โ Scribed by Filippo Maria Bianchi et al.
No coin nor oath required. For personal study only.
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.Front Matter ....Pages i-ix
Introduction (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 1-7
Properties and Training in Recurrent Neural Networks (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 9-21
Recurrent Neural Network Architectures (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 23-29
Other Recurrent Neural Networks Models (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 31-39
Synthetic Time Series (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 41-43
Real-World Load Time Series (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 45-55
Experiments (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 57-69
Conclusions (Filippo Maria Bianchi, Enrico Maiorino, Michael C. Kampffmeyer, Antonello Rizzi, Robert Jenssen)....Pages 71-72
Artificial Intelligence (incl. Robotics)
๐ SIMILAR VOLUMES
This research examines and analyzes the use of neural networks as a forecasting tool. Specifically a neural network's ability to predict future trends of Stock Market Indices is tested. Accuracy is compared against a traditional forecasting method, multiple linear regression analysis. Finally, the p
<p>"Analyzes the behavior, design, and implementation of artificial recurrent neural networks. Offers methods of synthesis for associative memories. Evaluates the qualitative properties and limitations of neural networks. Contains practical applications for optimal system performance."</p>
In the present book we concern ourselves exclusively with the qualitative analysis and synthesis of recurrent artificial neural networks. There is an abundance of papers, monographs, and books that address qualitative properties of such networks. However, whereas in these works, the analysis of the
<p>Since the outstanding and pioneering research work of Hopfield on recurrent neural networks (RNNs) in the early 80s of the last century, neural networks have rekindled strong interests in scientists and researchers. Recent years have recorded a remarkable advance in research and development work
The Article of Patricia M. West; Patrick L. Brockett; Linda L. Golden<br/>Marketing Science, Vol. 16, No. 4 (1997), 370-391.<div class="bb-sep"></div>This paper presents a definitive description of neural network methodology and provides an evaluation of its advantages and disadvantages relative to