Original Particle Swarm Optimization Research Articles

A novel importance-guided particle swarm optimization based on MLP for solving large-scale feature selection problems

Feature selection is a crucial data preprocessing technique that effectively reduces the dataset size and enhances the performance of machine learning models. Evolutionary computation (EC) based feature selection has become one of the most important parts of feature selection methods. However, the performance of existing EC methods significantly decrease when dealing with datasets with thousands of dimensions. To address this issue, this paper proposes a novel method called importance-guided particle swarm optimization based on MLP (IGPSO) for feature selection. IGPSO utilizes a two stage trained neural network to learn a feature importance vector, which is then used as a guiding factor for population initialization and evolution. In the two stage of learning, the positive samples are used to learn the importance of useful features while the negative samples are used to identify the invalid features. Then the importance vector is generated combining the two category information. Finally, it is used to replace the acceleration factors and inertia weight in original binary PSO, which makes the individual acceleration factor and social acceleration factor are positively correlated with the importance values, while the inertia weight is negatively correlated with the importance value. Further more, IGPSO uses the flip probability to update the individuals. Experimental results on 24 datasets demonstrate that compared to other state-of-the-art algorithms, IGPSO can significantly reduce the number of features while maintaining satisfactory classification accuracy, thus achieving high-quality feature selection effects. In particular, compared with other state-of-the-art algorithms, there is an average reduction of 0.1 in the fitness value and an average increase of 6.7% in classification accuracy on large-scale datasets.

A proactive grey wolf optimization for improving bioinformatic systems with high dimensional data

This paper introduces a new methodology for optimization problems, combining the Grey Wolf Optimizer (GWO) with Simi-stochastic search processes. Intelligent optimizations represent an advanced approach in machine learning and computer applications, aiming to reduce the number of features used in the classification process. Optimizing bioinformatics datasets is crucial for information systems that classify data for intelligent tasks. The proposed A-Proactive Grey Wolf Optimization (A-GWO) solves stagnation in GWO by applying a dual search with a Simi-stochastic search. This target is achieved by distributing the population into two groups using a different search technique. The model's performance is evaluated using two benchmarks: the Evolutionary Computation Benchmark (CEC 2005) and seven popular biological datasets. A-GWO demonstrates highly improved efficiency in comparision to the original GWO and Particle Swarm Optimization (PSO). Specifically, it enhances exploration in 66% of CEC functions and achieves high accuracy in 70% of biological datasets.

Efficient aerodynamic optimization of turbine blade profiles: an integrated approach with novel HDSPSO algorithm

PurposeThis paper delves into the aerodynamic optimization of a single-stage axial turbine employed in aero-engines.Design/methodology/approachAn efficient integrated design optimization approach tailored for turbine blade profiles is proposed. The approach combines a novel hierarchical dynamic switching PSO (HDSPSO) algorithm with a parametric modeling technique of turbine blades and high-fidelity Computational Fluid Dynamics (CFD) simulation analysis. The proposed HDSPSO algorithm introduces significant enhancements to the original PSO in three pivotal aspects: adaptive acceleration coefficients, distance-based dynamic neighborhood, and a switchable learning mechanism. The core idea behind these improvements is to incorporate the evolutionary state, strengthen interactions within the swarm, enrich update strategies for particles, and effectively prevent premature convergence while enhancing global search capability.FindingsMathematical experiments are conducted to compare the performance of HDSPSO with three other representative PSO variants. The results demonstrate that HDSPSO is a competitive intelligent algorithm with significant global search capabilities and rapid convergence speed. Subsequently, the HDSPSO-based integrated design optimization approach is applied to optimize the turbine blade profiles. The optimized turbine blades have a more uniform thickness distribution, an enhanced loading distribution, and a better flow condition. Importantly, these optimizations lead to a remarkable improvement in aerodynamic performance under both design and non-design working conditions.Originality/valueThese findings highlight the effectiveness and advancement of the HDSPSO-based integrated design optimization approach for turbine blade profiles in enhancing the overall aerodynamic performance. Furthermore, it confirms the great prospects of the innovative HDSPSO algorithm in tackling challenging tasks in practical engineering applications.

