CN111580889A - Method, device and equipment for unloading tasks of edge server and storage medium - Google Patents
Method, device and equipment for unloading tasks of edge server and storage medium Download PDFInfo
- Publication number
- CN111580889A CN111580889A CN202010403478.4A CN202010403478A CN111580889A CN 111580889 A CN111580889 A CN 111580889A CN 202010403478 A CN202010403478 A CN 202010403478A CN 111580889 A CN111580889 A CN 111580889A
- Authority
- CN
- China
- Prior art keywords
- task
- unmanned aerial
- edge server
- aerial vehicle
- base station
- 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
Images
Classifications
-
- 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
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44594—Unloading
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The application discloses a task unloading method for an edge server, which is characterized in that on the basis of fixing the position of a base station, a personnel dense area under the current flow of people is determined by analyzing the distribution of task positions in an area, and unmanned aerial vehicles are deployed in the personnel dense area, so that the transmission distance between a user terminal and the edge server can be shortened, the task unloading speed is increased, and the path loss is reduced; and the task unloading processing is carried out according to the position relation between the task to be processed and the edge server, so that the condition that the unloading task distribution among the edge servers is uneven due to unbalanced distribution of the flow of people can be relieved, the condition that the bearing pressure of a base station erected in the area is too large, the condition that the task is delayed due to the large service pressure of the base station can be avoided, and the user experience is optimized. The application also provides an edge server task unloading device, equipment and a readable storage medium, and the edge server task unloading device has the beneficial effects.
Description
Technical Field
The present application relates to the field of mobile edge computing technologies, and in particular, to a method, an apparatus, and a device for offloading tasks of an edge server, and a readable storage medium.
Background
Smart mobile devices are currently the dominant storage and computing device for applications, supporting many computing-intensive applications, such as interactive gaming, VR/AR, online social networking services, etc., and these applications often require extremely low network latency to respond to the user's needs, meanwhile, due to limited volume and limited computing and storage capacity of mobile equipment, with the increase of population base and the development of electronic equipment, explosive data traffic growth becomes a development trend in the future, in order to solve response processing of the mobile equipment under large data traffic, edge computing (which means an open platform integrating network, computing, storage and application core capabilities and providing nearest service nearby) is required to perform computing and offloading so as to meet delay performance, and at present, a base station (GBS) and an unmanned aerial vehicle (UVA) are mainly used as edge servers to achieve task offloading.
In the related art, the smart mobile device located within the service range of the base station (and/or the drone) sends the task to the base station (and/or the drone), and invokes the base station (and/or the drone) to perform task processing to achieve computation offloading, so as to meet the delay performance. In the method, once the ground base station is constructed, the position of the ground base station is fixed, the moving track of the unmanned aerial vehicle is also fixed, but the flow direction and the flow rate of people carrying the intelligent mobile device are not fixed and irregular, the condition that the quantity of people among base stations (and/or unmanned aerial vehicles) is unbalanced at a certain moment exists, the unloading tasks are distributed unevenly, the quantity of tasks to be processed of a certain base station (and/or unmanned aerial vehicle) is far higher than the bearing level, the problems that the ground base station is overloaded or some users cannot be served are further caused, and the base stations (and/or unmanned aerial vehicles) are subjected to larger energy consumption loss while the unloading delay of tasks is larger.
Therefore, how to reduce the average time delay of the user task within the range while avoiding the excessive task bearing pressure generated for the task owner is a problem which needs to be solved urgently by the technical task in the field.
Disclosure of Invention
The method can stably keep long-term accurate task unloading of the edge server; another object of the present application is to provide an edge server task offloading device, an apparatus and a readable storage medium.
In order to solve the technical problem, the present application provides a method for offloading a task of an edge server, where the edge server includes a base station and an unmanned aerial vehicle, and the method includes:
acquiring a task position distribution map of a target area; the base station is erected in the target area;
determining a task dense region in the target region according to the task position distribution map;
deploying the drone to the mission-intensive area;
determining a task to be processed;
determining a task bearer according to the position relation between the task to be processed and the edge server;
and calling the task bearer to carry out task unloading processing.
Optionally, determining a task-dense region in the target region according to the task position distribution map includes:
connecting the tasks with the distance smaller than a first threshold value in the task position distribution diagram to obtain a task distribution undirected graph; the first threshold value is set according to the service radius of the unmanned aerial vehicle;
and calling a maximum clustering algorithm to carry out task dense region solution on the task distribution undirected graph, and taking a complete graph obtained by the solution as the task dense region.
Optionally, before invoking a maximum clique algorithm to solve the task-intensive region of the task distribution undirected graph, the method further includes:
cutting tasks of which the total number of the tasks connected in the task distribution undirected graph does not reach a second threshold value;
and the second threshold is set according to the task processing capacity of the base station and the unmanned aerial vehicle in unit time.
