Nothing Special   »   [go: up one dir, main page]

KR20210078311A - Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm - Google Patents

Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm Download PDF

Info

Publication number
KR20210078311A
KR20210078311A KR1020190170182A KR20190170182A KR20210078311A KR 20210078311 A KR20210078311 A KR 20210078311A KR 1020190170182 A KR1020190170182 A KR 1020190170182A KR 20190170182 A KR20190170182 A KR 20190170182A KR 20210078311 A KR20210078311 A KR 20210078311A
Authority
KR
South Korea
Prior art keywords
data
building
machine learning
iot devices
smart
Prior art date
Application number
KR1020190170182A
Other languages
Korean (ko)
Inventor
박세현
고중혁
김승민
박상욱
박상민
최명인
Original Assignee
중앙대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 중앙대학교 산학협력단 filed Critical 중앙대학교 산학협력단
Priority to KR1020190170182A priority Critical patent/KR20210078311A/en
Publication of KR20210078311A publication Critical patent/KR20210078311A/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00Adapting or protecting infrastructure or their operation
    • Y02A30/60Planning or developing urban green infrastructure

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Data Mining & Analysis (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Strategic Management (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The present invention discloses data management between smart building IoT devices based on machine learning algorithms. Various IoT devices or sensors in smart buildings collect energy and other building energy. The collected data is processed through a big data engine. This big data engine uses machine learning algorithms to analyze and learn big data at the same time, predict building data patterns, and understand a current situation. The analyzed data is stored in a smart building data management storage. Data which has been processed by the big data engine is trimmed for convenient visual monitoring and is displayed through an application for administrators.

Description

머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리{Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm}Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm

본 발명은 머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리에 관한 것이다. The present invention relates to data management between smart building IoT devices based on machine learning algorithms.

기존의 스마트 빌딩의 제어를 위한 데이터 이용 시스템은 빌딩 내 에너지 과부하 방지 및 설비 기기의 정상 가동 유무 상태 감시와 중앙 관제실에서의 제어가 중심이었다. 스마트 빌딩을 정상적으로 운영하기 위한 전력 데이터의 모니터링을 통한 과부하 방지 및 각종 이상 사태 대비를 하였다. 또한, 중앙 제어를 위한 관제실에서의 데이터 흐름을 실시간으로 감시를 하게 되어있다. 따라서 현재의 스마트 빌딩 데이터 상태와 IoT 기기 및 센서 데이터의 정상 가동 상태 감시만 가능하다.The data usage system for controlling the existing smart building was centered on preventing energy overload in the building, monitoring the normal operation of equipment and controlling it in the central control room. In order to operate smart buildings normally, overload prevention and preparation for various abnormalities were made by monitoring power data. In addition, the data flow in the control room for central control is monitored in real time. Therefore, it is only possible to monitor the current smart building data status and the normal operation status of IoT devices and sensor data.

스마트 빌딩은 BEMS의 IT 소프트웨어로 빌딩 내 에너지 데이터를 지속적으로 관리하며 BIM으로 빌딩 정보를 관리한다. 데이터의 안정적인 예측과 효율성을 위해 데이터 유형에 맞는 머신러닝 알고리즘을 이용하여 데이터를 분석한다. 이를 통해 스마트 빌딩의 인프라를 최적화 하고자 한다.Smart building continuously manages energy data in buildings with BEMS' IT software and manages building information with BIM. Analyze data using machine learning algorithms suitable for data types for reliable prediction and efficiency of data. Through this, we want to optimize the infrastructure of smart building

상기한 바와 같은 목적을 달성하기 위하여, 본 발명의 일 실시예에 따르면, 머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리 시스템이 제공된다. In order to achieve the above object, according to an embodiment of the present invention, a machine learning algorithm-based smart building IoT device data management system is provided.

