KR20200139427A - System for providing ai based energy saving type street light control service using find dust filtering and energy generation - Google Patents

Abstract

Provided is a system for providing an AI-based power-saving streetlamp control service using fine dust filtering and energy generation. The system comprises: at least one streetlamp device to which an identifier corresponding to at least one position is assigned, controlling the illumination and on/off of at least one streetlamp by artificial intelligence control, and mapping and outputting sensing data sensed by at least one sensor with the identifier; and a streetlamp control service providing server including an assigning unit assigning the identifier corresponding to the at least one location where at least one streetlamp is installed and storing the identifier, an input unit receiving the sensing data received from the at least one streetlamp to input the sensing data as query data, an AI control unit generating output data by previously learned AI algorithm when the query data is inputted, and a transmission unit transmitting output data to the at least one streetlamp.

Description

System FOR PROVIDING AI BASED ENERGY SAVING TYPE STREET LIGHT CONTROL SERVICE USING FIND DUST FILTERING AND ENERGY GENERATION} using artificial intelligence-based fine dust filtering and energy generation

The present invention relates to a system for providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation, and uses energy obtained from nature to light a street light, and performs adaptive control to the situation and environment with an artificial intelligence algorithm. Provide a system that can do it.

The flashing system of streetlight lighting is being developed in the form of combining IT technology and LED lighting for efficient management and energy saving. Smart LED lighting control system is a combination of IT technology, that is, sensor and communication technology and LED lighting, and can achieve high efficiency and low power compared to existing light sources, as well as express various structures and light distribution, emotional lighting, light color variable, color rendering. It has advantages such as improvement. In addition, it is developing into an inter-industry and technology convergence system with a multifunctional solution with built-in content that meets the user's requirements. Recently, smart road lighting is a hardware that minimizes the dependence of administrators with an artificial intelligence two-way wireless lighting control system based on the Internet and smart sensors, shares information between systems, and provides a light environment suitable for the time and place where road lighting is required. It is developing into the concept of a software convergence system.

At this time, a method of controlling the flickering of street lights in consideration of the floating population has been researched and developed. In this regard, Korean Patent Publication No. 2008-0091946 (published on October 15, 2008), which is a prior art, provides statistical analysis of the floating population. A human body detection sensor unit that detects the movement of the human body, a floating population calculation unit that calculates the number of floating populations by time based on the output from the human body detection sensor unit, and a control program are built-in to intelligently control the lighting and lighting of streetlights. Thus, there is disclosed a configuration of a control unit that controls the lighting of and turning off streetlights based on information on the number of floating populations for each time period calculated from the number of floating populations.

However, the above-described configuration uses the term artificial intelligence, but since it is different from the recent concept of artificial intelligence equipped with deep learning or artificial neural networks, it cannot be said to be a true artificial intelligence street light. In the completion stage of the ultimate technology of smart road lighting, a road lighting system equipped with artificial intelligence provides a light environment optimized for unspecified and irregular road conditions, and analyzes all situations that may occur in the city and optimal response, autonomous vehicles, and crime. Research and development on the combination of artificial intelligence and streetlights because it aims to realize continuous decision-making ability by making decisions by itself through real-time networking and deep learning with various smart devices such as prevention, provision of personal information, and protection system for the elderly. Is being demanded.

An embodiment of the present invention provides an artificial intelligence platform capable of realizing continuous decision-making ability by making decisions by themselves through real-time networking and deep learning with various smart devices, and providing a light environment optimized for unspecified and irregular road conditions. It is possible to analyze and optimally respond to all situations that may occur in the city, and by detecting the power line, it is possible to prepare for an abnormal situation of streetlights.If the commercial power is supplied by bypassing the commercial power and overcurrent does not flow, a plurality of voltage drops Power can be saved by selectively supplying power in stages, and air pollution can be prevented by installing a filter and an inlet that can filter fine dust, while converting solar energy into electrical energy to supply power to power. It is possible to provide a method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation that can be supplied without environmental pollution by itself. However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

As a technical means for achieving the above-described technical problem, in an embodiment of the present invention, an identifier corresponding to at least one location is given, and illumination and on/off of at least one street light are controlled by artificial intelligence control, At least one street light device that maps and outputs detection data sensed by at least one sensor with an identifier, and a grant unit that assigns and stores an identifier corresponding to at least one location where at least one street light is installed, and at least one street light device An input unit that receives sensing data received from and inputs it as query data, an artificial intelligence control unit that generates output data using a previously learned artificial intelligence algorithm when the query data is input, and transmits the output data to at least one street light device It includes a streetlight control service providing server including a transmission unit.

