through indexes corresponding to the positions of the time slots; vehicle with a vehicle body having a vehicle body supportIs the position of (2)Sum speed ofEvery time according to the following formulaUpdating once per second:
wherein,,andminimum and maximum speeds of vehicle movement, respectively;for vehiclesFirst, theThe amount of speed change of the time slot,for vehiclesFirst, theAcceleration of each time slot, subject to truncationStandard gaussian distribution on;andrespectively vehiclesA maximum deceleration value and a maximum acceleration value of (a);
s23, if the vehicleSelecting to offload to VEC server, vehicleIs composed of four parts: latency of waitingTransmission delay timeCalculating time delayTime delay of switchingThe method comprises the steps of carrying out a first treatment on the surface of the If the vehicle isSelecting a locally calculated vehicleIs the calculated time delay;
wherein,,for the transmission power of the vehicle,is thatTo the point ofThe distance between the two plates is set to be equal,in order to be a path loss index,for the reference channel gain at the reference distance,is additive white noise power;
s24, uplink transmission rateBy signal-to-noise ratio selectionSelecting different transmission models and encoding rate calculation:
vehicle with a vehicle body having a vehicle body supportIs the first of (2)Data volume transmitted in each time slotIs approximately atThe average uplink transmission rate over the time slot interval:
Transmission delay timeFor vehiclesUploading tasks to a serverThe time required is full ofThe following formula is used:
the transmission delay must be such that the transmission is completed within the coverage of the server, i.e. the transmission delay cannot exceed the maximum transmission delay that can be uploaded at the corresponding server:
Maximum transmission delayIs the time required from the vehicle entering the server coverage to leaving the server coverage:
s25, calculating time delayThe time required for processing a task; if the vehicle isAt the local computing task, the time delay is calculatedThe method comprises the following steps:
wherein,,for vehiclesIs used to calculate the frequency of the local calculation of (a),representing the CPU cycles required for the computing task;
if the vehicle chooses to offload to the serverCalculating, namely calculating time delay as follows:
S26, at the serverWhen a vehicle moves out of the coverage range of a server during processing tasks, switching is needed, and a calculation result needs to be transmitted from a current server to a server in a range to which the position of the vehicle belongs after calculation is completed and then transmitted to the vehicle; the data quantity of the calculation result is smaller, and the feedback delay is ignored; obtaining the switching time delayThe method comprises the following steps:
wherein the method comprises the steps ofTo unload the server index of the range to which the vehicle position belongs after completion,indexing the transmitted server;the time required for completing one-time switching for two adjacent servers;
wherein,,representing a vehicleFrom entering the road to the task at the serverCalculating the number of time slots required by completion;
the vehicleSelecting to unload toIs not less than a thresholdThe method comprises the following steps:
s27, if the vehicle selects to calculate locally, the energy consumption of the vehicleTo calculate the energy consumption:
wherein,,as a factor of the energy consumption cost of the vehicle,for the energy coefficients specified in the vehicle CPU model,for vehiclesIs a local meter of (2)Calculating the frequency;
if the vehicle isSelectively offloading to calculation, vehicle energy consumptionThe energy consumption required for transmission:
step S3 includes the steps of:
s31, setting the optimization variable definition of task unloading asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
s32, converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the invention aims to jointly optimize the total time delay and the total energy consumption, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the vehicle is occupied;
s33, modeling the total optimization problem is finally obtained as follows:
step S4 includes the steps of:
s41, in order to solve the problem of unloading and matching of multiple vehicles and multiple servers, the invention adopts an algorithm based on cost minimization, and firstly calculates the vehiclesSelective offloading to a serverCost of (2)If the constraint condition in step S33 is not satisfied, thenIs infinite;
s42, calculating the priority of each server by the following formula:
wherein,,=1 indicates a vehicleMay be offloaded to the server, if the constraints are not met,the method comprises the steps of carrying out a first treatment on the surface of the Pressing on serverAnd (5) ascending order arrangement is carried out to obtain a server priority list.
S43, setting cost values which are unloaded to different servers according to selection for each vehicle, and arranging the cost values in ascending order to be used as a preference list of the vehicles;
s44, each vehicle selects the first server in the preference list, sends a matching request, and temporarily divides the vehicles into vehicle sets of the corresponding serversNeutralizing;
processing the matching request according to the order of the server priority list; for each server, if the received matching request exceedsAnd, toThe requests are arranged in ascending order according to the cost value, and the requests are arranged beforeThe vehicles corresponding to the matching requests are reserved; for each of the remaining vehicles, continuing to send a matching request to the next server in the preference list until a server is found that does not exceed the capacity limit, and classifying the corresponding vehicle intoNeutralizing; when all of the servers have been processed,the final vehicle server match.
