Implementation Of Particle Swarm Optimization Research Articles

Optimal design of brace-viscous damper and pendulum tuned mass damper using Particle Swarm Optimization

We implemented Particle Swarm Optimization (PSO) to determine the most optimal properties of the brace-viscous damper system (BVDS), pendulum tuned mass damper (PTMD), and combined BVDS-PTMD system in mitigation of dynamic response of a jacket platform. To do this, a scaled prototype of an offshore jacket is numerically simulated in ANSYS subjected to ocean waves. Concerning BVDS, at each story, the variables being optimized are (1) BVDS configuration such as chevron, toggle, diagonal; (2) damping coefficient, and (3) brace area. The properties of PTMD being optimized are the damping ratio (ξd), frequency ratio (β), structural excitation frequency ratio (α), and mass ratio (m¯). To do the optimization, the results of ANSYS are exploited to calculate the PSO cost function (standard deviation of deck displacements (σsd)). Regarding the deck displacement and base shear force, the optimization results proved that the optimal BVDS-PTMD combined system outperforms the optimal BVDS and the optimal BVDS performance is better than that of the PTMD system. Both in the optimal BVDS and integrated BVDS-PTMD, the chevron configuration for the top floor and toggle configuration for the first to third floors are evaluated as the optimum arrangement by the optimization algorithm.

Smart Proxy Modeling of a Fractured Reservoir Model for Production Optimization: Implementation of Metaheuristic Algorithm and Probabilistic Application

Numerical reservoir simulation has been recognized as one of the most frequently used aids in reservoir management. Despite having high calculability performance, it presents an acute shortcoming, namely the long computational time induced by the complexities of reservoir models. This situation applies aptly in the modeling of fractured reservoirs because these reservoirs are strongly heterogeneous. Therefore, the domains of artificial intelligence and machine learning (ML) were used to alleviate this computational challenge by creating a new class of reservoir modeling, namely smart proxy modeling (SPM). SPM is a ML approach that requires a spatio-temporal database extracted from the numerical simulation to be built. In this study, we demonstrate the procedures of SPM based on a synthetic fractured reservoir model, which is a representation of dual-porosity dual-permeability model. The applied ML technique for SPM is artificial neural network. We then present the application of the smart proxies in production optimization to illustrate its practicality. Apart from applying the backpropagation algorithms, we implemented particle swarm optimization (PSO), which is one of the metaheuristic algorithms, to build the SPM. We also propose an additional procedure in SPM by integrating the probabilistic application to examine the overall performance of the smart proxies. In this work, we inferred that the PSO had a higher chance to improve the reliability of smart proxies with excellent training results and predictive performance compared with the considered backpropagation approaches.

Directed particle swarm optimization with Gaussian-process-based function forecasting

Particle swarm optimization (PSO) is an iterative search method that moves a set of candidate solution around a search-space towards the best known global and local solutions with randomized step lengths. PSO frequently accelerates optimization in practical applications, where gradients are not available and function evaluations expensive. Yet the traditional PSO algorithm ignores the potential knowledge that could have been gained of the objective function from the observations by individual particles. Hence, we draw upon concepts from Bayesian optimization and introduce a stochastic surrogate model of the objective function. That is, we fit a Gaussian process to past evaluations of the objective function, forecast its shape and then adapt the particle movements based on it. Our computational experiments demonstrate that baseline implementations of PSO (i. e., SPSO2011) are outperformed. Furthermore, compared to, state-of-art surrogate-assisted evolutionary algorithms, we achieve substantial performance improvements on several popular benchmark functions. Overall, we find that our algorithm attains desirable properties for exploratory and exploitative behavior.

Determining Optimum Butt-Welding Parameters of 304 Stainless-Steel Plates Using Finite Element, Particle Swarm and Artificial Neural Network

Residual tensile stresses generated during butt welding of plates using arc welding process lead to deformation and deterioration of fatigue strength of welded parts. This research implemented particle swarm optimization (PSO) algorithm to present optimum welding parameters to minimize the tensile residual stresses of butt-welded 304 stainless-steel plates with 4–15 mm thicknesses. A set of 32 experiments was designed using Taguchi method and simulated using ABAQUS commercial software based on element birth-and-death finite element technique. An artificial neural network and PSO were utilized to discover the optimum welding settings. To ensure the accuracy of simulation results, slitting method was implemented to measure residual stresses utilizing digital image correlation technique beside the strain gauges.

