KR101421603B1 - Real time scheduling method of cyber physical system - Google Patents

Abstract

A real time scheduling method of a cyber physical system is disclosed. According to the embodiment of the present invention, the real time scheduling method of the cyber physical system comprises the steps in which a computing node receives information on physical elements and information on cyber elements from each of multiple opponent nodes which are located in the different region via a network; in which the computing node schedules the execution order of tasks of multiple opponent nodes by utilizing the information on physical elements and the information on cyber elements; and in which the computing node performs the tasks of the opponent nodes according to the scheduling.

Description

REAL TIME SCHEDULING METHOD OF CYBER PHYSICAL SYSTEM [

The present invention relates to a real-time scheduling method of a cyber physical system, and more particularly, to a method for real-time scheduling of a cyber physical system, in which a computing node needs to move to a region where a counterpart node is located for task execution in a cyber- And real-time scheduling techniques in which the execution of a task is completed within a deadline by considering both cyber elements and physical elements.

The cyber physics system is a system in which many cyber systems composed of networked embedded systems and physics systems (living space and industrial space apparatuses, machines, devices, facilities, etc.) are closely linked to provide users with useful and convenient services to provide.

Unlike embedded systems, which are focused on high performance hardware and software development, application areas of cyber physics systems that require high reliability and persistence in various real world such as defense, robotics, energy, healthcare, transportation and entertainment It is attracting attention as a new industrial field.

Most application fields of cyber physics system are characterized in that a task execution subject node or task execution object node moves from one region to another region and performs a task in real time. For example, a medical care support (corresponding to a task performing body) that supports medical care (corresponding to a task) to a battle box (corresponding to task performing object nodes) moves to a battle box. Conversely, when battlefields move to medical support.

In this case, if the task performing entity or the task performing object node must move to multiple regions in order to perform the task, it should be determined in which region the task should be performed first.

Cyber elements such as cycle, execution time, deadline, and start time are considered as factors for scheduling the task execution order, but the physical elements are not considered.

As a result, the task execution subject node or the task execution object node can not perform the task within a predetermined deadline.

A prior art related to the present invention is Korean Patent No. 10-1081157 (registered on November 01, 2011).

A real-time scheduling method of a cyber-physics system is proposed in which a task is performed within a deadline by considering both a cyber element and a physical element when a computing node needs to move to an area where a counterpart node is located.

The problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems that are not mentioned can be clearly understood by those skilled in the art from the following description.

According to an aspect of the present invention, there is provided a method for real-time scheduling of a cyber physical system, comprising: receiving a physical element information and cyber element information from a plurality of counterpart nodes located in different regions through a network; Scheduling a task execution order for a plurality of counterpart nodes by the computing node using the physical element information and the cyber element information; And the computing node performing tasks for a plurality of counterpart nodes in accordance with the scheduling.

The scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information may include calculating physical movement information of the physical element information for each of a plurality of counterpart nodes, The task execution order for a plurality of correspondent nodes can be scheduled using the calculated physical movement time and cyber element information of the corresponding node.

The physical element information of each of the plurality of correspondent nodes includes position information of the corresponding node, and the cyber element information of each of the plurality of counterpart nodes includes task execution deadline time information and task execution allowance time information at the corresponding node .

The step of scheduling a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information may include calculating an actual task execution deadline time using a physical movement time and a task execution deadline for each of a plurality of counterpart nodes, Effective deadlines can be obtained to schedule tasks for multiple counterpart nodes.

The actual task execution deadline for each of a plurality of correspondent nodes can be obtained by a difference between a physical movement time of the corresponding node and a task execution deadline.

The step of scheduling a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information may include scheduling a plurality of counterpart nodes so that a task of a counterpart node having a small task execution deadline is processed first, The task execution order can be scheduled.

The step of scheduling a task execution order for a plurality of correspondent nodes using the physical element information and the cyber element information may include calculating a real task execution allowance time using a physical movement time and a task execution allowance time for each of a plurality of counterpart nodes Effective slack time can be calculated to schedule task execution order for a plurality of correspondent nodes.

