CN113791878B - Distributed task unloading method for perceiving expiration date in edge calculation - Google Patents
Distributed task unloading method for perceiving expiration date in edge calculation Download PDFInfo
- Publication number
- CN113791878B CN113791878B CN202110828570.XA CN202110828570A CN113791878B CN 113791878 B CN113791878 B CN 113791878B CN 202110828570 A CN202110828570 A CN 202110828570A CN 113791878 B CN113791878 B CN 113791878B
- Authority
- CN
- China
- Prior art keywords
- task
- tasks
- expiration date
- edge server
- edge
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004364 calculation method Methods 0.000 title claims abstract description 19
- 230000008569 process Effects 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000008901 benefit Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 230000008447 perception Effects 0.000 claims 1
- 230000007246 mechanism Effects 0.000 description 8
- 238000005457 optimization Methods 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
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
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
-
- 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
- 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]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5022—Mechanisms to release resources
-
- 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]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- 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
Abstract
The invention discloses a distributed task unloading method for perceiving the expiration date in edge calculation, which comprises the following steps: the mobile user side sends a task unloading request to a plurality of base stations in a signal coverage area; the base station sends the information of the edge server connected with the base station to the mobile user terminal; the mobile user side distributes edge servers for the tasks in a distributed manner to calculate the tasks by combining the expiration date of the tasks, the expiration date type of the tasks and the information of all the received edge servers; and the edge server receives the distributed tasks sent by the mobile user terminal, and performs real-time scheduling on the tasks according to the type of the deadline of the tasks and the states of other running tasks so as to maximize the income of completing the tasks in the edge computing network. The invention can expand the types of the unloading tasks of the edge computing system; the problems of single point failure, slow unloading decision and the like caused by a centralized controller are avoided.
Description
Technical Field
The invention relates to the technical field of edge calculation, in particular to a distributed task unloading method for perceiving an expiration date in edge calculation.
Background
With the explosive growth of mobile users, delay-sensitive applications such as augmented reality, virtual reality, autopilot, etc. are becoming increasingly popular. Because of the limited computing resources on mobile devices, computing tasks often need to be transferred to the cloud for processing. However, unpredictable network delays between the remote cloud and the mobile device often do not meet the requirements of delay-sensitive applications.
To overcome the above problems, edge computation as a new example has been developed. Edge computing allows mobile users to offload computing tasks to edge servers at nearby base stations. The tasks that the mobile user offloads to the server typically have a hard expiration date or a soft expiration date. Ideally, all tasks should be completed before the expiration date. However, the capacity of the edge server is limited compared to the cloud server, so that it cannot be guaranteed that all tasks are completed before the expiration date. When a large number of tasks of different deadline types are offloaded to an edge server, an unsuitable task offload mechanism can significantly reduce the task completion rate, thereby reducing the quality of user experience. Therefore, there is a need to design an efficient task offloading mechanism in an edge computing environment.
In recent years, in order to achieve different optimization goals, various task offloading mechanisms have been proposed to achieve different optimization goals, such as maximizing task completion rate, maximizing task computing efficiency, minimizing task response time, minimizing energy consumption, and the like. Previous studies were primarily directed to tasks with hard deadlines, with tasks that missed hard deadlines simply discarded or offloaded onto the cloud. However, in the real world, not all delay sensitive tasks have to be completed before a certain period. Some tasks, such as multimedia tasks, video analysis tasks, have a soft expiration date. These tasks may miss the main expiration date but still be completed in time. Furthermore, another key issue with existing task offloading mechanisms is the delay caused by centralized optimization. These task offloading mechanisms typically rely on a centralized controller to determine the computational offloading policy in an offline manner, that is, existing offloading mechanisms assume that the complete information (e.g., task location, task release time, task expiration date) for all tasks is known in advance. In fact, since the compute offload problem is np-hard, a centralized controller takes too much time to determine the offload policy before offloading. Furthermore, in edge computing systems, user arrival and departure tend to be random. Thus, the tasks they want to offload are also random. However, offline computing offload methods often fail to handle a series of randomly arriving tasks.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a distributed task unloading method for perceiving the expiration date in edge calculation, so that an edge calculation system can process tasks with hard expiration dates and can effectively process tasks with soft expiration dates, and the types of the tasks unloaded by the edge calculation system are enlarged; the method supports the distributed task scheduling of the edge server, and avoids the problems of single point failure, slow unloading decision and the like brought by a centralized controller.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a method of off-load of a distributed task perceived by an expiration date in edge computation, the method comprising the steps of:
s1, a mobile user terminal sends an unloading request of a task generated by a delay sensitive application to a plurality of base stations in a signal coverage range, an edge server corresponding to the base stations calculates the unloading task, and each base station is connected with at least one edge server;
s2, the base station receiving the task unloading request sends the information of the edge server connected with the base station to the mobile user side, wherein the information of the edge server comprises the computing capacity of the server, the data transmission bandwidth and the running state of each task on the server;
s3, the mobile user side distributes edge servers for the tasks in a distributed manner to calculate the tasks by combining the expiration date of the tasks, the expiration date type of the tasks and the information of all the received edge servers; the expiration date type of the task comprises a hard expiration date and a soft expiration date, the income completed by the hard expiration date on time is larger than a preset income threshold, the uncompleted loss of the soft expiration date is smaller than a preset loss threshold, and the income and the loss are calculated based on the application performance of the delay sensitive application; the constraints of the allocation process are: tasks with hard expiration dates can always be completed;
s4, the edge server receives the distributed tasks sent by the mobile user terminal, and real-time scheduling is carried out on the tasks according to the type of the deadline of the tasks and the states of other running tasks so as to maximize the income of completing the tasks in the edge computing network;
s5, the edge server completes the calculation process of the task according to the scheduling result in the step S4.
In order to optimize the technical scheme, the specific measures adopted further comprise:
further, in step S1, the ith task T generated by the delay-sensitive application i Is a four-member groupWherein d is i The number of bits, w, that need to be transmitted for a task i For the workload of a task->Indicating the expiration date of the execution of the task +.>For the release time of the task, < > for>For the deadline of the task, I i The type of deadline for the task is characterized.
Further, in step S2, the edge server information includes an ith task T i Channel bandwidth b between corresponding mobile user terminal and edge server j i，j Transmission power p i，j Channel gain g i，j Noise power w o CPU frequency f j And the running state of each task in the edge server; the tasks are divided into two types according to the running states of the tasks in the edge server: one type of task that has been offloaded to the edge server, is doing computation or waiting for computation in a queue, and another type of task that has decided to be offloaded to the server, is currently being transmitted。
Further, in step S3, the process of distributively distributing the edge servers to the tasks to perform task computation by combining the expiration date of the tasks, the expiration date type of the tasks and all the received edge server information includes the following steps:
s31, calculating the task T according to the following formula i Time of transmission uploaded to edge server j
Wherein r is i，j For the task transfer rate, expressed as:
s32, estimating if the task T is to be executed according to the running state of each task in the edge server i Uploading to edge server j, and waiting time of task in process of receiving task from edge server j to executing task
S33, calculating the task T according to the following formula i Computation time on edge server j
S34, calculating the task T according to the following formula i Total completion time t at edge server j i，j ：
S35, according to t calculated in the step S34 i，j Detection task T i Whether the task can be completed on the edge server j before the corresponding expiration date, and if the task can be completed, selecting the task T i Unloading to the edge server j, if the unloading can not be completed, traversing all the edge servers covering the mobile user in turn according to the same calculation formula until the edge server allowing unloading is found, and ending the flow; if all edge servers cannot complete the task before the expiration date of the task, the step S36 is entered;
s36, only considering the tasks with hard expiration date in the edge server, and recalculating the task waiting timeAnd total completion time t i，j The method comprises the steps of carrying out a first treatment on the surface of the Counting the number of tasks violating the expiration date caused by the insert operation, and integrating the task T i And unloading to the edge server with the minimum number of tasks violating the expiration date, and ending the flow.
Further, in step S4, the process of scheduling the task in real time according to the type of the deadline of the task and the status of other running tasks includes the following steps:
s41, establishing a task income model according to a task expiration date;
s42, dividing tasks in the edge server into two types, wherein one type is tasks which can be before the expiration date at present and is recorded as { i } c One type of task that cannot be completed before the expiration date is denoted as { i } u -a }; definition { i } c Loss function c of task in } i，j The method is used for indicating the loss brought to the system if the execution time of the task i is pushed back so that the task cannot be completed before the expiration date; definition { i } u Gain function r of tasks in } i′，j For indicating what would be brought to the system if the execution time of task i' was advanced so that the task could be completed before the expiration dateIncome (E);
s43, from { i } c Select have minc }, have i，j Let a=minc i，j At the same time from { i u Select having maxr i′，j Let b=maxr i′，j The method comprises the steps of carrying out a first treatment on the surface of the If b is greater than or equal to a, the execution sequence of the tasks is interchanged, namely, the task i' is changed from { i } u Remove from { i } and advance its execution time, remove task i from { i } c Removing and pushing the task execution time;
s44, judging { i } c And { i } and u whether the task in the process is all traversed, if not, repeating the step S43, otherwise, ending the flow.
The beneficial effects of the invention are as follows:
(1) The invention provides the task unloading method for perceiving the expiration date in the edge calculation for the first time, so that the edge calculation system can process the task with the hard expiration date, can effectively process the task with the soft expiration date, and enlarges the types of the task unloading of the edge calculation system.
(2) The task allocation algorithm designed by the invention supports the user side to distributively allocate proper edge servers for tasks for calculation. The task scheduling algorithm designed by the invention supports the distributed scheduling of the tasks at the edge server side. The adopted distributed algorithm avoids the problems of single point failure, slow unloading decision and the like brought by the centralized controller.
(3) The invention supports real-time task unloading decision making, namely, when the invention makes task unloading decision making, all information (such as task position, task release time, task expiration date and the like) of all tasks do not need to be known in advance, and the real-time unloading decision making accords with the characteristic that a user dynamically sends a task unloading request in an edge computing system.
Drawings
FIG. 1 is a flow chart of a method of distributed task offloading of deadline awareness in edge computing of the present invention.
FIG. 2 is a schematic diagram of an edge computing task offloading scenario of the present invention.
FIG. 3 is a flowchart of a client-side task allocation algorithm of the present invention.
FIG. 4 is a flow chart of an edge server-side task scheduling algorithm of the present invention.
Fig. 5 is a flowchart of the interaction between the client and the edge server according to the present invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings.
It should be noted that the terms like "upper", "lower", "left", "right", "front", "rear", and the like are also used for descriptive purposes only and are not intended to limit the scope of the invention in which the invention may be practiced, but rather the relative relationship of the terms may be altered or modified without materially altering the teachings of the invention.
Referring to fig. 1, a method for offloading a distributed task perceived by an expiration date in edge computation, the offloading method comprising the steps of:
s1, a mobile user side sends an unloading request of a task generated by a delay sensitive application to a plurality of base stations in a signal coverage range, an edge server corresponding to the base stations calculates the unloading task, and each base station is connected with at least one edge server.
S2, the base station receiving the task unloading request sends the information of the edge server connected with the base station to the mobile user side, wherein the information of the edge server comprises the computing capacity of the server, the data transmission bandwidth and the running state of each task on the server.
S3, the mobile user side distributes edge servers for the tasks in a distributed manner to calculate the tasks by combining the expiration date of the tasks, the expiration date type of the tasks and the information of all the received edge servers; the expiration date type of the task comprises a hard expiration date and a soft expiration date, the income completed by the hard expiration date on time is larger than a preset income threshold, the uncompleted loss of the soft expiration date is smaller than a preset loss threshold, and the income and the loss are calculated based on the application performance of the delay sensitive application; the constraints of the allocation process are: tasks with hard expiration dates can always be completed.
And S4, the edge server receives the distributed tasks sent by the mobile user terminal, and real-time scheduling is carried out on the tasks according to the type of the deadline of the tasks and the states of other running tasks so as to maximize the income of completing the tasks in the edge computing network.
S5, the edge server completes the calculation process of the task according to the scheduling result in the step S4.
Aiming at the defects of the existing task unloading mechanism, the invention provides a method for carrying out task unloading decision in real time, and when a plurality of users want to carry out task unloading, different users can carry out task allocation decision in a distributed mode according to the type of the task unloading deadline and the information of surrounding edge servers. After the edge server receives the task, the task is scheduled in real time according to the type of the expiration date of the task and the states of other running tasks of the server, so that the income of completing the task is maximized.
FIG. 2 is an edge computing task offloading scenario of the present invention. In the edge computing system, each base station is provided with an edge server with certain storage and computing capabilities, and each base station has certain signal coverage. Mobile users within the range of the base station signal can offload the calculation tasks to an edge server at the base station for calculation. The base stations in the edge computing system are densely deployed, each mobile user may be within the signal coverage of multiple base stations, and the mobile user may offload tasks to one of the base stations. Furthermore, each edge server needs to handle multiple computing tasks due to the large number of mobile users. Because of the limited processing power of edge servers, the states of these tasks can be of two types: one class is tasks that the server is executing, and the other class is tasks that wait to be executed in a queued sequence.
FIG. 1 is a flowchart of a task offloading mechanism for deadline awareness in edge computing according to the present invention, including the steps of:
step one, a task generated by a mobile user and provided with the following information: task T i Is a four-member groupWherein d is i The number of bits, w, that need to be transmitted for a task i For the workload of a task->Indicating the expiration date of the execution of the task +.>For the release time of the task, < > for>For the deadline of the task, I i The type of task expiration date is characterized. In an edge computing environment, tasks can be classified into two classes according to their expiration dates, one class being tasks with a hard expiration date, such as virtual reality, augmented reality tasks, which must be completed well before the expiration date, otherwise the performance of the application will be greatly reduced. Another class of tasks is tasks with a soft expiration date, such as video analysis tasks, which properly violate their expiration date without significantly affecting the performance of the application. Different users generate different tasks in real time and broadcast task offloading requests to nearby base stations.
Step two, the base station receives the task unloading request of the user and sends the following information in the edge server connected with the base station to the mobile user: channel bandwidth b between user and server j i，j Transmission power p i，j Channel gain g i，j Noise power w o CPU frequency f j The running state of each task in the edge server. The tasks can be divided into two types according to the running states of the tasks in the server: one is the task that has been offloaded to this edge server, is doing computation or waiting for computation in the queue, and the other is the task that has decided to be offloaded to this server, currently being transmitted.
And thirdly, the mobile user receives information of each edge server transmitted by the nearby base station, and runs a task allocation algorithm to allocate the edge servers for tasks with different expiration dates to carry out task unloading. The specific distribution algorithm flow is shown in fig. 3. The specific flow of the allocation algorithm is as follows: firstly, the mobile user calculates the total completion time of task unloading to the server according to the running state of the existing task on the edge server and the information of task unloading, wherein the completion time comprises task uploading time, task calculating time and task waiting time. The user then detects whether the task can be completed on the edge server before the expiration date. If so, the user assigns tasks to the edge servers. If not, the user determines if there are additional candidate edge servers. If so, calculating the completion time of the task on the server according to the same formula, and judging whether the task can be completed before the expiration date. If not, the user only considers the tasks with the hard expiration date on the server, and recalculates the total completion time of the tasks. This operation is intended to be performed before inserting the offloaded task into the task with the soft deadline. The insert operation may cause the completion time of a task with a soft expiration date to violate its expiration date. And counting the number of tasks violating the expiration date caused by the inserting operation, and unloading the tasks to an edge server with the minimum number of tasks violating the expiration date. The allocation method ensures that the task with the hard expiration date can be completed always, and the task with the soft expiration date properly violates the expiration date.
And step four, the edge server receives tasks unloaded by the user, and a task scheduling algorithm is operated to determine the execution time and sequence of each task on the server so as to maximize the benefit of completing the tasks in the edge computing network. The specific scheduling algorithm flow is shown in fig. 4.
In the invention, an edge server receives tasks unloaded by a user, a task scheduling algorithm is operated to determine the execution time of each task on the server so as to maximize the income of completing the task in an edge computing network, and the scheduling process comprises the following steps:
the specific flow of the scheduling algorithm is as follows: first, the edge server builds a task revenue model according to the task deadline. Specifically, a task with a hard expiration date, if it can be completed before the expiration date, the system will receive a larger benefit if it cannot be completed on the expiration dateThe system will get a larger penalty when done earlier. Compared to tasks with hard expiration dates, tasks with soft expiration dates will get less revenue if they are completed before the expiration date, and less punishment if they cannot be completed before the expiration date. Secondly, the edge servers divide the tasks into two classes, one class being tasks that can be currently before the expiration date, noted as { i } c One type of task that cannot be completed before the expiration date is denoted as { i } u }. Definition { i } c Loss function c of task in } i，j The penalty function represents the penalty to the system if the execution time of the task is pushed back so that the task cannot be completed before the expiration date. Furthermore, define { i } u Gain function r of tasks in } i′，i The benefit function represents the benefit that would be brought to the system if the execution time of the task was advanced so that the task could be completed before the expiration date. Subsequently, the edge server is derived from { i } c Select have min c i，j Let a=min c i，j At the same time from { i u Select having maxr i′，j Let b=maxr i′，j . If b is greater than or equal to a, the execution sequence of the tasks is interchanged, namely, the task i' is changed from { i } u Remove from { i } and advance its execution time, remove task i from { i } c Removed and its task execution time pushed back. If b < a, the procedure ends. Subsequently, the edge server determines { i } c And { i } and u whether the task in the task is traversed entirely, and if not, repeating the scheduling step. Otherwise, the procedure ends.
The scheduling algorithm ensures that the obtained system benefit is a monotonically increasing function when task replacement is performed each time. The benefits achieved by the system are greatest when the replacement is stopped.
And fifthly, each task on the edge server obtains the execution time and sequence of the tasks through a scheduling algorithm. The tasks are sequentially executed according to the sequence determined by the scheduling algorithm, so that larger system benefits are obtained.
Fig. 5 is a flowchart of the interaction between the client and the edge server according to the present invention. First, a task offload request is sent by a mobile user to a nearby edge server. After receiving the request of the user, the edge server sends the information such as the computing capacity of the server, the data transmission bandwidth, the running state of each task on the server and the like to the mobile user. And the mobile user receives the information sent by the edge server, runs a task allocation algorithm, allocates a proper edge server for the task and performs task unloading. And the edge server receives the task uploaded by the user, runs a task scheduling algorithm and sets execution time and sequence for the task. After the task is calculated according to the scheduling algorithm, the server sends the calculated result to the mobile user. At this point, the task offloading process ends.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the invention without departing from the principles thereof are intended to be within the scope of the invention as set forth in the following claims.