The invention also provides a task unloading matching system based on the vehicle and the edge computing server, which comprises the following steps:
the initialization stage module is used for enabling the centralized control center MBS to collect basic information of vehicles and roadside units RSU;
the time delay and energy consumption calculation module is used for calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by taking into consideration random movement of the vehicles and various uploading rate calculation methods;
the model building module is used for building an optimization model which aims at jointly optimizing task unloading time delay and energy consumption and aims at task unloading decision and random movement of the vehicle as constraints;
and the model solving module is used for solving the established model by adopting a matching algorithm based on cost minimization to obtain the final matching condition of the vehicle server.
The model building module specifically comprises the following steps:
setting the optimization variables of task offloading to be defined asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the total time delay and the total energy consumption are jointly optimized, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the vehicle is occupied;
the final overall optimization problem is modeled as:
as shown in fig. 3, a cost simulation diagram under different unloading algorithms under different vehicle numbers is shown. As can be seen from fig. 3, under any number of vehicles, the matching algorithm based on the cost minimization of the method is much smaller than that of all local calculation, and the effect of reducing time delay and energy consumption is remarkable.
The invention designs a cooperation scheme between a plurality of road-side units (RSUs) and a plurality of vehicles. An edge computing server is deployed on the roadside unit, and the computing task of the vehicle can be selected to be calculated locally or uploaded to the server for calculation. Under the condition that the vehicle randomly runs, from the matching angle, an unloading scheme between the vehicle and the server is optimized so as to jointly optimize the time delay and the energy consumption of the system.
According to the method, the edge computing server is deployed on the roadside unit, and the computing task of the vehicle can be selected to be computed locally or uploaded to the server for computing; under the condition that the vehicle randomly runs, from the matching angle, optimizing an unloading scheme between the vehicle and a server to jointly optimize the time delay and the energy consumption of the system; the invention is different from the previous research that the uplink transmission rate is assumed to be constant, and the invention selects different transmission models and encoding rates according to the signal to noise ratio to calculate the uplink transmission rate, thereby ensuring the reliability of transmission; the matching algorithm based on the cost minimization can effectively reduce time delay and energy consumption.
The foregoing is only illustrative of the preferred embodiments and principles of the present invention, and changes in specific embodiments will occur to those skilled in the art upon consideration of the teachings provided herein, and such changes are intended to be included within the scope of the invention as defined by the claims.
Claims (8)
1. The task unloading matching method based on the vehicle and the edge computing server is characterized by comprising the following steps of:
s1, an initialization stage:
the central control center MBS collects basic information of vehicles and roadside units RSU;
s2, calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by considering random movement of the vehicles and various uploading rate calculation methods;
s3, establishing an optimization model taking joint optimization task unloading time delay and energy consumption as targets and taking task unloading decision and random movement of a vehicle as constraints;
and S4, solving the model established in the step S3 by adopting a matching algorithm based on cost minimization, and obtaining the final matching condition of the vehicle server.
2. The task offload matching method based on the vehicle and the edge calculation server according to claim 1, wherein in step S1, the basic information of the vehicle and the roadside unit RSU includes a task data size of the vehicle, a calculation capability of the vehicle, upper and lower limits of a moving speed and acceleration, and a calculation capability of the roadside unit RSU.
3. The vehicle and edge computing server-based task offload matching method according to claim 1, wherein step S2 includes the steps of:
s21, set in the VEC server layer, deployRSU of different coverage areas, the set of RSUs is recorded as ,Representing the braiding of different RSUs within the coverage area;is expressed as the coverage radius of (2);The computing resources provided for each vehicle are noted asThe method comprises the steps of carrying out a first treatment on the surface of the Network layer of vehicleVehicle composition, representing a collection of vehiclesThe method comprises the steps of carrying out a first treatment on the surface of the Binary group for vehicle taskTo represent;the data size representing the task is represented by a size of the data,representing the required CPU cycles;
s22, settingFor the length of time slot, the firstThe time slots are semi-closed intervalsThe method comprises the steps of carrying out a first treatment on the surface of the Each is discretized by adopting a discretization methodThe coverage area is divided into the same lengthIs defined between cells of (a); obtainingThe right boundary index of coverage of (c) isThe method comprises the steps of carrying out a first treatment on the surface of the Position index of roadThe method comprises the steps of carrying out a first treatment on the surface of the Vehicle with a vehicle body having a vehicle body supportFirst, thePosition of each time slotTracking through indexes corresponding to the positions of the time slots; vehicle with a vehicle body having a vehicle body supportIs the position of (2)Sum speed ofEvery time according to the following formulaUpdating once per second:
wherein,,andminimum and maximum speeds of vehicle movement, respectively;for vehiclesFirst, theThe amount of speed change of the time slot,for vehiclesFirst, theAcceleration of each time slot, subject to truncationStandard gaussian distribution on;andrespectively vehiclesA maximum deceleration value and a maximum acceleration value of (a);
