Particle Swarm Optimization Parameters Research Articles

A Hybrid Neural Network‐Based Improved PSO Algorithm for Gas Turbine Emissions Prediction

AbstractIn gas‐fired power plants, emissions may reduce turbine blade rotation, thus decreasing power output. This study proposes a hybrid model integrating the Feed forward Neural Network (FFNN) model and Particle Swarm Optimization (PSO) algorithm to predict gas emissions from natural gas power plants. The FFNN predicts gas turbine nitrogen oxides (NOx) and carbon monoxide (CO) emissions, while the PSO optimizes FFNN weights, improving prediction accuracy. The PSO adopts a unique random number selection strategy, incorporating the K‐Nearest Neighbor (KNN) algorithm to reduce prediction errors. Neighbor Component Analysis (NCA) selects parameters most correlated with CO and NOx emissions. The hybrid model is constructed, trained, and testedusing publicly available datasets, evaluating performance with statistical metrics like Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). Results show significant improvement in FFNN training with the PSO algorithm, boosting CO and NOx prediction accuracy by 99.18% and 82.11%, respectively. The model achieves the lowest MSE, MAE, and RMSE values for CO and NOx emissions. Overall, the hybrid model achieves high prediction accuracy, particularly with optimized PSO parameter selection using seed random generators.

Impact of initialization of a modified particle swarm optimization on cooperative source searching

Swarm robotic is well known for its flexibility, scalability and robustness that make it suitable for solving many real-world problems. Source searching which is characterized by complex operation due to the spatial characteristic of the source intensity distribution, uncertain searching environments and rigid searching constraints is an example of application where swarm robotics can be applied. Particle swarm optimization (PSO) is one of the famous algorithms have been used for source searching where its effectiveness depends on several factors. Improper parameter selection may lead to a premature convergence and thus robots will fail (i.e., low success rate) to locate the source within the given searching constraints. Additionally, target overshooting and improper initialization strategies may lead to a nonoptimal (i.e., take longer time to converge) target searching. In this study, a modified PSO and three different initializations strategies (i.e., random, equidistant and centralized) were proposed. The findings shown that the proposed PSO model successfully reduce the target overshooting by choosing optimal PSO parameters and has better convergence rate and success rate compared to the benchmark algorithms. Additionally, the findings also indicate that the random initialization give better searching success compared to equidistant and centralize initialization.

ANALYSIS OF IMPLEMENTATION OF PARTICLE SWARM OPTIMIZATION (PSO) METHOD ON LECTURERS ASSIGNMENTS TO STUDENTS

When preparing a program for a conference, it is very important to divide teaching and learning tasks according to the areas in which you are involved for teaching and learning to be effective. At the University, the assignment process is still done manually which is very time consuming. Therefore, an appropriate optimization method is needed to handle this. This problem can be solved using a population-based heuristic approach, Particle Swarm Optimization (PSO) has been applied to various fields such as scheduling and assignment. The data used in this research is lecturer assignment data in the form of prioritizing lecturer interest in teaching certain subjects. Based on the calculation results, a test was carried out to determine the effect of the test parameters on the fitness value obtained. From the results of the PSO parameter test, the best number of particles is 100, the best number of repetitions is 100, and the speed combination parameters c1 and c2 are 1.5 and 1.5 with the appropriate value of 94878. The system results, the solution obtained gives good results, i.e. always within tolerance limits, the error scores obtained by placing teachers on subjects that suit their preferences are lower

Inverse kinematic model of multi-section continuum robots using particle swarm optimization and comparison to four meta-heuristic approaches

Multi-section continuum robots’ (CRs) behavior is still an outstanding problem because of the highly non-linearity of its equation of motions. To this end, in this paper, particle swarm optimization (PSO) is adopted to solve the inverse kinematic model (IKM) of CRs. First, the CR’s structure is properly described. Then, the aforementioned algorithm is elaborately discussed and implemented in figuring out the IKM of CR and verified through forward kinematic model by choosing the PSO parameters, namely, cognitive factors [Formula: see text] and inertia weight [Formula: see text] for 200 positions on an arc-like trajectory. The optimal angle values ([Formula: see text] and [Formula: see text]) which ensure the lowest distance between the attainably desired position and the robot’s end effector are [Formula: see text] which is perfectly accurate. After that, simulation through MATLAB is carried out, namely, in the first simulation, a three-section CR follows a linear trajectory with a precision approximately equal to [Formula: see text]. Furthermore, PSO takes 7 ms as a mean consumption time to make the robot’s end effector attain to each position. Then, a circular trajectory is followed using PSO. Comparatively speaking, PSO is compared with four meta-heuristic approaches; it is remarked that PSO is a good compromise between accuracy and time consumption. Based on the obtained results, PSO can be considered as a trade-off between accuracy and time consumption for solving the IKM of CRs with complex structure.

Optimization Design of a Saturated Iron Core Fault Current Limiter Using a GA and PSO Algorithms Coupled With Finite Element Method

A dc-bias high-temperature superconducting (HTS) coil is the main part of the Saturated Iron Core Fault Current Limiter (SIC-SFCL). Another relevant part of the SIC-SFCL is the iron core, which represents the main volume of the device. Therefore, optimizing the iron core volume decreases the equipment cost significantly. Also, it is important to find an optimized geometry for the dc HTS coil that allows extracting the maximum potential of the superconducting material. This article proposes a full design optimization of a SIC-SFCL, combining the GA and the particle swarm optimization (PSO) methods. For the optimization procedure, the authors consider the superconducting tape and the ferromagnetic material. The COMSOL software is used to implement the finite element model and the Python language coupled to the COMSOL software codes the optimization algorithms. The authors study different cognitive, social, and inertial parameters in PSO, in order to evaluate the impact of those parameters in the optimization. The results present the ability of the algorithm to provide adequate SIC-SFCL design parameters without any expert intervention. To validate the proposed methodology, the authors perform experimental tests and compare them with the simulation results. The steady-state regime presents an error less than 1% and the short-circuit regime shows a maximum error equal to 10.3%.

Network traffic prediction model based on improved VMD and PSO‐ELM

SummaryThe rapid update of computing power leads to exponential data traffic growth, and the incidence of network attacks is also increasing. It is significantly important to analyze and predict network traffic accurately in the early stage and take corresponding preventive measures. The existing network flow integrated forecasting models still have some bottlenecks that are difficult to solve, for example, the slow optimization speed of modal decomposition parameters, easy falling into local optimal solutions, the slow convergence speed of the training process, and poor generalization capability. In this paper, particle swarm optimization (PSO) is utilized to improve the parameters selection process of the variational mode decomposition (VMD) algorithm and the extreme learning machine (ELM) algorithm. First, the PSO‐VMD combined with multi‐scale permutation entropy (MPE) is utilized to decompose the original network flow, and multiple eigenmode components are obtained. Second, the PSO‐ELM is utilized to train the network traffic prediction model, and the PSO parameters in PSO‐ELM are updated through adaptive weight adjustment and synchronous learning factors to increase the training and prediction speed, and the component prediction results are reconstructed to get a high‐precision network flow forecasting result. Finally, through the prediction and verification of the public network flow data of the WIDE backbone, the result of this experiment indicates that the VMD‐PSO‐ELM can break through the bottlenecks of slow optimization speed of VMD decomposition parameters, reduce the computational complexity of ELM, accelerate the convergence speed, and increase the forecasting accuracy.

Multi-Megawatt Horizontal Axis Wind Turbine Blade Optimization Based on PSO Method

Blade optimization methods are crucial for wind turbine design. In this research, a new set of values for the parameters of the Particle Swarm Optimization (PSO) method is proposed, and its effects on the enhancement of the power generation of the NREL WP-Baseline 1.5 MW horizontal axis wind turbine are investigated. First, the PSO parameters are tuned, and the convergence speed and the optimal accuracy of the objective function are improved. Then, the Class/Shape Transformation (CST) method is employed, and an appropriate order of the shape function polynomial is selected. In the third step, the WP-Baseline 1.5 MW blade is optimized according to the tuned PSO parameters, and the airfoil is represented by CST algorithms. Later, a CFD model, including 37 million cells and an IDDES turbulence model, was validated and used for a comparison of the power generation of the original and optimized blades. The optimized blade produced more power for all wind speeds above 4.5 m/s, with a maximum of 13.8% at 10 m/s and +7.25% at the rated wind speed (11.5 m/s). It should be noted that since the algorithms, tunings, and techniques adopted in the present study were general, the presented method can be used as a systematic approach for the aerodynamics shape optimization of multi-megawatt HAWTs.

Selection of PSO parameters based on Taguchi design-ANOVA- ANN methodology for missile gliding trajectory optimization

The proposed research deals with selection of particle swarm optimization (PSO) algorithm parameters for missile gliding trajectory optimization relying on Taguchi design of experiments, analysis of variance (ANOVA) and artificial neural networks (ANN). Population size, inertial weight and acceleration coefficients of PSO were chosen for the present study. The experiments have been designed as per Taguchi's design of experiments using L25 orthogonal array for selection of better PSO parameters. Missile gliding trajectory is optimized by discretizing angle of attack as control parameter, consequent conversion of optimal control problem to nonlinear programming problem (NLP) and finally solving the problem using PSO with optimized parameters to obtain optimum angle of attack and realization of maximum gliding range. Simulation results portrayed that the gliding range is maximized and missile glide distance is enhanced compared to earlier experiments. The efficiency of proposed approach was verified via different test scenarios.

Exploring the Impact of Random Distribution Choices on Particle Swarm Optimization: An Initial Analysis

Particle Swarm Optimization (PSO) is a robust stochastic optimization algorithm for solving complex and constrained optimization problems. This paper aims to systematically investigate the influence of diverse random number distributions on the learning parameters of PSO and evaluate the algorithm's sensitivity based on these parameters. To this end, several exhaustive numerical experiments were conducted on several test functions, including asymmetric Sphere, Easom, and Csendes. Initially, appropriate random distributions were identified for the learning parameters and proceeded to compare these distributions using all potential combinations. The sensitivity of PSO to these parameters was evaluated using the mean best score, the relative proximity of the best particle to the theoretical optimum, and the average objective function evaluations. The most significant contribution of this research lies in the insights derived from the experimental data. The discovery was that highly skewed and long-tailed distributions such as Chi, Chi-square, Lomax, and Exponential often underperform. On the other hand, distributions that are bounded proportionally to the problem domain consistently surpass the performance of the standard uniform distribution. These findings significantly enhance the understanding of PSO algorithms and provide valuable guidelines for their practical deployment.

Control design and performance evaluation of a grid connected PV–wind power system: A case study of Dongola, Sudan

Globally, considerable emphasis is being placed on developing clean and renewable energy systems. However, the utilization of such resources in Africa has not been fully exploited, especially in remote areas. Given the abundance of solar radiation and wind resources, Sudan has a lot of promise for clean energy solutions. This study describes a grid-connected PV–wind hybrid system’s comprehensive design, control strategy, and performance assessment in Dongola city located in Sudan’s northern region. The grid-connected hybrid system consists of a 3 MW wind turbine and a 1 MW solar system which is directly connected to the DC-link without any intermediate stages. The proposed configuration uses the grid-side converter to regulate the PV system terminal voltage, while Particle Swarm Optimization (PSO) algorithm determines the reference DC-link voltage. The PSO parameters have been thoroughly examined and selected for the maximum extraction of the PV system’s power. The hybrid system performance has been evaluated and validated using MATLAB/SIMULINK environment. Moreover, System Advisor Model (SAM) has been utilized to assess the proposed system’s expected energy considering the site’s historical solar irradiance and wind speed data. The simulation results revealed that the proposed system could produce 8,884 MWh annually, with an 89% share of wind generation and 10% produced by the PV system.

