KR20200080388A - Method and system for energy efficient lora enabled iot device using reinforcement learning - Google Patents

Abstract

Disclosed are a method for optimizing the energy of an Internet of things (IoT) device using a reinforcement learning technique and a system thereof. According to the present invention, an IoT energy optimization method, as a method performed in a gateway communicating with an IoT device or a computer system connected to the gateway, may comprise the step of adjusting the transmission power of the IoT device in a situation in which a spreading factor (SF) value of the IoT device is set.

Description

METHOD AND SYSTEM FOR ENERGY EFFICIENT LORA ENABLED IOT DEVICE USING REINFORCEMENT LEARNING}

The description below relates to energy optimization technology for a very small Internet of Things (IoT) device.

The emergence of a cyber-physical system (CPS) that has evolved a step further in the Internet of Things will lead to the emergence of ultra-compact IoT devices.

The micro IoT device is a communication module that transmits sensors and information that can measure limited physical events, and a microcontroller with minimal computing power that recognizes sensing information as digital information and parses data according to the communication module. It means a device comprising a.

Ultra-compact IoT devices can be said to be the most important technical elements to implement CPS, because they help users understand in the cyber space when a physical event occurs in a physical object without computing power.

The following is an example of using the ultra-small IoT device.

-To confirm that the other party has read the documents sent by them, attach a micro IoT device to the document bag and send a signal when the document bag is opened to confirm receipt of the document.

-Using a tiny IoT device, spray a tiny IoT device on several places in the mountain and collect fire information in winter in real time through temperature or smoke detection sensors.

Such a micro IoT device transmits a physical event discovered through wireless communication to a gateway, and for this, a wireless communication protocol for the micro IoT device is required.

For this, LPWA (Low Power Wide Area) communication protocols such as Sigfox, LoRa, RPMA, LTE-M, and NB-IoT are used.

Sigfox provides communication services for micro IoT devices such as Admiral Ivory and Admiral Blue, and even in LoRa, micro IoT devices can communicate with gateways using LoRa technology and LoRaWan protocol.

Communication between micro IoT devices can be divided into Cellular LPWA and Non-cellular LPWA.

ABI Research's investigation predicts that the use of non-cellular LPWA will increase rapidly, and LoRa and Sigfox are representative of non-cellular LPWA.

In the case of LoRa, the communication module is slightly more expensive than Sigfox, but LoRa's PHY technology shows high interference resistance and up to 17 times higher data rate, so LoRa will be used more among non-cellular LPWA technologies. Is expected.

Unlike the existing IoT devices, the ultra-small IoT device needs to efficiently use power because it receives energy through a battery that is not in the form of charging or power supply.

The LoRa module consumes the most energy when transmitting information and consumes more than twice the energy depending on the strength of the transmission power.

Therefore, it is important to successfully transmit sensing information to the gateway through proper transmission power strength to increase the energy efficiency of the micro IoT device.

Through this, it is possible to stably detect a physical event by increasing the life time of the ultra-small IoT device.

In LoRa, a signal is modulated to prevent interference between sensors using the same channel using CSS (chirp spread spectrum), and signals modulated with different CSS through one channel can be simultaneously received at the gateway.

Spreading factor (SF) refers to an index indicating which CSS is modulated using each signal, and orthogonality between two signals exists when signals are simultaneously transmitted using different SFs.

However, in theory, the interference between two signals is negligibly small, but a recent study of orthogonality between different SFs indicates that the interference between two signals with different SFs is more severe than the theory.

The signal using SF8 can be successfully received when there is a signal using SF7 when the signal-to-interference ratio (SIR) difference between two signals having different SF is 8dB or more.

If there is a device using SF7 near the gateway and a device using SF8 or higher is far away, if the transmit power strength of the device using SF7 is over a certain range, the transmission information of the device using SF8 or higher is not successfully received. It may not.

Currently, in the LoRa network, transmission energy is wasted due to transmission data loss caused by interference in the network, and a very small IoT device uses a lot of energy when transmitting information.

Therefore, in order to increase the energy efficiency of the ultra-small IoT device, it is necessary to reduce the loss of transmission data in the LoRa network.

Since the cause of transmission data loss in the LoRa network is interference between signals using different SFs, by reducing the interference between the signals, the data transmission success rate can be increased and the energy used to transmit information can be reduced.

Provides LoRa Enabled IoT energy optimization technology using reinforcement learning techniques.

The reinforcement learning algorithm for determining the transmission power of the ultra-small IoT device can be run on a gateway or an edge server connected to the gateway.

To recognize signals using different SFs, RSSI values of signals using different SFs successfully received at the gateway can be measured and reflected in the reinforcement learning algorithm.

An IoT energy optimization method comprising adjusting a transmission power of the IoT device in a situation in which a spreading factor (SF) value of the IoT device is set as a method performed in a gateway communicating with the IoT device or a computer system connected to the gateway. Gives

According to an aspect, the adjusting step may determine the transmission power using the RSSI value of the IoT device measured at the gateway.

According to another aspect, the adjusting step may adjust the transmission power by an adaptive date rate (ADR) algorithm on LoRaWan standard technology.

According to another aspect, the adjusting step may include determining the transmission power using a Q learning algorithm, which is a reinforcement learning technique.

According to another aspect, the determining step is an action of obtaining a maximum reward for a state indicating a degree of interference between the IoT device and a device belonging to another SF through the Q learning algorithm ( action).

According to another aspect, the determining may include setting a state indicating the degree of interference between the IoT device and a device belonging to another SF by using an RSSI value for each SF received signal; And determining an optimal transmission power that is an action of obtaining maximum compensation for the state based on the transmission power intensity setting information of the IoT device.

According to another aspect, the gateway may transmit the transmission power determined through the Q-learning algorithm to the IoT device using a field on LoRaWan standard technology.

As a method performed in a gateway communicating with an IoT device or a computer system connected to the gateway, interference between the IoT device and a device belonging to another SF through a Q learning algorithm that is a reinforcement learning technique in a situation in which the SF value of the IoT device is set. It provides an IoT energy optimization method comprising the step of adjusting the transmission power of the IoT device by determining the optimal transmission power to obtain the maximum compensation for the state indicating the degree.

An IoT energy optimization system, comprising: a gateway communicating with an IoT device or at least one processor implemented on a computer system connected to the gateway, and implemented to execute computer readable instructions, wherein the at least one processor comprises: It provides an IoT energy optimization system including a transmission power determining unit for determining the transmission power of the IoT device in a situation in which the spreading factor (SF) value of the IoT device is set.

According to the embodiments of the present invention, in a situation where the SF value of each device is set by the adaptive date rate (ADR) algorithm on LoRaWan standard technology, only the transmission power of each device is adjusted and the signals of more devices are received without loss and the devices are retransmitted By reducing the number of times, the transmission energy of each device can be reduced.

According to embodiments of the present invention, the transmit power strength of each device obtained through Q Learning among the reinforcement learning techniques can be transmitted to each device by using the LinkADRReq field on the LoRaWan standard protocol, and each device is powered by the received transmit power strength Setting is possible.

1 illustrates an example of SF deployment for each device through the ADR algorithm.
2 is an exemplary diagram for explaining the performance of a technique for adjusting only transmission power in a situation in which SF values of each device are set.
3 is a block diagram illustrating an example of an internal configuration of a computer system in an embodiment of the present invention.
4 is a SIR _xy for each LoRa module An example of a table of values is shown.
FIG. 5 is an exemplary diagram for describing definitions of states, actions, and rewards of each sensor.
6 shows an example of the Q Learning algorithm.
7 shows the overall system structure for IoT energy optimization using the Q Learning algorithm.
8 is a flowchart illustrating a method for determining an optimal transmit power strength through a Q Learning algorithm.

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

Embodiments of the present invention relate to LoRa Enabled IoT energy optimization technology utilizing reinforcement learning techniques.

Among the reinforcement learning techniques, the Q learning algorithm is used to recognize signals using different SFs and to reduce energy interference between signals using different SFs to optimize energy and predict transmission power of ultra-small IoT devices and adjust them with predicted values. .

In order to adjust the transmission power of each device, a Q Learning algorithm must be performed on each device, but a micro IoT device does not have the computing power to perform a Q Learning algorithm on each device.

In addition, when a device transmits information, in order to detect different SF signals, the Rx slot and the Tx slot must be opened in full duplex mode on the device. In some small IoT devices, there may be a half duplex mode. In some cases, other signals cannot be received.

Therefore, in the present invention, the Q Learning algorithm for determining the transmission power of the micro IoT device is driven by a gateway or an edge server connected to the gateway.