Automatic calibration of a discrete element model of a masonry arch by swarm intelligence methods

This paper addresses the automatic calibration of constitutive parameters of the Discrete Element Method (DEM) models of masonry structures. Three swarm intelligence algorithms were applied, which are efficient in problems characterised by the small number of unknown parameters but high computational demand for the evaluation of the target function. Trust-Based Particle Swarm Optimisation (TBPSO) was chosen due to its excellent convergence rate. It was already tested that TBPSO converged faster than the original Genetic Algorithm and Particle Swarm Optimisation Methods. Therefore, TBPSO was compared with two recent and promising methods, the Marine Predator Algorithm (MPA) and the Golden Eagle Optimiser (GEO). The paper also presents a novel two-step approach, which enhances the performance of the tested optimisation strategies. The methodology is capable to account for and precisely find the mode of failure using Convolutional Neural Networks (CNN). The three optimisation methods and the two-step approach were applied on the DEM model of a quasi-static masonry arch collapse experiment from the literature. Performance of the three algorithms in identifying the appropriate constitutive parameters values of the DEM model were compared. Clear evidence on the advantage of the two-step approach with TBPSO is demonstrated. Remarks about different modelling issues are also included.

Impact and Integration of Electric vehicles on renewable energy based Microgrid: Frequency profile improvement by a-SCA optimized FO-Fuzzy PSS approach

The modelling of an electric vehicle along with its integration and impact over a renewable energy based microgrid topology is well addressed in this manuscript. The frequent charging and discharging of the electric vehicle makes an oscillation over grid frequency. The performance especially frequency of an islanded AC microgrid is also affected seriously under the actions of different uncertainties like load dynamics, wind fluctuation in wind plant, solar intensity variation of PV plant etc. In order to maintain standard frequency, this research work aims to regulate the net power generation of the system in response to total demand. To monitor net generation, this work has intended a fractional order fuzzy power system stabilizer (FO-Fuzzy PSS) control scheme in several dynamic situations. The proposed FO-Fuzzy PSS control scheme acts as most potential candidate to pertain stability in system frequency in above discussed disturbances. The controller gains are tuned optimally with suggesting an advanced- Sine Cosine Algorithm (a-SCA) under different conditions. The performance of the optimal FO- Fuzzy PSS controller is compared over standard fuzzy controller and PID controller in regard to frequency regulation of microgrid system. It is observed that proposed FO-Fuzzy PSS control scheme has the credential to reduce settling time of ΔF1 (area1 microgrid frequency) by 98.60% and 250.82% over fuzzy controller & PID controller correspondingly. Further, the dynamic optimal performance of the proposed a-SCA is compared over original SCA and PSO techniques to justify its superiority.

Fuel Combination Optimization Model of Thermal Power Plant Based on New Particle Swarm Optimization Algorithm

Influenced by the unbalanced state of particle swarm in the process of fuel combustion in thermal power plants, the fuel cost in the thermal power generation stage is relatively high. Therefore, a new particle swarm optimization model for fuel combination in thermal power plants is proposed. Combined with the combustion properties of different fuels, from the point of view of particle swarm optimization, in the process of carrying out specific particle swarm optimization simulation, the original particle swarm optimization algorithm is improved adaptively. A new particle swarm optimization algorithm is constructed by coupling it with a multiphase turbulence model. The fuel combustion performance of the power plant is analyzed by using its coupling. The optimization model of fuel combination in the thermal power plant is constructed by maximizing the energy release of fuel as the core, and the state of the fluid-particle field is taken as the constraint condition. In the test results, the design of the fuel combination optimization model can fully improve the energy release degree of fuel and reduce fuel consumption under the same power generation demand, which has a positive effect on power generation cost control.

A Particle Swarm and Smell Agent-Based Hybrid Algorithm for Enhanced Optimization

The particle swarm optimization (PSO) algorithm is widely used for optimization purposes across various domains, such as in precision agriculture, vehicular ad hoc networks, path planning, and for the assessment of mathematical test functions towards benchmarking different optimization algorithms. However, because of the inherent limitations in the velocity update mechanism of the algorithm, PSO often converges to suboptimal solutions. Thus, this paper aims to enhance the convergence rate and accuracy of the PSO algorithm by introducing a modified variant, which is based on a hybrid of the PSO and the smell agent optimization (SAO), termed the PSO-SAO algorithm. Our specific objective involves the incorporation of the trailing mode of the SAO algorithm into the PSO framework, with the goal of effectively regulating the velocity updates of the original PSO, thus improving its overall performance. By using the trailing mode, agents are continuously introduced to track molecules with higher concentrations, thus guiding the PSO’s particles towards optimal fitness locations. We evaluated the performance of the PSO-SAO, PSO, and SAO algorithms using a set of 37 benchmark functions categorized into unimodal and non-separable (UN), multimodal and non-separable (MS), and unimodal and separable (US) classes. The PSO-SAO achieved better convergence towards global solutions, performing better than the original PSO in 76% of the assessed functions. Specifically, it achieved a faster convergence rate and achieved a maximum fitness value of −2.02180678324 when tested on the Adjiman test function at a hopping frequency of 9. Consequently, these results underscore the potential of PSO-SAO for solving engineering problems effectively, such as in vehicle routing, network design, and energy system optimization. These findings serve as an initial stride towards the formulation of a robust hyperparameter tuning strategy applicable to supervised machine learning and deep learning models, particularly in the domains of natural language processing and path-loss modeling.

An extended PSO algorithm for cold-chain vehicle routing problem with independent loading and minimum fuel volume

With the increasing complexity of the distribution environment, customers usually propose higher requirements, such as independent loading of local and foreign cold-chain items in the event of an emergency. Moreover, minimum fuel volume plays an important role in the process of transportation with different speeds and different kinds of vehicles. In this paper, we present a new mathematical model to characterize cold-chain vehicle routing optimization with independent loading of local and foreign items and minimum fuel volume. To address the above mathematical model, an extended particle swarm optimization (PSO) algorithm is proposed by combining original PSO with 2-opt optimization to improve diversity and reduce convergence speed. Six sets of experiments are set to verify the practical performance and stability of the extended PSO algorithm based on three standard datasets of C201, R201, and RC201 from Solomon.

Face recognition technology for video surveillance integrated with particle swarm optimization algorithm

With the rapid development of video surveillance technology, face recognition has become an important security and surveillance tool. To improve the accuracy and applicability of face recognition in video surveillance, this study improved the Inertia Weight (IW) and Learning Factor (LF) based on the Particle Swarm Optimization (PSO) algorithm. Support Vector Machine (SVM) algorithm and Local Binary Mode (LBP) were used to optimize the processing. The results showed that the optimal solution could be obtained after 10 iterations, and the recognition accuracy reached 92.3%. When the number of iterations reached 40, the recognition accuracy inertia weight reached 99.7%. The average operating time of the original PSO algorithm and the optimized PSO algorithm was 26.3 s and 24.7 s, respectively. This shows that the optimization algorithm not only improves the recognition accuracy, but also shortens the operation time, and enhances the convergence performance and robustness to varying degrees. The improved model can improve the recognition rate of video surveillance system, indicating that the optimization algorithm has great application potential in the video surveillance face recognition.

