國立虎尾科技大學 |

Recurrent neural networks for short-term load forecasting = an overview and comparative analysis /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Recurrent neural networks for short-term load forecasting/ by Filippo Maria Bianchi ... [et al.].
其他題名:	an overview and comparative analysis /
作者:	Bianchi, Filippo Maria.
其他作者:	Maiorino, Enrico.
出版者:	Cham :Springer International Publishing : : 2017.,
面頁冊數:	ix, 72 p. :ill., digital ; : 24 cm.;
Contained By:	Springer eBooks
標題:	Neural networks (Computer science) -
電子資源:	http://dx.doi.org/10.1007/978-3-319-70338-1
ISBN:	9783319703381

Recurrent neural networks for short-term load forecasting = an overview and comparative analysis /
Bianchi, Filippo Maria.

Recurrent neural networks for short-term load forecastingan overview and comparative analysis /[electronic resource] :by Filippo Maria Bianchi ... [et al.]. - Cham :Springer International Publishing :2017. - ix, 72 p. :ill., digital ;24 cm. - Springerbriefs in computer science,2191-5768. - Springerbriefs in computer science..

Introduction -- Properties and Training in Recurrent Neural Networks -- Recurrent Neural Networks Architectures -- Other Recurrent Neural Networks Models -- Synthetic Time Series -- Real-World Load Time Series -- Experiments -- Conclusions.

The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementations of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.

ISBN: 9783319703381

Standard No.: 10.1007/978-3-319-70338-1doiSubjects--Topical Terms:

528588
Neural networks (Computer science)

LC Class. No.: QA76.87

Dewey Class. No.: 006.32

Recurrent neural networks for short-term load forecasting = an overview and comparative analysis /
LDR:02805nam a2200337 a 4500 001 921881
003 DE-He213
005 20171109172652.0
006 m d
007 cr nn 008maaau
008 190624s2017 gw s 0 eng d
020 $a 9783319703381 $q (electronic bk.)
020 $a 9783319703374 $q (paper)
024 7 $a 10.1007/978-3-319-70338-1 $2 doi
035 $a 978-3-319-70338-1
040 $a GP $c GP
041 0 $a eng
050 4 $a QA76.87
072 7 $a UYQ $2 bicssc
072 7 $a TJFM1 $2 bicssc
072 7 $a COM004000 $2 bisacsh
082 0 4 $a 006.32 $2 23
090 $a QA76.87 $b .B577 2017
100 1 $a Bianchi, Filippo Maria. $3 1143173
245 1 0 $a Recurrent neural networks for short-term load forecasting $h [electronic resource] : $b an overview and comparative analysis / $c by Filippo Maria Bianchi ... [et al.].
260 $a Cham : $c 2017. $b Springer International Publishing : $b Imprint: Springer,
300 $a ix, 72 p. : $b ill., digital ; $c 24 cm.
490 1 $a Springerbriefs in computer science, $x 2191-5768
505 0 $a Introduction -- Properties and Training in Recurrent Neural Networks -- Recurrent Neural Networks Architectures -- Other Recurrent Neural Networks Models -- Synthetic Time Series -- Real-World Load Time Series -- Experiments -- Conclusions.
520 $a The key component in forecasting demand and consumption of resources in a supply network is an accurate prediction of real-valued time series. Indeed, both service interruptions and resource waste can be reduced with the implementation of an effective forecasting system. Significant research has thus been devoted to the design and development of methodologies for short term load forecasting over the past decades. A class of mathematical models, called Recurrent Neural Networks, are nowadays gaining renewed interest among researchers and they are replacing many practical implementations of the forecasting systems, previously based on static methods. Despite the undeniable expressive power of these architectures, their recurrent nature complicates their understanding and poses challenges in the training procedures. Recently, new important families of recurrent architectures have emerged and their applicability in the context of load forecasting has not been investigated completely yet. This work performs a comparative study on the problem of Short-Term Load Forecast, by using different classes of state-of-the-art Recurrent Neural Networks. The authors test the reviewed models first on controlled synthetic tasks and then on different real datasets, covering important practical cases of study. The text also provides a general overview of the most important architectures and defines guidelines for configuring the recurrent networks to predict real-valued time series.
650 0 $a Neural networks (Computer science) $3 528588
650 1 4 $a Computer Science. $3 593922
650 2 4 $a Artificial Intelligence (incl. Robotics) $3 593924
650 2 4 $a System Performance and Evaluation. $3 669346
650 2 4 $a Power Electronics, Electrical Machines and Networks. $3 768690
650 2 4 $a Energy Efficiency. $3 1112432
650 2 4 $a Performance and Reliability. $3 669802
700 1 $a Maiorino, Enrico. $3 1197069
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer eBooks
830 0 $a Springerbriefs in computer science. $3 888133
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-70338-1
950 $a Computer Science (Springer-11645)