And, in order to recognize signals using different SFs, the RSSI values of signals using different SFs successfully received at the gateway are measured and reflected in the Q Learning algorithm.

According to embodiments of the present invention, in a situation where the SF value of each device is set by the adaptive date rate (ADR) algorithm on the LoRaWan standard technology, only the transmission power of each device is adjusted while accepting signals from more devices without loss and retransmission of devices By reducing the number of times, the transmission energy of each device can be reduced.

In addition, the transmit power strength of each device obtained through Q Learning can be transmitted to each device by using the LinkADRReq field on the LoRaWan standard protocol, and each device can be set to the power of the transmitted power received. In other words, it can be said to be a technology that can be used without breaking standards.

Performance comparison of before (Fig. 2 (A)) and after (Fig. 2 (B)) of the present technology is applied based on the "SF deployment by device through the ADR algorithm" of Fig. 1 specified in the current LoRaWan standard. I want to

Here, it is assumed that all devices communicate using the same channel for the same gateway, and each device has a predetermined SF value.

In the case of (A) of FIG. 2, even if a device transmitting information using SF9 sends information using the maximum intensity, the signal strength (RSSI) received by the gateway is only 1 dBm due to path loss. At this time, it is less than the threshold of the RSSI value of the device using the SF7 located at a short distance to the gateway, and it cannot be received at the gateway.

In the case of (B) of FIG. 2, a device using SF7 reduces the Tx power from 17dBm to 5dBm through this technology, so that it can receive not only information transmitted by itself but also information of a device using SF9 at the gateway.

Through this, information loss in the LoRa network can be reduced and transmission energy required for retransmission can be reduced, thereby increasing the energy efficiency of the device.

Hereinafter, a specific embodiment of the energy optimization technology of the LoRa Enabled IoT device using the reinforcement learning technique will be described.

3 is a block diagram illustrating an example of an internal configuration of a computer system in an embodiment of the present invention.

The IoT energy optimization system according to embodiments of the present invention may be implemented through the computer system 300 of FIG. 3. As shown in FIG. 3, the computer system 300 is a component for executing an IoT energy optimization method utilizing reinforcement learning techniques, such as a processor 310, a memory 320, a permanent storage device 330, a bus ( 340), an input/output interface 350 and a network interface 360.

The processor 310 may include or be part of any device capable of processing a sequence of instructions. The processor 310 may include, for example, a computer processor, a processor in a mobile device or other electronic device, and/or a digital processor. The processor 310 may be included in, for example, a server computing device, a server computer, a series of server computers, a server farm, a cloud computer, a content platform, a mobile computing device, a smartphone, a tablet, a set top box, and the like. The processor 310 may be connected to the memory 320 through the bus 340.

The memory 320 may include volatile memory, permanent, virtual, or other memory for storing information used or output by the computer system 300. For example, the memory 320 may include random access memory (RAM) and/or dynamic RAM (DRAM). Memory 320 may be used to store any information, such as status information of computer system 300. The memory 320 can also be used to store instructions of the computer system 300 including instructions for controlling IoT energy optimization, for example. Computer system 300 may include one or more processors 310 as needed or appropriate.

The bus 340 may include a communication infrastructure that enables interaction between various components of the computer system 300. The bus 340 can transport data between components of the computer system 300, for example between the processor 310 and the memory 320. The bus 340 may include wireless and/or wired communication media between components of the computer system 300, and may include parallel, serial or other topology arrangements.

Persistent storage 330 may store components, such as memory or other permanent storage, as used by computer system 300 to store data for a predetermined extended period (eg, compared to memory 320). It can contain. Persistent storage 330 may include non-volatile main memory as used by processor 310 in computer system 300. For example, the permanent storage device 330 may include a flash memory, hard disk, optical disk, or other computer readable medium.

The input/output interface 350 may include interfaces to a keyboard, mouse, microphone, camera, display, or other input or output device. Configuration commands and/or input related to IoT energy optimization may be received via input/output interface 350.

Network interface 360 may include one or more interfaces to networks such as a local area network or the Internet. Network interface 360 may include interfaces for wired or wireless connections. Configuration commands may be received via network interface 360. Also, information related to IoT energy optimization may be received or transmitted through the network interface 360.

Further, in other embodiments, the computer system 300 may include more components than those in FIG. 3. However, there is no need to clearly show most prior art components. For example, the computer system 300 is implemented to include at least some of the input/output devices connected to the input/output interface 350 described above, or a transceiver, a global positioning system (GPS) module, a camera, various sensors, Other components, such as a database, may also be included. As a more specific example, when the computer system 300 is implemented in the form of a mobile device such as a smartphone, a camera, an acceleration sensor or a gyro sensor, a camera, various physical buttons, and a touch panel generally included in the mobile device are used. Various components such as a button, an input/output port, and a vibrator for vibration may be implemented to be further included in the computer system 300.

In this embodiment, it is assumed that there are N LoRa-based micro IoT devices in one gateway.

Later, in order to simplify the description, a micro IoT device is also specified as a sensor. The index of the sensor is i, and when naming the sensor, it is s _i .

In this technique, it is assumed that all sensors communicate with the gateway on one channel in one gateway, and it is assumed that the spreading factor (SF) is already specified for each sensor s _i .

In addition, it is assumed that all factors affecting the data rate in addition to the transmission power are fixed values. For example, it is assumed that all Coding Rates are equal to 4/5, and the uplink bandwidth of the sensors is set to the same BW, such as 125 kHz.

Initially, the transmission power value (P _i ) for each sensor is set to the value specified by the gateway (so the gateway always knows the transmission power of each sensor, and it is possible to match the information reception status and RSSI _i value according to P _i ) It is assumed that the gateway can grasp the RSSI value for the signal it successfully received for each time.

The sensors generate sensing data at a rate of d _i per hour and send all this information to the gateway. If the transmission fails and the sensing data is not transmitted, it is assumed that the sensing data is transmitted including the sensing data that was not transmitted at the next transmission opportunity.

It is assumed that there are enough buffers in each device to store the lost information. Therefore, if information loss occurs, each sensor must additionally use the transmission energy to send the lost data.

In this embodiment, the definition of the problem proceeds as follows.

Problem:

Here, E means the transmission energy efficiency of the N sensors and can be expressed as bit/joule.

In an accurate sense, E can be defined as (total amount of data transmitted per specific period)/(energy used to transmit the amount of data), and means a parameter that determines how much data has been transmitted using limited energy. do.

E can be defined as in Equation 1.

[Equation 1]

d _i denotes the data sensing speed per second (bit/s) of s _i , and D denotes a certain period of time (s). β means (size of data to be transmitted)/(size of payload), and α means (1-DER). DER means the data extraction rate, that is, the ratio of the data transmitted from the receiving side among the data transmitted in a certain period, and in the end, α means the ratio of the data lost during the transmission.

P _i refers to the transmission power when the transmit data s _i and T _i indicates the transmission time when the s _i send a 1-bit, and, T _i can be expressed as the reciprocal of the data rate of the s _i.

In LoRa, the theoretical DR _i value of s _i is defined as in Equation 2.

[Equation 2]

SF _i means the spreading factor value of s _i , and BW and CR mean channel bandwidth and coding rate, respectively. If this is reflected, the E function is constructed as in Equation 3.

[Equation 3]

Here, assuming that d _i and D, BW, CR, and β values are constant and SF _i values are already assigned to each sensor s _i , the total transmission energy of the sensors in charge of one gateway is It can be determined by α and P _i .

That is, it is possible to increase the energy efficiency of the overall communication time roseuyul sensor is less than or lower the transmit power P _i for each sensor s _i.

In general, in wireless communication, when the transmission power is increased, the loss rate can be reduced, but in this embodiment, in order to achieve high energy efficiency, P _i and the loss rate must be considered together, so a problem must be solved through a new approach.

In addition, the sensors assumed in this embodiment are difficult to solve through mathematical or statistical modeling because the loss rate varies depending on the strength of mutual transmission power between multiple sensors and the position of each sensor.

Since the loss ratio α of all sensors is non-linearly present in Pi, the present invention provides a technique for finding an optimal value of Pi to have a small loss ratio while consuming less transmission power using reinforcement learning.

In the present invention, through the reinforcement learning is to increase the communication energy efficiency of ultra-small IoT devices communicating based on LoRa.

In the present invention, each sensor uses a Q learning algorithm, which is a class of reinforcement learning, in order to obtain an optimal transmission power P _i . Since the Q learning algorithm for finding the optimal P _i value of each sensor s _i is not located in each micro IoT device, but is located at the gateway and is calculated, it uses the RSSI _i value of each sensor s _i measured at the gateway. The optimal P _i is searched so that the sensor s _i can transmit information with high energy efficiency. To use the Q learning algorithm, it is necessary to define states, actions, and rewards.

In the present invention, states, actions, and rewards are defined for each sensor s _i , and all of this information is present in the gateway.

state

For each state s _i S _i can be defined as in Equation (4).

[Equation 4]

I _ij means the degree of interference between s _i and s _j . x means the SF value of s _i , y means the SF value of s _j .

When receiving the signal of s _i from the gateway, compare the signal of s _{i with} the signal of s _j , and the SIR _{xy value.If} the signal of s _j can be received regardless of the situation of s _i , 0, if the signal of s _i If is too strong to receive the signal of s _j -1, the opposite is set to a value of 1.

The SIR _xy value can be obtained by actual measurement for each LoRa module as shown in the table shown in FIG. 4.

k means an SF index value to which s _i does not belong, and can be expressed by Equation (5).

[Equation 5]

j _k denotes a sensor that successfully receives the information from the sensor s _{j using} SF _k when the signal of s _i reaches the gateway.

ε _k means a weight factor for each SF, and since signal characteristics are different for each SF, in this embodiment, the weight factor is calculated by reflecting the characteristic. For example, in the case of SF 12, since the data rate is low and once the signal is interfered and transmission is not performed, a long time transmission must occur again, so it may be necessary to care more about the interference occurring in SF12 than the interference occurring in SF7. In that case, ε ₁₂ may be greater than ε ₇ , and these weight factors are set in the range of integers to make the state discrete.

That is, S _i can be said to be a parameter for determining the state of how interfering with devices belonging to other SFs from the standpoint of s _i .

behavior

S _i of each action A _i may be defined as Equation (6).

[Equation 6]

Here, m means the number of transmit power levels that can be applied by the sensor s _i . For example, if the transmission power can be set to -10, 0, 10, 20 dBm in the sensor, m is 4, and P _i ^(m) means the amount of transmission power at each transmission power level. In this example, P _i ⁽¹⁾ means -10dBm.

reward

Rewards can be defined as follows when performing an action in each state.

Means the S _i values high because the sensor that uses a different SF s _i is therefore mean not send the right information about the situation to give a reward to act when high S _i to have a high transmit power and, conversely, the S _i values because it means that information from other sensors due to the transmission power of s _i if negative, it does not correctly sent to the gateway, you should set the compensation so as to reduce the transmission power of s _i.

And, when S _i is close to the value of 0, it means equilibrium, so compensation should be set so as not to change the value of the transmission power.

In the end, since there is no difference between S _i and A _i , high compensation is required. Therefore, a reward function is obtained using the entropy formula. At this time, since the units of S _i and A _i may be different, they are all 0. After normalization with a value between 1 and 1, it is substituted into the compensation equation (Equation 7).

S _i is configured to function so that due to the presence in all integer ranges may be in order to normalized forward normalized by using a function such as a sigmoid, tanh, arctan, and reflected in the compensation after running A _i in the case of A _i (See FIG. 5).

[Equation 7]

Here, S _i 'means a normalized S _i value, and A _i ' means a normalized A _i value. For example, S _i ′ and A _i ′ may be normalized as in Equation 8 and Equation 9.

[Equation 8]

[Equation 9]

Since there are m steps in P _i , the h-th power level can be normalized to h/m.

The smaller the difference between S _i and A _i , the higher the reward, and when the difference between S _i and A _i is different, the lowest reward is obtained.

Based on S _i , A _i , and R _i of each sensor s _i previously set, a Q Learning algorithm for each sensor can be driven (see FIG. 6 ).

γ stands for learning rate and has a value between 0 and 1.

ε means ε-greedy parameter and has a value between 0.01 and 0.05. The ε-greedy parameter causes the signal to be transmitted at a random P _i value according to the ε probability to prevent the case where the optimal P _i value obtained through Q Learning is a local optimum.

λ means the discount factor and has a value between 0 and 1.

Through the Q learning algorithm, it is learned which A _i should be executed when the sensor s _i is a specific S _i , that is, a policy predicting an optimal P _i value.

7 shows the overall system structure.

The LoRa gateway 710 may include an RSSI measurement unit 711, an RSSI DB 712, and a transmission power setting unit 713.

The RSSI measurement unit 711 measures the RSSI value of the signal successfully received for each SF and transmits the measured information to the RSSI DB 712.

The RSSI DB 712 stores RSSI values for signals successfully received for each SF in a list, tuple, matrix, etc. format based on a time index.

The transmission power setting unit 713 stores the transmission power information of the corresponding device determined by the Q Learning module 730 in the LinkADRReq field of the LoRaWan standard and transmits it to the LoRa device 720.

The LoRa device 720 may include a transmission power setting unit 721, and when the transmission power setting unit 7210 receives a control message from the LoRa gateway 710, the transmission power (Tx power) value in the LinkADRReq field therein Set the transmission power with reference to.

The Q Learning module 730 may exist physically on the LoRa gateway 710 or on a computer system connected to the LoRa gateway 710, so that there is one Q Learning module 730 for each LoRa device 720. do. The computing space in which the Q Learning module 730 is present corresponds to the computer system 300 described through FIG. 3.

The Q Learning module 730 may include a reinforcement learning-based transmission power determination unit 731 and a database 732.

The reinforcement learning-based transmission power determination unit 731 may set the current state of the device by getting the RSSI value for each SF simultaneously measured from the RSSI DB value in the LoRa gateway 710. In addition, the behavior is obtained by obtaining the transmission power intensity setting information of each device in advance for each LoRa device 710, and the transmission power intensity of the device having the highest compensation behavior may be determined through the previously set state and behavior. At this time, Q values, parameters, and hyperparameters such as Q(s,a) and Q(s,a') are all stored in the database 732.

The flowchart of determining the optimal transmit power strength in the Q Learning module 730 (each module exists for each sensor s _i ) is shown in FIG. 8.

Referring to FIG. 8, the Q Learning module 730 determines the initial transmission power (P _i0 ) of the sensor s _i and acquires the value of A _i from the database together with the SIR table (S801 ).

The Q Learning module 730 transmits the determined transmission power value to the transmission power setting unit 713 of the LoRa gateway 710 (S802).

The Q Learning module 730 accesses the RSSI DB 712 on the LoRa gateway 710 every predetermined period and checks the RSSI values of all sensors of the corresponding period (S803).

The Q Learning module 730 determines whether the RSSI _i value of the sensor s _i is valid (S804) and, if valid, the RSSI value for the signal successfully received for each SF as the RSSI _i value measured by the LoRa gateway 710. If it is determined (S805) and it is not valid, it is determined as the default RSSI _i value (S806).

The Q Learning module 730 sets S _i using the RSSI value and the information on the SIR table (S807), and sets A _i using the transmit power value at each transmit power level (S808).

The Q Learning module 730 may predict A _i ′ (optimal transmission power value) through S _i and A _i (S809 ). In order to optimize energy by recognizing signals using different SFs and reducing interference between signals using different SFs, the transmission power can be predicted and adjusted with predicted values.

As described above, the IoT energy optimization technology according to the present invention can be effectively used when ultra-small IoT devices that perform LoRa-based wireless communication must exist on a large scale. Since it reduces the interference generated by LoRa, it can increase the energy efficiency of the LoRa device, and the Internet provider can also see the expected effect of improving the quality of the LoRa network because it reduces the overall loss of the LoRa network. In addition, since a device that communicates with LoRa requires a lot of energy to transmit information, it is possible to increase the life time of the device by reducing the energy used for LoRa. The device targeting to increase energy efficiency in the present invention is an ultra-small IoT device. The ultra-compact IoT device basically means a disposable sensor that receives power supply through a battery. If the life time of one sensor increases, the disposable ultra-compact IoT device can be used for a longer time, thereby saving resources and services. Cost savings are possible.

The device described above may be implemented with hardware components, software components, and/or combinations of hardware components and software components. For example, the devices and components described in the embodiments may include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor (micro signal processor), a microcomputer, a field programmable gate array (FPGA), and a programmable programmable logic array (PLU). It may be implemented using one or more general purpose computers or special purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may perform an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of understanding, a processing device may be described as one being used, but a person having ordinary skill in the art, the processing device may include a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include. For example, the processing device may include a plurality of processors or a processor and a controller. In addition, other processing configurations, such as parallel processors, are possible.

The software may include a computer program, code, instruction, or a combination of one or more of these, and configure the processing device to operate as desired, or process independently or collectively You can command the device. Software and/or data may be embodied in any type of machine, component, physical device, computer storage medium, or device in order to be interpreted by the processing device or to provide instructions or data to the processing device. have. The software may be distributed over networked computer systems, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. In this case, the medium may continuously store a program executable on a computer or may be temporarily stored for execution or download. In addition, the medium may be various recording means or storage means in a form of a single or several hardware combinations, and is not limited to a medium directly connected to a computer system, but may be distributed on a network. Examples of the medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magneto-optical media such as floptical disks, And program instructions including ROM, RAM, flash memory, and the like. In addition, examples of other media may include an application store for distributing applications or a recording medium or storage medium managed by a site, server, or the like that supplies or distributes various software.

As described above, although the embodiments have been described by the limited embodiments and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (15)

A method performed in a gateway communicating with an IoT device or a computer system connected to the gateway,
Adjusting the transmission power of the IoT device in a situation in which a spreading factor (SF) value of the IoT device is set
IoT energy optimization method comprising a. According to claim 1,
The adjusting step,
Determining the transmission power using the RSSI value of the IoT device measured at the gateway
IoT energy optimization method characterized in that. According to claim 1,
The adjusting step,
Adjusting the transmit power with an adaptive date rate (ADR) algorithm on LoRaWan standard technology
IoT energy optimization method characterized in that. According to claim 1,
The adjusting step,
Determining the transmission power using Q learning algorithm, a reinforcement learning technique
IoT energy optimization method comprising a. According to claim 4,
The determining step,
Through the Q-learning algorithm, determining an optimal transmission power that is an action to obtain a maximum reward for a state indicating the degree of interference between the IoT device and a device belonging to another SF
IoT energy optimization method characterized in that. According to claim 4,
The determining step,
Setting a state indicating the degree of interference between the IoT device and a device belonging to another SF using an RSSI value for each SF received signal; And
Determining an optimal transmission power that is an action of obtaining maximum compensation for the state based on transmission power intensity setting information of the IoT device
IoT energy optimization method comprising a. According to claim 4,
The gateway transmits the transmission power determined through the Q-learning algorithm to the IoT device using fields on the LoRaWan standard technology.
IoT energy optimization method characterized in that. A method performed in a gateway communicating with an IoT device or a computer system connected to the gateway,
In the situation where the SF value of the IoT device is set, the optimal transmission power for obtaining the maximum compensation for the state indicating the degree of interference between the IoT device and a device belonging to another SF is determined through Q learning algorithm, which is a reinforcement learning technique, Adjusting the transmission power of the IoT device
IoT energy optimization method comprising a. In the IoT energy optimization system,
It is implemented on a gateway that communicates with an IoT device or a computer system connected to the gateway,
At least one processor implemented to execute computer readable instructions
Including,
The at least one processor,
A transmission power determination unit that determines the transmission power of the IoT device in a situation in which a spreading factor (SF) value of the IoT device is set
IoT energy optimization system comprising a. The method of claim 9,
The transmission power determining unit,
Determining the transmission power using the RSSI value of the IoT device measured at the gateway
IoT energy optimization system, characterized by. The method of claim 9,
The transmission power determining unit,
Adjusting the transmit power with ADR algorithm on LoRaWan standard technology
IoT energy optimization system, characterized by. The method of claim 9,
The transmission power determining unit,
Determining the transmit power using Q-learning algorithm, a reinforcement learning technique
IoT energy optimization system, characterized by. The method of claim 12,
The transmission power determining unit,
Through the Q-learning algorithm, determining the optimal transmission power, which is an action to obtain maximum compensation for a state indicating the degree of interference between the IoT device and a device belonging to another SF
IoT energy optimization system, characterized by. The method of claim 12,
The transmission power determining unit,
An RSSI value for each SF received signal is used to set a state indicating the degree of interference between the IoT device and a device belonging to another SF, and based on the transmission power intensity setting information of the IoT device, the maximum for the state is set. Determining the optimal transmission power, which is the act of obtaining rewards
IoT energy optimization system, characterized by. The method of claim 12,
The gateway transmits the transmission power determined through the Q-learning algorithm to the IoT device using fields on the LoRaWan standard technology.
IoT energy optimization system, characterized by.

Images