Commercial, industrial and household electrical load modelling and short-term load forecasting

Marma, Hla-U-May (2020) Commercial, industrial and household electrical load modelling and short-term load forecasting. Masters thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (2MB)

Abstract

In this thesis, a transfer function-based load model is determined for commercial and industrial load. This model is derived from the composite load model which consist of an induction motor and static load. This developed model is compared to composite load model by considering two cases: 1) a small motor composition load or commercial load and 2) higher motor composition load or industrial load. The research is conducted through MATLAB/Simulink simulation. In order to compare the dynamic response of developed model, a comparative study has been done between the two models. In addition, the influence of voltage and frequency dependency terms on the overall model accuracy for developed model has been evaluated through several case studies considering both voltage and frequency dependency disturbances. A short-term load forecast model is developed for an electrically heated house. This research work is based on experimental data collected by installing current sensors in a house in St. Johns, Newfoundland, Canada. The data was collected for three years and only one-year data is used for this model. The model is based on Recurrent Neural Network (RNN) with wavelet transform. The proposed model is verified by comparing other developed models in the literature through MATLAB deep learning toolbox and wavelet toolbox. The proposed model can more accurately forecast the load.

Item Type: Thesis (Masters)
URI: http://research.library.mun.ca/id/eprint/14682
Item ID: 14682
Additional Information: Includes bibliographical references.
Keywords: Composite load model, transfer-function, static load, induction motors, Short-Term Load Forecasting, Stationary wavelet transform, Long short-term memory
Department(s): Engineering and Applied Science, Faculty of
Date: October 2020
Date Type: Submission
Digital Object Identifier (DOI): https://doi.org/10.48336/kfg3-4j76
Library of Congress Subject Heading: Electric power-plants--Load--Computer simulation.

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics