Generation of Alternative Clusterings Using Multi-objective Particle Swarm Optimization

A multi-objective particle swarm optimization (MOPSO) approach for multi-objective economic load dispatch problem in power system is presented in this paper. The economic load dispatch problem is a non-linear constrained multi-objective optimization problem. The proposed MOPSO approach handles the problem as a multi-objective problem with competing and non-commensurable fuel cost, emission and system loss objectives and has a diversity-preserving mechanism using an external memory (call “repository”) and a geographically-based approach to find widely different Pareto-optimal solutions. In addition, fuzzy set theory is employed to extract the best compromise solution. Several optimization runs of the proposed MOPSO approach were carried out on the standard IEEE 30-bus test system. The results revealed the capabilities of the proposed MOPSO approach to generate well-distributed Pareto-optimal non-dominated solutions of multi-objective economic load dispatch. Comparison with Multi-objective Evolutionary Algorithm (MOEA) showed the superiority of the proposed MOPSO approach and confirmed its potential for solving multi-objective economic load dispatch.

This paper addresses a multi-objective approach for simultaneous dynamic expansion planning of conventional sub-transmission grid and Regional Virtual Power Plant (RVPP). In such a feed-in tariff electricity market, it will assist RVVP’s stakeholders in deciding whether or not they should invest in new equipment’s installation. A Multi-Objective Particle Swarm Optimization (MOPSO) algorithm as a heuristic optimization method is proposed to eliminate the conventional centralized planning, which has led to competition between Regional Electric Company (REC) and RVPP for power delivery in sub-transmission system. Two objective functions are considered for simultaneous expansion planning of these two systems. The first one takes the minimum cost of the REC, as the sub-transmission grid operator, into account while the other one considers profit maximization for RVPP. To achieve the goals, MOPSO algorithm is employed to find the best expansion of REC and best location and capacity of RVPP’s resources. Having solved the proposed multi-objective optimization problem, a Pareto front is determined to show the trade-off between REC and RVPPs' contributions in joint optimal expansion planning of conventional sub-transmission grid and the RVPP. To demonstrate the applicability and effectiveness of the proposed approach, a realistic sub-transmission system in Guilan Province, Iran is used as a test system, and the results are evaluated accordingly.

Multi-objective particle swarm optimization model for conjunctive use of treated wastewater and groundwater

In this paper, a multi-objective particle swarm optimization algorithm based on the relative distance strategy is proposed to realize hydrodynamic coefficient identification, which can improve the accuracy of parameter identification without determining the weight manually. Firstly, single-objective particle swarm optimization (PSO) is used to identify the parameters of the model with a low coupling degree. Then, the parameters of the strongly coupled sway and yaw motion model are regarded as multi-objective, and a set of unbiased Pareto optimal solutions are obtained by the multi-objective particle swarm optimization (MOPSO) algorithm. Then the distance function of the Pareto solution is constructed to determine the parametric solution of the model. Finally, experimental identification is carried out by using the data set collected from the real ship. Experimental results show that the accuracy of model parameters obtained by this identification method is about 91.6%, and there is no need to set the weighting coefficient.

Feature selection is a dimensionality reduction method known as a main step in data mining and machine learning. The aim of feature selection is to remove redundant and unrelated features. In recent years several feature selection methods based on graph theory and social networking techniques have been proposed .In this study, a feature selection approach based on multi objective PSO algorithm and social network techniques is presented. In the proposed method, Fisher score, node centrality and edge centrality are used to construct the fitness function in order to present a multi objective particle swarm optimization (PSO) approach. The proposed method run over a variety of datasets and the results are compared with the well-known filter-based feature selection methods. The results show that the proposed method is effective and the performance of the proposed method better than other methods in some cases.

In this paper, a multi-objective hybrid firefly and particle swarm optimization (MOHFPSO) was proposed for different multi-objective optimal power flow (MOOPF) problems. Optimal power flow (OPF) was formulated as a non-linear problem with various objectives and constraints. Pareto optimal front was obtained by using non-dominated sorting and crowding distance methods. Finally, an optimal compromised solution was selected from the Pareto optimal set by applying an ideal distance minimization method. The efficiency of the proposed MOHFPSO technique was tested on standard IEEE 30-bus and IEEE 57-bus test systems with various conflicting objectives. Simulation results were also compared with non-dominated sorting based multi-objective particle swarm optimization (MOPSO) and different optimization algorithms reported in the current literature. The achieved results revealed the potential of the proposed algorithm for MOOPF problems.

The identification of nonlinear systems with artificial neural networks models has been successfully used in many applications. Most processes in industry are characterized by nonlinear and time-varying behavior. In this context, the identification of mathematical models for nonlinear systems is vital in many fields of engineering. The Radial Basis Function Neural Network (RBF-NN) is a powerful approach for nonlinear identification and can be improved using Particle Swarm Optimization (PSO) approaches. This paper presents a multivariable nonlinear system identification using RBF-NN combined with standard PSO and Constriction Factor PSO (CFPSO) approaches in order to determine the RBF-NN parameters. RBF-NN is considered to be a good choice for black-box modeling problems due to its rapid learning capacity and, therefore, has been applied successfully to nonlinear time series modeling and nonlinear identification. On the other hand, PSO was inspired by the choreography of bird flocks and fish schools and can be seen as a distributed behavior algorithm that performs multidimensional search. Furthermore, promising simulation results from performance analysis of the proposed RBF-NN with PSO training approaches are presented and discussed in this paper showing promising results.

