scholarly journals Locally tuned hybridized particle swarm optimization for the calibration of the nonlinear Muskingum flood routing model

2020 ◽  
Vol 11 (S1) ◽  
pp. 343-358 ◽  
Author(s):  
Umut Okkan ◽  
Umut Kirdemir
Keyword(s):  
Particle Swarm Optimization ◽  
Initial Conditions ◽  
Particle Swarm ◽  
Solution Space ◽  
Global Solutions ◽  
Pso Algorithm ◽  
Flood Routing ◽  
Swarm Optimization ◽  
Model Benchmark ◽  
Lm Algorithm

Abstract In the literature about the parameter estimation of the nonlinear Muskingum (NL-MUSK) model, benchmark hydrographs have been subjected to various metaheuristics, and in these studies the minor improvements of the algorithms on objective functions are imposed as ‘state-of-the-art’. With the metaheuristics involving more control variables, the attempt to search global results in a restricted solution space is not actually practical. Although metaheuristics provide reasonable results compared with many derivative methods, they cannot guarantee the same global solution when they run under different initial conditions. In this study, one of the most practical of metaheuristics, the particle swarm optimization (PSO) algorithm, was chosen, and the aim was to develop its local search capability. In this context, the hybrid use of the PSO with the Levenberg–Marquardt (LM) algorithm was considered. It was detected that the hybrid PSO–LM gave stable global solutions as a result of each random experiment in the application for four different flood data. The PSO–LM, which stands out with its stable aspect, also achieved rapid convergence compared with the PSO and another hybrid variant called mutated PSO.

Particle Swarm Optimization Algorithms Inspired by Immunity-Clonal Mechanism and Their Applications to Spam Detection

2012 ◽  
pp. 182-205 ◽  
Author(s):  
Ying Tan
Keyword(s):  
Particle Swarm Optimization ◽  
Optimization Algorithms ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Spam Detection ◽  
Swarm Optimization ◽  
Hole Model ◽  
Successive Generations ◽  
Benchmark Test Functions

Compared to conventional PSO algorithm, particle swarm optimization algorithms inspired by immunity-clonal strategies are presented for their rapid convergence, easy implementation and ability of optimization. A novel PSO algorithm, clonal particle swarm optimization (CPSO) algorithm, is proposed based on clonal principle in natural immune system. By cloning the best individual of successive generations, the CPSO enlarges the area near the promising candidate solution and accelerates the evolution of the swarm, leading to better optimization capability and faster convergence performance than conventional PSO. As a variant, an advance-and-retreat strategy is incorporated to find the nearby minima in an enlarged solution space for greatly accelerating the CPSO before the next clonal operation. A black hole model is also established for easy implementation and good performance. Detailed descriptions of the CPSO algorithm and its variants are elaborated. Extensive experiments on 15 benchmark test functions demonstrate that the proposed CPSO algorithms speedup the evolution procedure and improve the global optimization performance. Finally, an application of the proposed PSO algorithms to spam detection is provided in comparison with the other three methods.

Optimization Design of Gravity Dam Section Based on PSO Algorithm

2012 ◽  
Vol 424-425 ◽  
pp. 535-539
Author(s):  
Liang Ming Hu ◽  
Yi Zhi Li
Keyword(s):  
Particle Swarm Optimization ◽  
Optimization Design ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Gravity Dam ◽  
Actual Situation ◽  
Swarm Optimization

Particle Swarm Optimization (PSO) algorithm is a technique for optimization based on iteration, which initializes system to product a series of random solutions, in this solution space, particles commit themselves to search for a better solution and in the final the optimal one is found. Applying this algorithm to the design of gravity dam section then we find: PSO, as shown by the example given in this paper, is an available algorithm which is not only tally with the actual situation, but safe and economical. So, PSO provides a new idea and method for optimization design of gravity dam section.

Application of the particle swarm optimization method for the analysis of wide-angle X-ray diffraction curves of semicrystalline polymers

2017 ◽  
Vol 50 (1) ◽  
pp. 221-230 ◽  
Author(s):  
Małgorzata Rabiej
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Semicrystalline Polymers ◽  
Optimization Techniques ◽  
Wide Angle ◽  
X Ray Diffraction ◽  
Swarm Optimization ◽  
X Ray

The analysis of wide-angle X-ray diffraction curves of semicrystalline polymers is connected with a thorough decomposition of these curves into crystalline peaks and amorphous components. A reliable and unambiguous decomposition is the most important step in calculation of the crystallinity of polymers. This work presents a new algorithm dedicated to this aim, which is based on the particle swarm optimization (PSO) method. The PSO method is one of the most effective optimization techniques that employs a random choice as a tool for going through the solution space and searching for the global solution. The action of the PSO algorithm imitates the behaviour of a bird flock or a fish school. In the system elaborated in this work the original PSO algorithm has been equipped with several heuristics. The role of heuristics is performed by procedures which orient the search of the solution space using additional information. In this paper it is shown that this algorithm is faster to converge and more efficiently performs a multi-criterial optimization compared with other algorithms used for this purpose to date.