Optionally, deploying the drone to the mission-intensive area comprises:
if the task-intensive area does not exist, the unmanned aerial vehicle is not deployed;
if the number of the task-intensive areas is more than that of the unmanned aerial vehicles, deploying the unmanned aerial vehicles in the task-intensive areas according to the sequence of the distance between the task-intensive areas and the base station from far to near;
and if the number of the task-intensive areas is not more than the number of the unmanned aerial vehicles to be deployed, respectively deploying one unmanned aerial vehicle for each task-intensive area.
Optionally, determining a task bearer according to a position relationship between the to-be-processed task and the edge server, including:
if the task to be processed belongs to the service range of the unmanned aerial vehicle, taking the unmanned aerial vehicle as the task bearer;
if the task to be processed does not belong to the service range of the unmanned aerial vehicle but belongs to the service range of the base station, taking the base station as the task bearer;
and if the task to be processed does not belong to the service range of the unmanned aerial vehicle or the service range of the base station, taking a local end generated by the task to be processed as the task bearer.
Optionally, before invoking the task bearer to perform task offloading processing, the method further includes:
judging whether the unmanned aerial vehicle is overloaded or not;
and if so, calling the base station to carry out task unloading on the unmanned aerial vehicle.
Optionally, determining whether the drone is overloaded includes:
and judging whether the ratio of the number of the tasks actually carried by the unmanned aerial vehicle and the base station exceeds the ratio of the task carrying capacity.
The application also provides an edge server task uninstallation device, edge server includes basic station and unmanned aerial vehicle, and the device includes:
the task distribution acquisition unit is used for acquiring a task position distribution map of the target area; the base station is erected in the target area;
the dense region determining unit is used for determining a task dense region in the target region according to the task position distribution diagram;
an unmanned aerial vehicle deployment unit for deploying the unmanned aerial vehicle to the mission-intensive area;
the task determining unit is used for determining a task to be processed;
the task bearing determining unit is used for determining a task bearing party according to the position relation between the task to be processed and the edge server;
and the task unloading unit is used for calling the task bearer to carry out task unloading processing.
The present application further provides an edge server task offloading device, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the task unloading method of the edge server when executing the computer program.
The present application also provides a readable storage medium having a program stored thereon, which when executed by a processor, performs the steps of the edge server task offloading method.
According to the edge server task unloading method, on the basis of the fixed position of the base station, the intensive personnel area under the current flow is determined by analyzing the distribution of the task positions in the area, unmanned aerial vehicle deployment is carried out on the intensive personnel area, and the fixed ground base station can be assisted to realize the calculation unloading of the intensive personnel area. According to the method, the unmanned aerial vehicle is deployed in the task dense area, so that the transmission distance between the user terminal and the edge server can be shortened, the task unloading speed is increased, and the path loss is reduced; and the task unloading processing is carried out according to the position relation between the task to be processed and the edge server, so that the condition that the unloading task distribution among the edge servers is uneven due to unbalanced distribution of the flow of people can be relieved, the condition that the bearing pressure of a base station erected in the area is too large, the condition that the task is delayed due to the large service pressure of the base station can be avoided, and the user experience is optimized.
The application also provides an edge server task unloading device, equipment and a readable storage medium, which have the beneficial effects and are not described again.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and for the task of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a task offloading method for an edge server according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of task location distribution provided in an embodiment of the present application;
fig. 3 is a schematic diagram of a deployment of a location of an unmanned aerial vehicle according to an embodiment of the present application;
fig. 4 is a block diagram illustrating a structure of an edge server task offloading device according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an edge server task offloading device according to an embodiment of the present disclosure.
Detailed Description
The core of the application is to provide an edge server task unloading method, which can stably maintain long-term accurate edge server task unloading; at the other core of the application, an edge server task unloading device, equipment and a readable storage medium are provided.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments which can be derived from the embodiments given herein by the person skilled in the art without making any creative effort shall fall within the protection scope of the present application.
In a two-dimensional plane target area, there are 1 fixed ground base station and 1 drone (for simplifying the model, the description is given only in the case where the number of drones is 1, and the description of the embodiment may also be referred to for multiple drones, which is not described herein again), and the number and distribution of user tasks change with time.
With (x)i,yi0) and (x)n,ynAnd h) respectively represent the position coordinates of the task and the unmanned aerial vehicle. The distance between the mission and the drone may be expressed as:
where | · | | represents the euclidean distance.
The path loss can be expressed as:
wherein PL0(d0) Is shown at the reference distance d0The lower fundamental transmission loss, ρ, represents the path loss exponent with joint consideration of line-of-sight and non-line-of-sight. The transmission rate of data can be expressed as:
where K is the channel bandwidth, PTDenotes the transmission power, N0Representing the noise power.
