Metodologija predviđanja potrošnje električne energije primjenom algoritama umjetne inteligencije

master's thesis

• Title (english): The Methodology for Electricity Forecasting Using Artificial Intelligence Algorithms
• Author: Antonio Vidić
• Mentor: Slavko Krajcar (mentor)
• Committee member: Slavko Krajcar (predsjednik povjerenstva)
• Committee member: Ivan Rajšl (član povjerenstva)
• Committee member: Perica Ilak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Nastup opskrbljivača na tržištu električnom energijom zahtjevan je tehno-ekonomski proces, prije svega zbog visoke neizvjesnosti potrošnje potrošača. U radu je dan kratak pregled metodologije predviđanja potrošnje kroz povijest, sve do suvremenih algoritama umjetne inteligencije. Opisani su ključni parametri i izazovi za predviđanje potrošnje (temperatura, vjetar, sezonalnost, dani u tjednu i sl.) te razlike u krivuljama potrošnje karakterističnih skupina potrošača električne energije. Prema... More pravilima koje je propisao HEP-ODS d.o.o. opisana je metodologija predviđanja potrošnje električne energije specifičnog portfelja kupaca koje opskrbljuje opskrbljivač. LSTM model predviđanja potrošnje električne energije u ovome radu pripada skupini naprednih neuronskih mreža, a izrađen je upotrebom programskog jezika Python. Modelom se predviđa potrošnja električne energije distribucije te potrošnja svih potrošača u distribucijskom sustavu opremljenih intervalnim brojilom, nakon čega se primjenjuje metodologija predviđanja potrošnje za specifičan portfelj kupaca. Pokazatelji točnosti predviđanja potrošnje električne energije ovog modela su srednja apsolutna postotna pogreška te srednja apsolutna pogreška. Nakon izračuna potrošnje električne energije specifičnog portfelja kupaca opisan je izračun troškova energije uravnoteženja nastalih odstupanjem predviđene potrošnje od ostvarene potrošnje električne energije. Less

Abstract (english)

The appearance of suppliers on the electricity market is a demanding techno-economic process, primarily due to the high uncertainty of consumer consumption. The paper gives a brief overview of the methodology for predicting consumption throughout history, all the way to modern artificial intelligence algorithms. The key parameters and challenges for forecasting consumption (temperature, wind, seasonality, days of the week, etc.) and the differences in the consumption curves of... More characteristic groups of electricity consumers are described. The methodology for predicting the electricity consumption of a specific customer portfolio supplied by a supplier is described according to the rules prescribed by HEP-ODS d.o.o.. The LSTM model for predicting electricity consumption in this paper belongs to the group of advanced neural networks, and was developed using the Python programming language. The model predicts the consumption of electricity distribution and the consumption of all consumers in the distribution system equipped with an interval meter, after which the methodology of consumption forecasting for a specific customer portfolio is applied. The indicators of the accuracy of forecasting the electricity consumption for this model are the mean absolute percentage error and the mean absolute error. After calculating the electricity consumption of a specific customer portfolio, the calculation of balancing energy costs incurred by the deviation of the projected consumption from the realized electricity consumption is described. Less

• Keywords: električna energija; predviđanje potrošnje; neuronska mreža; portfelj kupaca; energija uravnoteženja
• Keywords (english): electricity; consumption forecasting; neural network; customer portfolio; balancing energy
• Language: croatian
• URN:NBN: urn:nbn:hr:168:929995
• 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 09:23:04