TPPSO: A Novel Two-Phase Particle Swarm Optimization

Particle swarm optimization (PSO) is a stout and rapid searching algorithm that has been used in various applications. Nevertheless, its major drawback is the stagnation problem that arises in the later phases of the search process. To solve this problem, a proper balance between investigation and manipulation throughout the search process should be maintained. This article proposes a new PSO variant named two-phases PSO (TPPSO). The concept of TPPSO is to split the search process into two phases. The first phase performs the original PSO operations with linearly decreasing inertia weight, and its objective is to focus on exploration. The second phase focuses on exploitation by generating two random positions in each iteration that are close to the global best position. The two generated positions are compared with the global best position sequentially. If a generated position performs better than the global best position, then it replaces the global best position. To prove the effectiveness of the proposed algorithm, sixteen popular unimodal, multimodal, shifted, and rotated benchmarking functions have been used to compare its performance with other existing well-known PSO variants and non-PSO algorithms. Simulation results show that TPPSO outperforms the other modified and hybrid PSO variants regarding solution quality, convergence speed, and robustness. The convergence speed of TPPSO is extremely fast, making it a suitable optimizer for real-world optimization problems.

State estimation for distribution power systems by applying an advanced optimization approach

New centralized automation functions in distribution system control centers are needed in order to ensure the control of both distribution network and connected DGs. Consequently, state estimators need to be developed for future distribution systems to assess the network’s state in real time, i.e., minutes typical time frame, based on real, and virtual measurements. This paper proposes a new method based on the particle community optimization algorithm to estimate the state of electricity distribution networks. To increase the efficiency, accuracy, and speed of convergence rate to the answer and prevent the main particle assembly algorithm from fluctuating, the second particle assembly loop is provided in addition to the mutation algorithm and the isolation function. To consider the uncertainty of loads in distribution networks, modeled as active and reactive, virtual measurements with realistic error have been modeled. Results are presented and discussed to prove the efficiency of the proposed method, including sensitivity analysis for parameters used by the algorithm. The simulation results on two 6-bus and 34-bus radial distribution networks of the IEEE test show that the estimation of the distribution state based on the proposed DLM-PSO algorithm has a lower estimation error and standard deviation than the original HBMO, GA, WLS, and PSO algorithms.

Optimization of Algorithm for Solving Railroad Power Conditioner Compensation Power Reference Value and System Power Quality Analysis Based on Optimal Compensation Model

At present, electrified railroads with complex road conditions are facing the problems of the existence of a single power supply method, the deterioration in power quality, and the difficulty in recycling regenerative braking energy. In order to improve the above problems, this paper establishes a traction power supply system containing photovoltaic units, proposes an optimized compensation model for the RPC (railroad power conditioner), and improves the particle swarm algorithm for solving the reference value of RPC compensation power. First, the structure of the RPC-based traction photovoltaic power generation system and the establishment of the integrated energy management strategy of the system are constructed. Then, the back-to-back converter compensation model with power quality index parameter constraints is established, which establishes the optimization function with the objectives of minimizing the negative sequence current, maximizing the power factor, and minimizing the RPC compensation power, as well as establishes constraints on the active converter capacity and three-phase voltage imbalance. Then, the particle swarm algorithm for solving the RPC compensation power reference value is improved, specifically in the original PSO by introducing dynamically changing inertia weights and learning factors. This not only solves the problem of the single power supply and realizes the nearby consumption of photovoltaic units in the traction system, but also realizes the recycling of regenerative braking energy and the coordinated control of the traction photovoltaic power generation system, improves the power quality of the system, and meets the demand of the RPC for real-time control. In order to verify the effectiveness of the optimized compensation model established in this paper and improve the convergence of the particle swarm algorithm for solving the RPC compensation power reference value, a simulation model of the traction PV power generation system is established in MATLAB/Simulink, and a real-time simulation is carried out to verify it based on the preset working condition data. The results show that the RPC optimization compensation model developed in this paper can coordinate the control system energy flow and improve the system power quality (the power factor increases and the negative sequence current decreases). The improved particle swarm algorithm is more convergent.