According to any one of the above-described problem solving means of the present invention, various smart devices and real-time networking and deep learning provide an artificial intelligence platform capable of self-decision making and realizing continuous decision-making ability, and It provides an optimized lighting environment, enables analysis and optimal response to all situations that may occur in the city, and prepares for abnormal situations of streetlights by detecting power lines, and supplies commercial power by bypassing the commercial power and does not cause overcurrent to flow. In this case, power can be saved by selectively supplying a plurality of power sources with reduced voltage in stages, and even air pollution can be prevented by installing a filter and an inlet that can filter fine dust, while converting solar energy into electric energy to save power. By allowing it to be supplied, even power can be supplied by itself without environmental pollution.

1 is a view for explaining a system for providing an ultra-power saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a street light device and a street light control service providing server included in the system of FIG. 1.
3 and 4 are views for explaining an embodiment in which an ultra-power saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention is implemented.
5 is a flowchart illustrating a method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement the present invention. However, the present invention may be implemented in various different forms and is not limited to the embodiments described herein. In the drawings, parts irrelevant to the description are omitted in order to clearly describe the present invention, and similar reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only "directly connected" but also "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, and one or more other features, not excluding other components, unless specifically stated to the contrary. It is to be understood that it does not preclude the presence or addition of any number, step, action, component, part, or combination thereof.

The terms "about", "substantially" and the like, as used throughout the specification, are used in or close to the numerical value when manufacturing and material tolerances specific to the stated meaning are presented, and are used in the sense of the present invention. To assist, accurate or absolute figures are used to prevent unfair use of the stated disclosure by unscrupulous infringers. As used throughout the specification of the present invention, the term "step (to)" or "step of" does not mean "step for".

In the present specification, the term "unit" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Further, one unit may be realized using two or more hardware, or two or more units may be realized using one hardware.

In this specification, some of the operations or functions described as being performed by the terminal, device, or device may be performed instead in a server connected to the terminal, device, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed by a terminal, device, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal means mapping or matching the unique number of the terminal or the identification information of the individual, which is the identification information of the terminal. Can be interpreted as.

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

1 is a view for explaining a system for providing an ultra-power saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention. Referring to FIG. 1, an ultra-power-saving street light control service providing system 1 using artificial intelligence-based fine dust filtering and energy generation may include at least one street light device 100 and a street light control service providing server 300. have. However, since the ultra-power-saving street light control service providing system 1 using artificial intelligence-based fine dust filtering and energy generation of FIG. 1 is only an embodiment of the present invention, the present invention is limitedly interpreted through FIG. no.

In this case, each component of FIG. 1 is generally connected through a network 200. For example, as shown in FIG. 1, at least one street light device 100 may be connected to a street light control service providing server 300 through a network 200. In addition, the streetlight control service providing server 300 may be connected to at least one streetlight device 100 through the network 200. Here, the network refers to a connection structure in which information exchange is possible between respective nodes such as a plurality of terminals and servers, and examples of such networks include RF, 3rd Generation Partnership Project (3GPP) network, and Long Term (LTE). Evolution) network, 5GPP (5th Generation Partnership Project) network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network) , Personal Area Network (PAN), Bluetooth (Bluetooth) network, NFC network, satellite broadcasting network, analog broadcasting network, Digital Multimedia Broadcasting (DMB) network, and the like, but are not limited thereto.

In the following, the term “at least one” is defined as a term including the singular number and the plural number, and even if the term “at least one” does not exist, each component may exist in the singular or plural, and may mean the singular or plural. It will be self-evident. In addition, it will be possible to change according to the embodiment that each component is provided in a singular or plural.

The at least one street light device 100 may be a device that controls a street light using a web page, an app page, a program, or an application related to an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation. At this time, the at least one street light device 100 transmits the detection data sensed by at least one sensor to the street light control service providing server 300, and receives the result data derived by the artificial intelligence algorithm to perform control. Can be In addition, the at least one street light device 100 is provided with an identifier that is an ID that can identify a location and a street light, and is stored, and when transmitting the sensing data to the street light control service providing server 300, include the identifier in the header. Alternatively, it may be transmitted by attaching it to a tag, and at this time, it may be a device that allows the location information and time information to be identified by the streetlight control service providing server 300 by transmitting the time together. In addition, the at least one street light device 100 may be a device that detects a short circuit or a short circuit of a power line, and may be a device that controls voltage drop and AC power by step (level) in order to minimize power consumption. In addition, at least one street light device 100 may be a device that inhales and filters outside air, and then discharges the purified air back to the outside when air cleaning control is received from the street light control service providing server 300. have. In addition, the at least one street light device 100 converts natural energy into electrical energy using primary energy, especially natural energy such as solar energy or wind energy, and stores the converted electrical energy or other connected It may be a device that transmits power to at least one street light device 100.

