KR101898144B1 - Method and apparatus for a task scheduling scheme in energy harvesting driven system - Google Patents

Abstract

A method for scheduling a task in a system driven by energy harvesting is disclosed. According to an embodiment of the present invention, the method for scheduling a task in a system driven by energy harvesting comprises the following steps: a task scheduling apparatus receives information on an exceptional situation which can be influence on energy harvesting; the task scheduling apparatus calculates the amount of available energy based on the remaining amount of energy in an energy storage and at least one of the amount of energy supplied through energy harvesting and the amount of energy consumed by performing a task; and the task scheduling apparatus adjusts a priority of the task based on the amount of available energy.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and apparatus for task scheduling in a system driven by energy harvesting,

The present invention relates to a method for scheduling tasks in a system driven by energy harvesting and an apparatus for performing the method. More particularly, the present invention relates to a method for re-adjusting a priority of a task in consideration of energy supply and demand in a device that receives energy required for driving using energy harvesting technology, and an apparatus for performing the method.

Internet of Things (IoT) is a technology that allows people to connect all things that can communicate with each other through a network so that they can communicate with people, objects, and objects anytime, anywhere. All objects can be classified as objects and can be used as sensors or data production and available modules with near or far communication capabilities.

IoT technology is used in various fields such as smart home, smart home appliance control, intelligent building, automobile, personal behavior analysis, and health care. Particularly, development of IoT devices capable of controlling illumination of spaces or electronic devices in homes, offices, workplaces, and the like is being actively carried out and implemented in a form capable of interlocking with user terminals.

Energy harvesting is also used to increase the utilization of these IoT devices. For example, it is possible to increase the lifetime and utilization of a sensor compared to a simple battery-based sensor by joining a solar cell to a sensor and supplying energy necessary for driving the sensor itself. Particularly, the utilization of IoT devices that need to operate in an environment where the power supply is unlikely, and wearable devices that require long-time operation can be further enhanced.

Despite increasing the utilization of IoT devices by combining IoT devices and energy harvesting, the task scheduling method of energy harvesting-driven systems is still far from being a battery-driven system. For example, simply schedules a task based on the energy stored in the current device, i.e., the amount of energy remaining in the storage that stores energy such as a battery or supercapacitor.

Conventional task scheduling method based on energy remaining amount in energy storage determines whether or not to perform a task according to the priority of the task when energy remaining amount in energy storage falls below a certain level. Therefore, high-priority tasks remain in operation even if the energy remaining in the energy storage is low, and low-priority tasks stop operating when the energy remaining in the energy storage is low. This conventional task scheduling method is maintained until the amount of energy remaining in the energy storage is restored to a sufficient state.

Such a conventional task scheduling method has a disadvantage that it does not accurately reflect the amount of energy obtained through energy harvesting. Even if the amount of energy remaining in the energy storage is low, it is possible to perform the task sufficiently considering the energy supplied through the energy harvesting. There is a need for a method to schedule tasks considering energy harvesting.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a method for scheduling a task in a system driven by energy harvesting and an apparatus for performing the method.

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

The task scheduling method in a system driven by energy harvesting according to an exemplary embodiment of the present invention includes: receiving information on an exception situation that may affect energy harvesting; Wherein the task scheduling device is operable to determine whether or not an exception occurs when at least one of the amount of energy received through the energy harvesting and the amount of energy consumed due to the performance of the task, Calculating an amount of energy; And the task scheduling apparatus adjusting the priority of the task based on the amount of available energy.

Preferably, the energy harvesting is energy harvesting using solar energy, and the information on the exceptional situation is weather information.

The computing of the amount of available energy may include subtracting the amount of energy consumed by the performance of the task from the amount of energy supplied through the energy harvesting plus the amount of energy remaining in the energy storage can do.

Preferably, the step of adjusting the priority of the task may include lowering the priority of the task when it is predicted that a situation in which the amount of the available energy is insufficient during execution of the task.

Preferably, the step of lowering the priority of the task further comprises: re-performing the step of re-executing the amount of available energy for the first task having a higher priority than the task; And lowering the priority of the first task when it is predicted that a situation in which the amount of the re-computed available energy is insufficient during execution of the first task is expected to occur.

