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)

An effortless hybrid method to solve economic load dispatch problem in power systems

This paper proposes a new approach and coding scheme for solving economic dispatch problems (ED) in power systems through an effortless hybrid method (EHM). This novel coding scheme can effectively prevent futile searching and also prevents obtaining infeasible solutions through the application of stochastic search methods, consequently dramatically improves search efficiency and solution quality. The dominant constraint of an economic dispatch problem is power balance. The operational constraints, such as generation limitations, ramp rate limits, prohibited operating zones (POZ), network loss are considered for practical operation. Firstly, in the EHM procedure, the output of generator is obtained with a lambda iteration method and without considering POZ and later in a genetic based algorithm this constraint is satisfied. To demonstrate its efficiency, feasibility and fastness, the EHM algorithm was applied to solve constrained ED problems of power systems with 6 and 15 units. The simulation results obtained from the EHM were compared to those achieved from previous literature in terms of solution quality and computational efficiency. Results reveal that the superiority of this method in both aspects of financial and CPU time. (C) 2011 Elsevier Ltd. All rights reserved.

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

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Artificial neural networks for load flow and external equivalents studies

In this paper an artificial neural network (ANN) based methodology is proposed for (a) solving the basic load flow, (b) solving the load flow considering the reactive power limits of generation (PV) buses, (c) determining a good quality load flow starting point for ill-conditioned systems, and (d) computing static external equivalent circuits. An analysis of the input data required as well as the ANN architecture is presented. A multilayer perceptron trained with the Levenberg-Marquardt second order method is used. The proposed methodology was tested with the IEEE 30- and 57-bus, and an ill-conditioned 11-bus system. Normal operating conditions (base case) and several contingency situations including different load and generation scenarios have been considered. Simulation results show the excellent performance of the ANN for solving problems (a)-(d). (C) 2010 Elsevier B.V. All rights reserved.

Efeito do ácido zoledrônico em tíbias de ratas ooforectomizadas: estudo prospectivo e randomizado

OBJETIVO: Investigar as repercussões clínicas, biomecânicas e histomorfométricas do ácido zoledrônico em tíbias de ratas osteoporóticas, após ooforectomia bilateral. MÉTODOS: Foram estudadas, prospectivamente, 40 ratas da linhagem Wistar (Rattus novergicus albinus). Com 60 dias de vida, os animais foram aleatorizados em dois grupos de acordo com o procedimento cirúrgico: ooforectomia bilateral (O) (n=20) e pseudo-cirurgia (sham) (P) (n=20). Após 30 dias, os animais foram divididos em quatro subgrupos, de acordo com a administração de 0,1mg/kg de ácido zoledrônico (AZ) ou água destilada (AD): OAZ (n=10), OAD (n=10), PAZ (n=10) e PAD (n=10). Após 12 meses, os animais foram eutanasiados e suas tíbias analisadas. No estudo clínico foi considerado o peso dos animais; no estudo biomecânico foram realizados ensaios compressivos e na análise histomorfométrica foi determinada a área trabecular óssea. RESULTADOS: Os grupos O tiveram aumento de peso significativamente maior que os grupos P (p=0,005). Os grupos OAZ e PAZ tiveram aumento, não significativo, de peso quando comparados aos grupos OAD (p=0,47) e PAD (p=0,68). Os grupos com ácido zoledrônico e com água destilada suportaram carga máxima, semelhante (p=0,2), no momento em que ocorreu fratura. Nos grupos com ácido zoledrônico verificou-se o aumento não significante da área trabecular óssea quando comparados aos grupos com água destilada (p=0,21). Houve correlação positiva entre a área trabecular e a carga máxima (p=0,04; r=0,95). CONCLUSÃO: O ácido zoledrônico não influiu significativamente no peso dos animais. Os resultados mostraram aumento, não significante, tanto da resistência óssea diafisária tibial, como da área trabecular óssea.