scholarly journals Control of a Robotic Swarm Formation to Track a Dynamic Target with Communication Constraints: Analysis and Simulation

2021 ◽  
Vol 11 (7) ◽  
pp. 3179
Author(s):  
Charles Coquet ◽  
Andreas Arnold ◽  
Pierre-Jean Bouvet
Keyword(s):  
Particle Swarm Optimization ◽  
Initial Conditions ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Function Optimization ◽  
Communication Constraints ◽  
Swarm Optimization ◽  
Simplifying Assumptions ◽  
Robotic Swarm ◽  
And Control

We describe and analyze the Local Charged Particle Swarm Optimization (LCPSO) algorithm, that we designed to solve the problem of tracking a moving target releasing scalar information in a constrained environment using a swarm of agents. This method is inspired by flocking algorithms and the Particle Swarm Optimization (PSO) algorithm for function optimization. Four parameters drive LCPSO—the number of agents; the inertia weight; the attraction/repulsion weight; and the inter-agent distance. Using APF (Artificial Potential Field), we provide a mathematical analysis of the LCPSO algorithm under some simplifying assumptions. First, the swarm will aggregate and attain a stable formation, whatever the initial conditions. Second, the swarm moves thanks to an attractor in the swarm, which serves as a guide for the other agents to head for the target. By focusing on a simple application of target tracking with communication constraints, we then remove those assumptions one by one. We show the algorithm is resilient to constraints on the communication range and the behavior of the target. Results on simulation confirm our theoretical analysis. This provides useful guidelines to understand and control the LCPSO algorithm as a function of swarm characteristics as well as the nature of the target.

Rebirthing particle swarm optimization algorithm: application to storm water network design

2008 ◽  
Vol 35 (10) ◽  
pp. 1120-1127 ◽  
Author(s):  
M. H. Afshar
Keyword(s):  
Particle Swarm Optimization ◽  
Network Design ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Network Design Problem ◽  
Storm Water ◽  
Water Network ◽  
Swarm Optimization ◽  
Original Algorithm

Stochastic search methods, such as the particle swarm optimization (PSO) algorithm, are primarily directed by two main features — exploration and exploitation. Exploration is the ability of the algorithm to broadly search through the solution space for new quality solutions, whereas exploitation is responsible for refining the search in the neighborhood of the good solutions found previously. Proper balance between these features is sought, to obtain good performance of these algorithms. An explorative mechanism is introduced in this paper to improve the performance of the PSO algorithm. The method is based on introducing artificial exploration into the algorithm by randomly repositioning the particles approaching stationary status. A velocity measure is used to distinguish between flying and stationary particles. This can be sought as a sudden death followed by a rebirth of these particles. Two options are tested for the rebirthing mechanism, which are (i) clearing and (ii) keeping the memory of rebirthing particles. The global best particle is exempted from rebirthing process so that the most useful of the swarm’s past experiences is not lost. The method is applied to a benchmark storm water network design problem and the results are presented and compared with those of the original algorithm and other methods. The proposed method, though simple, is shown to be very effective in avoiding local optima, leading to an improved version of the algorithm at no extra computational effort.

Particle Swarm Optimization Algorithm Based on Escape Boundary

2011 ◽  
Vol 361-363 ◽  
pp. 1426-1431
Author(s):  
Wen Hua Han
Keyword(s):  
Boundary Condition ◽  
Particle Swarm Optimization ◽  
Convergence Rate ◽  
Particle Swarm Optimization Algorithm ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Population Based ◽  
Global Optimum ◽  
Swarm Optimization

The particle swarm optimization (PSO) is a population-based stochastic evolutionary algorithm, noted for its capability of searching for the global optimum of complex problems. Particles flying out of the solution space will lead to invalid solutions. So often in engineering applications, boundary condition is used to confine the particles within the solution space. In this paper, a new boundary is proposed, which is called as escape boundary. The solution space is divided into three sections, that is, the inside，escape boundary and the outside of the boundary. The location of the global solution in the solution space, accordingly has two types, that is, the global optimum around the center of the solution space, and the global optimum close to the escape boundary. The proposed boundary is introduced into the PSO algorithm, and is compared to the damping boundary. The experimental results show that the PSO based on escape boundary has better search ability and faster convergence rate.

scholarly journals Flood routing by linear Muskingum method using two basic floods data using particle swarm optimization (PSO) algorithm