The method may further include maintaining the existing task scheduling policy as it is when the information about the exception situation is not received.

In a system driven by energy harvesting according to an embodiment of the present invention, a task scheduling apparatus includes a network interface; One or more processors; A memory for loading a computer program executed by the processor; And a storage for storing a task and a priority of the task, the computer program comprising: an operation for receiving information on an exception situation that may affect energy harvesting; And an operation for calculating an amount of available energy based on at least one of the amount of energy supplied through the energy harvesting and the amount of energy consumed due to the performance of the task and the remaining energy amount in the energy storage when the exception occurs, ; And adjusting the priority of the task based on the amount of available energy.

Preferably, the operation for calculating the amount of available energy includes an operation of subtracting the amount of energy consumed due to the performance of the task from a value obtained by adding the amount of energy supplied through the energy harvesting and the amount of energy remaining in the energy storage can do.

Preferably, the operation of adjusting the priority of the task may include an operation of lowering the priority of the task when it is predicted that a situation in which the amount of the available energy is insufficient during execution of the task.

Preferably, the operation of lowering the priority of the task may include: re-performing the step of re-executing the amount of available energy for a first task having a higher task priority than the task; And an operation of lowering the priority of the first task when it is predicted that a situation in which the amount of the re-computed available energy is insufficient during execution of the first task is expected to occur.

The effects according to the embodiment of the present invention are as follows.

In a system using energy harvesting technology, tasks can be scheduled considering the amount of energy supplied through energy harvesting. In particular, considering the external factors affecting energy harvesting, such as weather, the amount of energy received can be rapidly changed to reflect the priorities of tasks.

When scheduling a task on an IoT device that is powered by energy harvesting, if an abrupt change in the amount of energy acquired is anticipated, the exception information is reported to the IoT device to indicate that the task execution failure . This reduces the cost of rerunning failed tasks.

If the task execution fails, a backup and recovery process is needed to re-execute the failed task. This backup and recovery process adversely affects the task execution time and lowers the energy efficiency. Using the improved task scheduling method proposed in the present invention, it is possible to schedule a task considering an energy supply amount through energy hubbing and external factors, thereby minimizing the failure of task execution.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood to those of ordinary skill in the art from the following description.

1 is a view for explaining an energy harvesting technique.
2 is a view for explaining a difference in energy supply and demand according to weather in energy harvesting using photoelectric effect.
3 is a flowchart of a task scheduling method considering energy hubbing in the prior art.
FIG. 4 is a diagram for explaining a difference in energy supply and demand according to a sudden change in weather in energy harvesting using a photoelectric effect.
5 is a flowchart of a task scheduling method considering energy harvesting according to an embodiment of the present invention.
FIG. 6 is a view for explaining an energy harvesting-based IoT device according to an embodiment of the present invention.
FIGS. 7 to 11C are diagrams for explaining a method of scheduling a task in a system driven by energy harvesting according to an embodiment of the present invention.
12 is a hardware configuration diagram of a task scheduling apparatus in a system driven by energy harvesting according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms first, second, A, B, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

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

1 is a view for explaining an energy harvesting technique.

Referring to FIG. 1, an example of various energy sources used in energy harvesting technology can be seen. Energy Harvesting is a technology that makes it possible to collect the energy that is inadvertently discarded and replace it with electricity. Energy harvesting is composed of gravitational energy, light energy, position energy, electromagnetic energy, vibration energy and body energy. Although the amount of energy collected is not large, it can be very useful in small-size low-power electronic devices such as wearable appliances, health care appliances, and the Internet.

Currently, most of the devices used in energy harvesting technology are using four physical phenomena such as photoelectric effect, piezoelectric effect, thermoelectric effect and RF technology. The photoelectric effect is a phenomenon in which metals emit electrons when they absorb high-energy electromagnetic waves, and a representative example of energy harvesting technology using photoelectric effect is a solar cell.

2 is a view for explaining a difference in energy supply and demand according to weather in energy harvesting using photoelectric effect.