Platform Switching: Biomechanical Evaluation Using Three-Dimensional Finite Element Analysis

Purpose: The objective of this study was to evaluate, using three-dimensional finite element analysis (3D FEA), the stress distribution in peri-implant bone tissue, implants, and prosthetic components of implant-supported single crowns with the use of the platform-switching concept. Materials and Methods: Three 3D finite element models were created to replicate an external-hexagonal implant system with peri-implant bone tissue in which three different implant-abutment configurations were represented. In the regular platform (RP) group, a regular 4.1-mm-diameter abutment (UCLA) was connected to regular 4.1-mm-diameter implant. The platform-switching (PS) group was simulated by the connection of a wide implant (5.0 mm diameter) to a regular 4.1-mm-diameter UCLA abutment. In the wide-platform (WP) group, a 5.0-mm-diameter UCLA abutment was connected to a 5.0-mm-diameter implant. An occlusal load of 100 N was applied either axially or obliquely on the models using ANSYS software. Results: Both the increase in implant diameter and the use of platform switching played roles in stress reduction. The PS group presented lower stress values than the RP and WP groups for bone and implant. In the peri-implant area, cortical bone exhibited a higher stress concentration than the trabecular bone in all models and both loading situations. Under oblique loading, higher intensity and greater distribution of stress were observed than under axial loading. Platform switching reduced von Mises (17.5% and 9.3% for axial and oblique loads, respectively), minimum (compressive) (19.4% for axial load and 21.9% for oblique load), and maximum (tensile) principal stress values (46.6% for axial load and 26.7% for oblique load) in the peri-implant bone tissue. Conclusion: Platform switching led to improved biomechanical stress distribution in peri-implant bone tissue. Oblique loads resulted in higher stress concentrations than axial loads for all models. Wide-diameter implants had a large influence in reducing stress values in the implant system. INT J ORAL MAXILLOFAC IMPLANTS 2011;26:482-491

THE EFFECT of E-GLASS FIBERS and ACRYLIC RESIN THICKNESS on FRACTURE LOAD IN A SIMULATED IMPLANT-SUPPORTED OVERDENTURE PROSTHESIS

Statement of problem. Implant overdenture prostheses are prone to acrylic resin fracture because of space limitations around the implant overdenture components.Purpose. The purpose of this study was to evaluate the influence of E-glass fibers and acrylic resin thickness in resisting acrylic resin fracture around a simulated overdenture abutment.Material and methods. A model was developed to simulate the clinical situation of an implant overdenture abutment with varying acrylic resin thickness (1.5 or 3.0 mm) with or without E-glass fiber reinforcement. Forty-eight specimens with an underlying simulated abutment were divided into 4 groups (n=12): 1.5 mm acrylic resin without E-glass fibers identified as thin with no E-glass fiber mesh (TN-N); 1.5 mm acrylic resin with E-glass fibers identified as thin with E-glass fiber mesh (TN-F); 3.0 mm acrylic resin without E-glass fibers identified as thick without E-glass fiber mesh (TK-N); and 3.0 mm acrylic resin with E-glass fibers identified as thick with E-glass fiber mesh (TK-F). All specimens were submitted to a 3-point bending test and fracture loads (N) were analyzed with a 2-way ANOVA and Tukey's post hoc test (alpha=.05).Results. The results revealed significant differences in fracture load among the 4 groups, with significant effects from both thickness (P<.001) and inclusion of the mesh (P<.001). Results demonstrated no interaction between mesh and thickness (P=.690). The TN-N: 39 +/- 5 N; TN-F: 50 +/- 6.9 N; TK-N: 162 +/- 13 N; and TK-F: 193 +/- 21 N groups were all statistically different (P<.001).Conclusions. The fracture load of a processed, acrylic resin implant-supported overdenture can be significantly increased by the addition of E-glass fibers even when using thin acrylic resin sections. on a relative basis, the increase in fracture load was similar when adding E-glass fibers or increasing acrylic resin thickness. (J Prosthet Dent 2011;106:373-377)

Mechanical behavior of ceramic veneer in zirconia-based restorations: a 3-dimensional finite element analysis using microcomputed tomography data

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