Claims (5)
1. A method for offloading tasks in edge computing with deadline awareness, the method comprising the steps of:
s1, a mobile user terminal sends an unloading request of a task generated by a delay sensitive application to a plurality of base stations in a signal coverage range, an edge server corresponding to the base stations calculates the unloading task, and each base station is connected with at least one edge server;
s2, the base station receiving the task unloading request sends the information of the edge server connected with the base station to the mobile user side, wherein the information of the edge server comprises the computing capacity of the server, the data transmission bandwidth and the running state of each task on the server;
s3, the mobile user side distributes edge servers for the tasks in a distributed manner to calculate the tasks by combining the expiration date of the tasks, the expiration date type of the tasks and the information of all the received edge servers; the expiration date type of the task comprises a hard expiration date and a soft expiration date, the income completed by the hard expiration date on time is larger than a preset income threshold, the uncompleted loss of the soft expiration date is smaller than a preset loss threshold, and the income and the loss are calculated based on the application performance of the delay sensitive application; the constraints of the allocation process are: tasks with hard expiration dates can always be completed;
the method comprises the following steps: the mobile user side calculates the total completion time of task unloading to the edge server according to the running state of the existing task on the edge server and the information of task unloading, wherein the completion time comprises task uploading time, task calculating time and task waiting time; then, the mobile user side detects whether the task can be completed on the edge server before the expiration date; if the task can be completed, the mobile user side distributes the task to the edge server; if not, the mobile user terminal judges whether other candidate edge servers exist; if yes, calculating the completion time of the task on the edge server, and judging whether the task can be completed before the expiration date; if the task does not exist, the mobile user side only considers the task with the hard expiration date on the server, and the total completion time of the task is recalculated;
s4, the edge server receives the distributed tasks sent by the mobile user terminal, and real-time scheduling is carried out on the tasks according to the type of the deadline of the tasks and the states of other running tasks so as to maximize the income of completing the tasks in the edge computing network;
s5, the edge server completes the calculation process of the task according to the scheduling result in the step S4.
2. The method of distributed task offloading of deadline awareness in edge computing of claim 1, wherein in step S1 the delay sensitive application generates an ith task T i Is a four-member groupWherein d is i The number of bits, w, that need to be transmitted for a task i For the workload of a task->Indicating the expiration date for executing the task,for the release time of the task, < > for>For the deadline of the task, I i The type of deadline for the task is characterized.
3. The method for distributed task offloading of deadline awareness in edge computing of claim 2, wherein in step S2 the edge server information includes an ith task T i Channel bandwidth b between corresponding mobile user terminal and edge server j i,j Transmission power p i,j Channel gain g i,j Noise power w o CPU frequency f j And the running state of each task in the edge server; the tasks are divided into two types according to the running states of the tasks in the edge server: one is the task that has been offloaded to this edge server, is doing computation or waiting for computation in the queue, and the other is the task that has decided to be offloaded to this server, currently being transmitted.
4. The method for offloading tasks in a distributed manner by sensing an expiration date in edge computing as claimed in claim 3, wherein in step S3, the process of distributing the edge servers for tasks in a distributed manner to perform task computing by combining the expiration date of the task, the expiration date type of the task and all the received edge server information includes the following steps:
s31, calculating the task T according to the following formula i Time of transmission uploaded to edge server j
Wherein r is i,j For the task transfer rate, expressed as:
s32, estimating if the task T is to be executed according to the running state of each task in the edge server i Uploading to edge server j, and waiting time of task in process of receiving task from edge server j to executing task
S33, calculating the task T according to the following formula i Computation time on edge server j
S34, calculating the task T according to the following formula i Total completion time t at edge server j i,j ：
S35, according to t calculated in the step S34 i,j Detection task T i Whether the completion can be carried out on the edge server j before the expiration date, and if the completion can be carried out, the user selects the task T i Unloading to the edge server j, if the unloading can not be completed, traversing all the edge servers covering the mobile user in turn according to the same calculation formula until the edge server allowing unloading is found, and ending the flow; if all edge servers cannot complete the task before the expiration date of the task, the step S36 is entered;
s36, only examineTask waiting time is recalculated by considering tasks with hard expiration dates in edge serversAnd total completion time t i,j The method comprises the steps of carrying out a first treatment on the surface of the Counting the number of tasks violating the expiration date caused by the insert operation, and integrating the task T i And unloading to the edge server with the minimum number of tasks violating the expiration date, and ending the flow.