An Overview of Variants and Advancements of PSO Algorithm

Particle swarm optimization (PSO) is one of the most famous swarm-based optimization techniques inspired by nature. Due to its properties of flexibility and easy implementation, there is an enormous increase in the popularity of this nature-inspired technique. Particle swarm optimization (PSO) has gained prompt attention from every field of researchers. Since its origin in 1995 till now, researchers have improved the original Particle swarm optimization (PSO) in varying ways. They have derived new versions of it, such as the published theoretical studies on various parameters of PSO, proposed many variants of the algorithm and numerous other advances. In the present paper, an overview of the PSO algorithm is presented. On the one hand, the basic concepts and parameters of PSO are explained, on the other hand, various advances in relation to PSO, including its modifications, extensions, hybridization, theoretical analysis, are included.

Financial time series forecasting using optimized multistage wavelet regression approach.

This paper presents financial time series forecasting with multistage wavelet transform (WT). First, the time series data is processed through WT with different mother wavelet functions to extract high frequency and low frequency coefficients. Later, standard particle swarm optimization (PSO) algorithm is utilized to find optimal regression models in order to predict future samples. Mean square error (MSE) is opted as cost function for PSO to find optimal coefficients of the regression model. This study further extended to various mother wavelet functions and their decomposition levels to investigate their impacts on time series prediction. These investigations help to data scientists for selection of process parameters and variables. Further, the impact of control parameters of PSO is also discussed to show the importance in the search mechanism especially in regression problems.

Swarmed Grey Wolf Optimizer

Background: The Particle Swarm Optimization (PSO) algorithm is amongst the utmost favourable optimization algorithms often employed in hybrid procedures by the researchers considering simplicity, smaller count of parameters involved, convergence speed and capability of searching global optima. The PSO algorithm acquires memory and the collaborative swarm interactions enhances the search procedure. The high exploitation ability of PSO which intends to locate the best solution within a limited region of the search domain gives PSO an edge over other optimization algorithms. Whereas, low exploration ability results in lack of assurance of proper sampling of the search domain and thus enhances the chances of rejecting a domain containing high quality solutions. A perfect harmony between exploration and exploitation abilities in the course of selection of best solution is needed. High exploitation capacity makes PSO get trapped in local minima when its initial location is far off from the global minima. OBJECTIVES: The intent of this study is to reform this drawback of PSO of getting trapped in local minima. With an objective to upgrade the potential of Particle Swarm Optimization (PSO) to exploit along with preventing PSO of getting trapped in local minima, we require an algorithm with a positive acceptable exploration capacity. METHODS: We utilized, the recently developed metaheuristic Grey Wolf Optimizer (GWO) emulating the seeking and hunting techniques of Grey wolves for this purpose. In our way, the GWO has been utilized to assist PSO in a manner to unite their strengths and lessen their weaknesses. The proposed hybrid has two driving parameters to adjust and assign the preference to PSO or GWO. RESULTS: To test the act of the proposed hybrid it has been examined in comparison with the PSO and GWO methods. For this, eleven benchmark functions involving different unimodal and multimodal functions have been taken. The PSO, GWO and SGWO pseudo codes were coded in visual basic. In all the functions parameters of PSO and GWO were chosen as: w = 0.7, c1 = c2 = 2, population size = 30, number of iterations = 30. Experiments were redone 25 times for each of the method and for each benchmark function. The methods were compared with regard to their best and worst values besides their average values and standard deviations. The obtained results revealed that in terms of average values and standard deviations our hybrid SGWO outperformed both PSO and GWO notably. CONCLUSION: The outcomes of the experiments reveals that the proposed hybrid is better in comparison to both PSO and GWO in the search ability. Though the SGWO algorithm refines result quality, the computational complexity also gets elevated. Thus, lowering the computational complexity would be another issue of future work. Moreover, we will apply the proposed hybrid in the field of water quality estimation and prediction.

MLP-PSO Framework with Dynamic Network Tuning for Traffic Flow Forecasting

Traffic flow forecasting is the need of the hour requirement in Intelligent Transportation Systems (ITS). Various Artificial Intelligence Frameworks and Machine Learning Models are incorporated in today’s ITS to enhance forecasting. Tuning the model parameters play a vital role in designing an efficient model to improve the reliability of forecasting. Hence, the primary objective of this research is to propose a novel hybrid framework to tune the parameters of Multilayer Perceptron (MLP) using the Swarm Intelligence technique called Particle Swarm Optimization (PSO). The proposed MLP-PSO framework is designed to adjust the weights and bias parameters of MLP dynamically using PSO in order to optimize the network performance of MLP. PSO continuously monitors the gradient loss of MLP network while forecasting the traffic flow. The loss is reduced gradually using Inertia Weight (denoted as ω) which is the critical parameter of PSO. It is used to set a balance between the local and global search possibilities. The Inertia Weight has been varied in order to dynamically adjusts the network parameters of MLP. A comparison has been carried out among MLP and MLP-PSO models with variants of Inertia Weight Initializations. The results obtained justifies that, the proposed MLP-PSO framework reduces the forecasting error and improves reliability and accuracy than MLP model.

A Novel Modified Adaptive Controller Design for Non Negative DC–DC Converter Using Meta-Heuristic Algorithms for Bio Medical Hybrid Application

Purpose: Meta-heuristic (MH) methods are used to develop an adaptive sliding mode controller for a POEL converter. MH algorithms have been used to address a variety of engineering optimization problems. Which will use for Bio medical hybrid systems applications. Design/Methodology: Particle Swarm Optimization (PSO) approach is well known and it could expedite the convergence characteristic in numerous applications. By means of amending PSO parameters like, inertia mass, social and perceptive agents at every generation, Modern Parameter Improved Particle Swarm Optimization (MPIPSO) algorithm which is a more enhanced version of PSO is developed. Findings: Since the converter output voltage’s integral squared error (ISE) has been chosen as a neutral function, the optimal PI controller design may be expressed in terms of optimization problems. Originality/Value: The superiority of the proposed MPIPSO based sliding mode controller has been shown by comparing the results with other existing MH optimization methodologies.

Learning automata based particle swarm optimization for solving class imbalance problem

Class imbalance is an important problem in many domains such as disease classification, network intrusion detection, fraud detection, and spam filtering. While dealing with imbalanced datasets, traditional supervised machine learning algorithms do not often provide acceptable results. Several approaches are used to handle the class imbalance problem. Of these, undersampling approaches are mostly followed by the researchers in which the number of instances in the majority class gets reduced. Selection of instances from the majority class can be considered as an optimization problem. To this end, in this paper, we present an undersampling approach based on widely-used Particle Swarm Optimization (PSO). The majority class samples are first clustered to form the initial undersampled set. The samples to be selected are then optimized using PSO to give the best model. The parameters of PSO are fine tuned using Learning Automata. Appropriate metrics suitable for class imbalance problems have been used to construct the fitness function for optimizing the undersampled training set. The proposed method has achieved 2% to 10% performance improvement over most of the contemporary methods on various datasets with imbalance ratios ranging from 5 to 130, thus showing that the method is robust and useful in practical scenarios. The code of the proposed method can be accessed via https://github.com/kkg1999/Undersampling.

Design and Evaluation of Fuzzy Adaptive Particle Swarm Optimization Based Maximum Power Point Tracking on Photovoltaic System Under Partial Shading Conditions