이 시스템은 스마트 빌딩 내에서 IoT 디바이스로 수집되는 데이터를 머신러닝 알고리즘을 이용하여 분석해 효율적으로 데이터를 모니터링하고 관리하는 것을 목적으로 제안되었다. 따라서 제안된 시스템은 스마트 빌딩 내의 모든 유형의 데이터를 효율적으로 관리하게 함으로써 스마트 빌딩의 운영을 편의성을 높이고 예측을 통한 최적화된 빌딩 인프라 구조를 성립할 수 있다. 더 나아가, 제안된 시스템이 개발되고 사용된다면 스마트 빌딩 뿐 아니라 스마트 홈, 팩토리, 모빌리티 등 다양한 플랫폼에서 활용이 가능할 것이다.This system was proposed for the purpose of efficiently monitoring and managing data collected by IoT devices within a smart building by analyzing it using a machine learning algorithm. Therefore, the proposed system can efficiently manage all types of data in a smart building, thereby increasing the convenience of smart building operation and establishing an optimized building infrastructure structure through prediction. Furthermore, if the proposed system is developed and used, it will be possible to utilize it not only in smart buildings but also in various platforms such as smart homes, factories, and mobility.

도 1은 본 발명의 머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리 시스템의 전체적인 흐름을 나타낸 구조도이다.
도 2는 본 개발이 제시하는 시스템에 사용된 머신러닝 알고리즘을 사용한 데이터 분석 플랫폼을 나타낸 것이다.
1 is a structural diagram showing the overall flow of the data management system between smart building IoT devices based on the machine learning algorithm of the present invention.
Figure 2 shows a data analysis platform using the machine learning algorithm used in the system presented by this development.

본 발명은 다양한 변경을 가할 수 있고 여러 가지 실시예를 가질 수 있는 바, 특정 실시예들을 도면에 예시하고 상세하게 설명하고자 한다.Since the present invention can have various changes and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail.

그러나, 이는 본 발명을 특정한 실시 형태에 대해 한정하려는 것이 아니며, 본 발명의 사상 및 기술 범위에 포함되는 모든 변경, 균등물 내지 대체물을 포함하는 것으로 이해되어야 한다. However, this is not intended to limit the present invention to specific embodiments, and it should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present invention.

본 발명은 스마트 빌딩 내의 IoT 데이터의 안전과 효율성을 최적화하기 위해서 우리는 머신러닝 데이터 분석 엔진을 이용한다. 본 발명에서는 빌딩 내 각종 IoT 센서 및 기기로부터 수집된 여러 데이터를 머신러닝 알고리즘을 활용하여 분석하고 예측하여 실시간으로 에너지 데이터를 모니터링하고 관리할 수 있는 시스템이다. The present invention uses a machine learning data analysis engine to optimize the safety and efficiency of IoT data in smart buildings. In the present invention, it is a system that can monitor and manage energy data in real time by analyzing and predicting various data collected from various IoT sensors and devices in a building using a machine learning algorithm.

본 발명은 인공지능 기법 중 머신러닝 알고리즘을 기반으로 한 스마트 빌딩 내 IoT 기기 간 데이터 관리 시스템을 제안하고 있다.The present invention proposes a data management system between IoT devices in a smart building based on a machine learning algorithm among artificial intelligence techniques.

BIM(Building Information Modeling)의 정의는 건축프로젝트에서 초기의 디자인 단계부터 공사, 유지·보수, 철거에 이르는 수명주기 안에서 관련된 설계정보를 통합·관리하는 시스템이다. BIM은 이 각 과정을 시뮬레이션으로 보여주기 때문에 설계과정부터 잘못된 부분을 쉽게 수정할 수 있어 공기가 단축되고 비용절감 효과도 크다. 또한 BIM은 손쉽게 구조모델링을 지원하고 엔지니어링팀들의 공동작업을 지원하면서 이를 통해 설계오류를 줄이고 비용절감을 이루기에 다양한 도시계획프로젝트와 건설산업의 생태계변화를 이끌고 있다. BIM을 활용해 기획·설계된 건물들은 빌딩스마트화와 연계되지 않을 수 없다. 스마트빌딩은 건축, 통신, 사무자동화, 빌딩자동화 등 4가지 시스템을 유기적으로 통합하여 첨단서비스 기능을 제공함으로써 경제성, 효율성, 쾌적성, 기능성, 신뢰성, 안전성 등을 추구하는데, 냉·난방, 조명, 전력시스템 등의 자동화와 자동화재감지장치, 보안경비, 정보통신망 등의 기능을 통해 거주 및 작업환경을 개선하기 위한 자동콘트롤시스템을 홈네트워크로 통합한 고기능 첨단건물이다. 이 건물은 ‘Intelligent Building’ 내지 ‘Smart Building’으로 불리고 있다. BIM은 이러한 다양한 기능이 작동되는 건물의 효율적인 설계를 위해 필요하지만, 건축물의 기계·전기·배관 성능을 시뮬레이션할 수 있는 도구 외에도 빌딩의 에너지모델링 툴들과 유기적으로 통합될 수 있다.The definition of BIM (Building Information Modeling) is a system that integrates and manages relevant design information within the life cycle from the initial design stage to construction, maintenance, and demolition in an architectural project. Since BIM shows each of these processes as a simulation, mistakes can be easily corrected from the design process, shortening the period of time and greatly reducing costs. In addition, BIM is leading various urban planning projects and ecosystem changes in the construction industry as it easily supports structural modeling and supports the collaboration of engineering teams, thereby reducing design errors and achieving cost savings. Buildings planned and designed using BIM cannot but be linked with building smartization. Smart Buildings pursue economic efficiency, efficiency, comfort, functionality, reliability, and safety by organically integrating four systems such as architecture, communication, office automation, and building automation to provide cutting-edge service functions. It is a high-performance, high-tech building that integrates an automatic control system to improve living and working environment through functions such as automation of power system, automatic fire detection device, security guard, and information and communication network into home network. This building is called 'Intelligent Building' or 'Smart Building'. BIM is necessary for the efficient design of buildings in which these various functions operate, but in addition to tools that can simulate the mechanical, electrical, and plumbing performance of buildings, it can be organically integrated with building energy modeling tools.

도 1은 본 발명의 머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리 시스템의 전체적인 흐름을 나타낸 구조도이다.1 is a structural diagram showing the overall flow of the data management system between smart building IoT devices based on the machine learning algorithm of the present invention.

스마트 빌딩 내의 각종 IoT 기기 또는 센서(100)들을 통해 에너지 및 기타 빌딩 에너지를 수집한다. 수집된 데이터를 빅데이터 엔진(120)을 통해 처리를 한다. 이 빅데이터 엔진은 머신러닝 알고리즘을 이용하여 빅데이터를 분석함과 동시에 학습을 하고 빌딩 데이터 패턴을 예측하고 현황을 파악하는 등의 처리를 한다. 분석된 데이터는 스마트 빌딩 데이터 관리 스토리지(110)에 저장된다. 빅데이터 엔진으로 처리가 완료된 데이터는 시각적으로 모니터링 하기 편리하게 다듬어지며 이 데이터는 관리자용 어플리케이션(130)을 통해 나타내어진다. 어플리케이션은 데이터에 권한이 있는 사용자 및 관리자가 웨어러블 기기 또는 모바일 기기(140) 등으로 원격 모니터링을 할 수 있으며 각종 데이터 처리 작업을 할 수 있어 효율적으로 스마트 빌딩 내 데이터와 IoT 기기를 관리할 수 있다.Energy and other building energy are collected through various IoT devices or sensors 100 in the smart building. The collected data is processed through the big data engine 120 . This big data engine uses machine learning algorithms to analyze and learn big data at the same time, predict building data patterns, and understand the current situation. The analyzed data is stored in the smart building data management storage 110 . The data processed by the big data engine is trimmed for convenient visual monitoring, and this data is displayed through the manager application 130 . In the application, users and administrators with authority to data can remotely monitor with a wearable device or a mobile device 140 , and various data processing tasks can be performed to efficiently manage data and IoT devices in a smart building.

도 2는 본 개발이 제시하는 시스템에 사용된 머신러닝 알고리즘을 사용한 데이터 분석 플랫폼을 나타낸 것이다.Figure 2 shows a data analysis platform using the machine learning algorithm used in the system presented by this development.

설치된 IoT 기기, 센서 등으로 수집된 빌딩 에너지 및 기타 데이터(200)를 이용한다. 수집된 데이터를 데이터 전처리 과정을 거친다(210). 빌딩 데이터에 적합한 머신러닝 알고리즘을 탐색하기 위한 모델 분석을 실시한다. 또한, 사용자 데이터를 머신러닝 엔진(220)을 통해 데이터의 수집 장소, 용도별로 현황을 파악하고 패턴화하여 앞으로의 빌딩 데이터의 흐름을 예측한다. 이러한 플랫폼을 거쳐 분석 완료된 데이터(240)가 생성된다.Building energy and other data 200 collected by installed IoT devices, sensors, etc. are used. The collected data is subjected to a data preprocessing process ( 210 ). Perform model analysis to discover suitable machine learning algorithms for building data. In addition, the user data through the machine learning engine 220 to determine the current state of each data collection location and use, and to predict the flow of building data in the future by patterning. The analyzed data 240 is generated through these platforms.

