Victor Sauchelli

Time Series Forecasting Using Bayesian Method: Application to Cumulative Rainfall

In this work an algorithm to adjust parameters using a Bayesian method for cumulative rainfall time series forecasting implemented by an ANN-filter is presented. The criterion of adjustment comprises to generate a posterior probability distribution of time series values from forecasted time series, where the structure is changed by considering a Bayesian inference. These are approximated by the ANN based predictor in which a new input is taken in order for changing the structure and parameters of the filter. The proposed technique is based on the prior distribution assumptions. Predictions are obtained by weighting up all possible models and parameter values according to their posterior distribution. Furthermore, if the time series is smooth or rough, the fitting algorithm can be changed to suit, in function of the long or short term stochastic dependence of the time series, an on-line heuristic law to set the training process, modify the NN topology, change the number of patterns and iterations in addition to the Bayesian inference in accordance with Hurst parameter H taking into account that the series forecasted has the same H as the real time series. The performance of the approach is tested over a time series obtained from samples of the Mackey-Glass delay differential equations and cumulative rainfall time series from some geographical points of Cordoba, Argentina.

Rainfall Forecasting Using Sub sampling Nonparametric Methods

This article presents a comparison of two sub sampling nonparametric methods for designing algorithms to forecast time series from the cumulative monthly rainfall. Both approaches are based on artificial feed-forward neural networks ANNs. The main contribution is to divide the rainfall time series forecasting problem using non-parametric methods by subdivision into stages of smoothing, so in this manner the time series are smoothed in order to simplify the prediction problem. The first case depicts an algorithm to forecast high roughness time series that set the parameters of a nonlinear autoregressive model NAR based on ANNs, which uses as a reference the Hurst parameter associated to the time series. The second case, the methodology consists of generating smoothing time series by sampling the time series data, and each individual time series is associated with a predictor filter. Thus, depending on the data, others time series are obtained by sampling with an increasing interval. For each one of the time series generated, a specific ANN-based filter is adjusted, and each one generates a forecast that is then averaged among other subsamples time series, resulting so in a mix of predictor filters. The results are evaluated on high roughness time series from the Mackey Glass Equation MG and from cumulative monthly historical rainfall data from one geographic location. The results are encouraging; deserve study and investment in implementation effort for the geographical locations of interest.

Energy Associated Tuning Method for Short-Term Series Forecasting by Complete and Incomplete Datasets

Abstract This article presents short-term predictions using neural networks tuned by energy associated to series based-predictor filter for complete and incomplete datasets. A benchmark of high roughness time series from Mackay Glass (MG), Logistic (LOG), Henon (HEN) and some univariate series chosen from NN3 Forecasting Competition are used. An average smoothing technique is assumed to complete the data missing in the dataset. The Hurst parameter estimated through wavelets is used to estimate the roughness of the real and forecasted series. The validation and horizon of the time series is presented by the 15 values ahead. The performance of the proposed filter shows that even a short dataset is incomplete, besides a linear smoothing technique employed; the prediction is almost fair by means of SMAPE index. Although the major result shows that the predictor system based on energy associated to series has an optimal performance from several chaotic time series, in particular, this method among other provides a good estimation when the short-term series are taken from one point observations.

A New Approach for Time Series Forecasting: Bayesian Enhanced by Fractional Brownian Motion with Application to Rainfall Series

A new predictor algorithm based on Bayesian enhanced approach (BEA) for long-term chaotic time series using artificial neural networks (ANN) is presented. The technique based on stochastic models uses Bayesian inference by means of Fractional Brownian Motion as model data and Beta model as prior information. However, the need of experimental data for specifying and estimating causal models has not changed. Indeed, Bayes method provides another way to incorporate prior knowledge in forecasting models; the simplest representations of prior knowledge in forecasting models are hard to beat in many forecasting situations, either because prior knowledge is insufficient to improve on models or because prior knowledge leads to the conclusion that the situation is stable. This work contributes with long-term time series prediction, to give forecast horizons up to 18 steps ahead. Thus, the forecasted values and validation data are presented by solutions of benchmark chaotic series such as Mackey-Glass, Lorenz, Henon, Logistic, Rossler, Ikeda, Quadratic one-dimensional map series and monthly cumulative rainfall collected from Despenaderos, Cordoba, Argentina. The computational results are evaluated against several non-linear ANN predictors proposed before on high roughness series that shows a better performance of Bayesian Enhanced approach in long-term forecasting.

Improving Out-of-Band Power Emissions in OFDM Systems using Double-length Symbols

A method that improves the out-of-band power emissions in wireless systems that use orthogonal frequency division multiplexing (OFDM) in their air interface is proposed in this paper. The key idea behind this approach is to obtain the output signal using an inverse discrete Fourier transform (IDFT) calculation with double length, when compared to the single-length IDFT computation that takes place in a conventional OFDM system. Double-length symbols provide implicit continuity in half of the original union points of the whole transmission, and can be used in conjunction with other well-known techniques already proposed in the literature (e.g., spectral precoding). The use of cyclic prefix and suffix strategies is also presented for time-varying channels, enabling the accommodation of the output signal in the same original bandwidth (i.e., without affecting the sampling rate). Obtained results show important reductions in the out-of-band power emissions, which can be even further improved when combined with rate-one spectral precoding techniques. Since the output signal is completely obtained in a digital way, the proposed approach is suitable for future applications that are foreseen in the area of software defined radio (SDR) and cognitive radio (CR).

Short time series prediction: Bayesian enhanced modified approach with application to cumulative rainfall series

This article contributes with short time series prediction with complete and incomplete datasets based on a new framework by means of Bayesian enhanced modified approach BEMA combining permutation entropy. The focus of the proposed filter with particularly interest in incomplete datasets or missing data is by changing the structure of the predictor filter according to data model selected, in which the Bayesian approach can be combined with entropic information of the series. The simplest method adopted to imputing the missing data on the dataset is by linear average smoothing, then computational results are evaluated on high roughness time series selected from benchmark series, in which they are compared with artificial neural networks ANN nonlinear filters such as Bayesian enhanced approach BEA and Bayesian approach BA proposed in recent work, in order to show a better performance of BEMA filter. These results support the applicability of permutation entropy in analysing the dynamic behaviour of chaotic time series for short series predictions.

Long-term power consumption demand prediction: A comparison of energy associated and Bayesian modeling approach

This paper contributes with two different prediction approaches for long-term power consumption demand prediction using an artificial neural networks (ANN) short-term time series predictor filter. The techniques proposed here are non-linear stochastic models using the energy associated to series and Bayesian inference, implemented by ANN. The system has the advantage of requiring as input only the historical demand time series of power consumption and allows its extension to a forecast medium and long term 3-6-12-18 months forward. The paper predicts the power consumption in the area covered by the country during the period January 1980-November 2013 in Argentina. Thus, the next 18 forecasted values are presented by the evolution of total monthly power consumption demand of the National Interconnected System of Argentina. The computational results of the prediction comparison are evaluated against the classical non-linear ANN predictor on high roughness short term chaotic time series that shows a better performance of Bayesian approach in long-short-term forecasting.

Artificial Neural Network Applied to The Problem of Secondary Voltage Control

This paper presents the design of a controller based on an Artificial Neural Network (ANN) for the problem of the Secondary Voltage Control (SVC) in Electrical Power Systems (EPS). The design is based on the concept of Optimal Power Flow (OPF) and Pilots Nodes (PN), the obtained Controller is applied to a study case in order to validate the result. Finally the influence of various parameters that make the topology of a Neural Network are analyzed.

Noisy Chaotic time series forecast approximated by combining Reny's entropy with Energy associated to series method: application to rainfall series

This article proposes that the combination of smoothing approach considering the entropic information provided by Renyis method, has an acceptable performance in term of forecasting errors. The methodology of the proposed scheme is examined through benchmark chaotic time series, such as Mackey Glass, Lorenz, Henon maps, the Lynx and rainfall from Santa Francisca - Cordoba, with addition of white noise by using neural networks-based energy associated (EAS) predictor filter modified by Renyis entropy of the series. When the time series is short or long, the underlying dynamical system is nonlinear and temporal dependencies span long time intervals, in which this are also called long memory process. In such cases, the inherent nonlinearity of neural networks models and a higher robustness to noise seem to partially explain their better prediction performance when entropic information is extracted from the series. Then, to demonstrate that permutation entropy is computationally efficient, robust to outliers, and effective to measure complexity of time series, computational results are evaluated against several non-linear ANN predictors to show the predictability of noisy rainfall and chaotic time series reported in the literature.

Short-series Prediction with BEMA Approach: application to short rainfall series

This paper contributes with short time series prediction for complete and incomplete datasets based on a new framework by means of Bayesian enhanced modified approach (BEMA) combining permutation entropy. The focus of the proposed filter with particularly interest in incomplete datasets or missing data is by changing the structure of the predictor filter according to data model selected, in which the Bayesian approach can be combined with entropic information of the series. The simplest method adopted to imputing the missing data on the dataset is by linear average smoothing, then computational results are evaluated on high roughness time series selected from benchmark series, in which they are compared with artificial neural networks (ANN) nonlinear filters such as Bayesian Enhanced approach (BEA) and Bayesian Approach (BA) proposed in recent work, in order to show a better performance of BEMA filter. These results support the applicability of permutation entropy in analyzing the dynamic behavior of chaotic time series for short series predictions.