A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem

Pedro De Lima Abrão; Elizabeth F. Wanner; Paulo E.M. Almeida

doi:10.1145/2463372.2463523

A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem

Pedro De Lima Abrão
, Elizabeth F. Wanner
, Paulo E.M. Almeida

Centro Federal de Educação Tecnológica de Minas Gerais

Research output: Chapter in Book/Published conference output › Conference publication

5 Citations (Scopus)

Abstract

This paper presents a method based on Neural Networks and Evolutionary Algorithms to solve the Hydroelectric Unit Commitment Problem. A Neural Network is used to model the production function and a novel approach based on movable partitions is proposed, which makes it easier to model the desired power output equality constraint in the optimization modeling. Three evolutionary algorithms are tested in order to find optimized operation points: differential evolution DE/best/1/bin, a balanced version of DE and Particle Swarm Optimization algorithm (PSO). The results show that the proposed method is effective in terms of water consumption, reaching in some cases more than 1% of economy whether compared to the traditional commitment strategy.

Original language	English
Title of host publication	GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference
Pages	1205-1212
Number of pages	8
DOIs	https://doi.org/10.1145/2463372.2463523
Publication status	Published - 6 Jul 2013
Event	2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013 - Amsterdam, Netherlands Duration: 6 Jul 2013 → 10 Jul 2013

Publication series

Name	GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference

Conference

Conference	2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013
Country/Territory	Netherlands
City	Amsterdam
Period	6/07/13 → 10/07/13

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Energy generation and storage
Neural systems
Operations research
Optimization algorithms
Renewable energy

Access to Document

10.1145/2463372.2463523

Cite this

De Lima Abrão, P., Wanner, E. F., & Almeida, P. E. M. (2013). A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference (pp. 1205-1212). (GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference). https://doi.org/10.1145/2463372.2463523

De Lima Abrão, Pedro ; Wanner, Elizabeth F. ; Almeida, Paulo E.M. / A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem. GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference. 2013. pp. 1205-1212 (GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference).

@inproceedings{3d2c4d779a8f43cf94843f39e0893b64,

title = "A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem",

abstract = "This paper presents a method based on Neural Networks and Evolutionary Algorithms to solve the Hydroelectric Unit Commitment Problem. A Neural Network is used to model the production function and a novel approach based on movable partitions is proposed, which makes it easier to model the desired power output equality constraint in the optimization modeling. Three evolutionary algorithms are tested in order to find optimized operation points: differential evolution DE/best/1/bin, a balanced version of DE and Particle Swarm Optimization algorithm (PSO). The results show that the proposed method is effective in terms of water consumption, reaching in some cases more than 1\% of economy whether compared to the traditional commitment strategy.",

keywords = "Energy generation and storage, Neural systems, Operations research, Optimization algorithms, Renewable energy",

author = "\{De Lima Abr{\~a}o\}, Pedro and Wanner, \{Elizabeth F.\} and Almeida, \{Paulo E.M.\}",

year = "2013",

month = jul,

day = "6",

doi = "10.1145/2463372.2463523",

language = "English",

isbn = "9781450319638",

series = "GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference",

pages = "1205--1212",

booktitle = "GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference",

note = "2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013 ; Conference date: 06-07-2013 Through 10-07-2013",

}

De Lima Abrão, P, Wanner, EF & Almeida, PEM 2013, A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem. in GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference. GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference, pp. 1205-1212, 2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013, Amsterdam, Netherlands, 6/07/13. https://doi.org/10.1145/2463372.2463523

A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem. / De Lima Abrão, Pedro; Wanner, Elizabeth F.; Almeida, Paulo E.M.
GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference. 2013. p. 1205-1212 (GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem

AU - De Lima Abrão, Pedro

AU - Wanner, Elizabeth F.

AU - Almeida, Paulo E.M.

PY - 2013/7/6

Y1 - 2013/7/6

N2 - This paper presents a method based on Neural Networks and Evolutionary Algorithms to solve the Hydroelectric Unit Commitment Problem. A Neural Network is used to model the production function and a novel approach based on movable partitions is proposed, which makes it easier to model the desired power output equality constraint in the optimization modeling. Three evolutionary algorithms are tested in order to find optimized operation points: differential evolution DE/best/1/bin, a balanced version of DE and Particle Swarm Optimization algorithm (PSO). The results show that the proposed method is effective in terms of water consumption, reaching in some cases more than 1% of economy whether compared to the traditional commitment strategy.

AB - This paper presents a method based on Neural Networks and Evolutionary Algorithms to solve the Hydroelectric Unit Commitment Problem. A Neural Network is used to model the production function and a novel approach based on movable partitions is proposed, which makes it easier to model the desired power output equality constraint in the optimization modeling. Three evolutionary algorithms are tested in order to find optimized operation points: differential evolution DE/best/1/bin, a balanced version of DE and Particle Swarm Optimization algorithm (PSO). The results show that the proposed method is effective in terms of water consumption, reaching in some cases more than 1% of economy whether compared to the traditional commitment strategy.

KW - Energy generation and storage

KW - Neural systems

KW - Operations research

KW - Optimization algorithms

KW - Renewable energy

UR - https://www.scopus.com/pages/publications/84883102926

UR - https://dl.acm.org/doi/10.1145/2463372.2463523

U2 - 10.1145/2463372.2463523

DO - 10.1145/2463372.2463523

M3 - Conference publication

AN - SCOPUS:84883102926

SN - 9781450319638

T3 - GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference

SP - 1205

EP - 1212

BT - GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference

T2 - 2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013

Y2 - 6 July 2013 through 10 July 2013

ER -

De Lima Abrão P, Wanner EF, Almeida PEM. A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference. 2013. p. 1205-1212. (GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference). doi: 10.1145/2463372.2463523

A novel movable partitions approach with neural networks and evolutionary algorithms for solving the hydroelectric unit commitment problem

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this