An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL)

Cuneyt Suheyl Ozveren; A. T. Sapeluk; Alan Birch

doi:10.1109/UPEC.2014.6934819

An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL)

Cuneyt Suheyl Ozveren, A. T. Sapeluk, Alan Birch

Abertay University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Different ANN architectures using back propagation can forecast the electricity demand at half-hourly intervals for up to 24 hours ahead with various degrees of success that is highly dependent on mainly trial and error heuristic tailoring of the architecture and the various learning parameters to cover the solution space. This paper presents the results of an investigation of an approach in the neuro-evolution technique to the short term electricity forecasting (STFL) problem. This algorithm is called Neuro-Evolution through Augmenting Topologies (NEAT). We have chosen the methodology in the paper to be a simple, generic, adaptive, robust, and easy to implement approach, requiring modest computing resources, for the prediction of the electricity demand.

Original language	English
Title of host publication	Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781479965571, 9781479965564
DOIs	https://doi.org/10.1109/UPEC.2014.6934819
Publication status	Published - 2014
Event	49th International Universities Power Engineering Conference - Cluj-Napoca, Romania Duration: 2 Sep 2014 → 5 Sep 2014 Conference number: 49th

Conference

Conference	49th International Universities Power Engineering Conference
Abbreviated title	UPEC 2014
Country	Romania
City	Cluj-Napoca
Period	2/09/14 → 5/09/14

Access to Document

10.1109/UPEC.2014.6934819

Fingerprint Dive into the research topics of 'An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL)'. Together they form a unique fingerprint.

Cite this

Ozveren, C. S., Sapeluk, A. T., & Birch, A. (2014). An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL). In Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC) (pp. 1-5). IEEE . https://doi.org/10.1109/UPEC.2014.6934819

@inproceedings{4dd1d90b08854a7eb1e1c033e96c7c4e,

title = "An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL)",

abstract = "Different ANN architectures using back propagation can forecast the electricity demand at half-hourly intervals for up to 24 hours ahead with various degrees of success that is highly dependent on mainly trial and error heuristic tailoring of the architecture and the various learning parameters to cover the solution space. This paper presents the results of an investigation of an approach in the neuro-evolution technique to the short term electricity forecasting (STFL) problem. This algorithm is called Neuro-Evolution through Augmenting Topologies (NEAT). We have chosen the methodology in the paper to be a simple, generic, adaptive, robust, and easy to implement approach, requiring modest computing resources, for the prediction of the electricity demand.",

author = "Ozveren, {Cuneyt Suheyl} and Sapeluk, {A. T.} and Alan Birch",

year = "2014",

doi = "10.1109/UPEC.2014.6934819",

language = "English",

pages = "1--5",

booktitle = "Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC)",

publisher = "IEEE ",

note = "49th International Universities Power Engineering Conference, UPEC 2014 ; Conference date: 02-09-2014 Through 05-09-2014",

}

Ozveren, CS, Sapeluk, AT & Birch, A 2014, An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL). in Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC). IEEE , Piscataway, NJ, pp. 1-5, 49th International Universities Power Engineering Conference, Cluj-Napoca, Romania, 2/09/14. https://doi.org/10.1109/UPEC.2014.6934819

An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL). / Ozveren, Cuneyt Suheyl; Sapeluk, A. T.; Birch, Alan.

Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC). Piscataway, NJ : IEEE , 2014. p. 1-5.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An investigation into using neuro-evolution of Augmenting Topologies (NEAT) for short term load forecasting (STFL)

AU - Ozveren, Cuneyt Suheyl

AU - Sapeluk, A. T.

AU - Birch, Alan

N1 - Conference code: 49th

PY - 2014

Y1 - 2014

N2 - Different ANN architectures using back propagation can forecast the electricity demand at half-hourly intervals for up to 24 hours ahead with various degrees of success that is highly dependent on mainly trial and error heuristic tailoring of the architecture and the various learning parameters to cover the solution space. This paper presents the results of an investigation of an approach in the neuro-evolution technique to the short term electricity forecasting (STFL) problem. This algorithm is called Neuro-Evolution through Augmenting Topologies (NEAT). We have chosen the methodology in the paper to be a simple, generic, adaptive, robust, and easy to implement approach, requiring modest computing resources, for the prediction of the electricity demand.

AB - Different ANN architectures using back propagation can forecast the electricity demand at half-hourly intervals for up to 24 hours ahead with various degrees of success that is highly dependent on mainly trial and error heuristic tailoring of the architecture and the various learning parameters to cover the solution space. This paper presents the results of an investigation of an approach in the neuro-evolution technique to the short term electricity forecasting (STFL) problem. This algorithm is called Neuro-Evolution through Augmenting Topologies (NEAT). We have chosen the methodology in the paper to be a simple, generic, adaptive, robust, and easy to implement approach, requiring modest computing resources, for the prediction of the electricity demand.

U2 - 10.1109/UPEC.2014.6934819

DO - 10.1109/UPEC.2014.6934819

M3 - Conference contribution

SP - 1

EP - 5

BT - Proceedings of 2014 49th International Universities Power Engineering Conference (UPEC)

PB - IEEE

CY - Piscataway, NJ

T2 - 49th International Universities Power Engineering Conference

Y2 - 2 September 2014 through 5 September 2014

ER -