/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. This paper: 1) reviews different combinations between ANNs and evolutionary algorithms (EAs), including using EAs to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EAs; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.

/pdf/evolving-artificial-neural-networks-4kzrbu7pkn.pdf

Evolving artificial neural networks

Many areas in power systems require solving one or more nonlinear optimization problems. While analytical methods might suffer from slow convergence and the curse of dimensionality, heuristics-based swarm intelligence can be an efficient alternative. Particle swarm optimization (PSO), part of the swarm intelligence family, is known to effectively solve large-scale nonlinear optimization problems. This paper presents a detailed overview of the basic concepts of PSO and its variants. Also, it provides a comprehensive survey on the power system applications that have benefited from the powerful nature of PSO as an optimization technique. For each application, technical details that are required for applying PSO, such as its type, particle formulation (solution representation), and the most efficient fitness functions are also discussed.

/pdf/particle-swarm-optimization-basic-concepts-variants-and-4h7hr86hk4.pdf

Particle Swarm Optimization: Basic Concepts, Variants and Applications in Power Systems

Introduction to linear and nonlinear programming

This paper proposes a particle swarm optimization (PSO) method for solving the economic dispatch (ED) problem in power systems. Many nonlinear characteristics of the generator, such as ramp rate limits, prohibited operating zone, and nonsmooth cost functions are considered using the proposed method in practical generator operation. The feasibility of the proposed method is demonstrated for three different systems, and it is compared with the GA method in terms of the solution quality and computation efficiency. The experimental results show that the proposed PSO method was indeed capable of obtaining higher quality solutions efficiently in ED problems.

Particle swarm optimization to solving the economic dispatch considering the generator constraints

A genetics-based algorithm is proposed to solve an economic dispatch problem for valve point discontinuities. The algorithm utilizes payoff information of candidate solutions to evaluate their optimality. Thus, the constraints of classical LaGrangian techniques on unit curves are circumvented. The formulations of an economic dispatch computer program using genetic algorithms are presented and the program's performances using two different encoding techniques are compared. The results are verified for a sample problem using a dynamic programming technique. >

Genetic algorithm solution of economic dispatch with valve point loading

Several optimization techniques have been applied to the solution of the thermal unit commitment problem. They range from heuristics such as complete enumeration to the more sophisticated ones such as Augmented LaGrangian. The heuristics have even reappeared as expert systems. The problem to solve is the optimal scheduling of generating units over a short-term horizon, typically 168 hours. This paper is an overview of the literature in the unit commitment field over the past twenty five years. >

Unit commitment literature synopsis

A genetic-based algorithm is used to solve a power system economic dispatch (ED) problem. The algorithm utilizes payoff information of perspective solutions to evaluate optimality. Thus, the constraints of classical LaGrangian techniques on unit curves are eliminated. Using an economic dispatch problem as a basis for comparison, several different techniques which enhance program efficiency and accuracy, such as mutation prediction, elitism, interval approximation and penalty factors, are explored. Two unique genetic algorithms are also compared. The results are verified for a sample problem using a classical technique. >

Refined genetic algorithm-economic dispatch example

This paper compares the performance of four unit commitment methods, three of which are based on the dynamic programming approach. The paper also presents the modeling of inter-area flow constraints by linear flow network, so that such multi-area representation recognizes any existing transmission limitations which are normally ignored in most unit commitment methods. To assure realistic results, data for two large systems (up to 96 units) were used: EPRI Scenario System C and a midwestern utility. Unit commitment results for these two systems are presented in the paper and they demonstrate the importance of multiple area representation of a system in unit commitment. Such representation affects the schedule costs and assures the determination of realizable schedules.

Evaluation of Dynamic Programming Based Methods and Multiple area Representation for Thermal Unit Commitments

Conventional cost-based load management ignores the rate structure offered to customers. The resulting cost savings may cause revenue loss. In a deregulated power industry where utilities absorb the ultimate consequence of their decision making, reexamination of load management must be conducted. In this paper, profit-based load management is introduced to examine generic direct load control scheduling. Based upon the cost/market price function, the approach aims to increase the profit of utilities. Instead of determining the amount of energy to be deferred or to be paid back, the algorithm controls the number of groups power customer/load type to maximize the profit. In addition to the advantage of better physical feel on how the control devices should operate, the linear programming algorithm provides a relatively inexpensive and powerful approach to the scheduling problem.

Gerald B. Sheblé

Papers

Genetic algorithm solution of economic dispatch with valve point loading

Unit commitment literature synopsis

Refined genetic algorithm-economic dispatch example

Evaluation of Dynamic Programming Based Methods and Multiple area Representation for Thermal Unit Commitments

Direct load control-A profit-based load management using linear programming