Comparison Of Pso-Based Naive Bayes And Naive Bayes Algorithm In Determining The Feasibility Of Bumdes Credit

In analyzing a credit, sometimes an analysis performs an inaccurate analysis so that some customers are less able to make credit installment payments, resulting in less smooth or even bad loans. From these problems, researchers conducted a credit analysis using computerized techniques using RapidMiner software in data processing. The right data processing technique to use is classification. One method of data mining classification is the Naive Bayes algorithm. Researchers use weighting by implementing Particle Swarm Optimization (PSO) for attribute selection to improve the accuracy of Naive Bayes. After testing with two models namely Naive Bayes algorithm and Naive Bayes based on PSO, the results obtained are for the Naive Bayes algorithm with an accuracy value of 93.24%, while the Naive Bayes algorithm based on particle swarm optimization models produces a higher accuracy value of 98.16% compared to the Naive Bayes algorithm model. From these results, the difference between the two models is 4.92%. Then for the results of using the ROC curve for both models, for the Naive Bayes algorithm, the AUC value is 0.939 with an Excellent Classification diagnostic level, and for the Naive Bayes algorithm model based on particle swarm optimization, the AUC value is 0.977 with an Excellent Classification diagnostic level. From the evaluation of the ROC curve, it is seen that the Naive Bayes model based on particle swarm optimization is higher when compared to the Naive Bayes algorithm. From the results of the AUC, the difference between the two models is 0.038.

Robust nonlinear parameter estimation in tracer kinetic analysis using infinity norm regularization and particle swarm optimization

In positron emission tomography (PET) studies, the voxel-wise calculation of individual rate constants describing the tracer kinetics is quite challenging because of the nonlinear relationship between the rate constants and PET data and the high noise level in voxel data. Based on preliminary simulations using a standard two-tissue compartment model, we can hypothesize that it is possible to reduce errors in the rate constant estimates when constraining the overestimation of the larger of two exponents in the model equation. We thus propose a novel approach based on infinity-norm regularization for limiting this exponent. Owing to the non-smooth cost function of this regularization scheme, which prevents the use of conventional Jacobian-based optimization methods, we examined a proximal gradient algorithm and the particle swarm optimization (PSO) through a simulation study. Because it exploits multiple initial values, the PSO method shows much better convergence than the proximal gradient algorithm, which is susceptible to the initial values. In the implementation of PSO, the use of a Gamma distribution to govern random movements was shown to improve the convergence rate and stability compared to a uniform distribution. Consequently, Gamma-based PSO with regularization was shown to outperform all other methods tested, including the conventional basis function method and Levenberg–Marquardt algorithm, in terms of its statistical properties.

Optimizing Inverse Distance Weighting with Particle Swarm Optimization

Spatial analysis of hydrological data often requires the interpolation of a variable from point samples. Commonly used methods for solving this problem include Inverse Distance Weighting (IDW) and Kriging (KG). IDW is easily extensible, has a competitive computational cost with respect to KG, hence it is usually preferred for this task. This paper proposes the optimization of finding the IDW parameter using a nature-inspired metaheuristic, namely Particle Swarm Optimization (PSO). The performance of the improved algorithm is evaluated in a complex scenario and benchmarked against the KG algorithm for 51 precipitation series from the Dobrogea region (Romania). Apart from facilitating the process of applying IDW, the PSO implementation for Optimizing IDW (OIDW) is computationally lighter than the traditional IDW approach. Compared to Kriging, OIDW is straightforward to be implemented and does not require the difficult process of identification of the most appropriate variogram for the given data.

Implementation of Boolean PSO for Service Restoration Using Distribution Network Reconfiguration Simultaneously With Distributed Energy Resources and Capacitor Banks

This paper proposes an effective approach based on the integration of the Boolean algebra and particle swarm optimization (PSO) in the binary space to restore service to isolated sections of the distribution system. Firstly, the proposed approach identifies the switching operation plan for feeder reconfiguration. Then, the distributed energy resources (DERs) and capacitor banks (C-Bs) are allocated simultaneously after network reconfiguration. Different scenarios are studied with the objective of improving the system voltage stability index (VSI) taking into consideration different operating constraints. Typical IEEE distribution systems consisting of 33 and 69 buses are simulated in order to validate the benefit of the proposed approach. The simulation results show the effectiveness and resilience of the proposed approach compared with other existing methods.

RETRACTED: Pareto-based allocations of multi-type flexible AC transmission system devices for optimal reactive power dispatch using Kinetic Gas Molecule Optimization algorithm

Optimal reactive power dispatch is one of the key factors to attain cost-effective and stable functioning of power system. It is a complicated non-linear optimization issue with a combination of discrete and continuous control variables. Due to this complex feature of optimal reactive power dispatch, optimization technique has become an efficient method to solve this problem. In this work, Kinetic Gas Molecule Optimization algorithm with Pareto optimality is proposed for solving multi-objective optimal reactive power dispatch problem. The presentation of Kinetic Gas Molecule Optimization is improved by computing inertia weight and acceleration coefficients dynamically rather than a fixed value. Because of this reason, the searching capability of the particles in each iteration is improved. However, to improve the power system performance in optimal reactive power dispatch scenario, additional flexible AC transmission system devices like static VAR compensator, thyristor-controlled series compensator, and unified power flow controller are introduced to provide stable results when compared to conventional output because flexible AC transmission system devices are capable of controlling the flow of real power and reactive power. These details are implemented and tested on IEEE 30-bus test system with various objectives. The performance of proposed method is validated from MATLAB, which shows the value of power loss as 4.3583 and voltage deviation as 0.26499 with cost of US$469.6417 per MVAR, which shows considerably superior results when compared with implemented particle swarm optimization results. The proposed method provides an efficient result for solving multi-objective optimal reactive power dispatch issues.

Optimal Design of Integrated Heat Pipe Air-Cooled System Using TLBO Algorithm for SiC MOSFET Converters

Optimal thermal management system design is critical for power electronic converters to ensure the reliability of power semiconductor switches. Medium power density inverter systems are often air-cooled to ensure an efficient and cost-effective thermal management solution. In addition, using heat pipes as the heat transfer medium between the heat sources and the heat sink can provide lower volume for the entire inverter. This paper investigates the effectiveness of Teaching Learning Based Optimization (TLBO) for finding the optimal forced-air heat sink with heat pipe cooling system to achieve higher fan efficiency and lower inverter packaging volume. The optimal design is found utilizing commercially available fans and heat pipes. The TLBO design optimization is also compared to the highly implemented Particle Swarm Optimization (PSO) and it is found that TLBO uses 20 times fewer iterations than PSO to converge, and that the TLBO results are more robust for different design constraints.

Particle Swarm-Based Cell Range Expansion for Heterogeneous Mobile Networks

Traffic demand in wireless communication systems has emerged as a key issue over recent decades. An ever-increasing trend is projected for the next few years, with explosive data traffic expected to materialize and mobile users imposing new quality of service requirements. This growing traffic demand, combined with increasingly complex heterogeneous network (HetNet) scenarios, has presented ever more challenges for mobile network operators in terms of service, coverage, load balancing, and quality of service. Considering the traditional association mechanism based on maximum power received, HetNets tend to remain unbalanced, making it challenging to satisfy mobile users' traffic requirements. In this paper, instead of trying to maximize the achievable downlink rate per user, we couple the cell range expansion (CRE) technique with a particle swarm optimization (PSO) algorithm to maximize the number of users whose downlink requirements are met. The proposed scheme considers both the loads of base stations and the signal-to-interference-plus-noise ratio (SINR) of user equipment to model an objective function that seeks to compute specific CRE bias values per small base station. The proposed scheme is also compared with some classical PSO implementations. Numerical results validate the performance of the proposed schemes, which effectively fulfill users' data traffic requirements by reducing network imbalance.

An analytical framework for high-speed hardware particle swarm optimization

Engineering optimization techniques are computationally intensive and can challenge implementations on tightly-constrained embedded systems. Particle Swarm Optimization (PSO) is a well-known bio-inspired algorithm that is adopted in various applications, such as, transportation, robotics, energy, etc. In this paper, a high-speed PSO hardware processor is developed with focus on outperforming similar state-of-the-art implementations. In addition, the investigation comprises the development of an analytical framework that captures wide characteristics of optimization algorithm implementations, in hardware and software, using key simple and combined heterogeneous indicators. The framework proposes a combined Optimization Fitness Indicator that can classify the performance of PSO implementations when targeting different evaluation functions. The two targeted processing systems are Field Programmable Gate Arrays for hardware implementations and a high-end multi-core computer for software implementations. The investigation confirms the successful development of a PSO processor with appealing performance characteristics that outperforms recently presented implementations. The proposed hardware implementation attains 23,300 improvement ratio of execution times with an elliptic evaluation function. In addition, a speedup of 1777 times is achieved with a Shifted Schwefels function. Indeed, the developed framework successfully classifies PSO implementations according to multiple and heterogeneous properties for a variety of benchmark functions.