Assume that task i requires local processing or is submitted to an edge server for computation. By xinIndicates whether task i isOffload to edge Server n (x)in0 means no unloading, xin1 denotes ground base station offloading, xin2 denotes drone offload). For convenience of presentation, the local computation is denoted by the superscript "Loc" and the Edge computation is denoted by the superscript "Edge".
When the task selects local computation, the total time delay of the task is the computation time delay, which can be expressed as:
wherein the content of the first and second substances,
representing the total number of CPU cycles required for the task to compute locally,
representing the computing power of user i. Its energy consumption can be expressed as:
wherein, ηiA coefficient representing the energy consumption per CPU cycle.
When the task selects edge offload, the total delay of the task may be divided into two parts, one part is transmission delay, and the other part is processing delay, where the transmission delay may be expressed as:
wherein R (d)in) Is shown at a distance dinThe data transmission rate of time, a represents the data size at the time of transmission. Since the capacity of each edge server is limited, in each edge server, a queuing model of M/M/1/r/∞/FCFS is adopted in the embodiment, the queuing model of M/M/1/r/∞/FCFS is a model in queuing theory, the successive arrival interval time and service time of customers follow Poisson distribution, and only one server is providedThe queue length is not limited, the passenger source is not limited, and the service rule is first come first serve.
Thus, the processing delay of task i includes the queuing delay and the calculation delay, and the delay can be expressed as:
where L represents the average queue length, i.e., the sum of the number of tasks being served and the number of tasks waiting in line. Lambda [ alpha ]eRepresenting the effective arrival rate of the task. The total latency of the task can then be expressed as:
the energy consumption of the owner of the task may be expressed as:
wherein p isiIndicating the transmission power of the owner of the task.
Considering that the task requests are non-uniformly distributed, to ensure that the delay of task offloading is minimized without exceeding the maximum energy consumption constraint, the task processing delay can be stated as:
min∑t∑i∈IDi(10)
formula (10) is the sum of the task processing delays of all users in all time slots (unit time);
s.t.∑t∑i∈IEi≤Emax(10a)
s.t- ∑ in formula (10a)t∑i∈IEiNamely the task processing energy consumption of all users in all unit time;
xin∈{0,1,2} (10b)
constraint (10a) indicates that the total energy consumption of the task does not exceed EmaxThis threshold, constraint (10b), indicates that the problem is a ternary offload problem.
The minimization of the task processing delay and the task processing energy consumption is ensured under the condition of ternary unloading (a local end, a base station and an unmanned aerial vehicle), the task processing delay is known to be related to the total amount of tasks and the transmission distance according to a formula (4) and a formula (8), and the energy consumption is known to be related to the total amount of tasks and the transmission distance according to a formula (5) and a formula (9), so that the balance between the transmission distance and the task amount of a task processing end is required to be ensured in order to realize (10) and (10a) and (10 b). To this end, the present embodiment proposes an edge server task offloading method, which aims to minimize an average delay per task so as to treat each task in a target area fairly. Fig. 1 is a flowchart of a task offloading method for an edge server provided in this embodiment, where according to the flowchart, task processing latency and task processing energy consumption can be minimized, and the method mainly includes:
step s110, acquiring a task position distribution map of a target area;
the target area refers to an area where unmanned planes are to be deployed and tasks are to be unloaded, and can be a stadium, an airport, a park and the like. The method includes the steps that a user mobile intelligent terminal for performing task processing through an edge algorithm exists in a target area, namely, a task needing to call an edge server for task unloading exists, and the edge server in the embodiment mainly refers to a base station and an unmanned aerial vehicle. The traffic of people higher than usual can be generated in the target area at a specific time, and the purpose of this embodiment is to deploy the unmanned aerial vehicle to the target location at this time by utilizing the mobility of the unmanned aerial vehicle, improve the delay condition in the target area, and optimize the experience of the user.
The base station is erected in the target area, the base station can achieve task unloading of the user mobile intelligent terminal, the unmanned aerial vehicles are called to carry out task unloading in the target area, however, specific running tracks of the unmanned aerial vehicles need to be set according to subsequent steps, namely, the unmanned aerial vehicles are in a state to be deployed in the step. In this embodiment, the number of base stations and unmanned aerial vehicles erected in a certain area is not limited, and generally, a service area range of one base station and a nearby area may be used to divide a target area, so as to simplify an analysis process.
Since the task is initiated by the user mobile intelligent terminal, the task position distribution map can also be extended to be a person position distribution map, and the task or person position distribution map can be acquired according to the convenience of data acquisition, which is not limited herein. As shown in fig. 2, a task position distribution diagram is shown, in which horizontal and vertical coordinates respectively indicate positions within a region, circular points represent tasks, open circles represent service ranges of base stations, and dots (i.e., square points) of the open circles represent base stations.
