Advanced hybrid genetic algorithm for short-term generation scheduling

A A El Desouky, R Aggarwal, M M Elkateb, F Li

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

This paper is concerned with the development of hybrid techniques for short-term generation scheduling in which the basic element is a genetic algorithm (GA). Particular emphasis is placed on investigating hybrid approaches, involving combining a GA with an artificial neural network (ANN) and/or a priority list (PL), which are significantly more cost effective than the techniques available hitherto. First, a prescheduling of the generating units using the ANN is presented. Since the solution attained via the ANN may not be feasible for the entire scheduling period, the GA (or the GA with a PL) is subsequently employed to adjust the prescheduling. To take load-forecast uncertainty into account and to make the schedule feasible and cost effective, a typical ±5% load forecast error is incorporated into the ANN training data. The proposed techniques are shown to be efficient and flexible based on the simulations performed on the IEEE reliability test systems. In addition, the proposed hybrid techniques are shown to have higher potential to enhance performance and expedite the solution, overcoming the problems associated with the traditional GA-based technique
Original languageEnglish
Pages (from-to)511-517
Number of pages7
JournalGeneration, Transmission and Distribution, IEE Proceedings-
Volume148
Issue number6
Publication statusPublished - 2001

Fingerprint

Genetic algorithms
Scheduling
Neural networks
Costs

Keywords

  • learning (artificial intelligence)
  • genetic algorithms
  • IEEE reliability test systems
  • ANN
  • ANN training data
  • hybrid genetic algorithm
  • load forecasting
  • power generation scheduling
  • generation scheduling short-term
  • artificial neural network
  • load forecast error
  • load-forecast uncertainty
  • power system analysis computing
  • priority list
  • generating units prescheduling

Cite this

Advanced hybrid genetic algorithm for short-term generation scheduling. / El Desouky, A A; Aggarwal, R; Elkateb, M M; Li, F.

In: Generation, Transmission and Distribution, IEE Proceedings-, Vol. 148, No. 6, 2001, p. 511-517.

Research output: Contribution to journalArticle

@article{a3e192cb99874691a1429f3a0560fcd4,
title = "Advanced hybrid genetic algorithm for short-term generation scheduling",
abstract = "This paper is concerned with the development of hybrid techniques for short-term generation scheduling in which the basic element is a genetic algorithm (GA). Particular emphasis is placed on investigating hybrid approaches, involving combining a GA with an artificial neural network (ANN) and/or a priority list (PL), which are significantly more cost effective than the techniques available hitherto. First, a prescheduling of the generating units using the ANN is presented. Since the solution attained via the ANN may not be feasible for the entire scheduling period, the GA (or the GA with a PL) is subsequently employed to adjust the prescheduling. To take load-forecast uncertainty into account and to make the schedule feasible and cost effective, a typical ±5{\%} load forecast error is incorporated into the ANN training data. The proposed techniques are shown to be efficient and flexible based on the simulations performed on the IEEE reliability test systems. In addition, the proposed hybrid techniques are shown to have higher potential to enhance performance and expedite the solution, overcoming the problems associated with the traditional GA-based technique",
keywords = "learning (artificial intelligence), genetic algorithms, IEEE reliability test systems, ANN, ANN training data, hybrid genetic algorithm, load forecasting, power generation scheduling, generation scheduling short-term, artificial neural network, load forecast error, load-forecast uncertainty, power system analysis computing, priority list, generating units prescheduling",
author = "{El Desouky}, {A A} and R Aggarwal and Elkateb, {M M} and F Li",
year = "2001",
language = "English",
volume = "148",
pages = "511--517",
journal = "Generation, Transmission and Distribution, IEE Proceedings-",
issn = "1350-2360",
publisher = "Institute of Electrical Engineers",
number = "6",

}

TY - JOUR

T1 - Advanced hybrid genetic algorithm for short-term generation scheduling

AU - El Desouky, A A

AU - Aggarwal, R

AU - Elkateb, M M

AU - Li, F

PY - 2001

Y1 - 2001

N2 - This paper is concerned with the development of hybrid techniques for short-term generation scheduling in which the basic element is a genetic algorithm (GA). Particular emphasis is placed on investigating hybrid approaches, involving combining a GA with an artificial neural network (ANN) and/or a priority list (PL), which are significantly more cost effective than the techniques available hitherto. First, a prescheduling of the generating units using the ANN is presented. Since the solution attained via the ANN may not be feasible for the entire scheduling period, the GA (or the GA with a PL) is subsequently employed to adjust the prescheduling. To take load-forecast uncertainty into account and to make the schedule feasible and cost effective, a typical ±5% load forecast error is incorporated into the ANN training data. The proposed techniques are shown to be efficient and flexible based on the simulations performed on the IEEE reliability test systems. In addition, the proposed hybrid techniques are shown to have higher potential to enhance performance and expedite the solution, overcoming the problems associated with the traditional GA-based technique

AB - This paper is concerned with the development of hybrid techniques for short-term generation scheduling in which the basic element is a genetic algorithm (GA). Particular emphasis is placed on investigating hybrid approaches, involving combining a GA with an artificial neural network (ANN) and/or a priority list (PL), which are significantly more cost effective than the techniques available hitherto. First, a prescheduling of the generating units using the ANN is presented. Since the solution attained via the ANN may not be feasible for the entire scheduling period, the GA (or the GA with a PL) is subsequently employed to adjust the prescheduling. To take load-forecast uncertainty into account and to make the schedule feasible and cost effective, a typical ±5% load forecast error is incorporated into the ANN training data. The proposed techniques are shown to be efficient and flexible based on the simulations performed on the IEEE reliability test systems. In addition, the proposed hybrid techniques are shown to have higher potential to enhance performance and expedite the solution, overcoming the problems associated with the traditional GA-based technique

KW - learning (artificial intelligence)

KW - genetic algorithms

KW - IEEE reliability test systems

KW - ANN

KW - ANN training data

KW - hybrid genetic algorithm

KW - load forecasting

KW - power generation scheduling

KW - generation scheduling short-term

KW - artificial neural network

KW - load forecast error

KW - load-forecast uncertainty

KW - power system analysis computing

KW - priority list

KW - generating units prescheduling

M3 - Article

VL - 148

SP - 511

EP - 517

JO - Generation, Transmission and Distribution, IEE Proceedings-

JF - Generation, Transmission and Distribution, IEE Proceedings-

SN - 1350-2360

IS - 6

ER -