ANN versus Grey theory based forecasting methods implemented on short time series

Abstract

Two modern concepts implemented for forecasting based on reduced time series are contrasted. Results obtained by use of artificial neural nets (ANNs), already discussed at this conference, are compared with the ones obtained by implementation of the so called Grey theory or Grey Model (GM). Particularly, feed-forward accommodated for prediction (FFAP) and time controlled recurrent (TCR) ANNs are used along with the GM(1,1) algorithm for one-and two-steps-ahead forecasting of various quantities (obsolete computers, electricity loads, number of fixed telephones etc). Advantages of the ANN concept are observed. The GM(1,1) was studied in the appendix and compared with no advantages against the least-meansquares approximation by an exponential.

Optimization of the upstream bandwidth allocation in passive optical networks using internet users' behavior forecast

“…Since the historical data required by the network operator to forceast users' traffic behavior can be easily obtained and processed with the aim to classify the different customers, the focus will be on time series methods and especially on two major forecasting models, respectively Artificial Neural Networks and Grey theory. Artificial neural network (ANN) represents one of the most popular forecasting paradigms [14]. Classified as a machine learning approach, ANN has the ability to learn from complicated data and deduce its pattern and tendency.…”