It should be noted that, because of the randomness of the distribution of the human flow, the distribution of the human at different times is different, and in order to ensure the optimal task unloading at each time slot, the process of obtaining the task position distribution map of the target area in step s110 may specifically be: and acquiring a task position distribution map of the target area in each time slot. Namely, one time slot determines the real-time task distribution once, and the optimal deployment position of each time slot T can be ensured.
Step s120, determining a task dense area in the target area according to the task position distribution map;
due to the irregularity and randomness of the distribution of the human traffic, dense areas in the dense areas need to be determined according to the current task position distribution, the number and size of the dense areas are not limited in this embodiment, one or more than one determined dense areas need to be determined according to corresponding determination rules, and the specific determination rules of the dense areas are not limited in this embodiment, for example, the task distance may be used as a determination condition, and an area with any size, in which the adjacent task distance is not higher than a threshold, may be selected as a dense area for tasks.
Step s130, deploying the unmanned aerial vehicle to a task-intensive area;
the unmanned aerial vehicle is deployed to a mission-intensive area, a specific service range of the unmanned aerial vehicle needs to include a determined mission-intensive area, and as shown in fig. 3, a schematic diagram of unmanned aerial vehicle position deployment is shown, in the diagram, a solid triangle point is an Unmanned Aerial Vehicle (UAV), a hollow dotted circle is a service range of the unmanned aerial vehicle, a solid square point is a base station (BS or GBS), a hollow solid line circle is a service range of the base station, and a solid circle point is a mission (task).
In the embodiment, by deploying the movable edge servers (unmanned aerial vehicles) in the task-intensive area, the service pressure of the task-intensive area on the base station can be relieved, the balanced division of tasks is realized, and the task amount among the edge servers is balanced; meanwhile, the distance between the multi-task and the task receiving end in a task dense area can be reduced, and the data transmission distance is reduced.
Specifically, since the number of the determined task-intensive areas is not limited in step s120, in order to ensure efficient task processing in the task-intensive areas and reduce deployment cost of the unmanned aerial vehicle as much as possible, optionally, the process of deploying the unmanned aerial vehicle to the task-intensive areas may specifically include the following steps:
(1) if the task-intensive area does not exist, the unmanned aerial vehicle is not deployed;
(2) if the number of the task-intensive areas is more than that of the unmanned aerial vehicles, deploying the unmanned aerial vehicles in the task-intensive areas according to the sequence of the distance between the task-intensive areas and the base station from far to near;
(3) and if the number of the task-intensive areas is not more than the number of the unmanned aerial vehicles to be deployed, respectively deploying one unmanned aerial vehicle for each task-intensive area.
If the maximum clique is not found, the unmanned aerial vehicle is not deployed; when one unmanned aerial vehicle is arranged in the plurality of task-intensive areas, selecting the task-intensive area farthest from the base station to deploy the unmanned aerial vehicle; when a plurality of unmanned aerial vehicles are arranged in a plurality of task-intensive areas, the unmanned aerial vehicles are deployed according to the distance between the task-intensive areas and the base station from far to near.
Step s140, determining a task to be processed;
the tasks to be processed are calculation tasks generated in the user mobile intelligent terminal for task unloading processing through edge calculation, and all the tasks to be processed in the target area at the current time are determined and counted, so that reasonable distribution of the tasks is achieved.
It should be noted that the process of determining the task to be processed may be executed at any time period before step s150, and the execution time of step s140 is not limited in this embodiment.
Step s150, determining a task bearer according to the position relationship between the task to be processed and the edge server;
based on the above steps, the deployment position of the unmanned aerial vehicle can be obtained, the position of the base station and the position of each task to be processed are determined, and the rest problems are how to select unloading or not to unload the tasks and what kind of edge server is called to unload the tasks.
In order to ensure the minimization of the transmission distance between the task and the task bearer and reduce the transmission loss, in this embodiment, according to the position relationship between the task to be processed and the edge server, the device with the shortest distance to the task to be processed and the lowest task processing amount is selected as the task bearer, so as to implement the task processing with the lowest energy consumption and the lowest delay.
The following offloading principles may be specifically implemented for each task:
(1) if the task to be processed belongs to the service range of the unmanned aerial vehicle, taking the unmanned aerial vehicle as a task bearer;
(2) if the task to be processed does not belong to the service range of the unmanned aerial vehicle but belongs to the service range of the base station, taking the base station as a task bearer;
(3) and if the task to be processed does not belong to the service range of the unmanned aerial vehicle or the service range of the base station, taking the local end generated by the task to be processed as a task bearer.
If the task is close to the unmanned aerial vehicle (belonging to the service range of the unmanned aerial vehicle), the task is distributed to the unmanned aerial vehicle in order to reduce the load pressure of the base station; if this task is far away from unmanned aerial vehicle, carry out the task uninstallation for avoiding calling unmanned aerial vehicle and bring great transmission distance, influence the processing energy consumption, do not select unmanned aerial vehicle, and select the task carrier from local end and basic station, wherein, because the task throughput of basic station is far superior to local end, for the processing speed who promotes the task, if near the basic station (belong to the service range of basic station), the basic station that the call ability is strong carries out the task processing, if far away from the basic station, for reducing transmission loss, then call local end and carry out the task and bear. The method can automatically select the task bearing party with short transmission distance, small task processing pressure and strong task processing capacity, and further improve the total processing time delay and the processing energy consumption in the task unloading process once.
