KR101584263B1 - System for controlling cooling and heating real time per subway cabin - Google Patents

Abstract

According to the present invention, a real time cooling control system by subway cabin includes: a big data collecting module placed in a central control server, and collecting and storing the big data, accumulated from the management of subway, by subway station; a big data analyzing module placed in the central control server, classifying and digitizing the big data by parameter, and applying a weighted value to each parameter to generate passenger variation numerical value information, including the number of variable passengers by section, time, and subway station; an information providing module placed in the central control server, and transmitting the passenger variation numerical value information to a subway server; and a cooling and heating control module placed in the subway server, and identifying the number of passengers by cabin through the passenger variation numerical value information to differentially control the configuration of cooling and heating temperature. According to the present invention, the real time cooling control system by subway cabin is capable of differentially controlling cooling and heating temperature by cabin through the big data, accumulated from the management of the subway, in order to pursue the efficient management of the big data.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system and method for real-

The present invention relates to a real-time cooling and heating control system for each room of a subway, and more particularly to a system for controlling the real-time cooling and heating control of each subway car, in which subway cars are operated until now without accumulation of additional devices such as temperature sensors or occupant- The present invention relates to a system for efficiently controlling the cooling and heating of each room in real time based on Big Data and current subway facilities to prevent over-cooling heating and efficient power saving.

According to the statistical data, electric power costs in the metropolitan area reached 100 billion won, and the amount of electricity used for heating and cooling was 20%.

In particular, the cooling cost of heating and cooling in the summer occupies a considerable portion of the total cost of electricity used in the summer. As a result, the subway environment deteriorates or the subway operation deficit is worsened due to the subcooling room in summer or the inability to control the cooling efficiency. Increasing problems.

It is no exaggeration to say that Korea's electricity supply and demand problem has reached national crisis and emergency situation. In response to the sudden increase in power consumption due to the renewal of the maximum amount of electricity every summer, the energy saving participation movement of the whole nation is proceeding in the blackout crisis. However, in order to guarantee the comfort of public transportation, The subway is cooling properly.

However, especially in the summer, power wasted by subcooling by each room (passenger coach), causing problems of national loss and deterioration of the national health.

In order to prevent such subcooling heating problem, the subway corporation has been designing a "weak cooling compartment" in a specific passenger compartment of the subway for the past 10 years, but has not been able to offer any other solution that does not have high effectiveness. to be.

In addition, the complaints of passengers boarding each room are not shut down, but there are worries that the unnecessary work of the engineers will be increased and adversely affecting the safety of the subway operation, as frequent complaints of cold or hot are frequently raised.

As an example of subway cooling, we operate a 23-degree air-conditioner to set a temperature of 26 degrees for 160 people (100% of the congestion rate) for each room. The rush hour (from 7 am to 9 am) The congestion rate increases up to 200%, in this case, the cooling operation becomes full. However, after 9:00 am, if the passenger goes to the non-congestion time and performs the full-scale air-conditioning, a complaint about cold passenger is often generated. If the cooling operation was stopped in response to this, the complaints complained that it was hot, and many cases were brought into a frustrating situation.

Therefore, the real-time temperature control technology of the subway has been researched and published as a prior art in order to provide a comfortable environment to the people for national competitiveness as a nation-based transportation facility.

Korean Patent No. 101117496 provides a function to perform differential cooling and heating control in a room by sensing the calorific value and the number of passengers in the subway through a sensor for measuring the concentration of carbon dioxide in the subway cabin.

In this case, it is advantageous to drive and control air-conditioning differently and effectively according to the number of passengers in the room, but it is troublesome to install separate hardware equipments such as a carbon dioxide measuring sensor for each room, There is a problem.

At the current technology level, the use of hardware and software to receive various information through each station or central control center in the subway control system becomes common, so that the control functions such as speed control for proper spacing with the preceding train are automatically And a calculation and control unit for automatically controlling the speed according to the distance from the preceding train or controlling the temperature setting of each subway room is also provided.

According to the study of the factors affecting the heating and cooling service quality of the subway cabins (2013) and the research contents of the study, When it was set to 'automatic mode' of heating and cooling, it was found that the complaints were the most, and it was understood that not only the automatic setting of the temperature was necessary but the detailed and differential heating and cooling control technology was needed.

In addition, based on the analysis of the facilities and movement routes in Seoul Station and Sadang Station, the passenger movement status of the subway station is analyzed by referring to the "Transit Behavior Analysis in Transit History in Seoul City" And collecting them into a database in accordance with the detailed classification, thereby constructing comprehensive big data.

In other words, various information about the status of passengers' use of subway stations has been accumulating for many years in the Seoul metropolitan area or other areas other than the new subway, and it is necessary to analyze various parameters (travel route, travel time, ). In other words, such data can be called big data that grasps passengers' various situations using subway, passenger movement in subway history, and so on.

Therefore, the communication and control system already installed in the subway and the commercial equipment in the subway, without any trouble of maintenance and installation of separate equipment for each carriage and the subway are already accumulated while operating the subway as described above There is a need to develop a new and advanced subway cabin air conditioner control system capable of controlling the cooling and heating temperature of subway cabinets in real time by classifying and selecting big data related to the use of subway passengers in pursuit of valuable information value Is a reality.

SUMMARY OF THE INVENTION It is a general object of the present invention to provide a system for differentially controlling the temperature setting of each subway in accordance with a time zone by using big data accumulated during subway operation .

Another object of the present invention is to subdivide big data according to specific parameters in order to separately predict the number of passengers descending from the subway and the number of passengers riding on the subway.

Another object of the present invention is to analyze a CCTV image installed in a subway station in order to reinforce the passenger variation number prediction through the Big Data, and to perform an analysis using an adder boost algorithm to more accurately and quickly predict the number of passenger changes through the CCTV image .

In order to achieve the above object, a real-time cooling and heating control system for each subway room according to the present invention comprises a big data collection module provided in a central control server and collecting and storing big data accumulated for each subway station while operating a subway; A large data analysis unit that is provided in the central control server and classifies and digitizes the big data according to parameters and assigns weights to the respective parameters to generate passenger variation numerical information including the number of passengers varying by each subway station, module; An information providing module provided in the central control server for transmitting the passenger variation value information to the subway server; And a cooling / heating control module provided in the subway server for controlling the number of passengers per room through the passenger variation numerical information and differentially controlling the cooling / heating temperature setting for each guest room.

The big data analysis module extracts some of the big data according to the extracted passenger parameter library for predicting the passengers descending in the subway according to each time zone and the boarding section, Extracting some of the big data according to an incoming passenger parameter library for predicting and assigning different weights according to the extracted passenger parameter library and the incoming passenger parameter library to predict the number of the extracted passengers and the number of the incoming passengers, And a function of generating passenger variation numerical information.

In addition, the system includes a CCTV analysis module for analyzing the shape of the passenger and the direction of movement of the CCTV images installed in the boarding section and determining the number of passengers to ride and the number of passengers to ride, and generating CCTV image information as the difference value And the information providing module transmits the information corrected in the CCTV image information to the subway server in the passenger number information.

According to the real-time cooling / heating control system for each subway room according to the present invention,

1) Through the big data accumulated while operating the subway, the cooling and heating temperature control of each subway room is performed differently, so that the big data can be efficiently operated,

2) It is possible to efficiently classify the big data, which contains a lot of information, so as to distinguish between the passengers descending from the subway and the passengers,

3) Not only can you save money by not installing additional equipment in the subway.

4) CCTVs installed in the subway area are analyzed to reinforce the passenger variation forecast information through the big data, but it is possible to more quickly and accurately grasp the number of passenger changes in the CCTV image through the adder boost algorithm.

1 is a conceptual diagram showing a server interlocking relationship according to the present invention;
2 is a block diagram showing a configuration for a system of the present invention;
3 is a diagram illustrating an example of a subway history map for grasping fixed data according to the present invention.
FIG. 4 is a conceptual diagram showing an example of determining parameters and priority orders in the big data of the present invention; FIG.
FIG. 5 is a conceptual diagram illustrating a method of extracting feature information performed by an adder boost algorithm according to the present invention. FIG.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. The accompanying drawings are not drawn to scale and wherein like reference numerals in the various drawings refer to like elements.

1 is a conceptual diagram showing a server interlocking relationship according to the present invention.

The system according to the present invention is based on learning or preliminarily measured big data 40 on the basis of the use situation of passengers for each history of the subway, but additionally real time utilization information is reflected in such big data 40, (The difference between the passengers' real-time change of the passengers by the time of day, the difference between passengers and passengers at specific subway stations), providing this information to the subway, and then differentiating the air- As shown in FIG.

As shown in FIG. 1, the system of the present invention comprises a central control server 10 and a subway server 20, and additionally includes a local server 30 so that data transmission / As a result, the main function is to carry out customized cooling and heating control in a train (subway).

The central control server 10 is mainly responsible for analyzing and managing the accumulated big data 40 while operating the subway to provide the subway server 20 with information according to passenger variation, Refers to a database that compiles various statistical information accumulated for each subway history according to the time zone in which the subway is used. Such big data 40 will be described later in more detail.

The subway server 20, which is provided in the engine room of the subway, receives the passenger variation related information analyzed by the central control server 10 and additionally receives real time information of the local server 30, that is, CCTV analysis information, And performs a differential cooling control for each room through the control unit.

The local server 30, which is additionally provided in the present invention, is a server provided in each subway station (history), and generates real-time passenger variation information of each history, that is, CCTV analysis information and transmits it to the subway server 20 directly To the central control server (10).

That is, the system of the present invention is based on the big data accumulated while operating the subway, but additionally provides the subway server operating on the basis of the real-time utilization information collected from each subway station, So that the subway server automatically controls the air conditioning of each passenger car differentially.

2 is a block diagram showing the configuration of the system of the present invention.

Hereinafter, the detailed configuration shown in FIG. 2 will be described in more detail with reference to the server in FIG.

The central control server 10 includes a big data collection module 110, a big data analysis module 120, a passenger variation estimation module 130 and an information provision module 140. The subway server 20 includes a cooling / (150), and in addition, the local server (30) may include and describe a CCTV analysis module (160).

The big data collection module 110 of the present invention collects the accumulated big data 40 for each subway station while driving the subway (or receives a transmission from a local server provided at each subway station) Sorting, grouping, and grouping according to each subway station, time zone, and data format.

In the present invention, the big data 40 refers to a database which is accumulated while operating a subway by each subway station. Here, as a criterion for distinguishing the big data 40 by data type, .

Specifically, the data fixed at any time is referred to as 'fixed data' 41 in the present invention. For example, based on the subway history map information, the distance from the ticket gate to the boarding position distance data, the position or numbering of the elevator / escalator at the boarding point (the number of consecutive numbers such as 1, 2, 3, 4.5, 6, 7, 8, numbering) of the passengers, such as distance and numbering, related to the subway facilities, and the numerical value of the route and location, or the distribution of the passengers' mobility and location by facility distribution (convenience, store, restroom, resting space, etc.) It means the data providing the keynote.

3 is an exemplary view illustrating a subway history map for grasping fixed data according to the present invention.

As can be seen from FIG. 3, each design structure or facility is provided for each subway history. In the present invention, the drawings related to the facilities of the subway history as shown in FIG. 3 are referred to as a subway history map.

That is, the fixed data 41 is collected and recorded in advance according to each subway history, and various information (convenience location, shortest distance from each exit to the boarding space, escalator / elevator location) The information that can be numerically processed, such as the general usage distance according to the number of passengers in the passenger space), thereby providing a basis for roughly grasping the passenger distribution in the passenger space.

For example, when the boarding area is divided into a certain area by numbering the boarding sections such as 1-1, 1-2, 1-3, 1-4, 2-1, .... 10-4, Or stairs, transfer points) are located near the 1-4 and 5-2 compartments, and the elevator position is near the 9-1 compartments. The passenger compartment through which the passengers are driven is directly adjacent to the escalator / staircase / elevator / Can be predicted without difficulty. Further, the average passenger travel time can be determined based on the walking speed of a general adult male passenger through the distance from each exit of the subway history to the ticket gate, and the distance from the ticket gate to the escalator.

The fixed data 41 is used as a factor for deriving the real-time utilization information of passengers. However, rather than being a direct element for accurately measuring the amount of change of passengers that are moved by time, It is used as complementary and supplementary information which enables to grasp basically the distribution of the space on board.

In addition, the fixed data 41 provides a basis for predicting the inflow of the passengers and the distribution in the specific boarding space, as well as the inflow state of the passengers (the number of passengers descending in the subway). For example, The same subway history can provide a basic basis for roughly grasping the number of outflow passengers.

The data or parameters varying by time in the big data 40 of the present invention are referred to as 'changed data' 42 in the present invention. For example, data or parameters unique to the subway stations, (Temperature, humidity, etc.) data during N years (for example, 1 to 5 years), information on subway operation time, information on the subway history (For example, information on the period when the Cherry Blossom Festival is held for the subway line 9 of the National Assembly building), surrounding facilities information (such as the number of people around the subway station or the commercial area, company distribution, etc.) Data relating to passengers, temperature, and subway operation information.

Unlike the fixed data, the fluctuation data 42 collects and updates the trends that vary from each subway history by a certain period of time for each data. For example, the fluctuation data 42 records information previously learned in each subway history .

In other words, the big data 40 may be stored in the big data collection module 110 using various data collection means such as actual measurement, statistical analysis, programmed or specific data collection program / solution by a specific solution, Recording / recording / sorting processing.

Here, the big data collection program used in the present invention can use functions similar to the functions of the program for collecting data from SNS such as Twitter and Facebook. Such big data collection (including classification and storage) The detailed description thereof will be omitted.

The big data 40 is a statistical information accumulated for a predetermined period of time, and plays a role in roughly predicting the number of passengers traveling on and off the subway in a particular boarding zone for each subway station history and time zone .

In summary, the big data collection module 110 performs a function of storing information gathered for each subway history through a variety of data collection means, which have been measured in advance or as big data, in a separate data server.

The big data analysis module 120 of the present invention provides a main basis for predicting fluctuation information falling on the subway among the moving conditions of the passengers using the subway and the big data 40 stored in the big data collection module 110, The classification / analysis function is classified according to a specific criterion, and the classification / analysis function is specified by the following detailed configuration.

FIG. 4 is a conceptual diagram showing an example of determining parameters and priority orders in the big data of the present invention.

Specifically, the big data analysis module 120 includes a parameter selecting unit 121, a classifying unit 122, and a weight assigning unit 123.

The parameter selection unit 121 selects various parameters, i.e., parameters, for grasping the change in the number of passengers on and off according to a specific time zone and a specific boarding zone for each subway station.

 The parameter generally refers to an analysis factor or classification criteria such as a specific position and facility information of a subway station, a distance, a time, a passenger change in a ticket gate, etc. In the present invention, for example, Location, ground / underground segment, status of passenger according to time / segment, status of escalator / elevator, and change of passenger status at the ticket gate. These parameters serve as a reference for classifying the big data 40. [

The parameter selection unit 121 presents a criterion for classifying the big data 40. In other words, the parameter selection unit 121 can present a classification criterion for efficiently analyzing the collected big data 40, and the above-described examples can be referred to as parameters.

The classifying unit 122 classifies the big data 40 into subgroups or subgroups according to the parameters selected by the parameter selecting unit 121.

That is, the big data 40 which is not sorted by a specific criterion is sorted according to the parameters and stored again, which is referred to as a 'parameter library' in the present invention. That is, the parameter library means a database in which big data is classified and stored according to a predetermined parameter according to a preset reference (a reference selected by lookup table information accumulated by learning, etc.).

Referring to FIG. 4, an example of a parameter library corresponding to a plurality of parameters selected by the above-described parameter selection section can be found.

The parameters illustrated in Fig. 4 are selected from among the fixed data 41 and the fluctuation data 42 described above for predicting the passengers and riding passengers falling on the subway. The parameters in Fig. 4 are one example, But may be changed or updated.

In particular, the classifying unit 122 may classify the parameters into two broad libraries, that is, an incoming passenger parameter library and an extracted passenger parameter library, in order to predict a passenger and a passenger who descend based on a boarding section of a specific subway station.

The incoming passenger parameter library means parameters selected / classified for predicting passengers riding in the subway in a specific boarding section, for example, the distance between the transfer port and the boarding section, the distance between the escalator / elevator and boarding section, And at least one parameter among the parameters such as the number of persons who have entered the room and the like.

Also, the retrieved passenger parameter library refers to the parameters selected / classified to predict the passengers descending from the subway based on the boarding section of a specific subway station. The distance information of the transit section and the boarding section, A weight based on a standard, a distance between a transfer port and each boarding section, a distance between an escalator / elevator and each boarding section, and information on the number of passengers exiting the ticket gate, and the like.

The weight assigning unit 123 performs a function of assigning a weight to each of the parameters and provides a function for determining a relative priority for a specific parameter in a multiple regression analysis equation to be described later. It can also be set up according to preset criteria based on statistical data or it can be updated instead of fixed value. In FIG. 4, a simple example of such a weight value is shown.

The passenger variation prediction module 130 of the present invention performs a function of predicting a difference between the number of passengers on the subway and the number of passengers on the subway, that is, the passenger variation numerical information, for each time slot and the boarding segment in a specific subway station.

In the present invention, the 'passenger variation numerical information' is information for predicting the number of passengers (passengers riding in the subway) and passengers (passengers descending from the subway) flowing into the subway based on a specific boarding section, Means information on the number of passengers expected per section of each boarding area in history.

The passenger variation prediction module 130 may follow a method of analyzing each parameter illustrated in FIG. 4 by using a statistical calculation formula by multiple regression analysis.

This multiple regression analysis equation is illustrated in the following equation.

y1 = a1x1 + a2x2 + a3x3 + ,,, + a10x10

(Where a1 to a10 are weights,

x1 to x10 are values obtained by numerically processing the information extracted by the parameter reference in the fixed data and the fluctuation data forming the big data, that is, the information obtained by numerically processing the passenger analysis parameter,

y1 is the number of passengers who boarded / boarded on a certain boarding segment. y can be divided by y1 ~ y10 and can be calculated for each boarding compartment, and it is possible to divide the passengers with the y and y values into Y and Y values, as well as 1Y and 2Y according to the time zone)

That is, the passenger variation predicting module 130 predicts the approximate numerical values of the passengers and the passengers on the subway by time zone in a specific subway station according to the multiple regression analysis formula, Which is a value for the difference of the passenger number.

As mentioned above, it is possible to generate the passenger variation numerical information by time zone and boarding zone, so that the passenger variation numerical information is generated by a plurality of pieces of information.

The information providing module 140 of the present invention performs the function of providing the passenger variation numerical value information generated for each boarding section to the subway server 20 differentially according to the corresponding time zone.

In addition, the cooling / heating control module 150 of the present invention estimates the passengers varying in each subway through the passenger variation numerical information transmitted to the subway server 20, sets the temperature differentially for each room, .

Through the above-described configuration and detailed functions, the system of the present invention analyzes the accumulated big data while operating the subway, predicts the change of the passenger according to the subway station, time zone and boarding zone, Thereby providing a characteristic capable of performing cooling and heating temperature control.

FIG. 5 is a conceptual diagram illustrating a method of extracting feature information performed by the adder boost algorithm according to the present invention.

According to the above-mentioned function, it is possible to sufficiently predict the passenger variation state at the specific time zone and the boarding section by the big data 40 including the fixed data 41 and the variation data 42, The information on the number of passengers can be reflected in real time because it includes real-time variation related information such as the passenger distribution information of the passenger in the local server 30. However, in order to accurately reflect the passenger variation state without any error, And a CCTV analysis module 160 are additionally provided.

The CCTV analysis module 160 of the present invention performs a function of correcting the passenger variation numerical information by analyzing the CCTV image capturing the boarding section of each subway train in real time and in particular, It is an object of the present invention to provide a function of detecting an image for a specific area more quickly and accurately than detecting an image for a specific area in an existing image /

The CCTV analysis module 160 analyzes the shape of the passenger, specifically, the head shape and the moving direction of the CCTV image, and calculates the number of passengers and the number of passengers descending roughly, and generates CCTV image information .

However, the area specifying unit 161, the adder boost extracting unit 162, the comparison determining unit 163, and the analyzing unit 164 are used to more accurately and quickly identify the number of passengers through the CCTV image.

The area specifying unit 161 identifies an area of the passenger image (e.g., the head size and hair color of the passenger) in the image taken on the boarding section in the CCTV, identifies the passenger image and other backgrounds, As shown in FIG.

The characteristic of the passenger image is specified by the area specifying unit 161 based on the fact that the image information about the passenger is analyzed on a pixel basis and the shading information is grasped by comparing with the surrounding area, The front and side contours of the passenger's head, the background portion of the rest except for the passenger's head, the outline shape and the detailed shape of the passenger's head, the fluidity and the moving direction of the passenger's head, The shading information about the pixel is grasped and stored in a numerical value.

Since the detection method based on numerical calculation or learning theory according to the image area specification is already known, and the area specifying unit 161 according to the present invention follows the known moving picture area detecting method, a detailed description will be omitted , The area specifying unit 161 according to the present invention mainly performs a role of specifying a main part in which unnecessary backgrounds around the passenger are removed, and when a background shape of the passenger whose background is removed is excluded, for example, In the case where the head part is cut off, a step of connecting the cut part of the head part of the passenger by a predetermined curved line, that is, a curve prepared in advance according to the rough shape of the head part of the passenger who has become awkward after the background part is cut off The contour processing that carries out the contour processing by connecting the cut part of the passenger's head to the outline (outline) It is carried out.

When the region specification for the passenger is completed in the CCTV image through such a process, a process of finding an object suitable for the region information of the passenger image should be carried out.

Boost, which is a statistical theory introduced for passenger image comparison recognition, is an algorithm that produces a selection criterion with high accuracy by combining weak selection criteria when deriving results from data. The AdaBoost learning algorithm is the most well-known Boost algorithm and has the advantage of being simple and efficient.

Referring to FIG. 5, the adder boost learning algorithm by the adder boost extractor 162 groups the extracted feature information in stages, and extracts predetermined features in each step.

Specifically, the features determined to be ineligible in each step are classified as data that does not meet the selection criteria, and while passing through each step, other objects having similar information to the specific passenger image (backgrounds similar to the head color of the passenger ) Are extracted from the extracted feature information. That is, the approximate shape of each object can be characterized by a simple and convenient method by the equation shown in FIG. 5, and utilized as a step for comparing the feature information with each other.

The comparator 163 uses the formula for finding the Euclidean distance to determine that the object presented as the comparison object having the smallest distance is the same as or similar to the specified object, And extracts a predetermined object image of about 2 to 10 persons and finally sets a ranking of the most similar objects.

The formula for Euclidean distance is as follows.

d = Σ (i = 0 to N) (Fi2-Fi'2)

(d: Euclidian distance,

Fi: i-th feature value of the comparative image,

Fi ': the i-th feature value of the specific passenger head region, i.e., the reference passenger head region)

Through this object recognizing step, a comparative object having a shape similar to a specific passenger head shape to be a reference can be derived in a predetermined number according to the degree of similarity.