s23, if the vehicleSelecting to offload to VEC server, vehicleIs composed of four parts: latency of waitingTransmission delay timeCalculating time delayTime delay of switchingThe method comprises the steps of carrying out a first treatment on the surface of the If the vehicle selection is calculated locally, the vehicleIs the calculated time delay;
wherein,,for the transmission power of the vehicle,is thatTo the point ofThe distance between the two plates is set to be equal,in order to be a path loss index,for the reference channel gain at the reference distance,is additive white noise power;
s24, uplink transmission rateDifferent transmission models and coding rate calculations are selected by signal-to-noise ratio:
vehicle with a vehicle body having a vehicle body supportData volume transmitted in the first time slot of (a)Is approximately atThe average uplink transmission rate over the time slot interval:
Transmission delay timeFor vehiclesUploading tasks to a serverThe time required satisfies the following formula:
the transmission delay must be such that the transmission is completed within the coverage of the server, i.e. the transmission delay cannot exceed the maximum transmission delay that can be uploaded at the corresponding server:
Maximum transmission delayIs the time required from the vehicle entering the server coverage to leaving the server coverage:
s25, calculating time delay as time required by processing tasks; if the vehicle isAt the local computing task, the time delay is calculatedThe method comprises the following steps:
wherein,,for vehiclesIs used to calculate the frequency of the local calculation of (a),representing the CPU cycles required for the computing task;
if the vehicle isSelective offloading to a serverCalculating, then calculating the time delayThe method comprises the following steps:
s26, when the server processes the task and the vehicle moves out of the coverage area of the server, switching is needed, and the calculation result is transmitted from the current server to the server in the range of the calculated vehicle position and then transmitted to the vehicle; the data quantity of the calculation result is smaller, and the feedback delay is ignored; obtaining the switching time delayThe method comprises the following steps:
wherein the method comprises the steps ofTo unload the server index of the range to which the vehicle position belongs after completion,indexing the transmitted server;the time required for completing one-time switching for two adjacent servers;
wherein,,representing a vehicleFrom entering the road to the task at the serverCalculating the number of time slots required by completion;
the vehicleSelecting to unload toIs not less than a thresholdThe method comprises the following steps:
s27, if the vehicle selects to calculate locally, the energy consumption of the vehicleTo calculate the energy consumption:
wherein,,as a factor of the energy consumption cost of the vehicle,for the energy coefficients specified in the vehicle CPU model,for vehiclesIs a local calculation frequency of (2);
if the vehicle isSelecting to unload toCalculating the energy consumption of the vehicleThe energy consumption required for transmission:
s28, finally obtaining the vehicleIs of (2)And energy consumptionThe following expression is present:
4. the vehicle and edge computing server-based task offload matching method of claim 3, wherein step S3 comprises the steps of:
s31, setting the optimization variable definition of task unloading asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
s32, converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the total time delay and the total energy consumption are jointly optimized, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the vehicle is occupied;
s33, modeling the total optimization problem is finally obtained as follows:
5. the vehicle and edge computing server-based task offload matching method of claim 4, wherein step S4 comprises the steps of:
s41, adopting an algorithm based on cost minimization, firstly calculating the vehicleSelective offloading to a serverCost of (2)If the constraint condition in step S33 is not satisfied, thenIs infinite;
s42, calculating the priority of each server by the following formula:
6. The vehicle and edge computing server-based task offload matching method of claim 5, wherein step S4 further comprises the steps of:
s43, setting cost values which are unloaded to different servers according to selection for each vehicle, and arranging the cost values in ascending order to be used as a preference list of the vehicles;
s44, each vehicle selects the first server in the preference list, sends a matching request, and temporarily divides the vehicles into vehicle sets of the corresponding serversNeutralizing;
processing the matching request according to the order of the server priority list; for each server, if the received matching request exceedsThe requests are arranged in an ascending order according to the cost value, and the front is arrangedThe vehicles corresponding to the matching requests are reserved; for each of the remaining vehicles, continuing to send a matching request to the next server in the preference list until a server is found that does not exceed the capacity limit, and classifying the corresponding vehicle intoNeutralizing; when all of the servers have been processed,the final vehicle server match.
7. A vehicle and edge computing server based task offload matching system for implementing the vehicle and edge computing server based task offload matching method of any of claims 1-6, wherein the vehicle and edge computing server based task offload matching system comprises:
the initialization stage module is used for enabling the centralized control center MBS to collect basic information of vehicles and roadside units RSU;
the time delay and energy consumption calculation module is used for calculating time delay and energy consumption between different vehicles and roadside units (RSUs) by taking into consideration random movement of the vehicles and various uploading rate calculation methods;
the model building module is used for building an optimization model which aims at jointly optimizing task unloading time delay and energy consumption and aims at task unloading decision and random movement of the vehicle as constraints;
and the model solving module is used for solving the established model by adopting a matching algorithm based on cost minimization to obtain the final matching condition of the vehicle server.
