#### DMCA

## Evolutionary Techniques Based Combined Artificial Neural Networks for Peak Load Forecasting

### Citations

10038 |
Genetic Algorithms
- Goldberg
- 1989
(Show Context)
Citation Context ...tic Algorithm Genetic Algorithm(GA) is a global search algorithm based on the principles inspired from the genetic and evolution mechanisms observed in natural systems and populations of living being =-=[17, 18]-=-. A typical GA is usually composed of three operators. The first operator Reproduction or selection is a process in which individual strings (chromosomes) are copied according to a high fitness value;... |

3757 | Particle Swarm Optimization
- Kennedy, Eberhart
- 1995
(Show Context)
Citation Context ...article Swarm Optimization Particle Swarm Optimization (PSO) is a stochastic global optimization technique developed by Dr. Eberhart and Dr. Kennedy in 1995 based on simulation of social behaviors of =-=[15, 16]-=- bird flocking and fish schooling. It uses a number of particles that constitute a swarm. During flight or swim each particle adjusts its position according to its own experience and the experiences o... |

1544 | The Handbook of Genetic Algorithms
- DAVIS, Ed
- 1991
(Show Context)
Citation Context ...tic Algorithm Genetic Algorithm(GA) is a global search algorithm based on the principles inspired from the genetic and evolution mechanisms observed in natural systems and populations of living being =-=[17, 18]-=-. A typical GA is usually composed of three operators. The first operator Reproduction or selection is a process in which individual strings (chromosomes) are copied according to a high fitness value;... |

59 | Particle Swarm Optimization Method for Constrained Optimization Problems”,
- Parsopoulos, Vrahatis
- 2002
(Show Context)
Citation Context ...article Swarm Optimization Particle Swarm Optimization (PSO) is a stochastic global optimization technique developed by Dr. Eberhart and Dr. Kennedy in 1995 based on simulation of social behaviors of =-=[15, 16]-=- bird flocking and fish schooling. It uses a number of particles that constitute a swarm. During flight or swim each particle adjusts its position according to its own experience and the experiences o... |

48 | Improving model accuracy using optimal linear combinations of trained neural networks,”
- Hashem, Schmeiser
- 1992
(Show Context)
Citation Context ...s with best performance are selected and combined together to develop a CANN module for load forecasting application rather than using only the single best trained ANN. The Optimal Linear Combination =-=[11]-=- of these trained networks is achieved by five different computational techniques, such as, Unconstrained and Constrained methods [11], and the proposed methods Evolutionary Programming, Particle Swar... |

35 | Short term load forecasting using artificial neural network", - Lee, Park - 1992 |

34 | Neural network based short term load forecasting, Power Systems, - Lu, Wu, et al. - 1993 |

33 | A generalized knowledge-based short term load-forecasting technique,” - Rahman, Hazim - 1998 |

24 | Short term load forecasting using fuzzy neural networks - Bakirtzis, Theocharis, et al. - 1995 |

22 | Short-term load forecasting with local ANN predictors, Power Systems, - Drezga, Rahman - 1999 |

20 | A novel approach to short-term load forecasting using fuzzy neural networks - Papadakis, Theocharis, et al. |

15 | Cascaded artificial neural networks for short-term load forecasting,” - AlFuhaid, El-Sayed, et al. - 1997 |

10 |
Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA,
- El-Desouky, Elkateb
- 2000
(Show Context)
Citation Context ...and the results of these combinations are compared themselves and with the conventional ANN with best performance. The developed CANN module is proposed to achieve Medium Term Load Forecasting (MTLF) =-=[3, 13]-=-, where the objective is to predict daily peak load for the months of May, June and July 2005 (summer) for the power system of Chennai city (Tamilnadu State - India). 1 2 3 4 24 II. SYSTEM DATA AND AR... |

8 | Katsumi Uezato, and Toshihisa Funabashi, “One hour-ahead load forecasting using neural network - Senjyu, Takara - 2002 |

3 |
Input variable selection for ANN based short-term load forecasting
- Drezga, Rahman
(Show Context)
Citation Context ... ANN with a sigmoid function is selected for ANN modeling [6-8]. The back propagation algorithm is adopted to train the ANN. Using past experience and heuristics the structure and the input variables =-=[12]-=- are 680selected. Fig.1 shows the general architecture representation of ANN and Table 1 shows different input variables for ANN. Table I shows the list of selected input variables. With those input ... |

2 |
A Fuzzy Adaptive Correction Scheme for Short term load forecasting using fuzzy layered neural network”, ANNPS’93,IEEE Proceedings of the second international forum on application of neural networks to power systems, pp 432-437
- Dash, Rahman
- 1993
(Show Context)
Citation Context ...ecasting techniques use conventional smoothing techniques, regression models and statistical analysis. These techniques fail to produce an accurate load forecast because of their inherent limitations =-=[19]-=-. In the recent years, many studies have been reported and many models have been developed for load forecasting using the computational intelligence methods such as Fuzzy systems and Artificial Neural... |

1 | Shangyou Hao and Tie-Mao Peng, “An Implementation of a neural network based load forecasting model for the EMS - Papalexopoulos - 1994 |

1 |
Tatsuya Iizaka and Yoshikazu Fukuyama, “Peak load forecasting using analyzable structured neural network
- Matsui
(Show Context)
Citation Context ...and the results of these combinations are compared themselves and with the conventional ANN with best performance. The developed CANN module is proposed to achieve Medium Term Load Forecasting (MTLF) =-=[3, 13]-=-, where the objective is to predict daily peak load for the months of May, June and July 2005 (summer) for the power system of Chennai city (Tamilnadu State - India). 1 2 3 4 24 II. SYSTEM DATA AND AR... |

1 |
System Applications in Power Engineering – Evolutionary Programming and Neural Networks
- Lai
- 1998
(Show Context)
Citation Context ... ( x ) for all i,j (10) ij i k j k N k = 1 N is the cardinality of N and y ( x ) is the output of the ith ANN for the kth input in the data set N. C. Evolutionary Programming Evolutionary Programming =-=[14]-=- searches for and finds the optimal solution by evolving a population of candidate solutions over a number of iterations. Evolutionary Programming needs an initial population to start with, like natur... |