Design of Health Healing Lighting in a Medical Center Based on Intelligent Lighting Control System

The intelligent lighting control system will unify the management of lighting equipment in outpatient buildings, inpatient buildings, and other buildings of the hospital, thereby improving the service quality of the hospital, providing a comfortable and relaxed working environment for medical staff, and providing a warm and comfortable treatment environment for patients. This project aims to develop a health rehabilitation environment lighting automation control system based on combining Zigbee Wide Ad Hoc Network and RFID (Radio Frequency Identification) technology. It can be customized according to the comfort needs of patients and can achieve lighting adjustments before the patient arrives. A PSO-based intelligent lighting control method has been proposed. To overcome the shortcomings of PSO such as being prone to local minima and premature convergence, a new PSO optimization method is proposed based on the inertia weight PSO and combined with genetic optimization theory. This method can not only learn experience from individuals in the group but also avoid the possibility of parent particles falling into local extremum. Compared with the original particle swarm optimization algorithm, the new particle swarm optimization algorithm can quickly find the optimal combination of lighting devices, improve computational efficiency by 6.208%, and also reduce the energy consumption of the calculated lighting devices, indicating the advantages of the new particle swarm optimization algorithm.

Bayesian damage identification of an unsymmetrical frame structure with an improved PSO algorithm

With the development of artificial intelligence technology, intelligent algorithms are widely utilized in the field of probabilistic model updating to solve the optimization problems. In this study, the opposition-based learning based on population centroid and boundary rebound strategy was incorporated into PSO to improve the optimization performance on structural damage detection, and the damage identification of an unsymmetrical frame based on Bayesian model updating with the improved PSO algorithm is proposed for the first time. Six benchmark functions were firstly employed to test the optimization performance of the improved PSO algorithm, which overcomes the premature convergence of the original PSO algorithm in which trapped particles often fall into local optimum. Then three damage scenarios of a laboratory unsymmetrical frame were utilized to validate the effectiveness of the proposed method in structural damage identification. The encouraging experimental results exhibit that the proposed method not only can successfully identify the damage locations and extents, but the associated uncertainties of the identified results can be quantified by calculating the posterior probability density functions of the uncertain model parameters. In addition, the effects of the quantities of measured information on the posterior uncertainties of the model parameters were investigated, and the uncertainty analysis results reveal that the posterior uncertainties associated with the identified model parameters are sensitive to the amount of measurement used in model updating. The proposed method is expected to help in damage identification and condition assessment of the practical engineering structures.

Set-Based Particle Swarm Optimisation: A Review

The set-based particle swarm optimisation algorithm is a swarm-based meta-heuristic that has gained popularity in recent years. In contrast to the original particle swarm optimisation algorithm, the set-based particle swarm optimisation algorithm is used to solve discrete and combinatorial optimisation problems. The main objective of this paper is to review the set-based particle swarm optimisation algorithm and to provide an overview of the problems to which the algorithm has been applied. This paper starts with an examination of previous attempts to create a set-based particle swarm optimisation algorithm and discusses the shortcomings of the existing attempts. The set-based particle swarm optimisation algorithm is established as the only suitable particle swarm variant that is both based on true set theory and does not require problem-specific modifications. In-depth explanations are given regarding the general position and velocity update equations, the mechanisms used to control the exploration–exploitation trade-off, and the quantifiers of swarm diversity. After the various existing applications of set-based particle swarm optimisation are presented, this paper concludes with a discussion on potential future research.

Two-phase heat transfer microchannel system identification with Particle Swarm Optimization (PSO) approach

