Ajith Abraham

Computational Intelligence in Power Engineering

Computational Intelligence (CI) is one of the most important powerful tools for research in the diverse fields of engineering sciences ranging from traditional fields of civil, mechanical engineering to vast sections of electrical, electronics and computer engineering and above all the biological and pharmaceutical sciences. The existing field has its origin in the functioning of the human brain in processing information, recognizing pattern, learning from observations and experiments, storing and retrieving information from memory, etc. In particular, the power industry being on the verge of epoch changing due to deregulation, the power engineers require Computational intelligence tools for proper planning, operation and control of the power system. Most of the CI tools are suitably formulated as some sort of optimization or decision making problems. These CI techniques provide the power utilities with innovative solutions for efficient analysis, optimal operation and control and intelligent decision making. This edited volume deals with different CI techniques for solving real world Power Industry problems. The technical contents will be extremely helpful for the researchers as well as the practicing engineers in the power industry.

Metaheuristic Pattern Clustering – An Overview

This chapter provides a comprehensive overview to the data clustering techniques, based on naturally-inspired metaheuristic algorithms. At first the clustering problem, similarity and dissimilarity measures between patterns and the methods of cluster validation are presented in a formal way. A few classical clustering algorithms are also addressed. The chapter then discusses the relevance of population-based approach with a focus on evolutionary computing in pattern clustering and outlines the most promising evolutionary clustering methods. The chapter ends with a discussion on the automatic clustering problem, which remains largely unsolved by most of the traditional clustering algorithms.

Hybrid Evolutionary Algorithm for Solving Global Optimization Problems

Differential Evolution (DE) is a novel evolutionary approach capable of handling non-differentiable, non-linear and multi-modal objective functions. DE has been consistently ranked as one of the best search algorithm for solving global optimization problems in several case studies. This paper presents a simple and modified hybridized Differential Evolution algorithm for solving global optimization problems. The proposed algorithm is a hybrid of Differential Evolution (DE) and Evolutionary Programming (EP). Based on the generation of initial population, three versions are proposed. Besides using the uniform distribution (U-MDE), the Gaussian distribution (G-MDE) and Sobol sequence (S-MDE) are also used for generating the initial population. Empirical results show that the proposed versions are quite competent for solving the considered test functions.

Economic Load Dispatch Using a Chemotactic Differential Evolution Algorithm

This paper presents a novel stochastic optimization approach to solve constrained economic load dispatch (ELD) problem using Hybrid Bacterial Foraging-Differential Evolution optimization algorithm. In this hybrid approach computational chemotaxis of BFOA, which may also be viewed as a stochastic gradient search, has been coupled with DE type mutation and crossover of the optimization agents. The proposed methodology easily takes care of solving non-convex economic load dispatch problems along with different constraints like transmission losses, dynamic operation constraints (ramp rate limits) and prohibited operating zones. Simulations were performed over various standard test systems with different number of generating units and comparisons are performed with other existing relevant approaches. The findings affirmed the robustness and proficiency of the proposed methodology over other existing techniques.

Automatic Clustering Using a Synergy of Genetic Algorithm and Multi-objective Differential Evolution

This paper applies the Differential Evolution (DE) and Genetic Algorithm (GA) to the task of automatic fuzzy clustering in a Multi-objective Optimization (MO) framework. It compares the performance a hybrid of the GA and DE (GADE) algorithms over the fuzzy clustering problem, where two conflicting fuzzy validity indices are simultaneously optimized. The resultant Pareto optimal set of solutions from each algorithm consists of a number of non-dominated solutions, from which the user can choose the most promising ones according to the problem specifications. A real-coded representation of the search variables, accommodating variable number of cluster centers, is used for GADE. The performance of GADE has also been contrasted to that of two most well-known schemes of MO.

Automatic Hard Clustering Using Improved Differential Evolution Algorithm

This chapter describes a Differential Evolution (DE) based algorithm for the automatic clustering of large unlabeled datasets. In contrast to most of the existing clustering techniques, the proposed algorithm requires no prior knowledge of the data to be classified. Rather, it determines the optimal number of clusters in the data ‘on the run’. Superiority of the new method has been demonstrated by comparing it with two recently developed partitional clustering techniques and one popular hierarchical clustering algorithm. The partitional clustering algorithms are based on Genetic Algorithm (GA) and the Particle Swarm Optimization (PSO) algorithm. An interesting practical application of the proposed method to automatic segmentation of images is also illustrated.

A Takagi-Sugeno Fuzzy Model of a Rudimentary Angle Controller for Artillery Fire

Modern artilleries have the capability to hit targetswith high level of accuracy. However, a problem ariseswith the current firing procedure when neither theField Observer nor the Fire Direction Center isavailable to support the artillery crew with thenecessary information. In this situation, the detectionof environmental conditions would involve a number ofuncertainties and due to this reason, conventionalcontrol techniques will not deliver satisfying solutionssince the adjustment to the artillery’s firing line will bebased on data that is approximate rather than precise.In this paper, we propose a firing angle control systembased on the Takagi-Sugeno fuzzy model. Theadvantage of fuzzy logic is the ability to tune certainvariables easily by varying the linguistic rules or inputvariables. Experiments show that effective results canbe obtained using a fuzzy model, while demonstratingthat the model could come in handy when the firingangle has to be determined instantaneously with veryvague information about the target.

Differential Evolution Algorithm: Foundations and Perspectives

Differential Evolution (DE) has recently emerged as simple and efficient algorithm for global optimization over continuous spaces.DE shares many features of the classical Genetic Algorithms (GA). But it is much easier to implement than GA and applies a kind of differential mutation operator on parent chromosomes to generate the offspring. Since its inception in 1995, DE has drawn the attention of many researchers all over the world, resulting in a lot of variants of the basic algorithm, with improved performance. This chapter begins with a conceptual outline of classical DE and then presents several significant variants of the algorithm in greater details.

An Enhanced Fuzzy-Genetic Algorithm to Solve Satisfiability Problems

The satisfiability is a decision problem that belongs toNP-complete class and has significant applications invarious areas of computer science. Several works haveproposed high-performance algorithms and solvers toexplore the space of variables and look for satisfyingassignments. Pedrycz, Succi and Shai [1] have studieda fuzzy-genetic approach which demonstrates that aformula of variables can be satisfiable by assigningBoolean variables to partial true values between 0 and1. In this paper we improve this approach by proposingan improved fuzzy-genetic algorithm to avoidundesired convergence of variables to 0.5. Thealgorithm includes a repairing function that eliminatesthe recursion and maintains a reasonable computationalconvergence and adaptable population generation.Implementation and experimental results demonstratethe enhancement of solving satisfiability problems.

Fuzzy Clustering in the Kernel-Induced Feature Space Using Differential Evolution Algorithm

This chapter introduces a scheme for clustering complex and linearly non-separable datasets, without any prior knowledge of the number of naturally occurring groups in the data. The proposed method is based on a modified version of the classical Differential Evolution (DE) algorithm, which uses the neighborhood-based mutation strategy. It also employs a kernel-induced similarity measure instead of the conventional sum-of-squares distance. Use of the kernel function makes it possible to cluster data that is linearly non-separable in the original input space into homogeneous groups in a transformed high-dimensional feature space. The performance of the proposed method has been extensively compared with a few state of the art clustering techniques over a test-suite of several artificial and real life datasets. Based on the computer simulations, some empirical guidelines have been provided for selecting the suitable parameters of the DE algorithm.