A solar cell is a device that converts light energy into electrical energy. The solar module is composed of several solar cells. Solar cells are classified into crystalline silicon, amorphous silicon, and compound semiconductor depending on the material. When the solar cell receives enough light energy, the electrons inside the solid are free electrons that can move freely away from the attraction of the atomic nucleus. This is called the photoelectric effect. Free electrons deviating from the constraint of the nucleus move toward the n-type semiconductor according to the principle of the pn junction, and the current of the electron becomes the current soon.

As shown in FIG. 2, since the solar cell is greatly influenced by the amount of sunlight, there is a large energy difference between the clear day and the overcast day. Referring to FIG. 2, the horizontal axis represents time and the vertical axis represents the intensity of current flowing in the solar cell. The larger the current flowing in the solar cell, the greater the amount of energy supplied through the energy harvesting.

Solar cells are also greatly influenced by time. As can be seen in Figure 2, it is difficult to supply and receive energy before and after sunrise, and it receives the most energy in the day when the sun rises high. Since the solar cell is affected by time and weather, it is necessary to reflect the solar cell in the task scheduling when the system is operated.

As a matter of course, in addition to the task scheduling method based on the simple battery remaining amount, there has been a task scheduling method considering energy harvesting. In other words, when energy is supplied through energy harvesting, it has a periodicity. Therefore, it is possible to estimate the amount of energy to be supplied next based on the current time information, the amount of energy supply during the past time, and the increase / decrease trend. It schedules the task considering both the remaining battery capacity and the expected amount of energy to be received.

3 is a flowchart of a task scheduling method considering energy hubbing in the prior art.

Referring to FIG. 3, a conventional task scheduling method considering energy harvesting predicts the amount of energy supplied and received through energy harvesting (S1100). For example, the amount of energy received depends on whether the current time is night or night, and this periodicity is taken into account.

Therefore, the available energy is calculated based on the amount of currently stored energy plus the amount of energy to be received in the future, and the task is executed only when the available energy is sufficient to perform the task (S1200). However, the conventional task scheduling method does not guarantee the full execution of the task when the amount of energy supply and demand changes rapidly.

If an exception occurs due to an external factor such as suddenly blurring of the day (S1300), the amount of energy to be supplied may be reduced and a task failure may occur. Then, the information of the failed task is backed up (S1400). When the energy availability is sufficiently secured, the task information is recovered again (S1500) and the task is re-executed.

In summary, there is a conventional method of scheduling a task based on the remaining amount of the battery, and a method of scheduling a task by further improving the amount of energy supply through energy harvesting. However, even such a method of scheduling tasks by predicting the supply and demand of energy has a drawback that it can not actively respond to external factors such as weather change.

FIG. 4 is a diagram for explaining a difference in energy supply and demand according to a sudden change in weather in energy harvesting using a photoelectric effect.

Referring to FIG. 4, we can see the amount of energy supply in the morning when the weather is clear (Clear Day), and when the weather is suddenly cloudy (Overcast Day) since the afternoon. If a task is scheduled considering only the periodicity of energy supply and demand by energy hubbing by the same method as the conventional FIG. 3, a task failure may occur when there is a sudden change due to an external factor as shown in FIG.

That is, if there is a large difference between the amount of the available energy and the amount of available energy of the actual system due to the rapid change in the weather, the conventional task scheduling method as shown in FIG. 3 can not prevent the task failure. As a result, the information of the task being executed is backed up, and when the energy availability becomes sufficient, the task information is restored and re-executed.

Task backup and recovery processes cause additional energy consumption, so it is desirable to minimize this from a system point of view. In other words, reducing task failures saves the energy consumed by backup and recovery. In order to do this, sudden external factors such as Fig. 4 should be reflected in task scheduling.

In order to solve this problem, the method proposed in the present invention is a method of recognizing a situation in which energy supply and demand is suddenly changed in a system driven by energy harvesting and changing a task scheduling policy. This can reduce task failures and save energy from backup and recovery.

5 is a flowchart of a task scheduling method considering energy harvesting according to an embodiment of the present invention.

