Alexandre P. Alves da Silva

Automatic Kernel Based Models for Short Term Load Forecasting

The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high nonconvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.

A Hierarchical Self-Organizing Map Model in Short-Term Load Forecasting

This paper proposes a novel neural model to the problem of short-term load forecasting. The neural model is made up of two self-organizing map nets – one on top of the other. It has been successfully applied to domains in which the context information given by former events plays a primary role. The model was trained and assessed on load data extracted from a Brazilian electric utility. It was required to predict once every hour the electric load during the next 24 hours. The paper presents the results, and evaluates them.

Noninvasive monitoring of residential loads

This paper presents a new methodology for the noninvasive identification of residential loads. The main goal is to develop a prototype capable to determine in real-time consumers loads based upon their energy signatures. The mathematical modeling is based on identification using signal processing techniques. Both simulation and measurements were considered in the analysis.

Chaos theory applied to input space representation of autonomous neural network-based short-term load forecasting models

After 1991, the literature on load forecasting has been dominated by neural network based proposals. However, one major risk in using neural models is the possibility of excessive training, i.e., data overfitting. The extent of nonlinearity provided by neural network based load forecasters, which depends on the input space representation, has been adjusted using heuristic procedures. The empirical nature of these procedures makes their application cumbersome and time consuming. Autonomous modeling including automatic input selection and model complexity control has been proposed recently for short-term load forecasting. However, these techniques require the specification of an initial input set that will be processed by the model in order to select the most relevant variables. This paper explores chaos theory as a tool from non-linear time series analysis to automatic select the lags of the load series data that will be used by the neural models. In this paper, Bayesian inference applied to multi-layered perceptrons and relevance vector machines are used in the development of autonomous neural models.

Fully Automatic Bayesian Neural Forecaster - NN GC1

This paper combines several techniques to generate a fully data-driven forecasting model. Input selection is performed, without user intervention, by applying chaos theory and Bayesian inference. Afterwards, neural network models are estimated, without cross-validation, relying on data partitioning and Bayesian regularization for complexity control. Automatic data clustering has been used for data partitioning. The proposed forecasting model has been tested with datasets provided by the competition organizers.

Aplicação da transformada wavelet discreta na previsão de carga a curto prazo via redes neurais

The importance of short-term load forecasting has been increasing lately. With deregulation and competition, energy price forecasting has become a big business. Bus-load forecasting is essential to feed analytical methods utilized for determining energy prices. The variability and non-stationarity of loads are becoming worse due to the dynamics of energy prices. Besides, the number of nodal loads to be predicted does not allow frequent interventions from load forecasting experts. More autonomous load predictors are needed in the new competitive scenario. This paper proposes a novel wavelet transform-based technique for short-term load forecasting via neural networks. Its main goal is to develop more robust load forecasters. Two whole years of load data from a North-American electric utility has been used in order to test the proposed methodology.