System for low-power internet of things sensors management based on energy harvesting

Abstract

An energy harvesting-based IoT low-power sensor management system is provided, comprising: an energy harvesting device that stores and provides energy by receiving light; at least one IoT sensor that operates by receiving power from the energy harvesting device; a receiving unit that receives detection data detected by at least one IoT sensor; a classification unit that divides the detection data by type; an alert unit that provides an anomaly alert if the result of analyzing the detection data corresponds to a preset abnormal pattern; a data recording unit that logs the anomaly interval corresponding to the abnormal pattern; and an integrated control server that includes a charting unit that generates and provides a chart for the anomaly interval.

Description

Technology Field

[0001] The present invention relates to an energy harvesting-based IoT low-power sensor management system, and provides a system that drives, monitors, and detects anomalies in IoT low-power sensors based on energy harvesting. Background Technology

[0002] Energy harvesting-based IoT sensor networks are emerging as an alternative for continuously monitoring environmental and equipment conditions in spaces lacking power infrastructure or where wiring is difficult. In low-light indoor environments such as large warehouses, factories, and building interiors, battery replacement costs and the risk of operational downtime accumulate; data loss and delays are prone to occur due to wireless interference and multipath propagation; and dependency on gateways and maintenance costs skyrocket upon scaling up. Therefore, there is a need to design a distributed sensor network that operates self-drivingly on micropower while adaptively adjusting measurement, transmission, and sleep cycles to fit the energy budget, ensuring reliability and latency predictability through inter-node time synchronization and routing, and lowering installation and maintenance costs.

[0003] At this time, a method for constructing a smart farm or detecting anomalies in IoT devices using solar power and IoT sensors has been researched and developed. In this regard, prior art, Korean Published Patent No. 2025-0091013 (published June 20, 2025) and Korean Registered Patent No. 10-2686092 (published July 19, 2024), respectively disclose a configuration for driving at least one IoT sensor with solar power and controlling lighting, a humidity controller, and a ventilation opening using detection data detected by the IoT sensor, and a configuration for analyzing collected data from an IoT device and providing the results of the analysis of the collected data, provided that if the collected data is the result of anomaly detection, the results are provided to an administrator terminal.

[0004] However, the former utilizes solar power solely as an energy source, making it unusable indoors where sunlight does not reach or in locations with other energy sources; conversely, the latter does not provide energy harvesting-based IoT, but merely discloses a configuration that collects data from general IoT devices and performs anomaly detection. Furthermore, amidst growing demands for rapid alerts regarding anomalies, long-term continuous operation, eco-friendliness, and data-driven decision-making, a system equipped with a topology that guarantees energy balance and an on-site autonomous operation mechanism is required. Accordingly, research and development are needed for a system capable of operating IoT sensors based on energy harvesting and detecting anomalies based on detected data. The problem to be solved

[0005] One embodiment of the present invention provides an energy harvesting-based IoT low-power sensor management system that enables the installation of IoT sensors in locations without power sources or infrastructure by installing an energy harvesting device, and allows detection data to be received wirelessly from the IoT sensors, thereby eliminating the need for a person to directly access hard-to-reach places to retrieve detection data. Furthermore, by utilizing energy harvesting technologies such as light, vibration, and heat, and designing the system so that the produced energy always exceeds the consumed energy, it enables self-generation and operation by supplying power from ambient energy. However, the technical problem that this embodiment aims to solve is not limited to the technical problem described above, and other technical problems may exist. means of solving the problem

[0006] As a technical means for achieving the aforementioned technical task, one embodiment of the present invention comprises: an energy harvesting device that receives light and stores and provides energy; at least one IoT sensor that operates by receiving power from the energy harvesting device; a receiving unit that receives detection data detected by at least one IoT sensor; a classification unit that divides the detection data by type; an alert unit that provides an anomaly alert when the result of analyzing the detection data corresponds to a preset abnormal pattern; a data recording unit that logs the anomaly interval corresponding to the abnormal pattern; and a charting unit that generates and provides a chart for the anomaly interval. Effects of the invention

[0007] According to any one of the means for solving the problem of the present invention described above, by installing an energy harvesting device, IoT sensors can be installed even in places without power sources or infrastructure, and detection data from IoT sensors can be received wirelessly, thereby eliminating the need for a person to directly access hard-to-reach places to receive detection data. Furthermore, by utilizing energy harvesting technologies such as light, vibration, and heat, and designing the system so that the produced energy always exceeds the consumed energy, power is supplied from surrounding energy, thereby enabling self-generation and operation. Brief explanation of the drawing

[0008] FIG. 1 is a diagram illustrating an energy harvesting-based IoT low-power sensor management system according to one embodiment of the present invention. Figure 2 is a block diagram illustrating an integrated control server included in the system of Figure 1. FIGS. 3 and 4 are drawings for illustrating an embodiment in which an energy harvesting-based IoT low-power sensor management solution according to an embodiment of the present invention is implemented. FIG. 5 is an operation flowchart illustrating a method for providing an energy harvesting-based IoT low-power sensor management solution according to an embodiment of the present invention. Specific details for implementing the invention

[0009] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0010] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0011] Terms such as “about,” “substantially,” etc., used throughout the specification, are used to mean at or near the stated value when inherent manufacturing and material tolerances are presented in the stated meaning, and are used to prevent unscrupulous infringers from unfairly exploiting the disclosure in which precise or absolute values ​​are mentioned to aid in understanding the invention. Terms such as “step” or “step of” used throughout the specification of the invention do not mean “step for”.