Referring to FIG. 5, a modified task scheduling method proposed by the present invention can be seen. In the present invention, further exception information is further received to schedule the task (S2100), and if an exception occurs, the scheduling policy is changed (S2200, S2400). Of course, if the exception information is received but no exception occurs, the existing scheduling policy is maintained (S2300).

An exception here is an external factor that can affect energy harvesting, for example, a sudden diurnal change. If the weather changes suddenly, as shown in FIG. 4, the amount of energy supplied is rapidly changed, so it is reflected in the task scheduling. In addition, various external factors may be an exception depending on the type of energy source used in energy harvesting.

In a more specific example, exception information on weather extremes is received through the network. Of course, in some cases there may be situations where communication is not possible because of the small amount of available energy, or weather information can not be received due to other exceptional circumstances. If the weather information can not be received, the existing scheduling policy is maintained (S2300). That is, the amount of energy to be received in the future based on the tendency of the amount of energy supplied at the previous time, and performs scheduling.

On the other hand, when the weather information can be received, the scheduling policy is determined based on the exception occurrence information. When an exception occurs, it increases the priority of tasks with low energy consumption and lowers tasks with relatively high energy consumption. Or the operation mode is changed to the sleep state, thereby reducing the possibility that a task failure may occur. Of course, even if exception information is received, the existing task scheduling policy remains unchanged unless an exception occurs.

FIG. 6 is a view for explaining an energy harvesting-based IoT device according to an embodiment of the present invention.

Referring to FIG. 6, energy sources of energy harvesting technology include solar energy, thermal energy, vibration energy, and RF technology (RF / EM). Based on these energy sources, energy harvesters generate electrical energy and store it in energy storage. However, since the amount of energy received by energy harvesting varies depending on external factors, it receives weather information through a separate I / O bus and reflects it in the scheduling policy.

Here, external factors that affect energy harvesting are called exception information. One example of exception information is weather information. However, since additional overhead is generated in receiving and processing exception information such as weather information, analysis of weather information can be performed in the host system, and only information on the exception situation can be transmitted to the IoT device.

The task scheduling method proposed by the present invention has been described above. Next, a task scheduling method proposed by the present invention will be described with reference to FIGS. 7 through 11C, with reference to more specific drawings.

FIGS. 7 to 11C are diagrams for explaining a method of scheduling a task in a system driven by energy harvesting according to an embodiment of the present invention.

Referring to FIG. 7, the amount of supply of energy from the reference time 0 second to 51 seconds is illustrated. The amount of energy supply and demand illustrated in Fig. 7 is one example for helping understanding of the invention. In Fig. 7, the amount of energy supplied / received in a general case is indicated in blue. However, when an exception occurs between 14 and 26 seconds, the amount of energy supplied is indicated in orange. As can be seen in FIG. 7, when the exception occurs, the amount of energy received is reduced.

The amount of energy received below means the amount of energy received through energy harvesting. The amount of available energy is defined as the sum of the amount of energy stored in the existing energy storage and the amount of energy being received. If the energy supply is less than the amount of energy consumed by the task, then the amount of total available energy decreases. Conversely, if the amount of energy received exceeds the amount of energy consumed by the task, the amount of total available energy increases.

8A to 8B, information regarding a task to be used for description in the present invention can be seen. Tasks basically support priority-based preemptive scheduling. Priority-based preemptive scheduling means executing from a higher priority task according to a predetermined priority.

Referring to FIG. 8A, tasks T1 to T5 are illustrated. Each execution time is illustrated in seconds, and the energy consumed at that time is illustrated. The priority of each task is also illustrated. Priority-based preemption scheduling executes a task with a higher priority first, so that if the task is sorted in the Ready List according to the task, as shown in FIG. That is, the task is executed in the order of T2> T3> T1> T4> T5 in the order of priority.

FIG. 9 is a flowchart illustrating a process when the task of FIGS. 8A and 8B does not generate an exception. Referring to FIG. 9, it can be seen that the task is performed according to the priority according to the execution time for each task. In Fig. 9, blue indicates the amount of energy supplied and the gray area indicated in the task indicates the amount of energy consumed by each task.