And step s160, calling the task bearer to perform task unloading processing.
The process of invoking the task bearer to perform the task offloading processing may specifically refer to the introduction of the related art, and is not described herein again.
Based on the above description, the edge server task offloading method provided in this embodiment determines the person-dense area under the current pedestrian flow rate by analyzing task position distribution in the area on the basis of the fixed base station position, and performs unmanned aerial vehicle deployment on the person-dense area, so as to assist the fixed ground base station to achieve calculation offloading of the high-dense area. According to the method, the unmanned aerial vehicle is deployed in the task dense area, so that the transmission distance between the user terminal and the edge server can be shortened, the task unloading speed is increased, and the path loss is reduced; and the task unloading processing is carried out according to the position relation between the task to be processed and the edge server, so that the condition that the unloading task distribution among the edge servers is uneven due to unbalanced distribution of the flow of people can be relieved, the condition that the bearing pressure of a base station erected in the area is too large, the condition that the task is delayed due to the large service pressure of the base station can be avoided, and the user experience is optimized.
The determination method of the task-intensive area in the above embodiment is not limited, and in this embodiment, a solution for converting the population density problem into the maximum clique problem is provided based on the idea of a graph, and the area with the most intensive population in the graph is identified by using the theory of the maximum clique in the graph. One specific implementation is as follows:
the process of determining the task dense region in the target region according to the task position distribution map may specifically include:
(1) connecting the tasks with the intermediate distance of the task position distribution diagram smaller than a first threshold value to obtain a task distribution undirected graph; the first threshold value is set according to the service radius of the unmanned aerial vehicle;
it should be noted that, in the calling of the maximum blob algorithm, the scatter point is analyzed, and if a task position distribution map of the target region is obtained as a non-scatter map, each task needs to be further set as one point in the map.
(2) And calling a maximum clustering algorithm to carry out task dense region solution on the task distribution undirected graph, and taking a complete graph obtained by the solution as a task dense region.
The generation mode of the connecting line between the two tasks is as follows:
||ia,ib||≤RUAV(11)
wherein ia,ibRepresenting any two tasks, | | · | | is the Euclidean distance of two tasks, RUAVThe service radius of a drone equipped with an edge server.
When the distance between two tasks is less than RUAVWhen the maximum clique algorithm is implemented, an edge (connecting line) is added between two points, and the task position distribution graph after the edge (connecting line) is added can be used as an undirected graph.
On the basis of the undirected graph, the maximum clustering algorithm can be directly adopted to solve to obtain the most dense region of the current people, and specific algorithm implementation steps are not repeated herein and can refer to the introduction of related algorithms.
It should be noted that, in this embodiment, the determination of the task-intensive area by the maximum clique algorithm is taken as an example for introduction, and the method can accurately and quickly identify the task-intensive area, and improve the task unloading implementation efficiency. Since the determination method of the task-intensive area is not limited in the present application, the implementation process of setting the task-intensive area based on other algorithms or determination rules can refer to the description of this embodiment, and is not described herein again.
Due to the fact that the time complexity of the maximum clique problem is relatively high, the efficiency of determining the task dense area is further improved, the resource occupation is reduced, the graph can be further cut appropriately, and the tasks in the task sparse area are cut.
Specifically, before calling a maximum clique algorithm to solve the task-intensive region of the task distribution undirected graph, the following steps may be further performed: and cutting tasks of which the total number of the tasks connected in the task distribution undirected graph does not reach the second threshold value.
Introducing a second threshold value k, and then recursively deleting points smaller than k in the graph, wherein k is a threshold value of the number of edges (connecting lines) of the points, and if the number of the edges of the points is less, the area where the points are located is indicated to have sparser tasks, and the demand for deploying the unmanned aerial vehicle in the area is lower; if the number of the edges of the point is large, the task density of the area where the point is located is indicated, and a larger unmanned aerial vehicle deployment requirement exists relative to a sparse area. Increasing the k value not only can improve the operation speed of the algorithm, but also can be used for the decision of whether the unmanned aerial vehicle is deployed or not.
The value setting of k is not specifically limited, and k can be set according to the task processing capacity of the base station and the unmanned aerial vehicle in unit time in order to simplify the implementation process of the maximum clique algorithm and avoid excessive deletion of task points.