The step of scheduling a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information may include scheduling a task for a plurality of counterpart nodes so that the task of the counterpart node, The order of execution can be scheduled.

Wherein the step of scheduling task execution orders for a plurality of counterpart nodes using the physical element information and the cyber element information comprises the steps of performing task execution for a plurality of counterpart nodes using a schedule weight value obtained using the following equation The order can be scheduled.

[ Equation ]

(

)는 가중치이고,

는 타스크 수행 여유시간이며,

는 물리적 이동시간을 나타낸다.)(At this time,

(

) Is a weight,

Is the task execution time,

Represents the physical movement time.)

The step of scheduling task execution orders for a plurality of counterpart nodes using the physical element information and the cyber element information may include the step of assigning a task to a plurality of counterpart nodes so that a task of a counterpart node having a smaller schedule weight value is preferentially processed. The order of execution can be scheduled.

According to the embodiment of the present invention, when the computing node needs to move to the area where the counterpart node is located, the task execution deadline compliance ratio is improved by scheduling the task execution order considering both the cyber element and the physical element .

FIG. 1 is a flowchart illustrating a real-time scheduling method of a cyber physical system according to an embodiment of the present invention.
FIG. 2 is a diagram illustrating an application example of a real-time scheduling method of a cyber physical system according to an embodiment of the present invention.
3 is a diagram illustrating an application of a real-time scheduling method of a cyber physical system according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Embodiments of the present invention are provided to more fully describe the present invention to those skilled in the art, and the following embodiments may be modified in various other forms, The present invention is not limited to the following embodiments. Rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the invention to those skilled in the art.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an," and "the" include plural forms unless the context clearly dictates otherwise. Also, " comprise "and / or" comprising "when used herein should be interpreted as specifying the presence of stated shapes, numbers, steps, operations, elements, elements, and / And does not exclude the presence or addition of one or more other features, integers, operations, elements, elements, and / or groups. As used herein, the term "and / or" includes any and all combinations of one or more of the listed items.

Although the terms first, second, etc. are used herein to describe various elements, regions and / or regions, it should be understood that these elements, components, regions, layers and / Do. These terms do not imply any particular order, top, bottom, or top row, and are used only to distinguish one member, region, or region from another member, region, or region. Thus, the first member, region or region described below may refer to a second member, region or region without departing from the teachings of the present invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings schematically showing embodiments of the present invention. In the figures, for example, variations in the shape shown may be expected, depending on manufacturing techniques and / or tolerances. Accordingly, embodiments of the present invention should not be construed as limited to any particular shape of the regions illustrated herein, including, for example, variations in shape resulting from manufacturing.

1 is a flowchart of a real-time scheduling method of a cyber physical system according to an embodiment of the present invention.

Referring to FIG. 1, the present invention is applied to a case where a computing node needs to move to an area where a counterpart node is located, in order to perform a task. That is, when a computing node that performs a task and a plurality of counterparts that are task execution objects are physically located in different areas, the computing node moves to an area where a plurality of counterparts are located, . In this case, the task execution order can be determined using physical element information and cyber element information, which will be described later.

In order to schedule the task execution order, the computing node first receives physical element information and cyber element information from a plurality of counterpart nodes located in different regions through the network (S10). The network may be a wired network or a wireless network, or a combination of a wired network and a wireless network. Accordingly, it should be understood that a computing node and a plurality of correspondent nodes are all connected to a wired network and a wireless network to include a communication module capable of performing data communication.

The computing node schedules a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information (S20).

That is, the computing node computes the physical movement time between the computing node and the corresponding node using the physical element information for each of the plurality of counterpart nodes, calculates the physical movement time between the computing node and the counterpart node, The task execution order can be scheduled.

At this time, the physical element information of each of the plurality of counterpart nodes may include position information of the counterpart node. The cyber element information of each of the plurality of correspondent nodes may include task execution deadline time information and task execution time information at the corresponding node.

The computing node schedules a task execution order using physical element information and cyber element information of each of a plurality of counterpart nodes.

In one embodiment, the computing node obtains an actual deadline of a task using a physical movement time and a task execution deadline for each of a plurality of correspondent nodes, Lt; / RTI > In this case, the actual task execution deadline for each of a plurality of correspondent nodes can be obtained by a difference between the physical movement time and the task execution deadline of the corresponding node.