Referring to FIG. 9, although the amount of energy to be supplied is relatively similar, the available energy is reduced when the T1 task with a large energy consumption is performed, and the available energy is increased when the T4 and T4 tasks with low energy consumption are performed . Of course, when performing a T1 task, the available energy decreases, but it has a value larger than 0, so it can perform the T1 task stably.

10A to 10C show a process in which a task failure occurs under the conventional task scheduling method when an exception occurs in this situation.

Referring to FIG. 10A, FIG. 7 exemplifies how the performance of a task progresses when an exceptional situation occurs and the amount of energy supplied and received is reduced. Comparing FIG. 9 with FIG. 10A, it can be seen that there is a shortage of available energy about 17 seconds in the middle of the task T1. In this case, the task of T1 is suspended and a task failure occurs.

That is, from 17 seconds during the execution of the T1 task, the available energy becomes insufficient to execute the T1 task, and thus the T1 task failure occurs. T1 task should be executed for 11 seconds, but task failure occurs after about 7 seconds. If a task failure occurs, charge the amount of available energy until the task can be performed sufficiently and keep the system in an Idle state.

In this case, we are charging energy until we can hold the Idle state for 17-26 seconds and restart the T1 task. T1, T4, and T5 are executed in this case. Therefore, T1, T4, and T5 are executed sequentially from the T1 task according to the existing priority-based scheduling policy.

In other words, the Ready List is changed from the state shown in FIG. 10B to the state shown in FIG. 10C in which the execution of T2 and T3 is completed and the task failure occurs during execution of T1, and the task is executed again from T1. Charges energy between 17-26 seconds and T1 task starts to replay from 27 seconds. If a task failure occurs, it is assumed that the task is restarted from the beginning, not from the point of failure.

Therefore, the T1 task is restarted from the beginning, not starting from the failure time of 7 seconds. Since the available energy is fully charged, execution of tasks T1, T4, and T5 is completed without failure. The ending time of all tasks is 51 seconds, which means that it takes more time to recharge the available energy and time to re-execute the task until it is enough to execute the task, and 16 seconds more time than if the exception did not occur do. If the exception situation can not be predicted as shown in FIGS. 10A to 10C, overhead occurs in terms of execution time and total energy consumption. To overcome this problem, a scheduling policy for receiving exception information before an exception occurs is proposed.

Referring to FIGS. 11A to 11C, a task scheduling method proposed by the present invention is applied to FIGS. 10A to 10C. The task scheduling method proposed in the present invention recognizes beforehand that an exception situation in which the supply and demand energy can be drastically reduced occurs, and receives information on the exception situation through the network before the exception condition occurs (7 seconds).

Based on the received exception information, the task scheduling policy is changed to prevent the task failure and save the energy to be used next time before sudden changes in energy supply and demand occur. That is, it can be seen that the task scheduling policy as shown in FIG. 8A is adjusted as shown in FIG. 11B. In the past, tasks were scheduled in the order of T2> T3> T1> T4> T5, but the priority of tasks was readjusted in order of T3> T4> T5> T2>

In the example of FIG. 10C, a list of tasks when the T1 task fails can be seen. However, as shown in FIG. 11C, when the task scheduling method proposed in the present invention is applied, the energy consuming T1 is not executed first, but instead the T4 task and the T5 task are executed first to scale the energy, You can adjust it to run T1 when the situation is sufficient to perform the task.

If the task scheduling policy is changed as shown in FIG. 11B and FIG. 11C, the task is not performed after the first T2 and T3 tasks are executed, but the task is performed starting from a task with a low energy consumption, and the decrease in available energy is minimized. Charge. If the exception information can be received in advance, it is possible to prevent the task failure by changing the existing scheduling policy into a scheduling policy based on the energy consumption of the task.

11A, if the exception information can be received in advance, the idle task is executed until the time when the task is re-executed according to the task failure and the task can be re-executed, and the time for charging the energy is not consumed It is possible to reduce the time required for the entire task to be performed. Comparing FIG. 10A with FIG. 11A, it is reduced to 51-> 35 by 16 seconds, and the total energy consumption consumed can be reduced.

As described above, a method of scheduling a task in a system driven by energy harvesting proposed in the present invention has been described. The scheduling method proposed in the present invention relates to a method for handling an exception situation that may occur in the energy supply and demand process in a small device that receives energy through energy harvesting.

