Determining spatial resolution in spatial load forecasting using a grid-based model

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Previsão de vendas para uma indústria de equipamentos pesados: seleção de técnicas e análise

The continuous advance of the Brazilian economy and increased competition in the heavy equipment market, increasingly point to the need for accurate sales forecasting processes, which allow an optimized strategic planning and therefore better overall results. In this manner, we found that the sales forecasting process deserves to be studied and understood, since it has a key role in corporate strategic planning. Accurate forecasting methods enable direction of companies to circumvent the management difficulties and the variations of finished goods inventory, which make companies more competitive. By analyzing the stages of the sales forecasting it was possible to observe that this process is methodical, bureaucratic and demands a lot of training for their managers and professionals. In this paper we applied the modeling method and the selecting process which has been done for Armstrong to select the most appropriate technique for two products of a heavy equipment industry and it has been through this method that the triple exponential smoothing technique has been chosen for both products. The results obtained by prediction with the triple exponential smoothing technique were better than forecasts prepared by the industry experts

Estimation of a preference map of new consumers for spatial load forecasting simulation methods using a spatial analysis of points

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Electric load forecasting using a fuzzy ART&ARTMAP neural network

This work presents a neural network based on the ART architecture ( adaptive resonance theory), named fuzzy ART& ARTMAP neural network, applied to the electric load-forecasting problem. The neural networks based on the ARTarchitecture have two fundamental characteristics that are extremely important for the network performance ( stability and plasticity), which allow the implementation of continuous training. The fuzzy ART& ARTMAP neural network aims to reduce the imprecision of the forecasting results by a mechanism that separate the analog and binary data, processing them separately. Therefore, this represents a reduction on the processing time and improved quality of the results, when compared to the Back-Propagation neural network, and better to the classical forecasting techniques (ARIMA of Box and Jenkins methods). Finished the training, the fuzzy ART& ARTMAP neural network is capable to forecast electrical loads 24 h in advance. To validate the methodology, data from a Brazilian electric company is used. (C) 2004 Elsevier B.V. All rights reserved.

The use of simulation for forecasting the number of docks necessary in an expedition department

The simulation is a very powerful tool to develop more efficient systems, hence it is been widely used with the goal of productivity improvement. Its results, if compared with other methods, are not always optimum; however, if the experiment is rightly elaborated, its results will represent the real situation, enabling its use with a good level of reliability. This work used the simulation (through the ProModel (R) software) in order to study, understand, model and improve the expenditure system of an enterprise, with a premise of keeping the production-delivery flow considering quick, controlled and reliable conditions.

A fast electric load forecasting using neural networks

The objective of this work is the development of a methodology for electric load forecasting based on a neural network. Here, it is used Backpropagation algorithm with an adaptive process based on fuzzy logic. This methodology results in fast training, when compared to the conventional formulation of Backpropagation algorithm. Results are presented using data from a Brazilian Electric Company and the performance is very good for the proposal objective.

The bias in reversing the Box-Cox transformation in time series forecasting: An empirical study based on neural networks

The Box-Cox transformation is a technique mostly utilized to turn the probabilistic distribution of a time series data into approximately normal. And this helps statistical and neural models to perform more accurate forecastings. However, it introduces a bias when the reversion of the transformation is conducted with the predicted data. The statistical methods to perform a bias-free reversion require, necessarily, the assumption of Gaussianity of the transformed data distribution, which is a rare event in real-world time series. So, the aim of this study was to provide an effective method of removing the bias when the reversion of the Box-Cox transformation is executed. Thus, the developed method is based on a focused time lagged feedforward neural network, which does not require any assumption about the transformed data distribution. Therefore, to evaluate the performance of the proposed method, numerical simulations were conducted and the Mean Absolute Percentage Error, the Theil Inequality Index and the Signal-to-Noise ratio of 20-step-ahead forecasts of 40 time series were compared, and the results obtained indicate that the proposed reversion method is valid and justifies new studies. (C) 2014 Elsevier B.V. All rights reserved.