8. The vehicle and edge computing server based task offload matching system of claim 7, wherein the model building module is specifically as follows:
setting the optimization variables of task offloading to be defined asThe method comprises the steps of carrying out a first treatment on the surface of the Wherein,,representing a vehicleOffloading tasks toOtherwise, the device can be used to determine whether the current,;
converting the task unloading problem into a matching problem between the vehicle and the RSU; setting a vehicle to select only one server, and selecting one server at most simultaneouslyA server; the total time delay and the total energy consumption are jointly optimized, and the cost function of task calculation is obtained as follows:the method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresenting time delayThe weight of the vehicle is occupied;
the final overall optimization problem is modeled as:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211612847.6A CN116405569A (en) | 2022-12-15 | 2022-12-15 | Task unloading matching method and system based on vehicle and edge computing server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211612847.6A CN116405569A (en) | 2022-12-15 | 2022-12-15 | Task unloading matching method and system based on vehicle and edge computing server |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116405569A true CN116405569A (en) | 2023-07-07 |
Family
ID=87012904
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211612847.6A Pending CN116405569A (en) | 2022-12-15 | 2022-12-15 | Task unloading matching method and system based on vehicle and edge computing server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116405569A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117648182A (en) * | 2023-11-28 | 2024-03-05 | 南京审计大学 | Method for processing safety key calculation task by mobile audit equipment |
CN117648172A (en) * | 2024-01-26 | 2024-03-05 | 南京邮电大学 | Vehicle-mounted edge calculation scheduling optimization method and system |
-
2022
- 2022-12-15 CN CN202211612847.6A patent/CN116405569A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117648182A (en) * | 2023-11-28 | 2024-03-05 | 南京审计大学 | Method for processing safety key calculation task by mobile audit equipment |
CN117648172A (en) * | 2024-01-26 | 2024-03-05 | 南京邮电大学 | Vehicle-mounted edge calculation scheduling optimization method and system |
CN117648172B (en) * | 2024-01-26 | 2024-05-24 | 南京邮电大学 | Vehicle-mounted edge calculation scheduling optimization method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111786839B (en) | Calculation unloading method and system for energy efficiency optimization in vehicle-mounted edge calculation network | |
CN109068391B (en) | Internet of vehicles communication optimization algorithm based on edge calculation and Actor-Critic algorithm | |
CN109951869B (en) | Internet of vehicles resource allocation method based on cloud and mist mixed calculation | |
CN116405569A (en) | Task unloading matching method and system based on vehicle and edge computing server | |
CN111010684B (en) | Internet of vehicles resource allocation method based on MEC cache service | |
CN110650457B (en) | Joint optimization method for task unloading calculation cost and time delay in Internet of vehicles | |
CN113904947B (en) | Vehicle-road cooperative distributed edge computing task unloading and resource allocation method and system | |
CN111339554B (en) | User data privacy protection method based on mobile edge calculation | |
CN113286329B (en) | Communication and computing resource joint optimization method based on mobile edge computing | |
CN114189892A (en) | Cloud-edge collaborative Internet of things system resource allocation method based on block chain and collective reinforcement learning | |
CN111475274A (en) | Cloud collaborative multi-task scheduling method and device | |
CN112084025A (en) | Improved particle swarm algorithm-based fog calculation task unloading time delay optimization method | |
CN112188627B (en) | Dynamic resource allocation strategy based on state prediction | |
CN115209426B (en) | Dynamic deployment method for digital twin servers in edge car networking | |
CN112860429A (en) | Cost-efficiency optimization system and method for task unloading in mobile edge computing system | |
CN114928611B (en) | IEEE802.11p protocol-based energy-saving calculation unloading optimization method for Internet of vehicles | |
CN116566838A (en) | Internet of vehicles task unloading and content caching method with cooperative blockchain and edge calculation | |
CN115297171A (en) | Edge calculation unloading method and system for cellular Internet of vehicles hierarchical decision | |
CN116916386A (en) | Large model auxiliary edge task unloading method considering user competition and load | |
CN115987375A (en) | Power equipment association and resource optimization method, system and medium for converged network | |
CN113709249B (en) | Safe balanced unloading method and system for driving assisting service | |
CN112929412B (en) | Method, device and storage medium for joint bandwidth allocation and data stream unloading based on MEC single-vehicle single-cell | |
CN116634396A (en) | Graph attention-based vehicle networking multi-agent edge computing content caching decision method | |
CN116744367A (en) | Unloading method based on double-layer unloading mechanism and multi-agent algorithm under Internet of vehicles | |
CN114928893B (en) | Architecture based on intelligent reflecting surface and task unloading method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |