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.

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

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Singular value analyses of voltage stability on power system considering wind generation variability

Pós-graduação em Engenharia Elétrica - FEIS

The climatic rhythm and blooms of cyanobacteria in a tropical reservoir in São Paulo, Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Attraction of the sand fly Nyssomyia neivai (Diptera: Psychodidae) to chemical compounds in a wind tunnel

Background: Similar to other hematophagous insects, male and female sand flies must feed on plants to obtain sugar and, subsequently, energy to complete their life cycles. A large number of compounds emitted by plants may act as volatile signals to these insects. Primary alcohols have been detected in some plants, but in small amounts. In a previous report, the attractiveness of saturated primary alcohols with 7 to 9 carbons was evaluated for Lutzomyia longipalpis, the vector of American visceral leishmaniasis, with positive results.Methods: In the present study, a wide range of primary alcohols, 3 to 10 carbons, were tested to investigate their attractiveness to another sand fly species, Nyssomyia neivai, a putative vector of American cutaneous leishmaniasis. The mixture of compounds that induced the best sand fly response was also evaluated.Results: Of the eight compounds evaluated, hexanol and octanol elicited the best attractive responses for sand fly females.Conclusion: Phytochemicals may be an interesting source of search for new sand fly attractants.

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)

Energetic exploitation from a hybrid PV-wind power micro-generation rural electrification

Hybrid system micro-generation integration of PV-wind power is presented by a form of energy in which problems resulting from variability in the intensity of wind and solar intensity are possible mitigation either by complementation between one source to another or the largest stability configured by the generate the system. Based on this context, this work aims to assessing the performance of a hybrid system PV-wind power energy small of a rural property for their electrification. The study has been developed at the Rural Laboratory Powering from Engineering Department of UNESP. In order to present this research, a hybrid system has been installed PV-wind power, composed of one 400Wp windmill and a 300 Wp PV-system. The results obtained allowed us to evaluate the solar and wind energy supplied ranked among 285 and 360 kWh electric power generated by the PV-wind power hybrid system stood between 25,5 and 31 kWh. At is to say achieving yield of approximately than 10% during one year observation period, i.e., it was concluded that the performance of the hybrid system depended essentially the energy received and generated by the PV-system and that there was complementation between generating wind power and PV-systems with regard to time of day and the annual seasons by confirming the technical feasibility of this kind system of micro-generation in small rural properties.

The feasibility of using wind energy for rural populations lacking electric power in Brazil

In the wake of current global image involving environmental impacts, the use of wind power has had a remarkable growth in recent years as a technique for generating electricity. In fact, it is a source featuring strong dissemination of technology which provides decrease in costs and a greater access to low-income electricity. PROINFA (Incentive Program for Alternative Energy Sources) promotes a greater diffusion of new technologies for power generation, in particular wind-produced. Due to such a scenario on the exploitation of such energy source, current analysis discusses strategies for the development of domestic wind technology and the implications for electricity-lacking rural areas. Analysis shows a similar behavior between rural populations lacking electricity and the amount of potential energy available in the region. It is expected that this assay will contribute towards the establishment of public policies for wind-energy parks on rural farms in the North and Northeast regions of Brazil.

Nebraska Wind Power: A Comparitive Study of Knowledge and Attitudes

Abstract The goal of this project is to assess the knowledge and attitudes of Nebraskans on the issue of wind power. The point of this research is to learn whether the presence of wind power has a positive effect on a person’s knowledge about and attitudes toward wind power and wind turbines. Using mail surveys, qualitative and quantitative data were collected from the towns of Pierce and Ainsworth Nebraska. The surveys aided in seeing patterns of knowledge about wind power and wind turbines and positive and negative attitudes and major concerns regarding wind power.

The Evolution of Sonata Form in the Wind Music of W.A. Mozart

Mozart’s wind music occupies a rather small space in the overall scope of his compositional output, numbering a total of ten works. Yet when viewed in the larger context of Mozart’s life, the wind music was written over the span of nine years, encompassing a large period from his youth up to his last decade in Vienna. Ranging from the simple divertimenti (K. 166 and 186) through the Tafelmusik (K. 213, 240, 252, 253 and 270) and finally culminating in the three Serenades (K. 361, 375 and 388), the wind music demonstrates Mozart’s maturation in wind writing, and also serves to illustrate the evolution in his use of sonata forms.

