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.

A novel neural model to electrical load forecasting in transformers

The paper describes a novel neural model to electrical load forecasting in transformers. The network acts as identifier of structural features to forecast process. So that output parameters can be estimated and generalized from an input parameter set. The model was trained and assessed through load data extracted from a Brazilian Electric Utility taking into account time, current, tension, active power in the three phases of the system. The results obtained in the simulations show that the developed technique can be used as an alternative tool to become more appropriate for planning of electric power systems.

Analysis of forecasting capabilities of ground surfaces valuation using artificial neural networks

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

Electrical load forecasting formulation by a fast neural network

The objective of this work is to develop a methodology for electric load forecasting based on a neural network. Here, backpropagation algorithm is used with an adaptive process that based on fuzzy logic and using a decaying exponential function to avoid instability in the convergence process. This methodology results in fast training, when compared to the conventional formulation of backpropagation algorithm. The results are presented using data from a Brazilian Electric Company, and shows a very good performance for the proposal objective.

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.

Multinodal Load Forecasting in Power Electric Systems using a Neural Network with Radial Basis Function

In this paper we present the results of the use of a methodology for multinodal load forecasting through an artificial neural network-type Multilayer Perceptron, making use of radial basis functions as activation function and the Backpropagation algorithm, as an algorithm to train the network. This methodology allows you to make the prediction at various points in power system, considering different types of consumers (residential, commercial, industrial) of the electric grid, is applied to the problem short-term electric load forecasting (24 hours ahead). We use a database (Centralised Dataset - CDS) provided by the Electricity Commission de New Zealand to this work.

Multi-Agent Simulation of Urban Social Dynamics for Spatial Load Forecasting

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A Cellular Automaton Approach to Spatial Electric Load Forecasting

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Short-Term Multinodal Load Forecasting Using a Modified General Regression Neural Network

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

ALGORITHM FOR PROBABILISTIC ANALYSIS of DISTRIBUTION SYSTEMS WITH DISTRIBUTED GENERATION

In this paper an efficient algorithm for probabilistic analysis of unbalanced three-phase weakly-meshed distribution systems is presented. This algorithm uses the technique of Two-Point Estimate Method for calculating the probabilistic behavior of the system random variables. Additionally, the deterministic analysis of the state variables is performed by means of a Compensation-Based Radial Load Flow (CBRLF). Such load flow efficiently exploits the topological characteristics of the network. To deal with distributed generation, a strategy to incorporate a simplified model of a generator in the CBRLF is proposed. Thus, depending on the type of control and generator operation conditions, the node with distributed generation can be modeled either as a PV or PQ node. To validate the efficiency of the proposed algorithm, the IEEE 37 bus test system is used. The probabilistic results are compared with those obtained using the Monte Carlo method.

Análise de risco da ocorrência de Sigatoka-negra baseada em modelos polinomiais: um estudo de caso

A Sigatoka-negra (Mycosphaerella fijiensis) ameaça os bananais comerciais em todas as áreas produtoras do mundo e provoca danos quantitativos e qualitativos na produção, acarretando sérios prejuízos financeiros. Faz-se necessário o estudo da vulnerabilidade das plantas em diversos estádios de desenvolvimento e das condições climáticas favoráveis à ocorrência da doença. Objetivou-se com este trabalho desenvolver um modelo probabilístico baseado em funções polinomiais que represente o risco de ocorrência da Sigatokanegra em função da vulnerabilidade decorrente de fatores intrínsecos à planta e ao ambiente. Realizou-se um estudo de caso, em bananal comercial localizado em Jacupiranga, Vale do Ribeira, SP, considerando o monitoramento semanal do estado da evolução da doença, séries temporais de dados meteorológicos e dados de sensoriamento remoto. Foram gerados mapas georreferenciados do risco da Sigatoka-negra em diferentes épocas do ano. Um modelo para estimar a evolução da doença a partir de imagens de satélite foi obtido com coeficiente de determinação R² igual a 0,9. A metodologia foi desenvolvida para a detecção de épocas e locais que reúnem condições favoráveis à ocorrência da Sigatoka-negra e pode ser aplicada, com os devidos ajustes, em diferentes localidades, para avaliar o risco da ocorrência da doença em polos produtores de banana.

Spatial electric load forecasting using an evolutionary heuristic

A method for spatial electric load forecasting using elements from evolutionary algorithms is presented. The method uses concepts from knowledge extraction algorithms and linguistic rules' representation to characterize the preferences for land use into a spatial database. The future land use preferences in undeveloped zones in the electrical utility service area are determined using an evolutionary heuristic, which considers a stochastic behavior by crossing over similar rules. The method considers development of new zones and also redevelopment of existing ones. The results are presented in future preference maps. The tests in a real system from a midsized city show a high rate of success when results are compared with information gathered from the utility planning department. The most important features of this method are the need for few data and the simplicity of the algorithm, allowing for future scalability.

Implementação de um sistema Collaborative Planning, Forecasting, and Replenishment em uma grande rede de fast food por meio de um prestador de serviços logísticos

A gestão colaborativa é, atualmente, um elemento-chave no contexto da gestão da cadeia de suprimentos. Neste artigo, o tema é abordado mediante a análise de um caso real, em que uma grande rede mundial de fast-food e seu prestador de serviço logístico (PSL) trabalharam conjuntamente no Brasil em um projeto-piloto para a implementação de um collaborative planning, forecasting, and replenishment (CPFR). O trabalho faz uso de uma metodologia de pesquisa-ação e apresenta as principais variáveis que influenciaram o projeto, abordando os processos necessários para a implementação e os pontos que favorecem o CPFR. Com base no caso estudado, o trabalho apresenta um conjunto de propostas sobre o papel dos agentes da cadeia em projetos dessa natureza. A gestão da cadeia de suprimentos por intermédio da coordenação direta de um PSL também permite demonstrar as possibilidades e dificuldades desse sistema, contribuindo com a visão colaborativa na cadeia de suprimentos a partir da relação entre seus agentes.

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 probabilistic model for elastic-plastic fracture analysis of plane and axisymmetric structures

This work presents a methodology for elastic-plastic fracture reliability analysis of plane and axisymmetric structures. The structural reliability analysis is accomplished by means of the FORM analytical method. The virtual crack extension technique based on a direct minimization of potencial energy is utililized for the calculation of the energy release rate. Results are presented to illustrate the performance of the adopted methodology.