In this way, for example, when the passenger moves, it is possible to compare and analyze the shape and movement of the general head portion of the passenger by comparing and analyzing the motion of the passenger through the motion of the still image. Before the subway arrives at the boarding section, Since it waits for the subway in the state of low movement, it gives the characteristic that the comparison process with the comparative object can be performed more smoothly.

The analysis unit 164 extracts a portion of the CCTV image area that is closest to the comparison object and compares the number of the CCTV image area with the CCTV image area in the comparison determination process between the head part of the comparison object or the reference passenger and the CCTV image area It plays a role of measuring. In this case, the Euclidean distance is extracted as the priority order closest to the Euclidean distance, and a specific reference (threshold distance setting) is determined. If the distance is longer than the reference distance, the Euclidean distance is determined not to be recognized as a passenger. Extracts and counts the number of passenger heads in the image area, and generates CCTV analysis information including passenger variation values analyzed through CCTV.

The CCTV analysis information serves to correct the passenger variation value information. For example, the CCTV analysis information may be weighted by an average value or a boarding pass section, 150 to the subway server 20.

The CCTV analysis module 160 compares and analyzes a still image from a CCTV image with respect to a comparison object (for example, a reference passenger head shape), thereby determining the number of passengers while reducing errors. At this time, in the case of the passengers getting off and going, it is additionally determined based on the moving direction of the passenger, and the difference between the passenger and the passenger is judged so that the passenger variation status by the CCTV can be grasped.

As described above, the configuration and operation of the real-time cooling control system for each subway car according to the present invention are described in the above description and drawings, but the present invention is not limited to the above description and drawings, And various changes and modifications may be made without departing from the technical spirit of the present invention.

10: central control server 20: subway server
30: Local server 40: Big data
41: fixed data 42: variable data
110: Big data acquisition module 120: Big data analysis module
121: Parameter selection unit 122:
123: Whether to add weight 130: Passenger variation prediction module
140: Information providing module 150: Heating control module
160: CCTV analysis module 161:
162: Adder boost extracting unit 163:
164: Analysis Department

Claims (6)

A real-time cooling control system for each subway room,
A big data collection module provided in the central control server and collecting and storing the big data accumulated in the subway operation by each subway station;
A large data analysis unit that is provided in the central control server and classifies and digitizes the big data according to parameters and assigns weights to the respective parameters to generate passenger variation numerical information including the number of passengers varying by each subway station, module;
An information providing module provided in the central control server for transmitting the passenger variation value information to the subway server;
And a cooling / heating control module provided in the subway server for controlling the number of passengers per room through the passenger variation numerical information to differentially control the cooling / heating temperature setting for each room,
The big data analysis module includes:
Extracts some of the big data according to an extracted passenger parameter library for predicting passengers descending in the subway for each time zone and a boarding section,
Extracts some of the big data according to an incoming passenger parameter library for predicting the passengers riding in the subway for each time zone and the boarding section,
And a function of assigning different weights according to the extracted passenger parameter library and the incoming passenger parameter library to predict the number of passengers to be taken out and the number of passengers to enter and to generate passenger variation numerical information as a difference therebetween Real - time cooling control system. The method according to claim 1,
The big data includes:
Fixed data having a fixed value irrespective of the time zone,
Wherein the variable data is divided into variable data having a variable value varying according to a time zone. The method according to claim 1,
Wherein the incoming passenger parameter library comprises:
A distance between the escalator / elevator and the boarding section, and a number of passengers' information on the passenger at the ticket gate,
The retrieved passenger parameter library comprises:
Distance based on transit section and boarding section, weight based on information of commercial / office distribution around subway station, distance by transit section and each boarding section, distance by escalator / elevator and each boarding section, number of passengers Wherein the real-time cooling control system comprises at least one parameter among the parameters for the subway room. The method according to claim 1,
The system comprises:
A CCTV analysis module for analyzing the shape of the passenger and the direction of movement of the CCTV images installed in the boarding section to determine the number of passengers to ride and the number of passengers to ride and generate CCTV image information,
The information providing module includes:
And transmits the information corrected in the CCTV image information to the subway server in the passenger variation numerical information.
delete delete

Images