2005
DOI: 10.1109/tpwrs.2005.846210
|View full text |Cite
|
Sign up to set email alerts
|

Fuzzy Inference Systems Applied to LV Substation Load Estimation

Abstract: This paper describes a system for estimating load curves at Low Voltage Substations. The system is built by the aggregation of individual Fuzzy Inference Systems of the Takagi-Sugeno type. The model was developed from actual measurements forming a base of raw data of consumer behavior. This database allowed one to build large test and training sets of simulated LV substations, which led to the development of the Fuzzy System. The results are compared in terms of accuracy with the ones obtained with a previous … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2010
2010
2021
2021

Publication Types

Select...
5
2
1

Relationship

0
8

Authors

Journals

citations
Cited by 30 publications
(6 citation statements)
references
References 13 publications
0
6
0
Order By: Relevance
“…In a similar way, a range of different variables were considered in [121,123], including gender, age group, social class, and the number of other residents. The number of customers on an LV substation and the monthly energy consumption is used in [129]. In [110], the authors used the substation internal state in addition to lagged load, temperature and temporal features, which proved to be significant in improving the forecast.…”
Section: Econometric Variablesmentioning
confidence: 99%
“…In a similar way, a range of different variables were considered in [121,123], including gender, age group, social class, and the number of other residents. The number of customers on an LV substation and the monthly energy consumption is used in [129]. In [110], the authors used the substation internal state in addition to lagged load, temperature and temporal features, which proved to be significant in improving the forecast.…”
Section: Econometric Variablesmentioning
confidence: 99%
“…1) The intercept should be zero as there would be no load if customer number is zero; 2) Although customers with distributed generation may produce inverse power flow, they are not included in the total customer classes in (8). All customer classes are assumed to contribute positive load to the substation load and therefore the coefficient in (8) should be non-negative; 3) Within each cluster, there are variances between the normalized templates and substations' load shapes.…”
Section: A Clusterwise Weighted Constrained Regressionmentioning
confidence: 99%
“…It takes advantage of the information of customers' bills to aggregate individual customer's peak to substation peak. Based on this concept, recent work adopts advanced techniques including fuzzy regression [7], fuzzy inference [8] and artificial neural network (ANN) [9] to handle uncertainties, narrow confidence intervals and improve the accuracy. However, all these methods do not consider the diversifications in customer composition and structures of LV substations.…”
Section: Introductionmentioning
confidence: 99%
“…Beccali et al [8] used the output of the SOM as an input variable for the NN; whereas Fan and Chen [15] used the output of the SOM to call a specific set of support vector regression models. Espinoza et al [16], Konjic et al [17] and Sousa et al [10] clustered demand profiles of customer demographics and applied the known demand profiles to other customers in order to produce short-term demand forecasts. As noted by Hippert [7], machine learning techniques such as NNs can be used specifically for pattern recognition.…”
Section: Demand Profile Forecastingmentioning
confidence: 99%