Here, the at least one street light device 100 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like. In this case, the at least one street light device 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one street light device 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), 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) ) All types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs may be included.

The street light control service providing server 300 may be a server that provides a web page, an app page, a program, or an application for an ultra-power saving street light control service using artificial intelligence-based fine dust filtering and energy generation. In addition, the streetlight control service providing server 300 may be a server that collects at least one nature data, road condition data, and history log data that is a streetlight control history, builds big data, and then performs learning. In addition, the street light control service providing server 300 inputs the sensing data collected by the at least one street light device 100 and the position and time of the at least one street light into an artificial intelligence algorithm as query data, and the resultant control data is When output, it may be a server that transmits it to at least one street light device 100. In addition, the street light control service providing server 300, when detecting a short circuit or a short circuit of a power line from at least one street light device 100, or when the life of the LED of the street light is exhausted and needs to be replaced, etc. , It may be a server that transmits to the manager terminal (not shown) so that it can be repaired. In addition, the streetlight control service providing server 300 collects data such as the amount of fine dust generated at the location of the at least one streetlight device 100 or air pollution, and transmits a control signal to at least one streetlight so that air can be cleaned. It may be a server that transmits to the device 100.

Here, the streetlight control service providing server 300 may be implemented as a computer that can access a remote server or terminal through a network. Here, the computer may include, for example, a navigation system, a notebook equipped with a web browser, a desktop, a laptop, and the like.

2 is a block diagram illustrating a street light device and a street light control service providing server included in the system of FIG. 1, and FIGS. 3 and 4 are artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention. A diagram for explaining an embodiment in which an ultra-power-saving street light control service using is implemented.

Referring to FIG. 2, at least one street light device 100 may include a wire condition monitoring unit 110, a power reduction unit 120, an air cleaning unit 130, and a solar light management unit 140, The streetlight control service providing server 300 may include a granting unit 310, an input unit 320, a control unit 330, a transmission unit 340, a standby management unit 350, and an artificial intelligence unit 360.

A streetlight control service providing server 300 according to an embodiment of the present invention or another server (not shown) operated in conjunction with at least one streetlight device 100 and a manager terminal (not shown) to filter fine dust based on artificial intelligence And when transmitting an ultra-power-saving street light control service application, program, app page, web page, etc. using energy generation, at least one street light device 100 and a manager terminal (not shown) are provided with artificial intelligence-based fine dust filtering and energy. It is possible to install or open an ultra-power-saving street light control service application, program, app page, and web page using power generation. In addition, a service program may be driven in at least one street light device 100 and a manager terminal (not shown) by using a script executed in a web browser. Here, the web browser is a program that enables you to use the web (WWW: world wide web) service, and refers to a program that receives and displays hypertext described in HTML (hyper text mark-up language). For example, Netscape , Explorer, chrome, etc. In addition, the application means an application on the terminal, and includes, for example, an app that is executed on a mobile terminal (smartphone).

<Street light device>

The wire condition monitoring unit 110 is installed in the distribution board to identify a state of a power line supplying power to at least one street light device 100, and a short circuit or short circuit event to the street light control service providing server 300 in case of a short circuit or short circuit Is generated and transmitted, and a monitoring event, which is a result of monitoring the power line of the power line in real time, may be transmitted to the street light control service providing server 300. At this time, the wire condition monitoring unit 110 reads low-frequency data of a low voltage level, which is a preset voltage input between the power line line (R/T phase) and FG (Field Gound), to determine a short circuit or a short circuit event, and the power line is It detects a changeover event from the non-powered state to the power-on state, and can turn on the switch of the power line line when the power-on state is converted to the non-powered state. A configuration not described in an embodiment of the present invention is disclosed in Korean Patent Publication No. 2007-0003363 (published on January 5, 2007), and thus detailed description thereof will be omitted.

The power reduction unit 120 outputs a relay driving control signal for lighting at least one street light when the current of the power supplied to the at least one street light device 100 is less than a preset overcurrent reference value, and at least one street light is When turned on, it is possible to control the power to be supplied at a level in which the voltage is gradually decreased whenever a preset time elapses. At this time, since the configuration not described in the embodiment of the present invention is disclosed in Korean Patent Application Publication No. 2013-0066926 (published on June 21, 2013), a detailed description thereof will be omitted.

The air cleaning unit 130 has at least one hole formed in the housing of at least one street light, and filters fine dust contained in the inhaled air by sucking outside air inside the housing, and housing the filtered air. It can be discharged through at least one hole of. Typical factors of outdoor air quality are temperature and humidity. Here, the fine dust PM10 and PM2.5, which are the biggest problems recently, should be measured. Real-time air pollution level measurement operated by the Ministry of Environment Air Korea measures air quality information at about 360 locations nationwide in real time, and It is released in real time. However, since Air Korea has only about 360 measurement networks nationwide, it is installed in the metropolitan area and some metropolitan cities, and in the case of local areas, measurement networks are intermittently installed. Therefore, in addition to controlling air cleaning using information from the environment unit in the streetlight control service providing server 300 to be described later, a method of measuring fine dust in the streetlight itself will be described in an embodiment of the present invention.

First, the air cleaning unit 130 includes a fine dust sensor, and the fine dust sensor may use, for example, a PPD (Photo Particle Dectector), but is not limited thereto. PPD is a sensor that monitors the air in production processes of class 100,000 or more, detects invisible floating particles, and reacts sensitively to suspended dust with relatively large particle diameters related to allergy. The PPD narrows the light of a light source to an illumination area using an irradiation lens, and generates a scattered light pulse with an intensity corresponding to the size of the particle when the particles pass through the illumination area. At this time, the number of scattered light pulses per unit time is proportional to the number and concentration of suspended particles of the size of the dust, and it is a method of detecting as brightness (illuminance) by synthesizing the scattered light from multiple particles (smoke). This is because the amount of photocurrent and smoke concentration of the receiver are proportional.

The air cleaning unit 130 should measure fine dust using PPD, but when the time to determine when the dust enters becomes real-time, the amount of calculation increases and the amount of data increases, so it is determined based on the unit of measurement for the measurement time. can do. For example, when checking is performed at a period of 30 seconds, data may be accumulated in the air cleaning unit 130. When the quality of air is determined in this way, the air cleaning unit 130 should filter the air using a fine dust filter. The process of filtering the air separates particles and large and small ones and inhales them, and does not perform filtering. Since filtering is performed at once, it is filtered with one filter, but dust of various sizes is not filtered. Therefore, a step-by-step filter capable of filtering particles of different sizes step by step may be further provided. For example, the first filter of the step-by-step filter may use a pre-filter to remove the largest dust particles. The pre-filter is, for example, a pre-treatment primary filter in which a filter medium such as special synthetic fiber or metal is attached to various frames, and means a filter that collects dust of 10 μm or less. The second filter refers to a process of collecting dust by generating negative ions. That is, it can be described as an intangible filter generated by negative ions rather than a type of filter that exists physically. At this time, the second filter uses the principle of purifying the air by ionizing pollutants in the air, which is one of the characteristics of the electrostatic precipitating air purifier, and adsorbing it to a dust collecting plate with strong dust collecting power. Particles with positive charge are charged by +, and particles with + charge pass through the charging plate charged with + and -, receiving repulsive force from the positive plate and attracting attraction from the negative plate, so that the fine particles differ from the negative plate. Sticks. So it becomes possible to collect small dust. Of course, it will be apparent that various methods and filters can be used in addition to the above-described filtering method.

The photovoltaic management unit 140 includes a photovoltaic panel that condenses light to convert solar energy into electrical energy on an upper surface of at least one streetlight, and uses the photoelectric effect to convert the solar energy collected from the photovoltaic panel into electrical energy. And store the converted electrical energy. In this case, the solar power generation method may include a system-connected type that is complementarily used in connection with a power system and a stand-alone type that is used alone. In the case of the stand-alone type, an energy storage device such as a battery is required for normal use even at times when power generation is not possible, such as at night or in rainy weather, and in the case of the system-connected type, electricity can be exchanged by linking the production power with the commercial power system. To this end, a solar cell, a photodiode, a lithium-ion battery and a charging/discharging circuit, an LED and an LED driver may be included, but are not limited thereto.

In the case of a grid-connected configuration, the solar power management unit 140 uses the power generation module to charge the power generated during the day in the storage battery, and then lights the street light using the power charged in the storage battery in the evening when it is necessary to light the street light. It can be applied mainly to a location where installation is easy in the city. To this end, the configuration may include a charge controller, an AC/DC converter, a switching control, etc., the charge controller converts the power generated from the solar cell into a voltage and current suitable for charging the storage battery, and the AC/DC converter It converts the power to DC power used in LED streetlights, and the switching controller monitors the voltage of the battery to prevent overcharging and overdischarging of the battery, and the battery power source converts the source from the battery to AC voltage. The LED lamp and the SMPS for driving and the charge controller are configured as separate devices, and the AC system can be used as a backup.

When configured as a standalone type, if the sun does not shine throughout the day, that is, when the number of relief days increases, the power to be charged in the storage battery is insufficient and the streetlight may not be properly lit in the evening. Accordingly, the photovoltaic management unit 140 may be configured in a tracking method to which a photodiode is applied. The photodiode has a fast response speed and traces the sunlight, making it possible to track sunlight without applying a complex program method. The photodiode method is driven by the principle of sending an analog output by comparing and analyzing the amount of sunlight irradiated on a unit area of the solar tracking sensor. Through this type of tracking, the incidence angle of sunlight and the horizontal plane of the module are vertical in real time, so that the highest power generation point is maintained from sunrise to sunset. When the tracker is installed and operated at any point without additional correction work, the tracking is smooth and the convenience of use during installation can be guaranteed. Even if a problem occurs during sensor operation, it is possible to restore the system in a short time through a simple replacement operation to maintain normal operation. The solar charge controller may be a controller that charges the generated energy to a rechargeable battery and outputs energy when a lamp is lit. The circuit may have various configurations, but may include an OP-AMP, a regulator for constant voltage, and other protection devices. The input diode is a protection device for preventing reverse voltage, and a constant voltage regulator may be provided to supply a constant voltage to the OP-AMP. The OP-AMP may be configured to supply a constant current even when the input voltage fluctuates when compared to the reference voltage. Of course, it will be apparent that it is not limited to the above-described configuration or device.

Furthermore, the solar management unit 140 may operate in connection with the air cleaning unit 130. For example, when the remaining power exists after charging the battery with solar power generation, and fine dust is detected by the fine dust sensor (AND condition), the solar management unit 140 turns the power to the air cleaning unit 130 You can also supply. In this case, the battery may be reduced in size compared to the existing battery by boosting the voltage using a bidirectional DC/DC converter to minimize the occupied space. For example, the solar panel may absorb solar energy and output a voltage of 12V, and the solar management unit 140 may boost the 12V to 24V to charge the battery. Here, when solar power generation is impossible or an error occurs and the battery is discharged, the battery may be charged using a commercial power source. In addition, the motor drive and DSP board included in the air cleaning unit 130 may be driven through the power of the charged battery. Here, the air cleaning unit 130 drives a motor control algorithm to correspond to the amount of fine dust or the level of pollution, and adjusts the speed of the motor drive, and adjusts the intake amount and discharge amount of air. For example, the motor drive may use a three-phase inverter for driving a BLDC motor, and may be a drive capable of driving a motor through speed control using a speed command using PWM as an input value. Of course, it will be apparent that the method is not limited to the above-described method and can be variously changed according to various embodiments.

Meanwhile, the at least one street light device 100 may transmit and receive data by forming a channel with each other through Long Range (LoRa) communication among low power wide area communication. In addition, LoRaWAN (Long Range Wide-Area Network (LoRaWAN) can be used for remote communication, and voltage sensor and current sensor, temperature sensor and humidity sensor, illuminance sensor, GPS module, etc. Since the environment can be monitored and long-distance low-power communication is used, the problem of existing street lights can be solved. At this time, the ISM (Industry-Science Medical) band, which is an unlicensed frequency band, can be used, and the initial installation and maintenance costs are relatively high. In addition to the advantage of being inexpensive, the reliability of received data is high by automatically retransmitting information even if a transmission failure occurs because another channel without interference is automatically found even if there is interference in a specific channel.

Existing wireless communication technologies such as Wi-Fi or ZigBee support long-distance communication with a high transmission speed but short communication distance within 100m, but the minimum communication distance of LoRaWAN is about 500m. In order to have high security, AES base64 (Advanced Encryption Standard base64) method can be used, the communication distance is up to 16km, and the communication frequency band is an ISM band, 915MHz, which is an unlicensed band, so there is no cost for using the frequency. . In particular, even if there is interference in a specific frequency, LoRaWAN communication automatically finds another frequency without interference, and by using this, even if transmission fails, information is automatically retransmitted to provide stable and accurate information.

Through this communication, when the at least one street light device 100 initializes and starts the operation, the data collected through the at least one sensor is transmitted to the router through LoRaWAN communication. Based on this data, the street lamp operation You can observe the condition and the condition of the surrounding environment. When a change in the streetlight operation status is confirmed, the streetlight control service providing server 300 notifies the identification number and checks the identification number at the same time, and if an abnormality occurs, it is confirmed that the original state can be restored by resetting the streetlight. Thus, the operation status of the streetlight and the surrounding environment data are collected, but if a problem occurs continuously, it is registered as a problem streetlight, and based on this list, the problem can be solved by dispatching personnel related to failure and repair. In addition, the at least one street light device 100 and the street light control service providing server 300 synchronized through a channel connected by LoRaWAN automatically control the operation of the appropriate street light based on the data collected for the surrounding environment of the street light to blink. Or turn it on. The data frame of data transmitted and received through the LoRaWAN channel may include an initial value such as a frequency band, a network name, and a password. In order to save the settings as default, and to eliminate the hassle of setting initial values every time communication is performed, it can be coded to automatically fill in the specified values.

<Street light control service providing server>

The granting unit 310 may assign and store an identifier corresponding to at least one location where at least one street light is installed. At this time, the at least one street light device 100 is assigned an identifier corresponding to at least one position, and the illumination and on/off of at least one street light are controlled by artificial intelligence control, and the detection detected by at least one sensor Data can be mapped to an identifier and displayed.

The input unit 320 may receive sensing data received from at least one street light device 100 and input it as query data.

When the query data is input, the controller 330 may generate output data using a previously learned artificial intelligence algorithm. At this time, the pre-learned artificial intelligence algorithm is an algorithm that generates result data for query data according to the learning result of big data, and the artificial intelligence unit 360 includes sunrise time, sunset time, sunlight intensity, sunlight illuminance, In response to nature data including air pollution levels including fog and fine dust, road condition data including road congestion, and nature data and road condition data, the illumination and power control of at least one street light device 100 Raw data including historical log data performed are stored in parallel and distributed, and unstructured data, structured data, and semi-structured data included in the stored raw data are refined. And, it is possible to generate the aforementioned artificial intelligence algorithm by performing pre-processing including classification as meta data, and performing analysis including data mining of the pre-processed data to build and learn big data. . The artificial intelligence unit 360 derives and classifies an identifier by parsing data collected from at least one street light device 100 and data collected from at least one information providing server, and at least one information providing server The image information is extracted from the data collected from the data, the reference data having a preset similarity is extracted from the big data previously established based on the classified identifier and the extracted image information, and the control data is pre-mapped to the extracted reference data and stored. May be extracted and transmitted to at least one street light device 100.

At this time, in data mining, classification (Classification), which predicts a class of new data by learning a training data set with a known class by searching for an intrinsic relationship between preprocessed data, or clustering that group data based on similarity without class information ( Clustering) can be performed. Of course, there may be various other mining methods, and may be mined differently according to the type of big data to be collected and stored or the type of query to be requested later. The big data constructed in this way may be verified through deep learning or machine learning of artificial neural networks. At this time, the artificial neural network can use a CNN (Convolutional neural network) structure, which is a network structure using a convolutional layer, which is suitable for image processing, and can classify images based on features in the image by inputting image data. Because it can. In addition, text mining is a technology that aims to extract and process useful information from non/semi-structured text data based on natural language processing technology. Through text mining technology, meaningful information can be extracted from a vast bundle of texts, linkages with other information can be grasped, and the results can be obtained beyond finding a category of text or simply searching for information. Using this, in the streetlight control service according to an embodiment of the present invention, a large amount of language resources and statistical and regular algorithms may be used to analyze an identifier or natural language input as a query and discover hidden information therein. In addition, cluster analysis can be used to finally discover groups of similar characteristics while combining objects with similar characteristics.

The transmission unit 340 may transmit output data to at least one street light device 100. In this case, various short-range, medium-range, and long-distance communications may be used, which are the same as described above, and thus will not be described as redundant.

The standby management unit 350 collects fine dust data based on the location of at least one street light, and when the collected fine dust data exceeds preset reference data, the at least one street light device 100 installed at the location is used. It can be controlled to operate the air cleaning unit 130.

In addition, the streetlight control service providing server 300 may solve low-frequency vibration (Inter-area oscillation) through artificial intelligence learning. If the low-frequency vibration is not initially suppressed, since streetlights are installed in tens to hundreds of kilometers, it can cause great damage such as wide area power failure. In order to effectively suppress such vibrations, PSS (Power System Stabiizer), FACTS (Flexible AC Transmission System), etc. may be used. Furthermore, in an embodiment of the present invention, it is possible to suppress low-frequency vibration through machine learning and supervised learning.

