Skip to main content
IEEE PES Innovative Smart Grid Technologies Conference EuropeVolume 2022-October, 20222022 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2022; "Master" Congress Center in Novi SadNovi Sad; Serbia; 10 October 2022 through 12 October 2022; Category numberCFP22SGT-ART; Code 184786

Special Day Regression Model for Short-Term Load Forecasting(Conference Paper)

  • Jankovic, Z.,
  • Ilic, S.,
  • Vesin, B.,
  • Selakov, A.
  Save all to author list
  • aUniversity of Novi Sad, Faculty of Technical Sciences, Novi Sad, Serbia
  • bThe Institute for Artificial Intelligence Research and Development of Serbia, Novi Sad, Serbia
  • cUniversity of South-Eastern Norway, Department of Business, History and Social Sciences, Vestfold, Norway

Abstract

Short-Term Load Forecasting accuracy is profoundly affected by unexpected load shapes during so-called "special days."The lack of representative data sets for these days increases forecasting error. In this paper, the authors propose a novel method for forecasting accuracy improvements during special days. The proposed model tracks historical forecasting errors and uses the deviation trend to correct the most recent forecast. Model also contains the mechanism for recognizing hours for prediction correction on special days. Model validation was performed using Serbian Transmission System Company data and showed significant improvement for special days forecast accuracy. © 2022 IEEE.

Author keywords

RegressionSpecial DaysSTLF

Indexed keywords

Engineering controlled terms:Electric power plant loadsRegression analysis
Engineering uncontrolled termsAccuracy ImprovementData setForecasting accuracyForecasting errorNovel methodsRegressionRegression modellingShort term load forecastingSpecial daySTLF
Engineering main heading:Forecasting

Funding details

  • 1

    This research was supported by the Faculty of Technical Sciences, University of Novi Sad, Department of Power, Electronic and Telecommunication Engineering, within the project entitled: "Development and application of modern methods in teaching and research activities at the Department of Energy, Electronics and Telecommunications."

  • ISBN: 978-166548032-1
  • Source Type: Conference Proceeding
  • Original language: English
  • DOI: 10.1109/ISGT-Europe54678.2022.9960317
  • Document Type: Conference Paper
  • Publisher: IEEE Computer Society


© Copyright 2022 Elsevier B.V., All rights reserved.

Cited by 2 documents

Pajić, Z. , Janković, Z. , Selakov, A.
Autoencoder-Driven Training Data Selection Based on Hidden Features for Improved Accuracy of ANN Short-Term Load Forecasting in ADMS
(2024) Energies
Jankovic, Z. , Vesin, B.
Clean Genetic Algorithm Architecture for Improved Modularity and Extensibility
(2023) CIEES 2023 - IEEE International Conference on Communications, Information, Electronic and Energy Systems
View details of all 2 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Neural Network; Load Forecasting; Electric Power","id":116,"uri":"Topic/116","prominencePercentile":99.77584,"prominencePercentileString":"99.776","overallScholarlyOutput":0},"dig":"551a2f58b604d7aa248aff29362d44055ea62da9e784deda494ba49a2b8d351d"}

SciVal Topic Prominence

Topic:
Prominence percentile: