A.A. El-Keib

A fuzzy evolutionary programming-based solution methodology for security-constrained generation maintenance scheduling

Abstract A traditional mathematical model for maintenance scheduling of power generation systems may give an optimal schedule for a power system with known conditions. A change of the system condition due to uncertainties or sudden changes may render the resulting optimal schedule unsuitable or inapplicable for the power system under study. This paper presents a fuzzy model and an evolutionary programming-based solution technique for the security-constrained maintenance scheduling (MS) problem of generation systems with uncertainties in the load and fuel and maintenance costs. The proposed technique results are fuzzy optimal cost range that reflects the problem uncertainties. The technique solves a decomposed maintenance model of two interrelated subproblems, namely the maintenance and the security-constrained economic dispatch problem. Test results on the IEEE 30-bus system with six generating units reported in this paper are quite encouraging.

Optimal clustering of power networks using genetic algorithms

Abstract This paper presents a new method for optimal network decomposition based on genetic algorithms (GAs). GAs present a powerful, globally oriented optimization method which exploits the mechanism of natural genetics, working on populations of candidate solutions in an effort to reach optima or near optima. Test results on IEEE standard networks are given and compared with those using simulated annealing. The genetic algorithm approach is found to produce significantly better solutions.

An evolutionary programming-based solution methodology for power generation and transmission maintenance scheduling

Abstract This paper presents an evolutionary programming (EP)-based technique to the unified model of the maintenance scheduling (MS) problem of power generation and transmission systems. In this paper, the Hill-Climbing technique (HCT) is used in conjunction with the EP to find a feasible solution in the neighborhood of the new infeasible solutions during the solution process. The EP search ability and the feasibility watch of the HCT motivate the sequential solution of the two interrelated subproblems of the MS problem. The paper reports test results of the proposed algorithm on the IEEE 30-bus system with six generating units and 41 transmission lines.

A review of capacitor placement techniques on distribution feeders

Optimal sizing and placement of shunt capacitors on distribution feeders has received considerable attention from researchers for many years. This paper presents an extensive review of the different solution methods found in the literature and is intended as a guide for those interested in the problem or intending to do additional research in the area. The assumptions made and a brief description of the solution methods are presented.

Advancement of statistical based modeling techniques for short-term load forecasting

This paper presents a highly adaptable and robust short-term load forecasting algorithm developed using hybrid modeling techniques. Adaptive general exponential smoothing augmented with power spectrum analysis is proposed to account for the changing base load component. The algorithm includes an adaptive autoregressive modeling technique enhanced with partial autocorrelation analysis to model the random component of the load. The Akaike information criterion is employed to guarantee model parsimony. The weighted recursive least square estimate algorithm with variable forgetting factors is applied to estimate the model parameters. A nonlinear weather-sensitive model is used to represent the influence of weather changes on energy consumption. Simulations performed using historical load data from two large utilities revealed that the proposed approach produces highly accurate forecasting and is especially attractive for online applications with little human intervention. Details of the approach and test results are included in the paper.

A review of ANN-based short-term load forecasting models

Artificial neural networks (ANN) have recently received considerable attention and a large number of publications concerning ANN-based short-term load forecasting (STLF) have appeared in the literature. An extensive survey of ANN-based load forecasting models is given. The six most important factors which affect the accuracy and efficiency of the load forecasters are presented and discussed. The paper also includes conclusions reached by the authors as a result of their research in this area.<<ETX>>

A genetic algorithm-based approach to economic dispatch of power systems

In view of the Clean Air Act (CAA) of 1990, the economic dispatch problem considering the compensating generation plan provided in the Act is nonlinear, ill-structured and multimodal. This paper presents a genetic algorithm (GA) based approach to solve this problem. Test results show that the genetic algorithm-based approach produces significantly better solutions compared against those obtained using the standard economic dispatch approach. It also proves the robustness of this algorithm in solving this type of optimization problem.<<ETX>>

APPLICATION OF A GENETIC ALGORITHM TO POWER TRANSFORMER DESIGN

Design optimization is an important topic for electrical manufacturers. Optimization techniques that require derivatives are difficult to apply to the power transformer problem. This paper presents a new approach using the genetic algorithm to optimize power transformer design. An example design, included in this paper, indicates the viability of the proposed method to solve this problem and its ability to reduce the amount of engineering time spent comparing alternative designs.

Marginal cost-based pricing of wheeling transactions and independent power producers considering security constraints

Various proposed pricing policies for wheeling transactions and independent power producers under open transmission access do not compensate, in a direct manner, parties who participate in maintaining network security and provide the system reactive power requirements. Within this paper, a pricing structure that provides such compensation, based on physically meaningful price components, is developed. Prices determined by the proposed method reflect the cost of incurred losses and those of satisfying network security constraints. The effects of security constraint specifications on price calculations is investigated. Results are presented for the IEEE 6- and 30-bus test systems.

Training data sensitivity problem of artificial neural network-based power system load forecasting

A crucial problem with the artificial neural network-based load forecasting is that its forecasting performance is significantly affected by the selection of training data used to calculate the network weights. The inherent shortcoming of this approach is verified through a typical example presented in this paper. Test results show that the short-term load forecasting error is very sensitive to the amplitude of the noise signal which is added to a portion of the training data. The presented test cases approximately simulate the load conditions during abrupt weather changing periods. Possible strategies to remedy this problem are also discussed in the paper.<<ETX>>