At this time, machine learning is a field of developing algorithms that allow computers to learn by themselves as a category of artificial intelligence. Machine learning can be largely divided into supervised learning, unsupervised learning, and reinforcement learning. They commonly learn through learning data, but they can be classified according to the purpose of use. Among them, reinforcement learning is mainly used for games and control, and is learned through input and evaluation data (reward). Supervised learning is used for learning in which correct answers are given, and unsupervised learning is used for classification and clustering without correct answers. Unlike these, reinforcement learning learns through rewards, and learns through actions and rewards for specific states.

On the other hand, Q-learning is a learning method in which the agent's policy and the learning policy are separated and continuously explored, and learning is carried out according to the target policy through the Q function independently according to the behavior. The agent selects the behavior in its current state according to the greed policy, and the agent is rewarded from the environment and receives the next state. And when the agent knows the next state, it uses the largest queue function in that state to update the current queue function. Unlike other off-policy reinforcement learning, Q-learning can simplify its composition because the queue function is simple. In order to apply Q-learning to vibration suppression, the measured power value of the transmission line between the power system regions and the amount of change over time can be set as a state value. The learning algorithm may be performed based on a Back Propagation Algorithm (BPA). BPA, also known as backpropagation algorithm, is a method of adjusting the weight of each neuron by using the error between the data to be trained and the output. Here, the weight can be adjusted by applying the delta rule using the error. The delta rule is one of the weight adjustment calculation methods used in the backpropagation algorithm, and it is simple but effective. Supervised learning is learned through the correct answer data set for the input, and the error of the output and correct answer is spread in reverse, and the weight of each neuron is adjusted to learn. Accordingly, in an embodiment of the present invention, two artificial intelligence algorithms learned through supervised learning using Q-learning and deep learning, one of the basic algorithms of reinforcement learning, are used to suppress low-frequency vibrations occurring in the power system. can do. Of course, it is not limited to the above-described method, and various methods can be applied. In addition, it will be appreciated that the above-described algorithms are not only used for suppressing low-frequency vibration, but may be used for various functions of the present invention.

Hereinafter, the operation process according to the configuration of the above-described streetlight control service providing server of FIG. 2 will be described in detail with reference to FIGS. 3 and 4 as examples. However, it will be apparent that the embodiment is only any one of various embodiments of the present invention, and is not limited thereto.

3, (a) the streetlight control service providing server 300 collects big data for learning and learns an artificial intelligence algorithm. And, (b) when data is received from at least one street light device 100, the received data is input to the learned AI algorithm as query data, and the resultant data is output as shown in Fig. 4A. Is transmitted to at least one street light device 100, and (b) is driven to perform various functions as well as illumination control adaptively to various environments or situations.

For details that are not explained about the method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation of FIGS. 2 to 4 above, see FIG. 1 for ultra power saving using artificial intelligence-based fine dust filtering and energy generation. The description of the method for providing a type street light control service is omitted since it is the same as the description or can be easily inferred from the description.

5 is a flowchart illustrating a method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention. Referring to FIG. 5, the streetlight control service providing server assigns and stores an identifier corresponding to at least one location where at least one streetlight is installed (S5100). Then, the streetlight control service providing server receives sensing data received from at least one streetlight device and inputs it as query data (S5200), and when the query data is input, the output data is received by a previously learned artificial intelligence algorithm. It is created (S5300).

Finally, the street light control service providing server transmits the output data to at least one street light device (S5400).

The order between the above-described steps S5100 to S5400 is only an example and is not limited thereto. That is, the order of the above-described steps (S5100 to S5400) may be mutually changed, and some of the steps may be executed or deleted at the same time.

The matters that are not described about the method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy power generation of FIG. 5 are described above, as shown in FIGS. 1 to 4, and ultra power saving using artificial intelligence-based fine dust filtering and energy generation. The description of the method for providing a type street light control service is omitted since it is the same as the description or can be easily inferred from the description.

The method of providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment described with reference to FIG. 5 includes a computer-executable instruction such as an application or program module executed by a computer. It can also be implemented in the form of a recording medium. Computer-readable media can be any available media that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. Further, the computer-readable medium may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The method for providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention described above includes an application basically installed in a terminal (this is included in a platform or an operating system basically installed in the terminal). It can be executed by an application (that is, a program) installed directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. have. In this sense, the method for providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation according to an embodiment of the present invention described above is an application (i.e., a program) installed in a terminal or directly installed by a user. And recorded on a computer-readable recording medium such as a terminal.