Accurate and fast localization of randomly deployed sensor nodes is needed for many applications in wireless sensor networks. Localization also benefits in recognizing the geographically area where an event took place. There is no meaning of any event information without the knowledge of its location coordinates. DV-Hop is one of the main range free localization technique, which estimates the position of nodes using distance vector. Particle swarm optimization is suitable for the localization issues because of its fast computing speed and high precision. To further reduce the positioning error, the traditional DV-Hop localization algorithm based on single objective optimization algorithm is converted into a multi objective optimization algorithm. In our proposed scheme, we have considered six different single objective functions and three different multi objective functions. In this paper, a multi objective particle swarm optimization based DV-Hop localization is proposed in 3-dimensional wireless sensor networks. The proposed functions has been evaluated on the basis of computation time, average localization error and localization error variance. The simulation results show that our proposed multi objective function performs better as compared to traditional single objective function.

An integrated optimization strategy based on Kriging model and multi-objective particle swarm optimization (PSO) algorithm was constructed. As a new surrogate model technology, Kriging model has better fitting precision for nonlinear problem. The Kriging model was adopted to replace computer aided engineering (CAE) simulation as fitness function of multi-objective PSO algorithm, and the computation cost can be reduced greatly. By introducing multi-objective handling mechanism of crowding distance and mutation operator to multi-objective PSO algorithm, the entire Pareto front can be approximated better. It is shown that the multi-objective optimization strategy can get higher solving accuracy and computation efficiency under small sample.

A dynamic multiple populations particle swarm optimization algorithm based on decomposition and prediction

This paper is concerned with fuzzy tracking control optimized via multi-objective particle swarm optimization for stable walking of biped robots. To present an optimal control approach, multi-objective particle swarm optimization is used to design the parameters of the control method in comparison to three effectual multi-objective optimization algorithms in the literature. In particle swarm optimization, a dynamic elimination technique is utilized as a novel approach to prune the archive effectively. Moreover, a turbulence operator is used to skip the local optima and the personal best position of each particle is determined by making use of the Sigma method. Normalized summation of angles errors and normalized summation of control efforts are two conflicting objective functions addressed by dint of multi-objective optimization algorithms in the present investigation. By contrasting the Pareto front of multi-objective particle swarm optimization with the Pareto fronts of other methods, it is illustrated that multi-objective particle swarm optimization performs with high accuracy, convergence and diversity of solutions in the design of fuzzy tracking control for nonlinear dynamics of biped robots. Finally, the proper performance of the proposed controller is demonstrated by the results presenting an appropriate tracking system and optimal control inputs. Indeed, the appropriate tracking system and optimal control inputs prove the efficiency of optimal fuzzy tracking control in dealing with the nonlinear dynamics of biped robots.

Novel Artificial Human Optimization Field Algorithms - The Beginning

The optimal placement of Thyristor Controlled Series Compensators (TCSCs) in transmission systems is formulated as a multi-objective optimization problem with the objective of maximizing transmission system loadability, minimizing transmission loss and minimizing the cost of TCSCs. The thermal limits of transmission lines and voltage limits of load buses are considered as security constraints. Multi-Objective Particle Swarm Optimization (MOPSO) and Multi-Objective Comprehensive Learning Particle Swarm Optimizer (MOCLPSO) are applied to solve this problem. The proposed approach has been successfully tested on IEEE 14 bus system and IEEE 118 bus system. From the results it is inferred that MOCLPSO can obtain an evenly distributed pareto front. A multi-criterion decision-making tool, known as TOPSIS, has been employed to arrive at the best trade-off solution.

To overcome the defect of wide-ranged exploration for particle swarm optimization, a kind of multi-objective particle swarm optimization algorithm with disturbance operation(MPSOD) is proposed. It employs particle swarm optimization and disturbance operation to generate new population in order to enhance the wide-ranged exploration for particle swarm optimization algorithm. Numerical experiments are compared with NSGA-II, SPEA2 and MOPSO on six benchmark problems. The numerical results show the effectiveness of the proposed MPSOD algorithm.Keywordsmulti-objective optimizationparticle swarm optimizationdisturbance operation

This paper proposes a new multiobjective hybrid particle swarm optimization (PSO)–krill herd (KH) Pareto-based optimization algorithm to optimize number and location of the measurement devices for accurate state estimation (SE) in smart distribution networks. Three objectives are considered to be minimized: 1) the total cost; 2) the average relative percentage error (APE) of bus voltage magnitude; and 3) APE of bus voltage angle. As the objective functions are conflicting with respect to each other, a multiobjective Pareto-based nondominated sorting hybrid PSO–KH optimization algorithm is proposed. In this approach, the random variation in loads and the metrological error of the measurement devices are also taken into account. The proposed algorithm minimizes the cost and enhances the accuracy of the distribution state estimator for better monitoring and control of the system. Furthermore, the impacts of distributed generation on SE performance are also investigated. The feasibility of the proposed algorithm is demonstrated on IEEE 69-bus system and practical Indian 85-bus radial distribution network. The results obtained are compared with conventional KH algorithm and PSO, with well-known multiobjective nondominated sorting genetic algorithm and also with an existing technique based on dynamic programming method for validation.