Specifically, a setting rule of k is as follows:
wherein C isBS、CUAVThe number of tasks that can be processed by the base station and the drone that have the edge server installed in the unit time is shown. The formula (12) can delete tasks according to the processing capacities of the base station and the unmanned aerial vehicle, so that the maximization of the processing tasks of the edge server is guaranteed while the overweight load pressure generated on the edge server is avoided.
In order to deepen understanding of the deployment process of the unmanned aerial vehicle in the task-intensive area based on undirected graph generation and graph pruning generation described in this embodiment, a specific implementation algorithm is described as an example below, as shown in table 1 below.
TABLE 1
An undirected graph is generated according to equation (11) (lines 3-4), pruned and solved for the maximum cliques (i.e., task-dense regions) (lines 5-7). If the maximum clique is not found, the unmanned aerial vehicle is not deployed; if the number of drones is not unique, the position farthest from the base station is selected as the deployment position of the drone (row 10).
Based on the above embodiment, experiments prove that when tasks in an area are too dense and the unmanned aerial vehicle assists in unloading tasks more, the task unloading optimization effect is influenced. In order to avoid generating overweight bearing pressure for each edge server, balance the load of the unmanned aerial vehicle and the base station, prevent overload of one side, ensure that the unmanned aerial vehicle and the base station can carry out task unloading under the maximum processing capacity, and optionally, before the task bearing side is called to carry out task unloading processing, further judge whether the unmanned aerial vehicle is overloaded or not; if so, the base station is called to unload the tasks of the unmanned aerial vehicle.
Specifically, an implementation manner of judging whether the unmanned aerial vehicle is overloaded is as follows: and judging whether the ratio of the number of the tasks actually carried by the unmanned aerial vehicle and the base station exceeds the ratio of the task carrying capacity.
The following conditions need to be satisfied:
wherein sum (X)i1) and sum (X)i2) represent the number of tasks serviced by the GBS and UAV, respectively. And unloading the user within the service range of the unmanned aerial vehicle to the base station when the user is close to the base station until the proportion of the users to be served between the unmanned aerial vehicle and the base station reaches or approaches the proportion of the user service capacity.
Specifically, a task offloading implementation algorithm based on the above-mentioned overload processing is shown in table 2 below.
TABLE 2
Referring to fig. 4, fig. 4 is a block diagram of a task offloading device of an edge server according to the present embodiment; the method mainly comprises the following steps: the system comprises a task distribution acquisition unit 210, a dense area determination unit 220, an unmanned aerial vehicle deployment unit 230, a task determination unit 240, a task bearer determination unit 250, and a task unloading unit 260. The edge server task offloading device provided in this embodiment may be contrasted with the above-mentioned edge server task offloading method.
The task distribution obtaining unit 210 is mainly configured to obtain a task position distribution map of the target area; the base station is erected in a target area;
the dense region determining unit 220 is mainly configured to determine a task dense region in the target region according to the task position distribution map;
the unmanned aerial vehicle deployment unit 230 is mainly used for deploying unmanned aerial vehicles to a mission-intensive area;
the task determining unit 240 is mainly used for determining a task to be processed;
the task bearer determining unit 250 is mainly configured to determine a task bearer according to a position relationship between the task to be processed and the edge server;
the task offloading unit 260 is mainly used for invoking the task bearer to perform task offloading processing.
The embodiment provides an edge server task unloading device, which mainly includes: a memory and a processor.
Wherein, the memory is used for storing programs;
the processor is configured to implement the steps of the edge server task offloading method described in the above embodiments when executing the program, and specifically refer to the description of the edge server task offloading method.
Referring to fig. 5, a schematic structural diagram of an edge server task offloading device according to this embodiment is provided, where the edge server task offloading device may generate a large difference due to different configurations or performances, and may include one or more processors (CPUs) 322 (e.g., one or more processors), a memory 332, and one or more storage media 330 (e.g., one or more mass storage devices) storing an application 342 or data 344. Memory 332 and storage media 330 may be, among other things, transient storage or persistent storage. The program stored on the storage medium 330 may include one or more modules (not shown), each of which may include a series of instructions operating on a data processing device. Still further, the central processor 322 may be configured to communicate with the storage medium 330 to perform a series of instructional operations on the storage medium 330 on the edge server task off-load device 301.
The edge server task offload device 301 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input-output interfaces 358, and/or one or more operating systems 341, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
The steps in the method for offloading task of edge server described in fig. 1 above may be implemented by the structure of the task offloading device of edge server introduced in this embodiment.
The present embodiment discloses a readable storage medium, on which a program is stored, and the program, when being executed by a processor, implements the steps of the method for offloading task of an edge server described in the foregoing embodiment, which may be specifically referred to the description of the method for offloading task of an edge server in the foregoing embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Skilled artisans may further appreciate that the elements and algorithm steps of each example described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various example components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method, the apparatus, the device and the readable storage medium for offloading the task of the edge server provided by the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that for the ordinary technical task in the field of the present application, it can also be subjected to several improvements and modifications without departing from the principle of the present application, and these improvements and modifications also fall into the protection scope of the claims of the present application.