The above description of the present invention is for illustrative purposes only, and those of ordinary skill in the art to which the present invention pertains will be able to understand that other specific forms can be easily modified without changing the technical spirit or essential features of the present invention will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

Claims (10)

At least one identifier corresponding to at least one location is assigned, illumination and on/off of at least one street light is controlled by artificial intelligence control, and at least one that maps and outputs detection data sensed by at least one sensor with the identifier. Street light device; And
An assigning unit that assigns and stores an identifier corresponding to at least one location where the at least one street light is installed, an input unit that receives sensing data received from the at least one street light device and inputs it as query data, the query data A street light control service providing server including an artificial intelligence control unit that generates output data by a pre-learned artificial intelligence algorithm when is input, and a transmission unit that transmits the output data to the at least one street light device;
Ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, including.
The method of claim 1,
The at least one street light device,
A power line supplying power to the at least one street light device is installed in a distribution panel to identify a state, and when a short circuit or short circuit occurs, a short circuit or short circuit event is generated and transmitted to the street light control service providing server, and the power line line of the power line is real-time A wire condition monitoring unit that transmits a monitoring event, which is a result of monitoring, to the street light control service providing server;
An ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, comprising: a.
The method of claim 2,
The wire condition monitoring unit,
A short circuit or short circuit event is determined by reading low-frequency data of a low voltage level, which is a preset voltage input between the power line line (R/T phase) and FG (Field Gound), and the power line is converted from a non-power state to a power-on state. A system for providing an ultra-power-saving street light control service using artificial intelligence-based fine dust filtering and energy generation, characterized in that the switch of the power line line is turned on when a switching event is detected and the power line is switched from the power-on state to the non-power state.
The method of claim 1,
The at least one street light device,
When the current of the power supplied to the at least one street light device is less than a preset overcurrent reference value, a relay driving control signal for lighting the at least one street light is output, and when the at least one street light is turned on, a preset time has passed. A power reduction unit configured to control the power to be supplied at a level in which the voltage is gradually lowered every time;
An ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, comprising: a.
The method of claim 1,
The at least one street light device,
At least one hole is formed in the housing of the at least one street light, and filters fine dust contained in the inhaled air by inhaling external air inside the housing, and filtering the filtered air into at least one hole of the housing An air cleaning unit that discharges through;
Ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, characterized in that it further comprises.
The method of claim 5,
The streetlight control service providing server,
Collect fine dust data based on the location of the at least one street light, and when the collected fine dust data exceeds preset reference data, operate the air cleaning unit with at least one street light device installed at the location. A standby management unit to control;
Ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, characterized in that it further comprises.
The method of claim 1,
The at least one street light device,
A solar panel for condensing light to convert solar energy into electrical energy is included on the upper surface of the at least one street light, and the solar energy collected by the solar panel is converted into electric energy using a photoelectric effect, and the A solar light management unit for storing the converted electric energy;
An ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, comprising: a.
The method of claim 1,
The at least one street light device is an ultra power saving using artificial intelligence-based fine dust filtering and energy generation, characterized in that it transmits and receives data by forming a channel with each other through LoRa (Long Range) communication among long-distance low power communication (Low Power Wide Area). Type street light control service provision system.
The method of claim 1,
The pre-learned artificial intelligence algorithm is an algorithm that generates result data for query data according to the learning result of big data,
The streetlight control service providing server,
In response to the nature data including sunrise time, sunset time, sunlight intensity, sunlight illuminance, fog, and air pollution degree including fine dust, road condition data including road congestion, and the natural data and road condition data Row data including history log data for which illumination and power control of the at least one street light device is performed are stored in parallel and distributed, and unstructured data and structured data included in the stored row data ) Constructing and learning big data by purifying data and semi-structured data, performing pre-processing including classification as metadata, and analyzing the pre-processed data including data mining Artificial intelligence unit to proceed;
Ultra-power saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, characterized in that it further comprises.
The method of claim 9,
The artificial intelligence unit,
Parsing data collected from the at least one street light device and data collected from at least one information providing server to derive and classify an identifier, and extract image information from the data collected from the at least one information providing server And, based on the classified identifier and the extracted image information, extracts reference data having a preset similarity from pre-established big data, extracts control data pre-mapped to the extracted reference data, and stores the at least one An ultra-power-saving street light control service providing system using artificial intelligence-based fine dust filtering and energy generation, which is transmitted to a street light device.

Images