1992
DOI: 10.1109/59.141711
|View full text |Cite
|
Sign up to set email alerts
|

Advancement in the application of neural networks for short-term load forecasting

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
70
0
3

Year Published

1995
1995
2018
2018

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 332 publications
(80 citation statements)
references
References 15 publications
0
70
0
3
Order By: Relevance
“…It is proved by one another author also that artificial neural network models have learning ability (Kalogirou, 2000) and with this ability these models perform much better than other classical model many times. May be that is why Dillon et al (1991) and Peng et al (1992) didn't compare the outcomes comparatively. Moreover, wavelet transformation and neural network model was utilized by Yao et al (2000) in order to forecast electrical load.…”
Section: Forecasting the Electricity Demand And Strategic Planningmentioning
confidence: 99%
“…It is proved by one another author also that artificial neural network models have learning ability (Kalogirou, 2000) and with this ability these models perform much better than other classical model many times. May be that is why Dillon et al (1991) and Peng et al (1992) didn't compare the outcomes comparatively. Moreover, wavelet transformation and neural network model was utilized by Yao et al (2000) in order to forecast electrical load.…”
Section: Forecasting the Electricity Demand And Strategic Planningmentioning
confidence: 99%
“…Using neural networks which combine weather data and historical loads with non-linear curve-fitting has been popular [30,48,36]. Curve fitting was also used with fuzzy logic techniques [22,4] which avoids advanced mathematical models.…”
Section: Other Machine Learning Techniquesmentioning
confidence: 99%
“…Further, other machine learning techniques have been applied such as non-linear curve-fitting [48,36] and Support Vector Machines (SVM) [23,19]. It should be noted here that the load forecasting is significantly different from peak prediction [30] [37].…”
Section: Internal Structurementioning
confidence: 99%
“…The approach in this study is a simple but also very effective tool for forecasting problems since it has the ability to approximate any nonlinear function. Due to its datadriven properties, it is also able to solve problems where the input-output relationship is neither well defined nor easily computable [3][4][5][6][7][8]. According to the literature, the single hidden layer feed-forward network [9] is the most popular model for time series modeling and forecasting.…”
Section: Introductionmentioning
confidence: 99%