Kratkotrajna prognoza opterećenja elektroenergetskog sustava korištenjem umjetnih neuronskih mreža

master's thesis

• Title (english): Short term power load forecasting using artifical neural networks
• Author: Mario Crnčević
• Mentor: Ivica Pavić (mentor)
• Committee member: Ivica Pavić (član povjerenstva)
• Committee member: Ivan Rajšl (član povjerenstva)
• Committee member: Božidar Filipović-Grčić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Predviđanje potrošnje električne energije ima utjecaj na brojne aspekte društvenog života. Osim što donosi financijske uštede kod potrošnje i proizvodnje, povećava sigurnost opskrbe električnom energijom, pomaže razvoju i boljem planiranju infrastrukture. Zbog tih razloga razvijeni su različiti modeli predviđanja potrošnje električne energije. Svakako jedan od preciznijih predstavljaju neuronske mreže. U radu su dani primjeri upotrebe neuronskih mreža u mnogim poljima energetike. Vidjeli smo da one, uz dobre obrasce učenja i dovoljno podataka o čimbenicima koji utječu na potrošnju električne energije, olakšavaju kratkoročno predviđanje. Neuronske mreže su sigurno budućnost kratkoročnog predviđanja i njihova upotreba će samo rasti.

Abstract (english)

Forecasting electrical energy consumption has an impact on many aspects of social life. Apart from establishing financial savings with consumption and production, it increases security of electricity supply, helps in development of infrastructure. For these reasons, many different forecasting methods have been developed. Certainly, one of the more precise methods are neural networks. This study gives examples of the use of neural networks in many fields of energetics. We have seen that them, with good learning patterns and enough data of factors that affect electricity consumption, ease short-term forecasting. Neural networks are surely the future of short-term forecasts and their use will only grow.

• Keywords: električna energija; kratkoročno predviđanje; neuronske mreže; energetika
• Keywords (english): electric power; short-term forecast; neural network; energetics
• Language: croatian
• URN:NBN: urn:nbn:hr:168:683315
• 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: 2019-03-13 19:37:05