A cyclic bipolar wind in the interacting binary V 393 Scorpii

V393 Scorpii is a double periodic variable characterized by a relatively stable non-orbital photometric cycle of 253 d. Mennickent et al. argue for the presence of a massive optically thick disc around the more massive B-type component and describe the evolutionary stage of the system. In this paper, we analyse the behaviour of the main spectroscopic optical lines during the long non-orbital photometric cycle. We study the radial velocity of the donor determining its orbital elements and find a small but significant orbital eccentricity (e = 0.04). The donor spectral features are modelled and removed from the spectrum at every observing epoch using the light-curve model given by Mennickent et al. We find that the line emission is larger during eclipses and mostly comes from a bipolar wind. We also find that the long cycle is explained in terms of a modulation of the wind strength; the wind has a larger line and continuum emissivity at the high state. We report the discovery of highly variable chromospheric emission in the donor, as revealed by the Doppler maps of the emission lines Mg II 4481 and C I 6588. We discuss notable and some novel spectroscopic features like discrete absorption components, especially visible at blue depressed O I 7773 absorption wings during the second half-cycle, Balmer double emission with V/R curves showing 'Z-type' and 'S-type' excursions around secondary and main eclipses, respectively, and H beta emission wings extending up to +/- 2000 km s(-1). We also discuss possible causes for these phenomena and for their modulations with the long cycle.

Improved low-voltage-ride-through capability of fixed-speed wind turbines using decentralised control of STATCOM with energy storage system

The design and implementation of a new control scheme for reactive power compensation, voltage regulation and transient stability enhancement for wind turbines equipped with fixed-speed induction generators (IGs) in large interconnected power systems is presented in this study. The low-voltage-ride-through (LVRT) capability is provided by extending the range of the operation of the controlled system to include typical post-fault conditions. A systematic procedure is proposed to design decentralised multi-variable controllers for large interconnected power systems using the linear quadratic (LQ) output-feedback control design method and the controller design procedure is formulated as an optimisation problem involving rank-constrained linear matrix inequality (LMI). In this study, it is shown that a static synchronous compensator (STATCOM) with energy storage system (ESS), controlled via robust control technique, is an effective device for improving the LVRT capability of fixed-speed wind turbines.

Analysis of NDVI time series using cross-correlation and forecasting methods for monitoring sugarcane fields in Brazil

Brazil is the largest sugarcane producer in the world and has a privileged position to attend to national and international market places. To maintain the high production of sugarcane, it is fundamental to improve the forecasting models of crop seasons through the use of alternative technologies, such as remote sensing. Thus, the main purpose of this article is to assess the results of two different statistical forecasting methods applied to an agroclimatic index (the water requirement satisfaction index; WRSI) and the sugarcane spectral response (normalized difference vegetation index; NDVI) registered on National Oceanic and Atmospheric Administration Advanced Very High Resolution Radiometer (NOAA-AVHRR) satellite images. We also evaluated the cross-correlation between these two indexes. According to the results obtained, there are meaningful correlations between NDVI and WRSI with time lags. Additionally, the adjusted model for NDVI presented more accurate results than the forecasting models for WRSI. Finally, the analyses indicate that NDVI is more predictable due to its seasonality and the WRSI values are more variable making it difficult to forecast.

Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

This paper addressed the problem of water-demand forecasting for real-time operation of water supply systems. The present study was conducted to identify the best fit model using hourly consumption data from the water supply system of Araraquara, Sa approximate to o Paulo, Brazil. Artificial neural networks (ANNs) were used in view of their enhanced capability to match or even improve on the regression model forecasts. The ANNs used were the multilayer perceptron with the back-propagation algorithm (MLP-BP), the dynamic neural network (DAN2), and two hybrid ANNs. The hybrid models used the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called ANN-H and DAN2-H, respectively. The tested inputs for the neural network were selected literature and correlation analysis. The results from the hybrid models were promising, DAN2 performing better than the tested MLP-BP models. DAN2-H, identified as the best model, produced a mean absolute error (MAE) of 3.3 L/s and 2.8 L/s for training and test set, respectively, for the prediction of the next hour, which represented about 12% of the average consumption. The best forecasting model for the next 24 hours was again DAN2-H, which outperformed other compared models, and produced a MAE of 3.1 L/s and 3.0 L/s for training and test set respectively, which represented about 12% of average consumption. DOI: 10.1061/(ASCE)WR.1943-5452.0000177. (C) 2012 American Society of Civil Engineers.