2020 ◽  
Vol 20 (5) ◽  
pp. 1897-1908
Author(s):  
Hadi Norouzi ◽  
Jalal Bazargan
Keyword(s):  
Particle Swarm Optimization ◽  
Geometric Mean ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Arithmetic Mean ◽  
Flood Routing ◽  
Computational Accuracy ◽  
Swarm Optimization ◽  
Flood Peak ◽  
Muskingum Method

Abstract The Muskingum method is one of hydrological approaches that has been used for flood routing for many years thanks to its simplicity and reasonable accuracy over other methods. In engineering works, the calculation of the Peak section of a flood hydrograph is crucially important. In the present study, using the particle swarm optimization (PSO) algorithm, instead of using a single basic flood, the parameters of the linear Muskingum method (X, K, Δt) are calculated by computed arithmetic and geometric means relevant to two basic floods in the form of eight different models for calculating the downstream hydrograph. The results indicate that if the numerical values of the calculated flood inflow are placed in the interval of the inflow and the basic flood which the parameters X, K, Δt are from, the computation accuracy in approximating the outflow flood related to the peak section of the inflow hydrograph increases for all the mentioned models. In other words, if the arithmetic mean of X, K and the geometric mean of Δt, relevant to the two basic floods, are used instead of using values of X, K, Δt of a single basic flood, the computational accuracy in estimating the flood peak section of the hydrograph in downstream has the highest increase among all the eight models. Thus, the Mean Relative Error (MRE) relevant to the peak section of the inflow hydrograph of the third flood (observational flood) obtained by the first and second basic floods was equal to 4.89% and 2.91%, respectively, while in case of using the arithmetic mean of X and K and the geometric mean of Δt, related to the first and second basic floods (the best models presented in this study), this value is equal to 1.66%.

scholarly journals Effects of uncertainty in determining the parameters of the linear Muskingum method using the particle swarm optimization (PSO) algorithm

2021 ◽  
Author(s):  
Hadi Norouzi ◽  
Jalal Bazargan
Keyword(s):  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Flood Routing ◽  
Swarm Optimization ◽  
Mean Relative Error ◽  
Discharge Variation ◽  
Outflow Hydrograph ◽  
Muskingum Method ◽  
Inflow Discharge

Abstract The Muskingum method is one the simplest and most applicable methods of flood routing. Optimizing the coefficients of linear Muskingum is of great importance to enhance accuracy of computations on an outflow hydrograph. In this study, considering the uncertainty of flood in the rivers and by application of the particle swarm optimization (PSO) algorithm, we used the data obtained from three floods simultaneously as basic flood to optimize parameters of linear Muskingum (X, K and Δt), rather than using inflow and outflow hydrographs of a single basic flood (observational flood), and optimized the outflow discharge at the beginning of flood (O1) as a percentage of inflow discharge at the beginning of flood (I1). The results suggest that the closer inflow discharge variation of basic flood to the inflow discharge variation of observational flood, the accuracy of outflow hydrograph computations will increase. Moreover, when the proposed approach is used to optimize parameters of X, K and Δt, the accuracy of outflow hydrograph computations will increase too. In other words, if rather than using a single basic flood, the proposed approach is applied, the average values of mean relative error (MRE) of total flood for the first, second, third and fourth flood will be improved as 31, 13, 39 and 33%, respectively.

Particle Swarm Optimization Algorithms Inspired by Immunity-Clonal Mechanism and Their Applications to Spam Detection

2010 ◽  
Vol 1 (1) ◽  
pp. 64-86 ◽  
Author(s):  
Ying Tan
Keyword(s):  
Particle Swarm Optimization ◽  
Optimization Algorithms ◽  
Particle Swarm ◽  
Solution Space ◽  
Pso Algorithm ◽  
Spam Detection ◽  
Swarm Optimization ◽  
Hole Model ◽  
Successive Generations ◽  
Benchmark Test Functions

Compared to conventional PSO algorithm, particle swarm optimization algorithms inspired by immunity-clonal strategies are presented for their rapid convergence, easy implementation and ability of optimization. A novel PSO algorithm, clonal particle swarm optimization (CPSO) algorithm, is proposed based on clonal principle in natural immune system. By cloning the best individual of successive generations, the CPSO enlarges the area near the promising candidate solution and accelerates the evolution of the swarm, leading to better optimization capability and faster convergence performance than conventional PSO. As a variant, an advance-and-retreat strategy is incorporated to find the nearby minima in an enlarged solution space for greatly accelerating the CPSO before the next clonal operation. A black hole model is also established for easy implementation and good performance. Detailed descriptions of the CPSO algorithm and its variants are elaborated. Extensive experiments on 15 benchmark test functions demonstrate that the proposed CPSO algorithms speedup the evolution procedure and improve the global optimization performance. Finally, an application of the proposed PSO algorithms to spam detection is provided in comparison with the other three methods.

Sign in / Sign up

Export Citation Format

Share Document