[0012] In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized by one piece of hardware. Meanwhile, "part" is not limited to software or hardware, and "part" may be configured to reside in an addressable storage medium or configured to run on one or more processors. Accordingly, as an example, "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0013] Some of the operations or functions described herein as being performed by a terminal, device, or device may instead be performed by a server connected to said terminal, device, or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal, device, or device connected to said server.

[0014] In this specification, some of the operations or functions described as mapping or matching with a terminal may be interpreted as meaning mapping or matching the terminal's unique number or personal identification information, which is the terminal's identifying data.

[0015] The present invention will be described in detail below with reference to the attached drawings.

[0016] FIG. 1 is a diagram illustrating an energy harvesting-based IoT low-power sensor management system according to an embodiment of the present invention. Referring to FIG. 1, the energy harvesting-based IoT low-power sensor management system (1) may include at least one user terminal (100), an integrated control server (300), at least one IoT sensor (400), and at least one energy harvesting device (500). However, since the energy harvesting-based IoT low-power sensor management system (1) of FIG. 1 is merely an embodiment of the present invention, the present invention is not to be interpreted as being limited by FIG. 1.

[0017] At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal (100) can be connected to an integrated control server (300) through the network (200). And, the integrated control server (300) can be connected to at least one user terminal (100), at least one IoT sensor (400), and at least one energy harvesting device (500) through the network (200). Also, at least one IoT sensor (400) can be connected to the integrated control server (300) through the network (200). And, at least one energy harvesting device (500) can be connected to at least one user terminal (100), the integrated control server (300), and at least one IoT sensor (400) through the network (200).

[0018] Here, a network refers to a connection structure capable of exchanging information among individual nodes, such as multiple terminals and servers. Examples of such networks include Local Area Networks (LANs), Wide Area Networks (WANs), the World Wide Web (WWW), wired and wireless data networks, telephone networks, and wired and wireless television networks. Examples of wireless data communication networks include, but are not limited to, 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), 5GPP (5th Generation Partnership Project), 5G NR (New Radio), 6G (6th Generation of Cellular Networks), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, DMB (Digital Multimedia Broadcasting) network, etc.

[0019] In the following, the term "at least one" is defined as a term including both singular and plural forms, and it will be obvious that even if the term "at least one" does not exist, each component may exist in a singular or plural form and may mean singular or plural. Furthermore, whether each component is provided in a singular or plural form may be changed according to the embodiment.

[0020] At least one user terminal (100) may be a user terminal that monitors detection data of an IoT sensor (400) using a web page, app page, program, or application related to an energy harvesting-based IoT low-power sensor management solution, and receives and outputs the abnormal signs (abnormal patterns) when they are detected.

[0021] Here, at least one user terminal (100) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a navigation system, a laptop equipped with a web browser, a desktop, a laptop, etc. At this time, at least one user terminal (100) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one user terminal (100) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0022] The integrated control server (300) may be a server that provides an energy harvesting-based IoT low-power sensor management solution web page, app page, program, or application. Additionally, the integrated control server (300) may be a server that receives detection data from an IoT sensor (400), monitors it, detects abnormal patterns or signs of abnormality using an anomaly detection model, and provides the results to a user terminal (100). Here, the integrated control server (300) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a navigation system, a laptop, a desktop, a laptop equipped with a web browser.

[0023] At least one IoT sensor (400) may be a device that outputs detection data using a web page, app page, program, or application related to an energy harvesting-based IoT low-power sensor management solution.

[0024] At this time, at least one IoT sensor (400) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one IoT sensor (400) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc., as wireless communication devices that ensure portability and mobility.

[0025] At least one energy harvesting device (500) may be a device that produces energy from an ambient environment including heat, light, and vibration using a web page, app page, program, or application related to an energy harvesting-based IoT low-power sensor management solution, and supplies power to an IoT sensor (400).

[0026] Here, at least one energy harvesting device (500) may be implemented as a computer capable of connecting to a remote server or terminal via a network. Here, the computer may include, for example, a laptop, desktop, or laptop equipped with a navigation system or a web browser. At this time, at least one energy harvesting device (500) may be implemented as a terminal capable of connecting to a remote server or terminal via a network. At least one energy harvesting device (500) may include all kinds of handheld-based wireless communication devices, such as navigation, PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminal, smartphone, smartpad, tablet PC, etc.