상기한 본 발명의 실시예는 예시의 목적을 위해 개시된 것이고, 본 발명에 대한 통상의 지식을 가지는 당업자라면 본 발명의 사상과 범위 안에서 다양한 수정, 변경, 부가가 가능할 것이며, 이러한 수정, 변경 및 부가는 하기의 특허청구범위에 속하는 것으로 보아야 할 것이다.The above-described embodiments of the present invention have been disclosed for the purpose of illustration, and various modifications, changes, and additions will be possible within the spirit and scope of the present invention by those skilled in the art having ordinary knowledge of the present invention, and such modifications, changes and additions should be regarded as belonging to the following claims.

Claims (1)

머신러닝 알고리즘 기반 스마트 빌딩 IoT 기기 간 데이터 관리 시스템.

A data management system between smart building IoT devices based on machine learning algorithms.

KR1020190170182A 2019-12-18 2019-12-18 Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm KR20210078311A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020190170182A KR20210078311A (en) 2019-12-18 2019-12-18 Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020190170182A KR20210078311A (en) 2019-12-18 2019-12-18 Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm

Publications (1)

Publication Number Publication Date
KR20210078311A true KR20210078311A (en) 2021-06-28

Family

ID=76607871

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020190170182A KR20210078311A (en) 2019-12-18 2019-12-18 Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm

Country Status (1)

Country Link
KR (1) KR20210078311A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20240081721A (en) 2022-11-30 2024-06-10 주식회사 에이아이시티 Name service-based processing method and system using communication data of iot collected data

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20240081721A (en) 2022-11-30 2024-06-10 주식회사 에이아이시티 Name service-based processing method and system using communication data of iot collected data

Similar Documents

Publication Publication Date Title
KR101960162B1 (en) Building Integrated Management System and Method Based on Digital SOP and Prediction
CN113110221A (en) Comprehensive intelligent monitoring method and system for pipe gallery system
CN102681518B (en) Cable network running integrated management system and intelligent control platform
KR20170121536A (en) System for monitoring district heating customer facility based on internet of things and improving efficiency
CN104794578A (en) Could computing based smart water affair management system
KR20130049254A (en) The intelligent building integrated automatic control and energy goal management system based on 3-dimensional modeling and the method thereof
CN110633540A (en) Metal mine ventilation three-dimensional visual simulation aided decision control system and method
KR20210155217A (en) System for predicting and preventing disaster for electric power facilities and operation method thereof
CN115393142A (en) Intelligent park management method and management platform
CN112288320A (en) Subway operation risk monitoring and management system
RU2549514C2 (en) System for predicting and evaluating safety of hazardous production facility using integrated safety model
KR102519474B1 (en) System and method for predicting abnormal state of facilities in a building through facilities operation state analysis
KR20210078311A (en) Data Management System between Smart Building IoT Devices based on Machine Learning Algorithm
Lyu et al. Multi-agent modeling of cyber-physical systems for IEC 61499 based distributed automation
CN109801480A (en) A kind of intelligent floor monitoring management system based on BIM
Priyadarshana et al. Multi-agent controlled building management system
CN112948353B (en) Data analysis method, system and storage medium applied to DAstudio
KR20160087280A (en) Method and system for providing integrated managing service based smart water grid
CN115773100B (en) Driller intelligent auxiliary system
KR102512577B1 (en) System and method for predicting abnormal state of facilities in a building through energy consumption analysis
CN104301388A (en) Large running system monitoring and analyzing management system
KR20190048191A (en) 3D Implementation integrated management system and building integrated control
JP2010066896A (en) Remote monitoring system and method
KR20230013771A (en) Energy Management System of Buildings Using BIM Data
KR101876717B1 (en) Recovery resource management method and system for recovering disasters and accidents