KR20230038935A - Neural network-based energy harvesting method and system - Google Patents

Abstract

A neural network-based energy harvesting method and a system thereof are disclosed. According to an embodiment, the energy harvesting method comprises the following operations of: measuring a size of first power, which is power obtained by an energy harvester for a certain period of time; transmitting the magnitude of the first power to a central processing unit; receiving, from the central processing unit, a size of second power, which is power that the energy harvester can obtain for a certain period of time; and controlling the energy harvester based on the size of the first power. The size of the second power may be determined based on the size of the first power.

Description

Neural network-based energy harvesting method and system {NEURAL NETWORK-BASED ENERGY HARVESTING METHOD AND SYSTEM}

The disclosure below relates to a neural network based energy harvesting method and system.

Energy harvesting is a technology for reproducing energy by harvesting or using discarded energy. Energy harvesting is divided into an energy generating step, an energy conversion step, an energy storage step, and an energy consumption step.

The energy generation step is a step in which energy is generated from body energy, vibration energy, thermal energy, gravitational energy, potential energy, light energy, electromagnetic energy, and the like.

The energy conversion step includes piezoelectric conversion using a piezoelectric element by vibration or pressure, thermoelectric conversion using residual heat or waste heat from human bodies and machines, photoelectricity conversion converting light energy into electricity, and wave This is the step of converting energy through electromagnetism, which collects (vibration) into electromagnetic waves and converts them into electricity.

The energy storage step is a step of storing the converted energy by using a battery having an element capable of accumulating and preserving energy and having a low electrical leakage.

The energy consumption step is a step of consuming energy produced in the energy generation step, the energy conversion step, and the energy storage step.

Energy harvesting technology is attracting attention as a new power technology to overcome limitations such as the size and use time of a battery in the trend of miniaturization of IT devices, sensors, and industrial equipment.

If the power obtained from energy harvesting is smaller than the power consumed for energy harvesting, power consumption may increase.

According to the embodiment, it is possible to provide a technology for performing efficient energy harvesting by predicting power that can be obtained through energy harvesting based on a neural network.

However, the technical challenges are not limited to the above-described technical challenges, and other technical challenges may exist.

An energy harvesting method according to an embodiment includes an operation of measuring a magnitude of first power, which is power obtained by an energy harvester for a predetermined time, and an operation of transmitting the magnitude of the first power to a central processing unit; receiving an amount of second power, which is power that can be obtained by the energy harvester for a predetermined time, and controlling the energy harvester based on the amount of the second power, wherein the amount of the second power is It may be determined based on the magnitude of the first power.

The operation of controlling the energy harvester may include controlling the energy harvester by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester operates.

The energy harvester may include one or more energy harvesting circuits and one or more switches controlling the energy harvesting circuits.

The operation of controlling the energy harvester may include an operation of turning on the switch to harvest energy when the magnitude of the second power is greater than the reference power, and an operation of harvesting energy when the magnitude of the second power is smaller than the reference power. It may include an operation of not harvesting energy by turning off.

The CPU may include a neural network learned by receiving the magnitude of the first power, calculating a loss function based on the magnitude of the first power, and updating weights and biases to minimize the loss function. can

The learned neural network may output the magnitude of the second power when the magnitude of the first power is input.

An energy harvesting device according to an embodiment includes an energy harvester, a transceiver, a memory for storing one or more instructions, and a processor for executing the instruction, and when the instruction is executed, the processor may receive a constant from the energy harvester. Measures the magnitude of first power, which is power obtained during a period of time, transmits the magnitude of the first power to the central processing unit, and measures the level of second power, which is power that the energy harvester can obtain for a certain period of time, from the central processing unit. A magnitude of the second power may be received, the energy harvester may be controlled based on the magnitude of the second power, and the magnitude of the second power may be determined based on the magnitude of the first power.

The processor may control the energy harvester by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester operates.

The energy harvester may include one or more energy harvesting circuits and one or more switches controlling the energy harvesting circuits.

The processor turns on the switch to harvest energy when the magnitude of the second power is greater than the reference power, and turns off the switch to harvest energy when the magnitude of the second power is smaller than the reference power. may not

An energy harvesting system according to an embodiment includes at least one energy harvesting device and a central processing unit controlling the energy harvesting device, wherein the energy harvesting device is power obtained by an energy harvester for a predetermined time. Measuring the size of the first power, transmitting the size of the first power to the central processing unit, and receiving the size of the second power, which is the size of the power that the energy harvester can obtain for a certain period of time, from the central processing unit , The energy harvester may be controlled based on the size of the second power, and the size of the second power may be determined based on the size of the first power.

