IECON 2014 - 40th Annual Conference of the IEEE Industrial Electronics Society 2014
DOI: 10.1109/iecon.2014.7048513
|View full text |Cite
|
Sign up to set email alerts
|

Smart multi-model approach based on adaptive Neuro-Fuzzy Inference Systems and Genetic Algorithms

Abstract: A model of power demand represents the foundation of any intelligent Energy Management System, and its accuracy is the key factor determining the performance of such system. In order to improve the accuracy of the modeling process, a multi-model approach based on a Hierarchical Clustering of similar load behaviors is presented. The clustering algorithm joins similar data subsets in groups that are modelled separately using Adaptive Neuro-Fuzzy Inference Systems. Thus, each of the obtained models addresses only… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
1
0

Year Published

2015
2015
2018
2018

Publication Types

Select...
5
2

Relationship

1
6

Authors

Journals

citations
Cited by 7 publications
(3 citation statements)
references
References 17 publications
0
1
0
Order By: Relevance
“…This observation indicates that week 3 presents a behavior that differs from the rest of the data, as the resulting model achieves worse prediction performance when learning from the other cases. Finally, in order to quantify the increase of performance provided by the application of the proposed methodology, the obtained results have been compared with a classical load forecasting implementation based on ANFIS [35]. The evaluation of the power demand modeling stage using the proposed methodology resulted in decreased error metrics.…”
Section: Power Demand Modelingmentioning
confidence: 99%
“…This observation indicates that week 3 presents a behavior that differs from the rest of the data, as the resulting model achieves worse prediction performance when learning from the other cases. Finally, in order to quantify the increase of performance provided by the application of the proposed methodology, the obtained results have been compared with a classical load forecasting implementation based on ANFIS [35]. The evaluation of the power demand modeling stage using the proposed methodology resulted in decreased error metrics.…”
Section: Power Demand Modelingmentioning
confidence: 99%
“…GAs are heuristic search methods which attempt to approximate the mechanics of the natural selection and evolution process, offering powerful robustness and flexibility. They differ from traditional optimization techniques in several aspects, for instance GA allows parallelism in the searching process since multiple solutions can be considered concurrently [74]. GA is used for search problems or for finding optimal designs.…”
Section: Optimizationmentioning
confidence: 99%
“…A second concept that is important in the EMS is the online modeling or also called "auto tuning" [66], [67]. It gives the LMSF the ability to closely match the operating conditions to the model.…”
Section: Auto Tuningmentioning
confidence: 99%