Modeliranje željenih klimatizacijskih uvjeta korisnika pomoću IoT uređaja i neuronskih mreža

master's thesis

• Title (english): Modelling of user-defined climate conditions by IoT controller with neural networks
• Author: Nikica Perić
• Mentor: Vinko Lešić (mentor)
• Committee member: Vinko Lešić (predsjednik povjerenstva)
• Committee member: Mato Baotić (član povjerenstva)
• Committee member: Šandor Ileš (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Zgrade su jedan od najvećih potrošača energije u svijetu te ujedeno i prostor za ostvarenje značajnih ušteda energije. Učenje ponašanja korisnika je preduvjet za predviđanje potrošnje i moguću optimizaciju klimatizacije prostorija i cijele zgrade prilagođenu ponašanju korisnika. U sklopu diplomskog rada izrađen je IoT uređaj koji postavlja željenu temperaturu u prostoriji te modelira ponašanja korisnika na razini jedne godine, u različitim dobima dana, vremenskim uvjetima, godišnjim dobima te radnim i neradnim danima. Učenje modela je provedeno na unaprijed dostupnom skupu podataka koji sadrži vanjske i unutarnje vremenske uvjete. Vanjski vremenski uvjeti se sastoje od temperature, vlage te direktne, difuzne i ukupne sunčeve dozračenosti. Unutarnji uvjeti se odnose na jedan od ureda Fakulteta Elektrotehnike i Računarstva, a dostupni su temperatura zraka, način rada kontrolera ventilokonvektora te referentne temperature u prošlosti. Model je naučen korištenjem neuronske mreže s dugom kratkoročnom memorijom (LSTM) koja je u posljednjim godinama najčešće korištena mreža dubokog učenja za predviđanje vremenskih serija. Naučeni model implementiran je kao Python skripta na Raspberry Pi mikroračunalo tako da u stvarnom vremenu daje predviđeno ponašanje korisnika 24 i 36 sati unaprijed.

Abstract (english)

Buildings are one of the largest consumers of energy in the world and at the same time a space for significant energy savings. Learning user behavior is a prerequisite for predicting consumption and possible optimization of air conditioning of rooms and the entire building adapted to user behavior. As part of the thesis, it was created an IoT device that sets the desired room temperature and models user behavior at the level of one year, at different times of the day, weather conditions, seasons and working and non-working days. Model learning was conducted on a pre-available dataset containing external and internal weather conditions. Outdoor weather conditions consist of temperature, humidity and direct, diffuse and global solar radiation. The internal conditions refer to one of the offices of the Faculty of Electrical Engineering and Computing, and the air temperature, the mode of operation of the fan coil controller and the set temperatures in the past are available. The model was learned using a neural network with Long Short Term Memory (LSTM), which in recent years has been the most commonly used deep learning network for predicting time series. The learned model is implemented as a Python script on a Raspberry Pi microcomputer so that it provides real-time predicted user behavior 24 and 36 hours in advance.

• Keywords: ušteda energije; zgradarstvo; referentna temperatura; neuronska mreža; RNN; LSTM; duboko učenje; Internet stvari; Raspberry Pi; matematički model; Python; Tensorflow
• Keywords (english): energy saving; buildings; temperature setpoint; Neural network; RNN; LSTM; Deep learning; Internet of Things; Raspberry Pi; mathematical model; Python; Tensorflow
• Language: croatian
• URN:NBN: urn:nbn:hr:168:195813
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 13:27:40