The computing node may schedule a task execution order for a plurality of counterpart nodes so that the task of the counterpart node having a smaller effective deadline is processed first. This corresponds to the concept of the Real Earliest Deadline First (R-EDF) algorithm.

In another embodiment, the computing node obtains an actual slack time using a physical movement time and a task execution time (slack time) for each of a plurality of correspondent nodes, The task execution order can be scheduled. That is, the computing node can schedule a task execution order for a plurality of counterpart nodes so that a task of a counterpart node having a small actual task execution time is processed for each of a plurality of counterpart nodes. This corresponds to the concept of the Real Least Slack Time First (R-LST) algorithm.

In yet another embodiment, the computing node may schedule a task execution order for a plurality of counterpart nodes using the schedule weight values obtained using Equation (1).

(

)는 가중치이고,

는 타스크 수행 여유시간이며,

는 상대 노드의 물리적 이동시간을 나타낸다.At this time,

(

) Is a weight,

Is the task execution time,

Represents the physical movement time of the correspondent node.

The computing node may schedule a task execution order for a plurality of counterpart nodes so that a task of a counterpart node having a smaller schedule weight value is preferentially processed. This corresponds to the concept of the Least Result First Using Adaptive Weight (LRF-AW) algorithm.

After the scheduling of the task execution order of the plurality of counterpart nodes is determined, the computing node performs a task on a plurality of counterpart nodes according to the scheduling (S30). At this time, each time the computing node completes the task according to the scheduling, the computing node can process the task of the counterpart node having the smallest task performance margin time by comparing the task performance margin time of each of the remaining counterpart nodes to perform the task.

Hereinafter, a case in which a task execution order is scheduled for a plurality of correspondent nodes in consideration of physical element information and cyber element information will be described with reference to FIG. 2 as an example.

First, there are the Earliest Deadline First (EDF) algorithm, the Least Slack Time First (LST) algorithm, the Traveling Salesman Algorithm (TSA), and the Optimal Scheduling Algorithm (OSA).

The EDF algorithm is an algorithm that performs the task of a relative node with a short deadline, first of all, at a computing node.

The LST algorithm is an algorithm that performs the task of a relative node with a short slack time around a computing node.

TSA is an algorithm that processes tasks in the order of shortest path after full comparison of all possible paths.

OSA is an algorithm that processes tasks in the order of maximum performance after full comparison of all possible paths.

On the other hand, there are R-EDF algorithm, R-LST algorithm, LRF-AW algorithm, and the like as described above for simultaneously considering physical element information and cyber element information. The description thereof has been described above, and therefore, it will be omitted.

A performance comparison of the algorithms for scheduling the task execution order will be described with reference to FIG.

Referring to FIG. 2, C is a computing node that moves to correspondent nodes (S1, S2, S3, S4) to perform a task. The physical movement time required for C to move to S1, for example, physical movement time is 6, the physical movement time for C to move to S2 is 14, and the physical movement time for C to move to S3 is 11 And the physical move time required for C to move to S4 is 7 and the physical move time required for C to move from S1 to S2 is 5 and the physical move time for C to move from S1 to S3 is 8 and C The physical move time required to move from S1 to S4 is 4, the physical move time required for C to move from S2 to S3 is 4, the physical move time to move from S2 to S4 is 16, and C The physical movement time required to move from S3 to S4 may be nine. The time unit may be seconds, but is not limited thereto.

The task execution margin of the corresponding nodes in (22, 2), (18, 3), (15, 1), (8, 7) described at the top of the correspondent nodes S1, S2, Slack time and task execution deadline. For example, in the case of S1, it is expressed as (22, 2), "22" represents the task execution time of S1, and "2" represents the task execution deadline of task S1.

It is assumed that the cyber physical system illustrated in FIG. 2 is a defense cyber physical system that performs network-centered operations. S1, S2, S3, and S4 are assumed to be combat-capable, and C is assumed to be a medical support that supports combat. S1, S2, S3 and S4 require real-time treatment (corresponding to the task) according to the state of the soldiers' injury.

Accordingly, the medical support organization determines the task execution order and performs the task.

The task execution order can be determined by the above-described EDF algorithm, LST algorithm, REDF algorithm, RLSF algorithm, LRF-AW algorithm, and TSA.

In the case of the EDF algorithm, the task execution sequence is S4-> S3-> S2-> S1 and the total cost due to physical movement is 25 (= 7 + 9 + 4 + 5) Execution deadline compliance rate) is "0 ".

In the case of the LST algorithm, the task execution order is S4-> S3-> S2-> S1, the total cost due to physical movement is 25 (= 7 + 9 + 4 + 5) 1 ".

In the case of the REDF algorithm, the task execution order is S2, the total cost due to the physical movement is "14 "

In the case of the RLSF algorithm, the task execution sequence is S4-> S1, the total cost due to the physical movement is 11 (= 7 + 4), and the real-

In the case of the LRF-AW algorithm (α = 0.4), the task execution order is S1, the total cost due to the physical movement is "6", and the real-time medical support success rate is "1".

In TSA, the task execution sequence is S4->S1->S2-> S3 and the total cost due to physical movement is 20 (= 7 + 4 + 5 + 4) Deadline compliance rate) is "3 ".

As described above, according to the scheduling algorithm, it can be confirmed that there is a difference between the cost according to the physical movement time and the real-time medical support rate (the task execution deadline compliance rate).

The real-time scheduling method of the cyber physical system according to the embodiment of the present invention can be applied to the fields as shown in Table 1 shown in FIG.

The present invention has been described above with reference to the embodiments. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. Therefore, the scope of the present invention is not limited to the above-described embodiments, but should be construed to include various embodiments within the scope of the claims and equivalents thereof.

Claims (10)

Receiving a physical element information and cyber element information from a plurality of counterpart nodes located in different regions through a network;
Scheduling a task execution order for a plurality of counterpart nodes by the computing node using the physical element information and the cyber element information; And
And the computing node performing a task for a plurality of correspondent nodes according to the scheduling.
The method according to claim 1,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
A physical movement time between a computing node and a corresponding node is calculated using physical element information for each of a plurality of counterpart nodes, and a task execution is performed on a plurality of counterpart nodes using the computed physical movement time and cyber element information of the corresponding counterpart Wherein the scheduling of the real-time scheduling of the cyber physical system is performed according to the scheduling order.
The method of claim 2,
The physical element information of each of the plurality of counterpart nodes includes position information of the counterpart node,
Wherein the cyber element information of each of the plurality of correspondent nodes includes task execution deadline time information and task execution allowable time information at the corresponding node.
The method of claim 3,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
Wherein the scheduling of the task execution order of the plurality of correspondent nodes is performed by obtaining an actual deadline of the task using the physical movement time and the task execution deadline for each of the plurality of correspondent nodes, Scheduling method.
The method of claim 4,
Wherein the actual task execution deadline is determined as a difference between a physical movement time of the corresponding node and a task execution deadline for each of the plurality of correspondent nodes.
The method of claim 5,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
And scheduling a task execution order for a plurality of counterpart nodes so that a task of the counterpart node having a smaller actual task execution deadline is preferentially processed.
The method of claim 3,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
Wherein the task scheduling unit schedules a task execution order for a plurality of correspondent nodes by obtaining an effective slack time using a physical movement time and a task execution allowance time for each of a plurality of counterpart nodes, Real time scheduling method.
The method of claim 7,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
And scheduling a task execution order for a plurality of counterpart nodes so that the tasks of the counterpart node having a small actual task execution allowance time are prioritized.
The method of claim 3,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
And scheduling a task execution order for a plurality of correspondent nodes using a schedule weight value obtained using the following equation.
[ Mathematical Expression ]

(At this time,

(

) Is a weight,

Is the task execution time,

Represents the physical movement time.)
The method of claim 9,
Wherein the scheduling of a task execution order for a plurality of counterpart nodes using the physical element information and the cyber element information comprises:
And scheduling a task execution order for a plurality of counterpart nodes so that a task of the counterpart node having a smaller schedule weight value is preferentially processed.

Images