For example, when energy is supplied using energy sources such as solar cells and wind power, the amount of energy supplied and received is irregular because the energy received is affected by the surrounding environment. When a battery is used as a power source for a device, the battery can continuously supply energy beyond the minimum energy level needed to drive the device reliably, even if the amount of energy charged to the battery decreases.

However, when the energy supplied through energy harvesting is used as a power source for a small device, the energy received through energy harvesting is irregular in size and is smaller than the energy supplied by the battery, thereby ensuring stable operation of the device I can not.

If the energy is less than the amount required by the device, a task failure that can not normally complete a running task occurs. If a task failure occurs, the information of the currently executed task is backed up, and if enough energy is secured for the replay afterwards, the backup data is recovered and the task is restarted from the point of time when the task is interrupted.

However, if there is no energy available to back up a running task at the time of the task failure, the information about the running task is lost, and if enough energy is available to re-execute the task The task will be executed again from the beginning.

If the backup fails when the task failure occurs, executing the task again from the beginning means that the task execution is waste of energy until the task failure occurs. Therefore, it is necessary to schedule a task so that task backup can be performed even if a task failure occurs, so as to minimize the task failure as much as possible.

On the contrary, when performing a backup when a task failure occurs, execution of the task can be restarted from the point of time when the task is stopped. Therefore, the task execution before the task failure does not lead to energy wastage, but energy loss due to backup and recovery occurs. Therefore, it is necessary to reduce the frequency of occurrence of task failure as much as possible, so that the task is restarted from the beginning or energy loss caused by backup recovery is reduced.

The existing task scheduler is designed based on an environment that supplies stable energy such as battery power. Therefore, the existing scheduler distributes the resources of the system to a task having a high priority based on the priority among the tasks preset by the user according to the purpose of use, or sets a time that can be operated for each task in advance, And allocating resources to the task.

The commonality of these scheduling methods is that task scheduling is performed without considering the available energy of the system. Among the devices using the battery as the power source, the scheduling policy may be changed depending on the remaining amount of the battery. When the remaining amount of the battery drops below a certain level, the operation frequency of the device is limited and the task is selectively performed. However, this scheduling method is intended to use the device as much as possible with the remaining energy in the battery.

For example, in case of a smartphone, when the remaining battery level is below a certain level, the brightness of the screen of the smartphone, the restriction of the execution of a specific application, and the operation frequency are limited. This allows you to maintain power for as long as possible with the remaining battery charge, providing long-lasting key functions such as call and text services.

That is, in a battery-based device, it is possible to supply a certain amount of energy or more even if the remaining battery capacity is insufficient, so that it is possible to perform the task as when the remaining battery capacity is sufficient. However, Energy-based scheduling. Also, in a battery-based device, energy failures do not occur as long as the remaining battery power is present, and therefore, task failures due to energy are not considered in the scheduling process.

While the battery can stably supply a certain amount of energy, the energy supply through the energy harvesting irregularly supplies an unequal amount of energy. And the amount of energy to supply is often insufficient compared to the battery. As a result, the energy becomes insufficient during task execution, leading to task failure.

In the present invention, an exception situation that may affect energy supply and demand is informed to a system using energy harvesting in advance and the task is reflected in the task scheduling process to reduce the task failure. Accordingly, the task scheduling method considering energy harvesting proposed in the present invention receives exception information that affects energy supply and demand in a device using energy harvesting, corrects the task scheduling policy based on the received exception information, And to prevent a task failure according to an exception situation in advance.

12 is a hardware configuration diagram of a task scheduling apparatus in a system driven by energy harvesting according to an embodiment of the present invention.

12, in a system powered by energy harvesting, a task scheduling apparatus 10 may include one or more processors 510, memory 520, storage 560, and interface 570. The processor 510, the memory 520, the storage 560, and the interface 570 transmit and receive data via the system bus 550.

