SHORT-TERM LOAD FORECASTING BY A NEURAL-NETWORK AND A REFINED GENETIC ALGORITHM

被引：20

作者：

MAIFELD, T

SHEBLE, G

机构：

来源：

ELECTRIC POWER SYSTEMS RESEARCH | 1994年 / 31卷 / 03期

关键词：

LOAD FORECASTING; ARTIFICIAL NEURAL NETWORK; GENETIC ALGORITHMS;

D O I：

10.1016/0378-7796(94)90074-4

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Feedforward artificial neural networks have many properties that make them specially suited to short-term load forecasting. However, the main drawback is not having a training algorithm that finds a nearly global set of weights in a reasonable amount of time. A genetic algorithm is a robust optimization method that find solutions to problems by an evolutionary process based on natural selection. This paper presents short-term load forecasting using a genetic algorithm to optimize the weights of an artificial neural network. It also presents a technique that allows a genetic algorithm to consistently find a good set of weights for an artificial neutral network. A 12-hour power system forecast is then performed comparing the refined genetic algorithm's training algorithm, the back-propagation training algorithm, and an interior point training algorithm.

引用

页码：147 / 152

页数：6

共 11 条

[1]

Chen, Yu, Moghaddamjo, Weather sensitive short-term load forecasting using non-fully connected artificial neural network, IEEE Trans. Power Syst., 7, pp. 1098-1105, (1992)

[2]

Park, El-Sharkawi, Marks, Atlas, Damborg, Electric load forecasting using an artificial neural network, IEEE Trans. Power Syst., 6, pp. 442-449, (1991)

[3]

Welsh, Artificial neural network training via interior point algorithms, Masters Thesis, (1993)

[4]

Montana, Davis, Training feedforward neural networks using genetic algorithms, Proc. 11th Int. Joint Conf. Artificial Intelligence, (1989)

[5]

Walters, Sheble, Genetic algorithm solution of economic dispatch with valve point loading, IEEE Trans. Power Syst., 8, pp. 1325-1332, (1993)

[6]

Elshafiey, Udpa, Udpa, Improved back-propagation training algorithm using modified steepest descent, Proc. 1st Midwest Electro-Technology Conf., pp. 122-125, (1992)

[7]

Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, (1989)

[8]

Koza, Genetic Programming, (1992)

[9]

Brittig, Sheble, Refined genetic algorithm—economic dispatch example, IEEE PES Winter Meeting, (1994)

[10]

Grady, Groce, Huebner, Lu, Crawford, Enhancement, implementation, and performance of an adaptive short-term load forecasting algorithm, IEEE Transactions on Power Systems, 6, pp. 1404-1410, (1992)

← 1 2 →