The energy harvesting device may control the energy harvester by comparing the size of the second power and the size of reference power, which is power consumed when the energy harvester operates.

The energy harvester may include one or more energy harvesting circuits and one or more switches controlling the energy harvesting circuits.

The energy harvesting device turns on the switch to harvest energy when the magnitude of the second power is greater than the reference power, and turns off the switch when the magnitude of the second power is smaller than the reference power to generate energy may not be harvested.

The CPU may include a neural network learned by receiving the magnitude of the first power, calculating a loss function based on the magnitude of the first power, and updating weights and biases to minimize the loss function. can

The learned neural network may output the magnitude of the second power when the magnitude of the first power is input.

1 shows an example of an energy harvesting system according to an embodiment.
FIG. 2 shows a schematic block diagram of the energy harvesting device shown in FIG. 1 .
FIG. 3 is a diagram for explaining the operation of the energy harvester shown in FIG. 2 .
4 shows an example of an energy harvesting method according to an embodiment.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be changed and implemented in various forms. Therefore, the form actually implemented is not limited only to the specific embodiments disclosed, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical idea described in the embodiments.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, operation, component, part, or combination thereof exists, but one or more other features or numbers, It should be understood that the presence or addition of steps, operations, components, parts, or combinations thereof is not precluded.

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. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in this specification, it should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted.

1 shows an example of an energy harvesting system according to an embodiment.

The energy harvesting system 10 may perform energy harvesting that reproduces energy by harvesting or using discarded energy.

The energy harvesting system 10 may include one or more energy harvesting devices 100 (eg, 100-1, to 100-n) and a central processing unit 200.

The energy harvesting device 100 may include a first energy harvesting device 100-1 to an n-th energy harvesting device 100-n. The first energy harvesting device 100-1 to the n-th energy harvesting device 100-n may be each energy source (eg, the first energy source 300-1 to the n-th energy source 300-n) ), energy harvesting can be performed. The configuration and operation of the energy harvesting device 100 will be described in detail with reference to FIG. 2 .

The central processing unit 200 may control the first energy harvesting device 100-1 to the nth energy harvesting device 100-n. As the central processing unit 200 controls the one or more energy harvesting devices 100 as a whole, overall efficiency of energy harvesting may be improved. For example, the overall efficiency of energy harvesting is higher when the central processing unit 200 performs energy harvesting using the information of each energy harvesting apparatus 100 than when the energy harvesting apparatus 100 performs energy harvesting. It can be further improved in the case of controlling and performing energy harvesting by collecting.

The central processing unit 200 may include a neural network, and the neural network receives the magnitude of the first power, which is the power that the energy harvester has acquired for a certain period of time, from the energy harvesting devices 100, and receives the received first power. It can be learned by calculating a loss function based on the magnitude of power and updating the weights and biases to minimize the calculated loss function.

The central processing unit 200 may perform neural network calculation using an accelerator. The central processing unit 200 may perform neural network calculation using an accelerator.

The accelerator may include a graphics processing unit (GPU), a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or an application processor (AP). Also, the accelerator may be implemented as a software computing environment such as a virtual machine.

The central processing unit 200 may train the neural network. Neural networks (or artificial neural networks) can include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to an overall model having a problem-solving ability by changing synaptic coupling strength through learning of artificial neurons (nodes) formed in a network by synaptic coupling.

A neuron in a neural network may contain a combination of weights or biases. A neural network may include one or more layers composed of one or more neurons or nodes. A neural network can infer a result to be predicted from an arbitrary input by changing the weight of a neuron through learning.

The neural network may include a deep neural network. Neural networks include CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), perceptron, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM(Boltzmann Machine), RBM(Restricted Boltzmann Machine), DBN(Depp Belief Network), DCN(Deep Convolutional Network), DN(Deconvolutional Network), DCIGN(Deep Convolutional Inverse Graphics Network), GAN(Generative Adversarial Network) ), LSM (Liquid State Machine), ELM (Extreme Learning Machine), ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Computer), NTM (Neural Turning Machine), CN (Capsule Network), It may include a Kohonen Network (KN) and an Attention Network (AN).

The central processing unit 200 may be implemented as a printed circuit board (PCB) such as a motherboard, an integrated circuit (IC), or a system on chip (SoC). For example, the central processing unit 200 may be implemented as an application processor.

Also, the central processing unit 200 may be implemented as a personal computer (PC), a data server, or the like.

Portable devices include laptop computers, mobile phones, smart phones, tablet PCs, mobile internet devices (MIDs), personal digital assistants (PDAs), and enterprise digital assistants (EDAs). , digital still camera, digital video camera, portable multimedia player (PMP), personal navigation device or portable navigation device (PND), handheld game console, e-book ( e-book) or a smart device. A smart device may be implemented as a smart watch, a smart band, or a smart ring.

When the magnitude of the first power is input to the learned neural network, the magnitude of the second power may be output.

The central processing unit 200 may receive the magnitude of the first power from the energy harvesting apparatus 100 . The CPU 200 may input the magnitude of the first power to the learned neural network to obtain the magnitude of the second power. The central processing unit 200 may transmit the magnitude of the second power to the energy harvesting device 100 so that the energy harvesting device 100 performs energy harvesting based on the magnitude of the second power.

The energy harvesting system 10 may reduce energy consumed by the energy harvesting device 100 by performing machine learning (or deep learning) in the central processing unit 200 . In addition, the energy harvesting system 10 can implement the energy harvesting device 100 through a processor (or control unit) having lower processing power than the processor of the energy harvesting device that directly performs machine learning (or deep learning) there is.

FIG. 2 shows a schematic block diagram of the energy harvesting device shown in FIG. 1 .

The energy harvesting device 100 may perform energy harvesting that regenerates energy by harvesting or using discarded energy.

The energy harvesting device 100 may include a transceiver 110 , an energy harvester 130 , a memory 150 , and a processor 170 .

The transceiver 110 may receive the amount of first power, which is the amount of power obtained by the energy harvester 130 for a certain period of time, from the processor 170 and transmit the received amount to the central processing unit 200 . The transceiver 110 may receive the amount of second power, which is the amount of power that the energy harvester 130 can obtain for a certain period of time, from the central processing unit 200 and transmit the received amount to the processor 170 . The size of the second power may be determined from the size of the first power.

The energy harvester 130 may perform energy harvesting from an energy source. The structure and operation of the energy harvester 130 will be described in detail with reference to FIG. 3 .

Memory 150 may store instructions (or programs) executable by processor 170 . For example, the instructions may include instructions for executing the operation of the processor and/or the operation of each component of the processor 170 .

The memory 150 may be implemented as a volatile memory device or a nonvolatile memory device.

The volatile memory device may be implemented as dynamic random access memory (DRAM), static random access memory (SRAM), thyristor RAM (T-RAM), zero capacitor RAM (Z-RAM), or twin transistor RAM (TTRAM).

Non-volatile memory devices include electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic RAM (MRAM), spin-transfer torque (STT)-MRAM (conductive bridging RAM), and conductive bridging RAM (CBRAM). , FeRAM (Ferroelectric RAM), PRAM (Phase change RAM), Resistive RAM (RRAM), Nanotube RRAM (Polymer RAM (PoRAM)), Nano Floating Gate Memory Memory (NFGM)), holographic memory, molecular electronic memory device (Molecular Electronic Memory Device), or Insulator Resistance Change Memory.

The processor 170 may process data stored in the memory 150 . The processor 170 may execute computer readable code (eg, software) stored in the memory 150 and instructions triggered by the processor 170 .

The processor 170 may be a data processing device implemented in hardware having a circuit having a physical structure for executing desired operations. For example, desired operations may include codes or instructions included in a program.

For example, a data processing unit implemented in hardware includes a microprocessor, a central processing unit, a processor core, a multi-core processor, and a multiprocessor. , Application-Specific Integrated Circuit (ASIC), and Field Programmable Gate Array (FPGA).

The processor 170 may measure the magnitude of first power, which is power acquired by the energy harvester 130 for a predetermined period of time. The processor 170 may transmit the amount of the first power to the central processing unit 200 through the transceiver 110 . The processor 170 may receive, through the transceiver 110, the amount of second power, which is power that the energy harvester 130 can obtain for a certain period of time, from the central processing unit 170. The processor 170 may control the energy harvester 130 based on the received second power. The magnitude of the second power may be determined from the magnitude of the first power through the neural network of the central processing unit 200 .

The processor 170 may control the energy harvester 130 by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester 130 operates. A specific operation of the processor 170 controlling the energy harvester 130 will be described in detail with reference to FIG. 3 .

FIG. 3 is a diagram for explaining the operation of the energy harvester shown in FIG. 2 .

The energy harvester 130 may perform energy harvesting from one or more energy sources 300 .

The energy source 300 may include a first energy source 300-1 to an n-th energy source 300-n, and the number of energy sources 300 is not limited. The first energy source 300-1 may be an energy source based on the piezoelectric effect, the second energy source 300-2 may be an energy source based on the thermoelectric effect, and the third energy source 300-3 may be an energy source based on the photoelectric effect. , and the n-th energy source 300-1 may be an energy source based on electromagnetic effects.

The energy harvester 130 may include one or more energy harvesting circuits 131 and a switch 132 . The energy harvester 130 may control the energy harvesting circuit 131 through the switch 132 .

The energy harvesting circuit 131 may perform energy harvesting from the energy source 300 . The energy harvesting circuit 131 may include a first energy harvesting circuit 131-1 to an n-th energy harvesting circuit 131-n, and the number of energy harvesting circuits 131 is not limited. .

The switch 132 is located between the energy source 300 and the energy harvesting circuit 131, so that the energy harvesting circuit 131 can be turned on to perform energy harvesting from the energy source 300, and The ting circuit 131 may be turned off so as not to perform energy harvesting from the energy source 300 . The switch 132 may include a first switch 132-1 to an n-th switch 132-n, and the number of switches 132 may correspond to the number of energy harvesting circuits 131.

A processor (the processor 170 of FIG. 2 ) may control the energy harvester 130 . Specifically, the processor 170 may control energy harvesting by controlling the switch 131 included in the energy harvester 130 .

The processor 170 compares the size of the second power, which is power that the energy harvester 130 can obtain for a certain period of time, with the size of the reference power, which is the power consumed when the energy harvester 130 is operating, to obtain the energy harvester 130. You can control it.

When the level of the second power is greater than the reference power, the processor 170 may turn on the switch 132 to allow the energy harvesting circuit 131 to harvest energy, and the level of the second power is smaller than the reference power. In this case, the energy harvesting circuit 131 may be controlled not to harvest energy by turning off the switch 132 .

Specifically, the processor 170 determines that the size of the 2-1st power, which is the power obtainable for a certain period of time from the first energy source 300-1, is consumed when the first energy harvesting circuit 131-1 operates. When the power is greater than the first reference power, the first switch 132-1 may be turned on to control the first energy harvesting circuit 131-1 to perform energy harvesting.

In addition, the processor 170 determines that the magnitude of the second-third power, which is the power obtainable for a certain period of time from the third energy source 300-3, is the power consumed when the third energy harvesting circuit 131-3 operates. When the magnitude of the third reference power is greater than that of the third reference power, the third switch 132-3 may be turned off to control the third energy harvesting circuit 131-3 not to perform energy harvesting.

The processor 170 may control the energy harvester 130 to efficiently perform energy harvesting by comparing power consumed for energy harvesting with power obtained through energy harvesting.

4 shows an example of an energy harvesting method according to an embodiment.

Referring to FIG. 4 , the energy harvesting system 10 may perform efficient energy harvesting based on machine learning.

In operation 410, the energy harvesting device 100 may measure the magnitude of first power, which is power acquired by the energy harvester 130 for a predetermined period of time.

In operation 420 , the energy harvesting device 100 may transmit the amount of first power to the central processing unit 200 through the transceiver 110 .

In operation 430, the energy harvesting device 100 may receive the amount of second power, which is power that the energy harvester 130 can obtain for a certain period of time, from the central processing unit 200 through the transceiver 110. At this time, the central processing unit 200 may include a neural network, and the neural network receives the magnitude of the first power, calculates a loss function based on the magnitude of the first power, and weights to minimize the loss function. and by updating the bias. The magnitude of the second power may be obtained by inputting the magnitude of the first power to the learned neural network.

In operation 440, the energy harvesting device 100 may control the energy harvester 130 based on the magnitude of the second power. The energy harvesting device 100 may control the energy harvester 130 by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester 130 operates.

Specifically, when the magnitude of the second power is greater than the reference power, the energy harvesting device 100 turns on the switch 132 so that the energy harvesting circuit 131 performs energy harvesting, and the second power When the magnitude of is smaller than the reference power, the energy harvester 131 may be controlled not to perform energy harvesting by turning off the switch 132 .

The energy harvesting system 10 may reduce energies consumed by the energy harvesting device 100 by performing machine learning (or deep learning) in the central processing unit 200 . In addition, the energy harvesting system 10 may implement the energy harvesting device 100 through a processor (or control unit) having lower processing power than the processor of the energy harvesting device that performs machine learning (or deep learning). .

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. You can command the device. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on computer readable 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. A computer readable medium may store program instructions, data files, data structures, etc. alone or in combination, and program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in the art of computer software. there is. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

The hardware device described above may be configured to operate as one or a plurality of software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on this. For example, the described techniques may be performed in an order different from the method described, and/or the components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

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

Claims (16)

measuring a magnitude of first power, which is power obtained by the energy harvester for a predetermined period of time;
transmitting the magnitude of the first power to a central processing unit;
receiving, from the central processing unit, a magnitude of second power, which is power that the energy harvester can obtain for a predetermined period of time; and
Controlling the energy harvester based on the magnitude of the second power
including,
The magnitude of the second power is determined based on the magnitude of the first power, energy harvesting method.
According to claim 1,
The operation of controlling the energy harvester,
Controlling the energy harvester by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester operates.
Including, energy harvesting method.
According to claim 2,
The energy harvester,
one or more energy harvesting circuits; and
One or more switches controlling the energy harvesting circuit
Including, energy harvesting method.
According to claim 3,
The operation of controlling the energy harvester,
harvesting energy by turning on the switch when the magnitude of the second power is greater than the reference power; and
Operation of not harvesting energy by turning off the switch when the magnitude of the second power is smaller than the reference power
Including, energy harvesting method.
According to claim 1,
The central processing unit,
Receiving the magnitude of the first power;
Calculate a loss function based on the magnitude of the first power;
A neural network trained by updating weights and biases to minimize the loss function.
Including, energy harvesting method.
According to claim 5,
The trained neural network is
The energy harvesting method of outputting the magnitude of the second power when the magnitude of the first power is input.
energy harvester;
transceiver;
a memory that stores one or more instructions; and
A processor to execute the instruction
including,
When the instruction is executed, the processor:
Measuring the magnitude of first power, which is power obtained by the energy harvester for a certain period of time;
Transmitting the magnitude of the first power to a central processing unit;
Receiving from the central processing unit the amount of second power, which is power that the energy harvester can obtain for a predetermined time;
Controlling the energy harvester based on the magnitude of the second power;
The magnitude of the second power is determined based on the magnitude of the first power,
energy harvesting device.
According to claim 7,
the processor,
Controlling the energy harvester by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester operates.
energy harvesting device.
According to claim 8,
The energy harvester,
one or more energy harvesting circuits; and
One or more switches controlling the energy harvesting circuit
Including, energy harvesting device.
According to claim 9,
the processor,
When the magnitude of the second power is greater than the reference power, the switch is turned on to harvest energy;
When the magnitude of the second power is smaller than the reference power, the switch is turned off to not harvest energy.
energy harvesting device.
one or more energy harvesting devices; and
Central processing unit controlling the energy harvesting device
including,
The energy harvesting device,
Measuring the magnitude of first power, which is power obtained by the energy harvester for a certain period of time;
Transmitting the magnitude of the first power to the central processing unit;
Receiving from the central processing unit the amount of second power, which is the amount of power that the energy harvester can obtain for a predetermined time;
Controlling the energy harvester based on the magnitude of the second power;
The magnitude of the second power is determined based on the magnitude of the first power,
energy harvesting system.
According to claim 11,
The energy harvesting device,
Controlling the energy harvester by comparing the size of the second power with the size of reference power, which is power consumed when the energy harvester operates.
energy harvesting system.
According to claim 12,
The energy harvester,
one or more energy harvesting circuits; and
One or more switches controlling the energy harvesting circuit
Including, energy harvesting system.
According to claim 13,
The energy harvesting device,
When the magnitude of the second power is greater than the reference power, the switch is turned on to harvest energy;
When the magnitude of the second power is smaller than the reference power, the switch is turned off to not harvest energy.
energy harvesting system.
According to claim 11,
The central processing unit,
Receiving the magnitude of the first power;
Calculate a loss function based on the magnitude of the first power;
A neural network trained by updating weights and biases to minimize the loss function.
Including, energy harvesting system.
According to claim 15,
The trained neural network is
An energy harvesting system that outputs the amount of the second power when the amount of the first power is input.

Images