5. The method for offloading tasks in accordance with the expiration date perception in edge computing according to claim 1, wherein in step S4, the process of scheduling the tasks in real time according to the expiration date type of the tasks and the status of other tasks running on the task itself comprises the following steps:
s41, establishing a task income model according to a task expiration date;
s42, dividing tasks in the edge server into two types, wherein one type is tasks which can be before the expiration date at present and is recorded as { i } c One type of task that cannot be completed before the expiration date is denoted as { i } u -a }; definition { i } c Loss function c of task in } i,j The method is used for indicating the loss brought to the system if the execution time of the task i is pushed back so that the task cannot be completed before the expiration date; definition { i } u Gain function r of tasks in } i′,j For representing the benefits brought to the system if the execution time of the task i' is advanced so that the task can be completed before the expiration date;
s43, from { i } c Select have minc }, have i,j Let a=minc i,j At the same time from { i u Select having maxr i′,j Let b=maxr i′,j The method comprises the steps of carrying out a first treatment on the surface of the If b is greater than or equal to a, the execution sequence of the tasks is interchanged, namely, the task i' is changed from { i } u Remove from { i } and advance its execution time, remove task i from { i } c Removing and pushing the task execution time;
s44, judging { i } c And { i } and u whether or not the tasks in the sequence are all traversedIf not all traversed, repeat step S43, otherwise, end the flow.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110828570.XA CN113791878B (en) | 2021-07-21 | 2021-07-21 | Distributed task unloading method for perceiving expiration date in edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110828570.XA CN113791878B (en) | 2021-07-21 | 2021-07-21 | Distributed task unloading method for perceiving expiration date in edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113791878A CN113791878A (en) | 2021-12-14 |
| CN113791878B true CN113791878B (en) | 2023-11-17 |
Family
ID=79181232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110828570.XA Active CN113791878B (en) | 2021-07-21 | 2021-07-21 | Distributed task unloading method for perceiving expiration date in edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113791878B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920279A (en) * | 2018-07-13 | 2018-11-30 | 哈尔滨工业大学 | A kind of mobile edge calculations task discharging method under multi-user scene |
| CN110647403A (en) * | 2019-10-31 | 2020-01-03 | 桂林电子科技大学 | Cloud computing resource allocation method in multi-user MEC system |
| CN112099932A (en) * | 2020-09-16 | 2020-12-18 | 广东石油化工学院 | Optimal pricing method and system for soft-hard deadline task offloading in edge computing |
| CN112231009A (en) * | 2020-09-17 | 2021-01-15 | 浙江工业大学 | Energy capture network model task calculation unloading decision and scheduling method |
| CN112351503A (en) * | 2020-11-05 | 2021-02-09 | 大连理工大学 | Task prediction-based multi-unmanned-aerial-vehicle-assisted edge computing resource allocation method |
| CN112995023A (en) * | 2021-03-02 | 2021-06-18 | 北京邮电大学 | Multi-access edge computing network computing unloading system and computing unloading method thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10009222B2 (en) * | 2016-03-30 | 2018-06-26 | International Business Machines Corporation | Input method engine management for edge services |
| US20210191827A1 (en) * | 2018-08-30 | 2021-06-24 | Teiefonaktiebolaget LM Ericsson (pub!) | System and method for collaborative task offloading automation in smart containers |
-
2021