[0027] FIG. 2 is a block diagram for explaining an integrated control server included in the system of FIG. 1, and FIG. 3 and FIG. 4 are drawings for explaining an embodiment in which an energy harvesting-based IoT low-power sensor management solution according to an embodiment of the present invention is implemented.

[0028] Referring to FIG. 2, the integrated control server (300) may include a receiving unit (310), a classification unit (320), a notification unit (330), a data recording unit (340), a charting unit (350), a user linkage unit (360), a design unit (370), a dynamic control unit (380), and a topology generation unit (390).

[0029] When an integrated control server (300) or another server (not shown) operating in conjunction with an embodiment of the present invention transmits an energy harvesting-based IoT low-power sensor management solution application, program, app page, web page, etc. to at least one user terminal (100), at least one IoT sensor (400), and at least one energy harvesting device (500), the at least one user terminal (100), at least one IoT sensor (400), and at least one energy harvesting device (500) may install or open the energy harvesting-based IoT low-power sensor management solution application, program, app page, web page, etc. Additionally, a service program may be operated on at least one user terminal (100), at least one IoT sensor (400), and at least one energy harvesting device (500) using a script executed in a web browser. Here, a web browser refers to a program that enables the use of web (WWW: World Wide Web) services and receives and displays hypertext described in HTML (Hyper Text Mark-up Language), and includes, for example, Chrome, Microsoft Edge, Safari, Firefox, Whale, UC Browser, etc. Additionally, an application refers to an application on a terminal, and includes, for example, an app running on a mobile terminal (smartphone).

[0030] Referring to FIG. 2, the receiver (310) can receive detection data detected by at least one IoT sensor (400). The energy harvesting device (500) can store and provide energy by receiving light. The energy harvesting device (500) refers to a device that converts micro-energy wasted in the surroundings into electricity to power and charge low-power devices such as sensors and the Internet of Things (IoT). In one embodiment of the present invention, indoor lighting was used as an energy source, but it is understood that various sources such as heat, vibration, and RF waves can be used.

[0031] energy source Harvesting method Representative converter Recommended application environment light PV, Photovoltaic, converts light energy into electrical energy. Uses a-Si / μ-Si / III-V PV cells, applies MPPT (Maximum Power Point Tracking), rectifies and charges using a PMIC (Power Management IC) and DC-DC converter, and stores power using supercapacitors / small lithium polymers. Applicable to indoor 200–1000 Lux lighting and fixed sensors near windows / lights. heat (temperature difference) TEG, Thermoelectric Generator, converts temperature difference into electrical energy. Uses a Seebeck effect-based TEG module, secures ΔT with heatsinks and conductive pads, and manages cold start and charging with Buck / Boost PMICs. Applicable to machine rooms, boiler rooms, etc., where a persistent temperature difference exists between the equipment surface and the air. Vibration / Deformation Converting mechanical energy into electrical energy through piezoelectricity, electromagnetic induction, and triboelectricity. PZT / PVDF piezoelectric elements, coil-magnet induction type, TENG (Triboelectric Nanogenerator) applied, rectification bridge and low-noise LDO / PMIC configuration, resonance frequency matching design. Applicable near motors / pumps / ducts and around equipment with structural vibrations Small wind power (micro wind) Power generation by converting airflow into machine rotation using a micro wind turbine Utilizes ultra-low friction bearing turbine, micro generator, and rectification / charging PMIC; features a waterproof and dustproof housing design. Applicable to ventilation duct outlets and passages with constant airflow. Fluid flow Converts pipe flow into rotational energy using a Fluid Flow Turbine Uses inline microturbine, corrosion-resistant bearings, and rectification / charging PMIC; pressure loss minimized by bypass installation Applicable to lines with a constant flow rate, such as HVAC and process piping. Acoustics / Ultrasonic High sound pressure is converted to piezoelectricity using Acoustic / Ultrasonic Energy Harvesting Uses broadband / resonant piezoelectric transducers, rectified / low-noise PMIC, and features a dustproof and soundproof case design. Applied to high-noise equipment rooms and near ultrasonic cleaning equipment RF waves Power is generated by rectifying ambient radio wave energy through RF energy harvesting. Designed a multi-band antenna using a Rectenna (DC antenna), impedance matching network, and RF-to-DC converter. Applied to wake-up signals and ultra-low power tags in base station / Wi-Fi dense indoor environments salinity gradient Powering ion movement using salinity gradients Utilizes ion exchange membranes and electrochemical cells, and features low-current, high-durability electrodes and rectification circuits. Applied to long-period base power in special environments such as seawater / freshwater contacts

[0032] The IoT sensor (400) can operate by receiving power from an energy harvesting device (500). The sensor may include a temperature sensor, a humidity sensor, a leak sensor, an ammonia sensor, and a TVOC (Total Organic Volatile Compound) sensor, but is not limited to those listed and is not excluded for reasons not listed.

[0033] Sensor types Applications How to use result Temperature sensor Applied to temperature monitoring in warehouses, buildings, and machine rooms, and to refrigeration and freezing quality control. Attach to a location with minimal convection influence, and set the sampling period and critical temperature after calibration. Provides temperature time series, maximum / minimum, and average, and sends threshold exceedance notifications. humidity sensor Applied to management of condensation, mold, and corrosion risk zones, and dehumidification / humidification control Avoid condensation and direct sunlight, and set period and alarm thresholds after initial calibration. Estimation of relative humidity time series and dew point, and calculation of condensation risk level leak sensor Applied to early detection of leaks in pipes, trays, and under ceilings Select Cable / Point type, fix along the path, and set segment identification. Record location and time and transmit immediate alarm in case of leak NH₃ sensor Applicable to air quality safety in livestock barns, cold storage warehouses, and chemical handling areas Separate the intake port from turbulent wind at the recommended height and set the zero point correction / calibration cycle. Provides NH₃ concentration trends and exposure levels, and sends alerts when limits are exceeded. TVOC sensor Applied to painting, bonding, and printing processes, and indoor air quality hygiene management After warming up, save the reference gas correction value and set the sampling period considering the ventilation status. Detects TVOC surge events and sends alerts requiring ventilation carbon dioxide sensor Applied to enclosed space ventilation control, comfort management, and crowd density estimation Install considering the effects of HVAC intake and exhaust, and set correction and critical concentrations. Provides CO₂ concentration time series and outputs ventilation control signals carbon monoxide sensor Applied to hazardous gas safety management in boiler rooms and parking lots Installed away from the exhaust gas path and minimizes false detection through cross-detection. CO concentration trend and alarm status recording, and siren / emergency exhaust interlock fine dust sensor Applied to dust management in indoor and process spaces and filter replacement decisions Secures air intake path and periodically removes dust, applies calibration profile Provides PM index and concentration ratings and sends filter maintenance notifications Light sensor Determining harvesting-capable illuminance and applying it to plant cultivation and work light control Install at the representative location considering the effects of diffuse reflection and correct the standard light source. Provides illuminance time series and percentile statistics and integrates with lighting / harvesting policies. differential pressure sensor Applied to monitoring pressure drop before and after cleanrooms and filters, and duct leak detection Performed filter pre- and post-port connection and zero-point calibration. Provides differential pressure trends, threshold exceedance events, and filter replacement notifications Vibration / Acceleration Sensor Applied to predictive maintenance for motor and pump bearing abnormalities Attach considering resonance frequency, and perform window analysis and threshold setting. Provides RMS / spectral feature values ​​and transmits abnormal pattern alarms water level sensor Applied to tank and reservoir level management and pump control Install according to the environment among floating, pressure, or ultrasonic types, and set the deadband. Provides water level time series and sudden change events, and integrates with pump on / off control smoke detector Applied to initial fire smoke detection and fire prevention interlocking Install in the recommended ceiling location away from direct airflow and set the self-inspection cycle. Smoke concentration rise detection and emergency alarm / disaster prevention equipment interlock

[0034] The classification unit (320) can divide the detection data by type. It identifies the type of detection data, and by dividing it, it sets what the abnormal pattern of the detection data is.

[0035] The notification unit (330) can provide an outlier notification if the result of analyzing the detection data corresponds to a pre-set abnormal pattern. Before analyzing the detection data, preprocessing can be performed to organize the signal and correct missing intervals. When organizing the signal, spike removal (STL (Seasonal-Trend decomposition using LOESS)) can be performed, and for missing values, EWMA (Exponentially Weighted Moving Average) can be used. In addition, de-noising can be performed using a Kalman Filter, and standardization and normalization can be performed. Next, features capable of detecting abnormal patterns or signs of abnormality can be extracted, a baseline can be set, and inference can be performed in the anomaly detection model. This process is summarized as shown in Table 3 below.

[0036] Anomaly detection process step purpose Major tasks tool or model 1. Ingestion Sensor time series acquisition and meta synchronization secured Collect BLE / Gateway, assign timestamp, node ID, and quality metrics (RSSI / ETX). Uses MQTT (Message Queuing Telemetry Transport), BLE Mesh, TSCH (Time Slotted Channel Hopping), and InfluxDB / TimescaleDB 2. Preprocessing Signal cleanup and missing data correction Performed spike removal, missing data (EWMA / interpolation), denoising, and standardization / normalization Using STL (Seasonal-Trend decomposition using LOESS), EWMA (Exponentially Weighted Moving Average), and Kalman Filter 3. Feature Engineering Generates abnormally sensitive features Generates moving statistics (mean / variance / IQR), rate of change, window spectrum, leakage interval length, etc. Using Pandas, NumPy, and SciPy 4. Calculation of Baseline Calculated normal range (including seasonality) Estimation of normal bands based on daily / weekly cycles, calculation of percentile thresholds per node Using STL and Holt-Winters 5. Model Inference Determine outliers / change points Performed univariate / multivariate anomaly detection and change point detection See Table 4 below. 6. Post-processing Suppression and strengthening of the Five Swords Hysteresis, k consecutive iterations condition, multi-sensor cross-validation applied Uses Rule Engine, PyDantic for policy implementation 7. Severity Assessment (Scoring) Alarm Classification Grade is determined based on deviation magnitude, duration, and simultaneous multi-sensor operation. Using Scikit-learn scoring pipeline 8. Alert & Action Performs notifications and automatic actions by channel Trigger actions such as push / webhook / slack, valve shut-off in case of leak Uses Webhook, Slack API, IFTTT, and Grafana Alerting 9. Feedback / Online Learning (Feedback) Performance improved by incorporating on-site tagging Collected false / unverified labels, performed threshold / weighted retraining Used River (Online ML) and PyOD (Python Outlier Detection) 10. Governance Maintaining reproducibility and audit records Manages version, parameter, ROC / PR history, and model rollback Using MLflow and DVC (Data Version Control)

[0037] Selection of Anomaly Detection Model (by Situation) situation Anomaly detection model Input / Features merit Points to note tool Univariate rapid change detection (temperature / humidity / TVOC) CUSUM (Cumulative Sum Control Chart), EWMA Normalized time series, baseline deviation Lightweight and easy to explain Critical readjustment required during drifting NumPy / SciPy, Edge firmware compatible Seasonal anomalies (daily cycles) STL+residual threshold, Holt-Winters residual-based Residuals after trend and season decomposition Strong at removing periodicity Initial tuning required Using statsmodels Turning point (leakage starts / NH₃ surge starts) Bayesian Online Change Point Detection (BOCPD) Real-time cumulative Udo Strong in starting point detection Calculation costs increase (Gateway recommended) Using ruptures and bayesian-changepoint Multivariate anomaly (simultaneous pattern of temperature, humidity, and TVOC) Isolation Forest, One-Class SVM (One-Class Support Vector Machine) Multidimensional feature vector Strong against complex patterns Scale and Kernel dependencies Using Scikit-learn and PyOD Non-linear complex patterns / predictions Autoencoder, LSTM-AE (Long Short-Term Memory Autoencoder) Window sequence features Strong in complex patterns and time series memory Training data and resources are required Using TensorFlow Lite Micro (Edge) and ONNX Runtime Density / neighborhood-based anomaly LOF(Local Outlier Factor), kNN Distance Anomaly value relative to local density Adaptive data distribution Vulnerability to scarcity and high dimensions Using Scikit-learn and PyOD Rule+Model Mix (Safety threshold required) Rule-based + Model Ensemble Rule threshold + model score Explanation and ensuring safety Rule management costs exist Uses Rule Engine, sklearn Voting

[0038] For example, leak or gas alerts can be triggered based on k consecutive occurrences by building a model using [STL residuals + CUSUM redundancy], and in the case of complex air quality issues, alerts can be triggered by checking with Isolation Forest first-order and LSTM-AE second-order when the threshold is exceeded. Data

[0039] The recording unit (340) can log outlier intervals corresponding to an abnormal pattern as shown in FIG. 41. The charting unit (350) can generate and provide a chart for the outlier intervals as shown in FIG. 41.

[0040] The user linkage unit (360) transmits detection data to the user terminal (100) to allow the user terminal (100) to monitor the detection data, and can generate and provide anomaly alerts and charts for the anomaly range. As shown in FIG. 4k, at least one IoT sensor (400) and the user terminal (100) can be connected directly via Bluetooth or through a gateway. Looking at FIG. 4p, it can be seen that detection data is collected to the user terminal (100) through the gateway. The gateway can constantly scan packets periodically broadcast by the IoT sensor (400) or periodically poll, and uplink the collected values ​​to the LAN / Internet (MQTT / HTTPS). When installing the gateway, the coverage radius of one gateway can be measured first (based on RSSI / packet loss rate), and then two to three gateways can be distributed in the necessary areas.

[0041] The design department (370) measures the illuminance of the site to install the energy harvesting device (500) at the site, calculates the area of ​​the indoor solar cell and the capacity of the battery based on the illuminance and the type, number, and power consumption of at least one IoT sensor (400), and can finalize the design with the calculated area of ​​the solar cell and the capacity of the battery when the energy produced by the energy harvesting device (500) is greater than the energy consumed.

[0042] First, let's assume that each IoT sensor (400) is a Node, and that each Node i is 1 to N. Let's assume that the measurement period is tmeas,i[s], the communication period is ttx,i[s], the sleep time is tsleep,i[s], the measurement power is Pmeas,i[W], the communication power is Ptx,i[W], and the sleep power is Psleep,i[W], the indoor illuminance distribution during the day is L(t)[Lux] (or minimum / percentile illuminance Lmin, Lp), and the dark period (night) duration is Tdark[h]. Let's assume that the indoor standard is 500~600 Lux.

[0043] <Average Power Consumption per Node>

[0044] Next, the average power consumption for each node (sensor) must be calculated, which can be expressed as Equation 1 below. The average power consumption in Equation 1 refers to the average power consumption of one cycle of node i.

[0045]

[0046] The total sum of all N units is ΣPavg,i, but since harvesting is based on a node-independent design, Equation 1 is used.

[0047] Harvesting (Power Generation) Model

[0048] Next, the generated power of the energy harvesting device (400) at indoor illuminance L (Lux) is as follows in Equation 2.

[0049]

[0050] Acell is the effective area of ​​the photovoltaic cell [m2], ηconv is the photovoltaic conversion efficiency (5~15% range for small indoor cells), ηpmic is the power management / rectification / charging efficiency [0~1], klux is the Lux→radiation intensity conversion constant [W / (m^2·Lux)] (constant for indoor light approximation), and L is the illuminance [Lux].

[0051] <Capacitance (Matte Duration) Design>

[0052] The energy to be withstood during the dark period Tdark is given by the following mathematical formula 3.

[0053]

[0054] In this case, γ is the safety factor (usually 1.2 to 1.5). The required capacitance (when using a capacitor-based design) is given by Equation 4 below.

[0055]

[0056] Inverse Design Formula

[0057] <Fix Period → Calculate Panel Area>

[0058] Next, if the operation cycle of the IoT sensor (400) is fixed, the panel area of ​​the energy harvesting device (500) can be calculated as shown in Equation 5 below since Pavg is fixed.

[0059]

[0060] <Fix Panel Area → Adjust Cycle>

[0061] Alternatively, if the Acell, which is the panel area of ​​the energy harvesting device (500), is fixed, the operation cycle of the IoT sensor (400) can be adjusted.

[0062]

[0063] At this time, Emeas is the energy consumed in the measurement section of one cycle of the IoT sensor (400), Etx is the energy consumed in the wireless transmission section of one cycle of the IoT sensor (400), and Esleep is the energy consumed in the sleep section of the IoT sensor (400).

[0064] Optimization Model

[0065] <Objective Function>

[0066] In addition to the method described above, an energy harvesting device (500) can be designed using an optimization model, so that the energy harvesting device (500) can satisfy the energy self-sufficiency condition while minimizing the panel area or total cost.

[0067]

[0068] Here, Acell is the harvesting cell area [m2], Cstore is the capacitance [F], tcycel is the measurement / transmission cycle [s], Pmeas, Ptx, Psleep are the power of each mode [W], and tmeas, ttx, tsleep are the duration of each mode [s]. wi is the design priority weight.

[0069] <Constraints>

[0070] Constraints may include energy balance constraints, battery stability constraints, and operation constraints. The energy balance constraint requires that energy produced exceeds energy consumed, the battery stability constraint requires that the battery lasts during the off-peak period, and the operation constraint requires that the cycle have upper and lower limits to account for sensor accuracy or response delay.

[0071] Non-linear Constraint Optimization

[0072] Nonlinear programming can utilize Sequential Quadratic Programming (SQP) or the Interior-Point method, which is a method of finding decision variables under a nonlinear objective function and nonlinear / linear constraints to minimize or maximize the target value. Of course, it goes without saying that the energy harvesting device (500) can be designed in various ways in addition to the methods described above.

[0073] The dynamic control unit (380) can collect and learn real-time illuminance detected by the energy harvest device (500) and power usage pattern data of at least one IoT sensor (400), predict the amount of power generated in the next time period, and dynamically control the duty cycle of at least one IoT sensor (400). At this time, the duty cycle refers to a control that adjusts the proportion of measurement, transmission, and sleep in the ratio of active time to total time in one cycle of the IoT sensor (400) to match the average power consumption. The control objective is to dynamically adjust tmeas, ttx, and tsleep so that the average power consumption Pavg is always kept below the predicted power generation (hat)Pgen for the next time period.

[0074] 1. Forecast Predicting the (hat)Pgen power generation of the next window using illuminance time series Options: AutoRegressive Integrated Moving Average (ARIMA), Kalman Filter, Long Short-Term Memory (LSTM), Prophet (Facebook Prophet) 2. Consumption Estimation (Load Model) Pavg is estimated using measured, transmitted, and slip power in the recent cycle. 3. Control Law - Simple scaling (refer to Equation 8) - Safety limit (refer to Equation 9) 4. Priority Rules - Event-type data (leakage, gas) is prioritized for immediate transmission. - During normal operation, batch transmission (batch of multiple samples) is used to minimize the number of transmissions. 5. Feedback Automatically corrects thresholds and weights by reflecting O-Gam and Mi-Gam tagging

[0075]

[0076] α is the sensitivity (0.3 to 0.7 recommended), and you can set it to increase the period if it is insufficient and decrease it if there is room.

[0077]

[0078] If the requirement is not met, an emergency power saving profile can be applied.