The processor 510 executes a computer program loaded into the memory 520 and the memory 520 loads the computer program from the storage 560. [ The computer program may include an exception information reception operation 521, an energy supply / demand prediction operation 523, and a priority adjustment operation 525. [

The exception information reception operation 521 receives the exception information through the interface 570 and stores the exception information through the system bus 550 as the exception information 563 of the storage 560. Here, the exception information 563 is an external factor that may affect energy harvesting, and is information such as a sudden change in weather.

The energy supply forecasting operation 523 loads the exception information 563 into the storage 560 and compares the amount of energy received and the energy consumption of each task 561 on the basis of this information to predict how the available energy will change.

The priority adjustment operation 525 adjusts the priority 565 of the task 561 based on the prediction of the energy availability. That is, if it is predicted that the task is difficult to perform due to a decrease in available energy, the priority of the task with low energy consumption is increased, and if necessary, the task is executed so that the system enters the idle state The priority of the task can be adjusted.

12 may be software or hardware such as an FPGA (Field Programmable Gate Array) or an ASIC (Application-Specific Integrated Circuit). However, the components are not limited to software or hardware, and may be configured to be addressable storage media, and configured to execute one or more processors. The functions provided in the components may be implemented by a more detailed component, or may be implemented by a single component that performs a specific function by combining a plurality of components.

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

Claims (10)

The task scheduling apparatus comprising: receiving information on an exception situation that may affect energy harvesting;
Wherein the task scheduling device is operable to determine whether or not an exception occurs when at least one of the amount of energy received through the energy harvesting and the amount of energy consumed due to the performance of the task, Calculating an amount of energy; And
The task scheduling apparatus includes a step of adjusting a priority of the task based on the amount of the available energy and changing the order of execution of the task in the preemptive scheduling in which a plurality of tasks are sequentially executed according to a priority order ,
The step of changing the order of execution of the task comprises:
And lowering the priority of the task when it is predicted that a situation in which the amount of the available energy is insufficient during execution of the task,
The step of lowering the priority of the task comprises:
Performing again the step of re-executing the amount of available energy for a first task having a higher task priority than the task; And
And lowering the priority of the first task when it is predicted that a situation in which the amount of the re-computed available energy is insufficient during execution of the first task is expected to occur,
Method of scheduling tasks in a system driven by energy harvesting. The method according to claim 1,
The energy harvesting,
It is energy harvesting using solar energy,
The information on the exception condition may be,
Weather information,
Method of scheduling tasks in a system driven by energy harvesting. The method according to claim 1,
Wherein the step of computing the amount of available energy comprises:
Subtracting the amount of energy consumed due to the performance of the task from the energy amount received through the energy harvesting plus the energy remaining amount in the energy storage.
Method of scheduling tasks in a system driven by energy harvesting. delete delete The method according to claim 1,
Further comprising the step of maintaining the existing task scheduling policy intact when the information about the exception situation is not received.
Method of scheduling tasks in a system driven by energy harvesting. Network interface;
One or more processors;
A memory for loading a computer program executed by the processor; And
And a storage for storing a task and a priority of the task,
The computer program comprising:
An operation to receive information about exception conditions that may affect energy harvesting;
And an operation for calculating an amount of available energy based on at least one of the amount of energy supplied through the energy harvesting and the amount of energy consumed due to the performance of the task and the remaining energy amount in the energy storage when the exception occurs, ; And
And an operation of changing the order of execution of the task in preemptive scheduling in which a plurality of tasks are sequentially executed according to a priority order by adjusting a priority of the task based on the amount of available energy,
The operations for changing the order of execution of the tasks include:
And an operation of lowering the priority of the task when it is predicted that a situation in which the amount of the available energy is insufficient during execution of the task,
The operations for lowering the priority of the task include:
Re-executing the step of re-executing the amount of available energy for a first task having a higher task priority than the task; And
The method of claim 1 or 2, further comprising: decreasing a priority of the first task when it is predicted that a situation in which the amount of the re-
Task scheduling device in a system driven by energy harvesting. 8. The method of claim 7,
The operation for calculating the amount of available energy is,
Subtracting the amount of energy consumed by the performance of the task from the energy amount received through the energy harvesting plus the energy remaining amount in the energy storage,
Task scheduling device in a system driven by energy harvesting. delete delete

Images