- 2021-07-21 CN CN202110828570.XA patent/CN113791878B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108920279A (en) * | 2018-07-13 | 2018-11-30 | 哈尔滨工业大学 | A kind of mobile edge calculations task discharging method under multi-user scene |
| CN110647403A (en) * | 2019-10-31 | 2020-01-03 | 桂林电子科技大学 | Cloud computing resource allocation method in multi-user MEC system |
| CN112099932A (en) * | 2020-09-16 | 2020-12-18 | 广东石油化工学院 | Optimal pricing method and system for soft-hard deadline task offloading in edge computing |
| CN112231009A (en) * | 2020-09-17 | 2021-01-15 | 浙江工业大学 | Energy capture network model task calculation unloading decision and scheduling method |
| CN112351503A (en) * | 2020-11-05 | 2021-02-09 | 大连理工大学 | Task prediction-based multi-unmanned-aerial-vehicle-assisted edge computing resource allocation method |
| CN112995023A (en) * | 2021-03-02 | 2021-06-18 | 北京邮电大学 | Multi-access edge computing network computing unloading system and computing unloading method thereof |
Non-Patent Citations (5)
| Title |
|---|
| Latency Optimization-based Joint Task Offloading and Scheduling for Multi-user MEC System;Tiantian Yang 等;《2020 29th Wireless and Optical Communications Conference (WOCC)》;全文 * |
| Offloading Deadline-aware Task in Edge Computing;Xin He等;《 2020 IEEE 13th International Conference on Cloud Computing (CLOUD)》;全文 * |
| 智能边缘系统中的训练数据收集及任务调度研究;陈玺;《中国优秀硕士学位论文全文数据库 信息科技辑》;全文 * |
| 绿色能源驱动的移动边缘计算动态任务卸载;马惠荣;陈旭;周知;于帅;;计算机研究与发展(09);全文 * |
| 面向边缘计算的资源优化技术研究进展;陈贵海等;《大数据》;第5卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113791878A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509276B (en) | Video task dynamic migration method in edge computing environment | |
| Wei et al. | QoS-aware resource allocation for video transcoding in clouds | |
| CN111381950B (en) | Multi-copy-based task scheduling method and system for edge computing environment | |
| CN110109745B (en) | Task collaborative online scheduling method for edge computing environment | |
| US7856501B2 (en) | Network traffic prioritization | |
| US20050055694A1 (en) | Dynamic load balancing resource allocation | |
| CN110489176B (en) | Multi-access edge computing task unloading method based on boxing problem | |
| CN104168318A (en) | Resource service system and resource distribution method thereof | |
| CN110955463B (en) | Internet of things multi-user computing unloading method supporting edge computing | |
| WO2009026321A2 (en) | Media streaming with online caching and peer-to-peer forwarding | |
| CN110072130B (en) | HTTP/2-based HAS video slice pushing method | |
| Zhong et al. | Age-aware scheduling for asynchronous arriving jobs in edge applications | |
| US10965613B2 (en) | Multi-pipe bandwidth control in hosted systems | |
| US20160080239A1 (en) | Real-time, low memory estimation of unique client computers communicating with a server computer | |
| CN109150756B (en) | Queue scheduling weight quantification method based on SDN power communication network | |
| US20140359182A1 (en) | Methods and apparatus facilitating access to storage among multiple computers | |
| CN111935783A (en) | Edge cache system and method based on flow perception | |
| CN111741249B (en) | Network congestion detection method and device | |
| He et al. | Tians scheduling: Using partial processing in best-effort applications | |
| CN113038187A (en) | Practical network bandwidth allocation method with fair video experience quality | |
| CN116366576A (en) | Method, device, equipment and medium for scheduling computing power network resources | |
| CN115150891A (en) | Interrupt probability auxiliary task unloading optimization method based on mobile edge calculation | |
| WO2015110047A1 (en) | Data processing method and apparatus used for terminal application | |
| CN113791878B (en) | Distributed task unloading method for perceiving expiration date in edge calculation | |
| CN113778675A (en) | Calculation task distribution system and method based on block chain network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |