magistrsko delo
Nac Stoklas (Author), Matjaž Kukar (Mentor)

Abstract

Pomemben del v verigi dobavljanja električne energije so prodajalci, ki skrbijo za dobavo električne energije končnim uporabnikom. Točne kratkoročne napovedi porabe zmanjšajo skrbi o presežkih in primanjkljajih, ki so del njihovega vsakdana. V ta namen se uporablja širok nabor metod za analizo časovnih vrst (avtokorelacija, dekompozicija, motivi, diskordi) in njihovo napovedovanje (drevesne metode, globoko učenje, statistične metode). Pred nekaj leti se je pojavila metoda za hiter izračun matričnega profila, ki omogoča preprosto zaznavanje motivov in diskordov. Z uporabo matričnih profilov analiziramo podatkovno množico (gospodinjski odjem v Mariboru) in prepoznamo področja, na katerih je smiselno iskati relevantne značilke. V našem delu se osredotočimo predvsem na gospodinjski odjem, za katerega smo zgradili modele, ki napovedujejo porabo na uro natančno. Primerjamo različne modele in analiziramo napako glede na različne nabore značilk. Najboljši nabor značilk apliciramo tudi na ločeno podatkovno množico in primerjamo točnost med obema. Predstavimo tudi metodo, ki uporabi matrični profil za generiranje značilk. Rezultati nakazujejo, da lahko podoben nabor značilk uporabimo na različnih podatkovnih množicah porabe električne energije in pričakujemo dobre rezultate.

Keywords

napovedovanje porabe elektrike;regresija;azure;matrično profiliranje;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [N. Stoklas]
UDC: 004.85:66.012.3(043.2)
COBISS: 69305347 Link will open in a new window
Views: 318
Downloads: 52
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Energy load forecasting with machine learning and matrix profiling
Secondary abstract: An important part in supplying electricity to residential areas are companies selling them the electricity. Accurate daily forecasts alleviate some of the concern related to providing the right amount of electricity without any surplus or shortages. The predictions are made after using a wide array of methods to analyze time series data (autocorrelations, time series decomposition, motifs and discords, etc.) and algorithms to build forecasting models (tree based methods, deep learning, statistical methods, etc.). Recently a method was presented which efficiently calculates the matrix profile of a time series. Matrix profile enables us simple discovery of motifs and discords. We use matrix profiles to analyse our dataset (residential energy load in Maribor) and recognize the areas from which we should draw our features. We focused on residential energy consumption for which we built models, which forecast hourly energy demand. We compare different models and analyse the forecasting accuracy using different features. We apply the most successfull feature set to another data set and compare the forecasting accuracy. We also develop and present a method, that uses matrix profiles to generate features. The result indicate that we can use a similar set of features, which work well on Maribor dataset, and apply it to another residential consumption dataset and expect similarly good results.
Secondary keywords: energy load forecasting;machine learning;regression;azure;matrix profiling;computer science;computer and information science;master's degree;Strojno učenje;Poraba električne energije;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 61 str.
ID: 13085123