Artificial neural network for dynamic iterative forecasting : forecasting hourly electricity demand

K. A. D. Deshani; Liwan Liyanage-Hansen; Dilhari Attygalle

doi:10.12691/ajams-7-1-2

Artificial neural network for dynamic iterative forecasting : forecasting hourly electricity demand

K. A. D. Deshani, Liwan Liyanage-Hansen, Dilhari Attygalle

Western Sydney University

Research output: Contribution to journal › Article › peer-review

Abstract

This paper presents the procedure of building a dynamic predictive model using an artificial neural network to perform an iterative forecast. An algorithm is proposed and named as "Artificial Neural Network Approach for Dynamic Iterative Forecasting". The development of this algorithm focused on feature selection, identification of best network architecture for the model, moving window selection and finally the iterative prediction. This proposed algorithm was deployed to forecast next day's hourly total demand in Sri Lanka as an illustration. Inclusion of a clustering effect that were based on the specialty of the day, as an input was investigated through this application, from which improved accuracies were shown.

Original language	English
Pages (from-to)	9-17
Number of pages	9
Journal	American Journal of Applied Mathematics and Statistics
Volume	7
Issue number	1
DOIs	https://doi.org/10.12691/ajams-7-1-2
Publication status	Published - 2019

Open Access - Access Right Statement

© The Author(s) 2019. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Keywords

Sri Lanka
algorithms
electric power consumption
forecasting
neural networks (computer science)

Access to Document

10.12691/ajams-7-1-2

Cite this

@article{5837c4c5a645428a91e3a4d1d4fa54df,

title = "Artificial neural network for dynamic iterative forecasting : forecasting hourly electricity demand",

abstract = "This paper presents the procedure of building a dynamic predictive model using an artificial neural network to perform an iterative forecast. An algorithm is proposed and named as {"}Artificial Neural Network Approach for Dynamic Iterative Forecasting{"}. The development of this algorithm focused on feature selection, identification of best network architecture for the model, moving window selection and finally the iterative prediction. This proposed algorithm was deployed to forecast next day's hourly total demand in Sri Lanka as an illustration. Inclusion of a clustering effect that were based on the specialty of the day, as an input was investigated through this application, from which improved accuracies were shown.",

keywords = "Sri Lanka, algorithms, electric power consumption, forecasting, neural networks (computer science)",

author = "Deshani, {K. A. D.} and Liwan Liyanage-Hansen and Dilhari Attygalle",

year = "2019",

doi = "10.12691/ajams-7-1-2",

language = "English",

volume = "7",

pages = "9--17",

journal = "American Journal of Applied Mathematics and Statistics",

issn = "2328-7292",

publisher = "Science and Education Publishing",

number = "1",

}

TY - JOUR

T1 - Artificial neural network for dynamic iterative forecasting : forecasting hourly electricity demand

AU - Deshani, K. A. D.

AU - Liyanage-Hansen, Liwan

AU - Attygalle, Dilhari

PY - 2019

Y1 - 2019

N2 - This paper presents the procedure of building a dynamic predictive model using an artificial neural network to perform an iterative forecast. An algorithm is proposed and named as "Artificial Neural Network Approach for Dynamic Iterative Forecasting". The development of this algorithm focused on feature selection, identification of best network architecture for the model, moving window selection and finally the iterative prediction. This proposed algorithm was deployed to forecast next day's hourly total demand in Sri Lanka as an illustration. Inclusion of a clustering effect that were based on the specialty of the day, as an input was investigated through this application, from which improved accuracies were shown.

AB - This paper presents the procedure of building a dynamic predictive model using an artificial neural network to perform an iterative forecast. An algorithm is proposed and named as "Artificial Neural Network Approach for Dynamic Iterative Forecasting". The development of this algorithm focused on feature selection, identification of best network architecture for the model, moving window selection and finally the iterative prediction. This proposed algorithm was deployed to forecast next day's hourly total demand in Sri Lanka as an illustration. Inclusion of a clustering effect that were based on the specialty of the day, as an input was investigated through this application, from which improved accuracies were shown.

KW - Sri Lanka

KW - algorithms

KW - electric power consumption

KW - forecasting

KW - neural networks (computer science)

UR - http://handle.westernsydney.edu.au:8081/1959.7/uws:51997

UR - http://pubs.sciepub.com/ajams/7/1/2/index.html

U2 - 10.12691/ajams-7-1-2

DO - 10.12691/ajams-7-1-2

M3 - Article

SN - 2328-7292

VL - 7

SP - 9

EP - 17

JO - American Journal of Applied Mathematics and Statistics

JF - American Journal of Applied Mathematics and Statistics

IS - 1

ER -

Artificial neural network for dynamic iterative forecasting : forecasting hourly electricity demand

Abstract

Open Access - Access Right Statement

Keywords

Access to Document

Other files and links

Fingerprint

Cite this