Claims (10)
1. An edge server task unloading method is characterized in that an edge server comprises a base station and an unmanned aerial vehicle, and the method comprises the following steps:
acquiring a task position distribution map of a target area; the base station is erected in the target area;
determining a task dense region in the target region according to the task position distribution map;
deploying the drone to the mission-intensive area;
determining a task to be processed;
determining a task bearer according to the position relation between the task to be processed and the edge server;
and calling the task bearer to carry out task unloading processing.
2. The edge server task offloading method of claim 1, wherein determining the task-intensive regions in the target region from the task position profile comprises:
connecting the tasks with the distance smaller than a first threshold value in the task position distribution diagram to obtain a task distribution undirected graph; the first threshold value is set according to the service radius of the unmanned aerial vehicle;
and calling a maximum clustering algorithm to carry out task dense region solution on the task distribution undirected graph, and taking a complete graph obtained by the solution as the task dense region.
3. The edge server task offload method of claim 2, before invoking a maximal clique algorithm to perform task-intensive area solution on the task distribution undirected graph, further comprising:
cutting tasks of which the total number of the tasks connected in the task distribution undirected graph does not reach a second threshold value;
and the second threshold is set according to the task processing capacity of the base station and the unmanned aerial vehicle in unit time.
4. The edge server task offloading method of claim 1, wherein deploying the drone to the task-intensive area comprises:
if the task-intensive area does not exist, the unmanned aerial vehicle is not deployed;
if the number of the task-intensive areas is more than that of the unmanned aerial vehicles, deploying the unmanned aerial vehicles in the task-intensive areas according to the sequence of the distance between the task-intensive areas and the base station from far to near;
and if the number of the task-intensive areas is not more than the number of the unmanned aerial vehicles to be deployed, respectively deploying one unmanned aerial vehicle for each task-intensive area.
5. The method for unloading task of edge server according to claim 1, wherein determining the task bearer according to the position relationship between the task to be processed and the edge server comprises:
if the task to be processed belongs to the service range of the unmanned aerial vehicle, taking the unmanned aerial vehicle as the task bearer;
if the task to be processed does not belong to the service range of the unmanned aerial vehicle but belongs to the service range of the base station, taking the base station as the task bearer;
and if the task to be processed does not belong to the service range of the unmanned aerial vehicle or the service range of the base station, taking a local end generated by the task to be processed as the task bearer.
6. The edge server task offload method of claim 1, before invoking the task bearer for task offload processing, further comprising:
judging whether the unmanned aerial vehicle is overloaded or not;
and if so, calling the base station to carry out task unloading on the unmanned aerial vehicle.
7. The edge server task offloading method of claim 6, wherein determining whether the drone is overloaded comprises:
and judging whether the ratio of the number of the tasks actually carried by the unmanned aerial vehicle and the base station exceeds the ratio of the task carrying capacity.
8. The utility model provides an edge server task uninstallation device, its characterized in that, edge server includes basic station and unmanned aerial vehicle, includes:
the task distribution acquisition unit is used for acquiring a task position distribution map of the target area; the base station is erected in the target area;
the dense region determining unit is used for determining a task dense region in the target region according to the task position distribution diagram;
an unmanned aerial vehicle deployment unit for deploying the unmanned aerial vehicle to the mission-intensive area;
the task determining unit is used for determining a task to be processed;
the task bearing determining unit is used for determining a task bearing party according to the position relation between the task to be processed and the edge server;
and the task unloading unit is used for calling the task bearer to carry out task unloading processing.
9. An edge server task offload device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the edge server task offloading method of any of claims 1 to 7 when executing the computer program.
10. A readable storage medium, characterized in that the readable storage medium has stored thereon a program which, when being executed by a processor, carries out the steps of the edge server task offloading method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010403478.4A CN111580889A (en) | 2020-05-13 | 2020-05-13 | Method, device and equipment for unloading tasks of edge server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010403478.4A CN111580889A (en) | 2020-05-13 | 2020-05-13 | Method, device and equipment for unloading tasks of edge server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111580889A true CN111580889A (en) | 2020-08-25 |
Family
ID=72115410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010403478.4A Pending CN111580889A (en) | 2020-05-13 | 2020-05-13 | Method, device and equipment for unloading tasks of edge server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111580889A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112702714A (en) * | 2020-12-28 | 2021-04-23 | 湖南大学 | Unmanned aerial vehicle cooperative type vehicle networking operation task unloading method |
| CN113709728A (en) * | 2021-08-27 | 2021-11-26 | 西北工业大学 | NOMA (non-oriented multi-agent) and unmanned aerial vehicle-assisted two-stage mobile edge computing communication method |
| WO2022242468A1 (en) * | 2021-05-18 | 2022-11-24 | 北京航空航天大学杭州创新研究院 | Task offloading method and apparatus, scheduling optimization method and apparatus, electronic device, and storage medium |
| CN116126428A (en) * | 2023-04-14 | 2023-05-16 | 昆明理工大学 | Unmanned aerial vehicle calculation task unloading method for energy collection |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108810849A (en) * | 2018-06-19 | 2018-11-13 | 广东工业大学 | A kind of moving method, device and the unmanned plane of unmanned plane calculating task |
| CN110149588A (en) * | 2019-05-17 | 2019-08-20 | 电信科学技术研究院有限公司 | Determine the method, apparatus, equipment and storage medium of the position of unmanned plane base station |
| CN110766159A (en) * | 2019-09-29 | 2020-02-07 | 南京理工大学 | Task allocation method for multi-UAV service edge calculation based on improved genetic algorithm |
-
2020
- 2020-05-13 CN CN202010403478.4A patent/CN111580889A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108810849A (en) * | 2018-06-19 | 2018-11-13 | 广东工业大学 | A kind of moving method, device and the unmanned plane of unmanned plane calculating task |
| CN110149588A (en) * | 2019-05-17 | 2019-08-20 | 电信科学技术研究院有限公司 | Determine the method, apparatus, equipment and storage medium of the position of unmanned plane base station |
| CN110766159A (en) * | 2019-09-29 | 2020-02-07 | 南京理工大学 | Task allocation method for multi-UAV service edge calculation based on improved genetic algorithm |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112702714A (en) * | 2020-12-28 | 2021-04-23 | 湖南大学 | Unmanned aerial vehicle cooperative type vehicle networking operation task unloading method |
| WO2022242468A1 (en) * | 2021-05-18 | 2022-11-24 | 北京航空航天大学杭州创新研究院 | Task offloading method and apparatus, scheduling optimization method and apparatus, electronic device, and storage medium |
| CN113709728A (en) * | 2021-08-27 | 2021-11-26 | 西北工业大学 | NOMA (non-oriented multi-agent) and unmanned aerial vehicle-assisted two-stage mobile edge computing communication method |
| CN116126428A (en) * | 2023-04-14 | 2023-05-16 | 昆明理工大学 | Unmanned aerial vehicle calculation task unloading method for energy collection |
| CN116126428B (en) * | 2023-04-14 | 2023-06-13 | 昆明理工大学 | Unmanned aerial vehicle calculation task unloading method for energy collection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111580889A (en) | Method, device and equipment for unloading tasks of edge server and storage medium | |
| CN111240701B (en) | Task unloading optimization method for end-side-cloud collaborative computing | |
| CN109857546B (en) | Multi-server mobile edge computing unloading method and device based on Lyapunov optimization | |
| CN112188442B (en) | Vehicle networking data-driven task unloading system and method based on mobile edge calculation | |
| CN109829332B (en) | Joint calculation unloading method and device based on energy collection technology | |
| CN109639833B (en) | Task scheduling method based on wireless metropolitan area network micro-cloud load balancing | |
| CN114567895A (en) | Method for realizing intelligent cooperation strategy of MEC server cluster | |
| CN110570075A (en) | Power business edge calculation task allocation method and device | |
| CN112887905B (en) | Task unloading method based on periodic resource scheduling in Internet of vehicles | |
| CN113347267A (en) | MEC server deployment method in mobile edge cloud computing network | |
| CN110780986B (en) | Internet of things task scheduling method and system based on mobile edge computing | |
| CN115460154B (en) | Priority adjustment method and device and electronic equipment | |
| CN114205316A (en) | Network slice resource allocation method and device based on power service | |
| CN111050387B (en) | Base station dormancy method and device based on energy efficiency estimation, electronic equipment and medium | |
| CN115150893A (en) | MEC task unloading strategy method based on task division and D2D | |
| CN112888021B (en) | Task unloading method for avoiding interruption in Internet of vehicles | |
| CN113766037A (en) | Task unloading control method and system for large-scale edge computing system | |
| CN112559078B (en) | Method and system for hierarchically unloading tasks of mobile edge computing server | |
| Yan et al. | Fairness-aware data offloading of IoT applications enabled by heterogeneous UAVs | |
| CN117201408A (en) | Large-scale internet of things equipment load balancing solution method based on group game | |
| CN111580943A (en) | Task scheduling method oriented to multi-hop unloading in low-delay edge calculation | |
| CN115499875A (en) | Satellite internet task unloading method and system and readable storage medium | |
| Chousainov et al. | An analytical framework of a C-RAN supporting random, quasi-random and bursty traffic | |
| CN115827185A (en) | 6G aerial base station and Beidou aerial obstacle avoidance combined method, storage medium and equipment | |
| CN113784372A (en) | Joint optimization method for terminal multi-service model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |
|
| RJ01 | Rejection of invention patent application after publication |