Večkriterijska optimizacija pametnih stavb z evolucijskim algoritmom

diplomsko delo

Nejc Ambrožič (Author), Marko Robnik Šikonja (Mentor), Bogdan Filipič (Co-mentor)

Abstract

Energetsko učinkovito delovanje bivanjskih stavb je ključnega pomena pri globalnem zmanjšanju porabe električne energije, saj povpraševanje po energiji, skladno s tehnološkim razvojem in povečano dostopnostjo tehnologije, narašča. Za optimiziranje delovanja pametnih stavb je v diplomskem delu predstavljen in razvit evolucijski algoritem, ki upošteva kriterija energetske učinkovitosti in uporabnikovega udobja. Namesto ene rešitve je moč poiskati Pareto optimalno fronto, na kateri se nahajajo kompromisne rešitve po več kriterijih. S poganjanjem simulacij v različnih testnih scenarijih smo pokazali, da algoritem na podlagi začetnega urnika, ki ga nastavi uporabnik, najde kompromisne rešitve, ki žrtvujejo udobje, a so stroškovno učinkovitejše.

Keywords

pametna stavba;večkriterijska optimizacija;evolucijski algoritem;Pareto optimalnost;računalništvo;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2015
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[N. Ambrožič]
UDC:	004.021:728(043.2)
COBISS:	1536551107
Views:	815
Downloads:	197
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Multicriteria optimization of smart buildings using evolutionary algorithm
Secondary abstract:	Energy efficiency of residential buildings is crucial to the global reduction of electricity consumption, as energy demand, in line with technological development and the increased availability of technology, is increasing. To optimize the functioning of smart buildings, an evolutionary algorithm that takes into account the criteria of energy efficiency and comfort of the user, is presented and developed. Instead of a single solution, it is possible to find a Pareto optimal front, consisting of trade-off solutions. By simulating different test scenarios we show that the algorithm finds trade-off solutions based on the initial schedule set by the user. The obtained solutions sacrifice comfort, but are more cost-effective.
Secondary keywords:	smart house;multicriteria optimization;evolutionary algorithm;Pareto optimality;computer science;computer and information science;diploma;
File type:	application/pdf
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	53 str.
ID:	8966424