Assessment of Joint Space in Knee Osteoarthritis using Particle Swarm Optimization Technique

Osteoarthritis (OA) is one of the most common joint disorder which is debility seen in elderly & overweight people which affects the cartilage of bone joints like knee, feet, hip, and spine. In OA usually, cartilage is ruptured due to the kneading of bones with each other which will end up causing severe pain. In this condition, it is necessary to analyze the severity of OA which involves various medical imaging and clinical examination techniques. In this paper, automated analysis and detection of OA are proposed by calculating the thickness of cartilage which also helps to effectively detect and analyze the abnormalities in bone structures. Where we have considered various knee X-ray images. Initially, preprocessing and noise removal is performed. Further by implementing Particle Swarm Optimization (PSO) segmentation and thresholding, the specified knee region is cropped and analyzed to calculate the thickness of cartilage to detect the presence of OA.

Assessment of Joint Space in Knee Osteoarthritis using Particle Swarm Optimization Technique

Osteoarthritis (OA) is one of the most common joint disorder which is debility seen in elderly & overweight people which affects the cartilage of bone joints like knee, feet, hip, and spine. In OA usually, cartilage is ruptured due to the kneading of bones with each other which will end up causing severe pain. In this condition, it is necessary to analyze the severity of OA which involves various medical imaging and clinical examination techniques. In this paper, automated analysis and detection of OA are proposed by calculating the thickness of cartilage which also helps to effectively detect and analyze the abnormalities in bone structures. Where we have considered various knee X-ray images. Initially, preprocessing and noise removal is performed. Further by implementing Particle Swarm Optimization (PSO) segmentation and thresholding, the specified knee region is cropped and analyzed to calculate the thickness of cartilage to detect the presence of OA.

PSO Fined-tuned Model-Free PID Controller with Derivative Filter for Buck-Converter Driven DC Motor

Traditionally, the PID controller parameters are tuned heuristically based on time response behavior of the system. This method is tiresome job and can cause undesirable system response. Therefore, this research suggests the tuning method of a model-free PID controller with derivative filter (PIDF) by implementing Particle Swarm Optimization (PSO). This tuning method is applied to buck-converter driven DC motor control. The speed of DC motor is controlled by PIDF controller. The parameters of PIDF controller are fine-tuned by implementing PSO algorithms. The fitness functions of the algorithm are evaluated based on Sum Square Error (SSE) and Sum Absolute Error (SAE). The state-space representation of buck-converter/DC motor is considered to confirm the design of the control method. The results of the proposed tuning method are compared with PI controller and PIDF controller tuned by PID Tuner Simulink. The time response specifications of angular velocity, armature current and duty cycle input energy are considered as a control scheme performance. Finally, the suggested tuning technique promises a very minimum duty cycle energy and a fast input tracking of DC motor angular velocity.

Implementation and model uniqueness of Particle Swarm Optimization method with a 2D smooth modeling approach for Radio-Magnetotelluric data

We present a simple workflow for 2D smooth modeling of Radio-Magnetotelluric (RMT) data using Particle Swarm Optimization (PSO). The workflow aims for the general problems of the Global Optimization (GO) methods, encountered during multidimensional geophysical modeling; time consumption, and difficulties in solving large amount of model parameters. In our implementation of PSO, starting models are used and an optimum parameter change vector (Δm) is searched by the algorithm. Our initial studies showed, implementing a smooth modeling approach is necessary for modeling large amount of model parameters using PSO. To obtain smooth models and avoiding multi-objective optimization we used an operator to smooth the model parameters to the desired level. As result, we used the PSO to search for the Δm minimizing the functional when the model parameters are smoothed. The smoothness is gradually decreased when rougher models are wanted. As the smoothness decrease, artefacts are found to be emerging; especially at the low sensitivity zones. To prevent these artefacts, we added Minimum Gradient Support (MGS) to our functional with a multiplier. Since the value of this multiplier is necessarily small, the algorithm doesn't search for a balance between these objectives, and the contribution from the MGS acts as a threshold value to introduce a structure to the model. We tested this approach using a synthetic and a field dataset. In all cases the algorithm successfully minimized the functional and obtained geologically meaningful models. We also compared the uniqueness of the models recovered from the field dataset by multiple modeling realizations using smooth inversion and PSO. Our results suggest, when higher smoothness and minimum structures are aimed, the uniqueness of the models is significantly higher, however, for a fixed set of modeling parameters with moderate values, the non-uniqueness is observed to be higher than that suggested by the smooth inversions.

Implementation and Comparison of Particle Swarm Optimization and Genetic Algorithm Techniques in Combined Economic Emission Dispatch of an Independent Power Plant

This paper presents the optimization of fuel cost, emission of NOX, COX, and SOX gases caused by the generators in a thermal power plant using penalty factor approach. Practical constraints such as generator limits and power balance were considered. Two contemporary metaheuristic techniques, particle swarm optimization (PSO) and genetic algorithm (GA), have were simultaneously implemented for combined economic emission dispatch (CEED) of an independent power plant (IPP) situated in Pakistan for different load demands. The results are of great significance as the real data of an IPP is used and imply that the performance of PSO is better than that of GA in case of CEED for finding the optimal solution concerning fuel cost, emission, convergence characteristics, and computational time. The novelty of this work is the parallel implementation of PSO and GA techniques in MATLAB environment employed for the same systems. They were then compared in terms of convergence characteristics using 3D plots corresponding to fuel cost and gas emissions. These results are further validated by comparing the performance of both algorithms for CEED on IEEE 30 bus test bed.

Heterogeneous Acceleration of Hybrid PSO-QN Algorithm for Neural Network Training

Artificial neural network (ANN) has successfully provided solutions to many practical problems. One of the difficulties in training ANNs is finding the ideal solution to the network weights quickly. This paper designs an implementation of the hybrid particle swarm optimization (PSO) and quasi-Newton (QN) algorithm on CPU-GPU platform using OpenCL to accelerate ANN training. The PSO-QN implementation combines the strength of the PSO algorithm in global search and the advantage of the QN algorithm in fast convergence rate. A configurable parallel line search implementation and an efficient parallel reinitialization implementation are proposed to improve the performance and reduce data transmission. Experiments show the PSO-QN hybrid parallel implementation on CPU-GPU platform can achieve up to $362\times$ and $8.9\times$ acceleration compared with the C++ implementations of PSO and BFGS-QN on CPU, respectively. Compared with the PSO and BFGS-QN parallel implementations, the training loss of the PSO-QN hybrid implementation at given training time is reduced by 15.16% and 3.97%, and the testing error is reduced by 13.66% and 6.86%, respectively.

Implementation of Particle Swarm Optimization Technique for Spectrum Sensing in Cognitive Radio Network

The scarcity of spectrum can be overcome by using the spectrum efficiently and effectively. There is a need for devising techniques that can help in sensing the spectrum judiciously so that the Secondary Users can optimally access the spectrum holes. This will support higher transmission of data, thereby enhancing the throughput. Further, the presence of Primary Users should be detected accurately in order to avoid interference. The sensing-throughput trade-off problem of spectrum sensing stage of cognitive radios can be optimized by means of computational intelligence techniques like swarm intelligence. This paper implements Particle Swarm Optimization technique to optimize Throughput, Probability of false alarm and sensing time under varying Signal-to-Noise Ratio conditions. It has been studied that bigger swarm-size does not improve the results, but takes longer processing time.

Parameter Estimation in Ordinary Differential Equations Modeling via Particle Swarm Optimization

Researchers using ordinary differential equations to model phenomena face two main challenges among others: implementing the appropriate model and optimizing the parameters of the selected model. The latter often proves difficult or computationally expensive. Here, we implement Particle Swarm Optimization, which draws inspiration from the optimizing behavior of insect swarms in nature, as it is a simple and efficient method for fitting models to data. We demonstrate its efficacy by showing that it outstrips evolutionary computing methods previously used to analyze an epidemic model.