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.

Detection and classification of voltage disturbances using a Fuzzy-ARTMAP-wavelet network

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

Cost assessment of efficiency losses in hydroelectric plants

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A Bilevel Approach to Transmission Expansion Planning Within a Market Environment

We present a bilevel model for transmission expansion planning within a market environment, where producers and consumers trade freely electric energy through a pool. The target of the transmission planner, modeled through the upper-level problem, is to minimize network investment cost while facilitating energy trading. This upper-level problem is constrained by a collection of lower-level market clearing problems representing pool trading, and whose individual objective functions correspond to social welfare. Using the duality theory the proposed bilevel model is recast as a mixed-integer linear programming problem, which is solvable using branch-and-cut solvers. Detailed results from an illustrative example and a case study are presented and discussed. Finally, some relevant conclusions are drawn.

Stability analysis of power systems described with detailed models by automatic method

The power system stability analysis is approached taking into explicit account the dynamic performance of generators internal voltages and control devices. The proposed method is not a direct method in the usual sense since conclusion for stability or instability is not exclusively based on energy function considerations but it is automatic since the conclusion is achieved without an analyst intervention. The stability test accounts for the nonconservative nature of the system with control devices such as the automatic voltage regulator (AVR) and automatic generation control (AGC) in contrast with the well-known direct methods. An energy function is derived for the system with machines forth-order model, AVR and AGC and it is used to start the analysis procedure and to point out criticalities. The conclusive analysis itself is made by means of a method based on the definition of a region surrounding the equilibrium point where the system net torque is equilibrium restorative. This region is named positive synchronization region (PSR). Since the definition of the PSR boundaries have no dependence on modelling approximation, the PSR test conduces to reliable results. (C) 2008 Elsevier Ltd. All rights reserved.

Energy system contributions in indoor rock climbing

The present study cross-sectionally investigated the influence of training status, route difficulty and upper body aerobic and anaerobic performance of climbers on the energetics of indoor rock climbing. Six elite climbers (EC) and seven recreational climbers ( RC) were submitted to the following laboratory tests: ( a) anthropometry, (b) upper body aerobic power, and ( c) upper body Wingate test. on another occasion, EC subjects climbed an easy, a moderate, and a difficult route, whereas RC subjects climbed only the easy route. The fractions of the aerobic (WAER), anaerobic alactic (W-PCR) and anaerobic lactic (W-[La(])-) systems were calculated based on oxygen uptake, the fast component of excess post-exercise oxygen uptake, and changes in net blood lactate, respectively. on the easy route, the metabolic cost was significantly lower in EC [ 40.3 ( 6.5) kJ] than in RC [60.1 ( 8.8) kJ] ( P < 0.05). The respective contributions of the WAER, WPCR, and W-[La(])- systems in EC were: easy route = 41.5 (8.1), 41.1 (11.4) and 17.4% (5.4), moderate route = 45.8 (8.4), 34.6 (7.1) and 21.9% (6.3), and difficult route = 41.9 (7.4), 35.8 (6.7) and 22.3% (7.2). The contributions of the WAER, WPCR, and W-[La(])- systems in RC subjects climbing an easy route were 39.7 (5.0), 34.0 (5.8), and 26.3% (3.8), respectively. These results indicate that the main energy systems required during indoor rock climbing are the aerobic and anaerobic alactic systems. In addition, climbing economy seems to be more important for the performance of these athletes than improved energy metabolism.

Cogeneration in a solid-wastes power-station: a case-study

Nowadays, natural gas is viewed as the solution to the problem of energy supply for Latin America, Europe and North America for the next few decades; Brazil is increasingly becoming dependent upon the Bolivian natural-gas supply - many industries and some entrepreneurs are deciding to construct industrial cogeneration systems and new thermal power-stations burning natural gas because of its low environmental impact and attractive price. However, natural gas is a finite resource: this will cause, in the future, an increase of its unit price. This paper details questions involved in the energy generation and presents solid-waste burning as a possible alternative fuel for the future, especially in the context of cogeneration practice in which the thermal and electric energy are used primarily for the industries located in an industrial district. Two cogeneration schemes are proposed for the burning of municipal solid wastes, associated or not with natural gas, and their technical and economic feasibilities are examined. (C) 1999 Elsevier B.V. Ltd. All rights reserved.

A neural approach for determination of global energetic efficiency indicator in groundwater wells

In most of the cases, the systems of water distribution from groundwater wells use electrical submersible pumps. All electrical energy is applied to the pumps; however, other components (pipes, valves, etc.) of these systems are also responsible by the higher or lower consumption of electric energy. The supervisors and operators of the systems should thus have knowledge of the global energetic behavior of the process in order to administrate it properly. This work suggests a 'Global Energetic Efficiency Indicator' for groundwater wells by using mathematical equations and neural networks. Simulation results will be presented in order to demonstrate the validity of the proposed approach.