[0079] In addition to the control methods described above, Model Predictive Control (MPC) may also be used. Of course, in addition to this method, LSTM may be used to learn real-time illuminance and usage pattern data to predict power generation for the next time period and automatically adjust the cycle, or a Reinforcement Learning-based scheduler may be used to correct the dynamic difference between Pgen(t) and Pavg(t) in real time and extend the sleep when it is below a threshold. Furthermore, Mixed-Integer Linear Programming (MILP) or Distributed Optimization may be used to integrate and optimize power generation and consumption of multiple nodes at the network level, and a Maximum Power Point Tracking (MPPT) algorithm may be used to track the optimal point of the VI curve in real time according to indoor light fluctuations.

[0080] The topology generation unit (390) can generate a topology from at least one sensor and synchronize time between at least one sensor within the topology. The reason for generating the topology is that the idle receiver standby power is significantly reduced because the nodes wake up and go to sleep simultaneously based on the same time standard, which is advantageous for no power or ultra-low power.

[0081] <Initial Bootstrap>

[0082] At least one IoT sensor (400) can form a list of adjacent nodes based on the received signal strength by broadcasting a Universally Unique Identifier and a Received Signal Strength Indicator when power is supplied to at least one IoT sensor (400). When creating the list of adjacent nodes, a distance-based weight wij and a link quality Qij including the received signal strength (RSSI) and packet success rate are calculated.

[0083] Local Topology Configuration

[0084] Then, at least one IoT sensor (400), when generating a graph based on a list of adjacent nodes, can select the node with the highest link quality (Qij), including RSSI and packet success rate, among each node as the parent node, and then set the parent node as the link set for synchronization. That is, the graph is configured as G=(V,E) like a GNN, and each node selects the node with the highest Qij among its k neighbors as the parent node. Also, when the routing tree or mesh link is completed, the link set for synchronization is determined in the form Tsync={(i,j)|Qij>=θ}.

[0085] Synchronization and Slot Assignment

[0086] When the leader node, selected as the parent node with the highest link quality, transmits a Time Beacon, at least one node can synchronize its time using the parent node as the synchronization link set. Each node transmits and receives only within its assigned slot and sleeps during the remaining time.

[0087] Hereinafter, the operation process according to the configuration of the integrated control server of FIG. 2 described above will be explained in detail with reference to FIG. 3 and FIG. 4. However, it is obvious that the embodiment is merely one of the various embodiments of the present invention and is not limited thereto.

[0088] Referring to FIG. 3, (a) when the integrated control server (300) designs the energy harvesting device (500), it measures the field illuminance, determines the type and number of IoT sensors (400), and then designs the solar cell area and battery capacity. That is, as shown in FIG. 4j, it determines the energy that can be generated (energy produced) and the energy to be consumed (energy consumed), determines the solar cell area so that the energy produced can be higher than the energy consumed, and also sets the battery capacity so that it can operate even in a blackout mode.

[0089] Then, (b) once the design is finalized, the energy harvesting device (500) is produced and installed accordingly, and the integrated control server (300) transmits the detection data measured from the IoT sensor (400) to the user terminal (100) so that the user can monitor the detection data. Also, as in (c), the integrated control server (300) can detect abnormal patterns or abnormal signs and provide them to the user terminal (100).

[0090] A platform (tentatively named Neometric) according to one embodiment of the present invention provides a solution as shown in FIG. 4c to solve a problem as shown in FIG. 4b. The product configuration may be as shown in FIG. 4d, and each component may be connected as shown in FIG. 4e. Additionally, sensors may be configured as shown in FIG. 4f to 4h, and an energy harvesting device (500) may be configured as shown in FIG. 4i and 4j, and may be linked with an application of the present invention as shown in FIG. 4k, and the application may be as shown in FIG. 4l. The platform of the present invention may be applied in a place such as FIG. 4m and may be applied as shown in FIG. 4n. It may also have a goal as shown in FIG. 4o and a vision as shown in FIG. 4p. FIG. 4q to 4u are enlarged drawings of the application of the present invention.

[0091] As for the details regarding the method of providing an energy harvesting-based IoT low-power sensor management solution shown in FIGS. 2 to 4 that are not described, they are identical to or can be easily inferred from the details described above regarding the method of providing an energy harvesting-based IoT low-power sensor management solution shown in FIG. 1, so further explanation will be omitted.

[0092] FIG. 5 is a diagram illustrating the process of transmitting and receiving data between each component included in the energy harvesting-based IoT low-power sensor management system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described through FIG. 5, but the present invention is not to be interpreted as being limited to such an embodiment, and it is obvious to those skilled in the art that the process of transmitting and receiving data illustrated in FIG. 5 may be changed according to various embodiments described above.

[0093] Referring to FIG. 5, the integrated control server receives detection data detected by at least one IoT sensor (S5100) and divides the detection data by type (S5200).

[0094] Then, the integrated control server provides an outlier notification if the result of analyzing the detection data corresponds to a pre-set abnormal pattern (S5300), and logs the outlier interval corresponding to the abnormal pattern (S5400).

[0095] In addition, the integrated control server generates and provides a chart for the outlier range (S5500).

[0096] The order of the steps described above (S5100~S5500) is merely an example and is not limited thereto. That is, the order of the steps described above (S5100~S5500) may vary, and some of these steps may be executed simultaneously or deleted.

[0097] As for the details regarding the method of providing an energy harvesting-based IoT low-power sensor management solution of Fig. 5 that are not described, they are identical to or can be easily inferred from the details described above regarding the method of providing an energy harvesting-based IoT low-power sensor management solution through Figs. 1 to 4, so further explanation will be omitted.

[0098] A method for providing an energy harvesting-based IoT low-power sensor management solution according to one embodiment described through FIG. 5 may also be implemented in the form of a recording medium containing computer-executable instructions, such as an application or program module executed by a computer. A computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, as well as removable and non-removable media. Additionally, a computer-readable medium may include all computer storage media. A computer storage medium includes both volatile and non-volatile, removable and non-removable media implemented by any method or technique for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0099] The method for providing an energy harvesting-based IoT low-power sensor management solution according to one embodiment of the present invention described above may be executed by an application basically installed on a terminal (which may include a program included in a platform or operating system, etc., basically installed on the terminal), or by an application (i.e., a program) directly installed by a user on a master terminal through an application providing server, such as an application store server, an application, or a web server related to the service. In this sense, the method for providing an energy harvesting-based IoT low-power sensor management solution according to one embodiment of the present invention described above may be implemented as an application (i.e., a program) that is basically installed on the terminal or directly installed by a user, and may be recorded on a computer-readable recording medium such as a terminal.

[0100] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.

[0101] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.

Claims

Claim 1 An energy harvesting device that stores and provides energy by receiving light; at least one IoT sensor that operates by receiving power from the energy harvesting device; The integrated control server comprises: a receiving unit for receiving detection data detected by at least one IoT sensor; a classification unit for dividing the detection data by type; an alert unit for providing an anomaly alert when the result of analyzing the detection data corresponds to a preset abnormal pattern; a data recording unit for logging an anomaly interval corresponding to the abnormal pattern; and a charting unit for generating and providing a chart for the anomaly interval. The integrated control server comprises: a design unit for measuring the illuminance of the site and calculating the area of ​​an indoor solar cell and the capacity of a battery based on the illuminance and the type, number, and power consumption of at least one IoT sensor, and for finalizing the design with the calculated area of ​​the solar cell and the capacity of the battery when the energy produced by the energy harvesting device is greater than the energy consumed; and a unit for collecting and learning real-time illuminance detected by the energy harvesting device and power usage pattern data of at least one IoT sensor, predicting the power generation amount for the next time period, and dynamically controlling the duty cycle of at least one IoT sensor. Dynamic control unit; topology generation unit that generates a topology from at least one IoT sensor and synchronizes time between at least one IoT sensor within the topology;It includes, and at least one IoT sensor, when power is supplied to the at least one IoT sensor, broadcasts a Universally Unique Identifier and a Received Signal Strength Indicator to form an adjacent node list based on the Received Signal Strength; when creating the adjacent node list, calculates a distance-based weight wij and a link quality Qij including the Received Signal Strength (RSSI) and packet success rate; when creating a graph based on the adjacent node list, selects the node with the highest link quality including the Received Signal Strength and packet success rate among each node as the parent node, sets the parent node as the synchronization link set, and when the routing tree or mesh link is completed, the synchronization link set is determined in the form Tsync={(i,j)|Qij>=θ}; when the leader node selected as the node with the highest link quality among the parent nodes transmits a time reference signal (Time Beacon), at least one node synchronizes time using the parent node as the synchronization link set, and the notification unit removes spikes before analyzing the detection data, An energy harvesting-based IoT low-power sensor management system characterized by performing preprocessing including at least one of missing value correction, noise removal, standardization, and normalization, extracting features capable of detecting abnormal patterns or signs of abnormality, setting a baseline and performing inference in an anomaly detection model, providing an anomaly notification by applying at least one of hysteresis, a consecutive k-times condition, and multi-sensor cross-validation to the inference result of the anomaly detection model, and the dynamic control unit dynamically adjusting tmeas, ttx, and tsleep to always maintain the average power consumption Pavg relative to the predicted power generation Pgen for the next time period below a certain level, prioritizing immediate transmission in the case of event-type leaks or gas, minimizing the number of transmissions through batch transmission during normal times, and applying an emergency power saving profile when the threshold is not met. Claim 2 An energy harvesting-based IoT low-power sensor management system, characterized in that, in claim 1, the integrated control server further comprises a user linkage unit that transmits the detection data to a user terminal to enable the user terminal to monitor the detection data, and generates and provides an outlier notification and a chart for the outlier interval. Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 delete

Images