Artificial intelligence methods such as fuzzy logic and particle swarm optimization (PSO) have been applied to maximum power point tracking (MPPT) for solar panels. The P-V curve of a solar panel exhibits multiple peaks under partial shading condition (PSC) when all modules of a solar panel do not receive the same solar irradiation. Although conventional PSO has been shown to perform well under uniform insolation, it is often unable to find the global maximum power point under PSC. Fuzzy adaptive PSO controllers have been proposed for MPPT. However, the controller became computation-intensive in order to adjust the PSO parameters for each particle. In this paper, fuzzy adaptive PSO-based and conventional PSO-based MPPT are compared and evaluated in the aspect of design and performance. A simple fuzzy adaptive PSO controller for MPPT was designed to reach the global optimal point under PSC and uniform irradiation. The controller combines the advantages of both PSO and fuzzy control. The fuzzy controller dynamically adjusts the PSO parameter to improve the convergence speed and global search capability. Since tuning of the PSO parameter is designed to be common for all particles, it reduced the computation complexity. The fuzzy controller’s rule base is designed to obtain a fast transient response and stable steady state response. Design of the fuzzy adaptive PSO-based MPPT is verified with simulation results using a boost converter. The results are evaluated in comparison to the results using a conventional PSO controller under PSC. Simulation shows the fuzzy adaptive PSO-based MPPT is able to improve the global search process and increase the convergency speed. The comparison indicates the settling time using the fuzzy adaptive PSO-based MPPT is 14% faster under PSC on average and 30% faster under uniform irradiation than the settling time using the conventional PSO. Both the fuzzy adaptive and conventional PSO controllers have similar output power tracking accuracy.

Application of hybrid intelligent systems in predicting the unconfined compressive strength of clay material mixed with recycled additive

A reliable prediction of the soil properties mixed with recycled material is considered as an ultimate goal of many geotechnical laboratory works. In this study, after planning and conducting a series of laboratory works, some basic properties of marine clay treated with recycled tiles together with their unconfined compressive strength (UCS) values were obtained. Then, these basic properties were selected as input variables to predict the UCS values through the use of two hybrid intelligent systems i.e., the neuro-swarm and the neuro-imperialism. Actually, in these systems, respectively, the weights and biases of the artificial neural network (ANN) were optimized using the particle swarm optimization (PSO) and imperialism competitive algorithm (ICA) to get a higher accuracy compared to a pre-developed ANN model. The best neuro-swarm and neuro-imperialism models were selected based on several parametric studies on the most important and effective parameters of PSO and ICA. Afterward, these models were evaluated according to several well-known performance indices. It was found that the neuro-swarm predictive model provides a higher level of accuracy in predicting the UCS of clay soil samples treated with recycled tiles. However, both hybrid predictive models can be used in practice to predict the UCS values for initial design of geotechnical structures.

OPTIMIZATION OF K-NEAREST NEIGHBOUR TO CATEGORIZE INDONESIAN'S NEWS ARTICLES

Text classification is the process of grouping documents based on similarity in categories. Some of the obstacles in doing text classification are many words appeared in the text, and some words come up with infrequent frequency (sparse words). The way to solve this problem is to conduct the feature selection process. There are several filter-based feature selection methods; some are Chi-Square, Information Gain, Genetic Algorithm, and Particle Swarm Optimization (PSO). Aghdam's research shows that PSO is the best among those methods. This study examined PSO to optimize the k-Nearest Neighbour (k-NN) algorithm's performance in categorizing news articles. k-NN is an algorithm that is simple and easy to implement. If we use the appropriate features, then the k-NN will be a reliable algorithm. PSO algorithm is used to select keywords (term features), and it is continued with classifying the documents using k-NN. The testing process consists of three stages. The stages are tuning the parameter of k-NN, the parameter of PSO, and measuring the testing performance. The parameter tuning process aims to determine the number of neighbours used in k-NN and optimize the PSO particles. Otherwise, the performance testing compares the performance of k-NN with and without using PSO. The optimal number of neighbours is 9, with the number of particles is 50. The testing showed that using the k-NN with PSO and a 50% reduction in terms. The results 20 per cent better accuracy than k-NN without PSO. Although the PSO's process did not always find the optimal conditions, the k-NN method can produce better accuracy. In this way, the k-NN method can work better in grouping news articles, especially in Indonesian language news articles

SIMULATION OF PARTICLE SWARM OPTIMIZATION FOR INVESTMENTS ON STOCK MARKET

This work reports simulations performed using Particle Swarm Optimization (PSO) as applied to investments on the stock market. About 480 stocks belonging to the S&P500 index have been taken into account. A naive approach has been developed in which one simulation step corresponded to one trading period. As a second ingredient of the investment strategy, the relative strength of an asset has been employed. The results are analyzed with respect to the parameters of PSO.