Allocation of the costs of transmission losses

An analysis of the performance of six major methods of loss allocation for generators and demands was conducted, based on pro-rata (two), on incremental factors (two), on proportional sharing (PS) (one), and on electric circuit theory (one). Using relatively simple examples which can easily be checked, the advantages and disadvantages of each were ascertained and the results confirmed using a larger sample system (IEEE-118). The discussion considers the location and size of generators and demands, as well as the merits of the location of these agents for each configuration based on an analysis of the effect of various network modifications. Furthermore, an application in the South-Southeastern Brazilian Systems is performed. Conclusions and recommendations are presented. (C) 2004 Elsevier B.V. All rights reserved.

Economic and technical feasibility study of a combined-cycle cogeneration system associated with cellulose plants

In this paper, is presented an economical and technical feasibility study of a combined cycle cogeneration system proposed to be used in a pulp plant located in Brazil, where around 95% of country's pulp production is done by the use of Kraft Process. This process allows the use of black liquor and other by-products as fuel. This study is based upon actual data from a pulp plant with a daily production of 1000 tons., that generates part of the energy demanded by the process in a conventional cogeneration system with condensing steam turbine and two extractions. The addition of a gas turbine was studied to compare electricity production level and its related costs between original system and the new one, considering that the former can use industrial by-products and firewood as fuel, when required. Several parameters related to electric generation systems operation and production costs were studied. The use of natural gas in the combined cycle, in comparison with the use of firewood in the conventional system was studied. The advantages of natural gas fuel are highlighted. The surplus availability and the electricity generation costs are presented as a function of pulp and black liquor production.

Thermoeconomic analysis: A criterion for the selection of cogeneration systems

The economical viability of three cogeneration schemes as supplying alternatives for a hypothetical industrial process has been studied. A cost appropriation method based on Valero's studies (1986) has been used. This method enables the determination of exergetic flows, the Second Law efficiency of equipment and the monetary costs of the products acquired by the industrial process (steam and electrical energy). The criterion adopted for the selection is the global cost of the supplied products to the industrial process as regarding in Brazilian conditions.

Control automatico de un sistema electrico mediante logica difusa

Substitution of fuzzy logic control in an electrical system normally controlled by proportional-integral frequency was studied and analyzed. A linear model of an electrical system, the concepts which govern the theory of fuzzy logic, and the application of this theory to systems control, are briefly presented. The methodology of fuzzy logic was then applied to develop a model for an electrical energy system. The results of the simulation demonstrated that fuzzy logic control eliminated the area frequency error and permitted that only the area experiencing an increase in charge responds to this variation. Based on the results, it is concluded that control based on fuzzy logic is simple, is easy to maintain, is of low cost, and can be used to substitute traditional velocity controllers.

Control preventivo dinamico de sistemas de energia electrica usando redespacho de generacion y corte de carga

A model for preventive control in electrical systems is presented, taking into account the dynamic aspects of the network. Among these aspects, the effects provoked by perturbations which cause oscillations in synchronous machine angles (transient stability), such as electric equipment outages and short circuits, are presented. The energy function is used to measure the stability of the system using a procedure defined as the security margin. The control actions employed are load shedding and generation reallocation. An application of the methodology to a system located in southern Brazil, which is composed of 10 synchronous machines, 45 busses, and 72 transmission lines. The results confirm the theoretical studies.

A techno-economic analysis for MCFC cogeneration system

In this paper, a methodology for the study of a fuel cell cogeneration system and applied to a university campus is developed. The cogeneration system consists of a molten carbonate fuel cell associated to an absorption refrigeration system. The electrical and cold-water demands of the campus are about 1,000 kW and 1,840 kW (at 7°C), respectively. The energy, exergy and economic analyses are presented. This system uses natural gas as the fuel and operates on electric parity. In conclusion, the fuel cell cogeneration system may have an excellent opportunity to strengthen the decentralized energy production in the Brazilian tertiary sector.

Study of a hybrid solid oxide fuel cell: Energetic analysis and sankey diagram

In this paper a hybrid solid oxide fuel cell (SOFC) system is analyzed. This system applies a combined cycle utilizing gas turbine associated to a SOFC for rational decentralized energy production. Initially the relative concepts about the fuel cell are presented, followed by some chemical and technical informations such as the change of Gibbs free energy in isothermal fuel oxidation (or combustion) directly into electricity. This represents a very high fraction of the lower heating value (LHV) of a hydrocarbon fuel. In the next step a methodology for the study of SOFC associated with a gas turbine system is developed, considering the electricity and steam production for a hospital, as regard to the Brazilian conditions. This methodology is applied to energetic analysis. Natural gas is considered as a fuel. In conclusion, it is shown by a Sankey Diagram that the hybrid SOFC system may be an excellent opportunity to strengthen the decentralized energy production in Brazil. It is necessary to consider that the cogeneration in this version also is a sensible alternative from the technical point of view, demanding special methods of design, equipment selection and mainly of the contractual deals associated to electricity and fuel supply.