The complex behavior of two-phase flow particularly in microchannels can be unpredictable. Experimental measurements are near impossible because of the unavailable compatible assessment equipment. Meanwhile, repeated experiments for reliability of outcomes are costly and involved much time and effort. Environmentally friendly propane is currently being considered as a replacement for hazardous coolants in available refrigeration and air-conditioning systems. This paper reports a system identification (SI) analysis of the collected experimental data of two-phase flow of refrigerant R290 in a microchannel test rig. An ARX model was chosen as the dynamic model, and the modeling of the input–output data was done using a new methodology based on particle swarm optimization (PSO) technique. Measured temperature difference across the microchannel test section and the mass flow rate were the input and output, respectively. The performance of the particle swarm optimization with discoverer (PSOd) was investigated and compared to the original PSO technique. The model was then validated by mean-squared error (MSE). Results demonstrate the advantages of discoverer in PSOd over its standard counterpart with a smaller MSE of 6.2629 × 10−11 and a faster convergence. The SI allows a better prediction of the mass flow rate before any further experiments to obtain the heat transfer coefficient are done. The model provides better management of design of experiments that involve the complex two-phase flow in a microchannel, consequently saving experimental time and cost.

An Efficient Metaheuristic Algorithm for Job Shop Scheduling in a Dynamic Environment

This paper proposes an Improved Multi-phase Particle Swarm Optimization (IMPPSO) to solve a Dynamic Job Shop Scheduling Problem (DJSSP) known as an non-deterministic polynomial-time hard (NP-hard) problem. A cellular neighbor network, a velocity reinitialization strategy, a randomly select sub-dimension strategy, and a constraint handling function are introduced in the IMPPSO. The IMPPSO is used to solve the Kundakcı and Kulak problem set and is compared with the original Multi-phase Particle Swarm Optimization (MPPSO) and Heuristic Kalman Algorithm (HKA). The results show that the IMPPSO has better global exploration capability and convergence. The IMPPSO has improved fitness for most of the benchmark instances of the Kundakcı and Kulak problem set, with an average improvement rate of 5.16% compared to the Genetic Algorithm-Mixed (GAM) and of 0.74% compared to HKA. The performance of the IMPPSO for solving real-world problems is verified by a case study. The high level of operational efficiency is also evaluated and demonstrated by proposing a simulation model capable of using the decision-making algorithm in a real-world environment.

Improved Particle Swarm Path Planning Algorithm with Multi-Factor Coupling in Forest Fire Spread Scenarios

In this paper, a solution based on an improved particle swarm algorithm is proposed for the path planning problem without a road network in forest fire rescue scenarios. The algorithm adopts an adaptive inertia weight and a dynamically updated learning factor strategy to enhance the global and local search capabilities of the algorithm. In terms of cost function design, the article considers three factors: path length, terrain slope, and obstacle avoidance ability to ensure the safety and effectiveness of the path. The experimental results show that: (1) the path planning algorithm based on improved particle swarm optimization can effectively avoid spreading wildfire and reach the designated target point with a good “detour” effect; (2) the path planned by the improved PSO algorithm performs better than the original PSO algorithm in terms of fitness evaluation and average slope; and (3) changes in the particle population, dimensions, and learning factors in the particle swarm optimization algorithm can affect the convergence of the final path. Increasing the particle dimensions can bring more reasonable and specific paths; decreasing the learning factor increases the convergence iterations, but also obtains a better path planning solution and higher fitness.

Prediction of TBM operation parameters using machine learning models based on BPSO

Rational parameters of TBM (Tunnel Boring Machine) are the key to ensuring efficient and safe tunnel construction. Machine learning (ML) has become the main method for predicting operating parameters. Grid Search and optimization algorithms, such as Particle Swarm Optimization (PSO), are often used to find the hyper parameters of ML models but suffer from excessive time and low accuracy. In order to efficiently construct ML models and enhance the accuracy of predicting models, a BPSO (Beetle antennae search Particle Swarm Optimization) algorithm is proposed. Based on the PSO algorithm, the concept of BAS (Beetle Antennae Search) is integrated into the updating process of an individual particle, which improves the random search capability. The convergence of the BPSO algorithm is discussed in terms of inhomogeneous recursive equations and characteristic roots. Then, based on the proposed BPSO prototype, a hybrid ML model BPSO-XGBoost (eXtreme Gradient Boosting) is proposed. We applied the model to the Hangzhou Central Park tunnel project for the prediction of screw conveyer rotational speed. Finally, our model is compared with existing methods. The experimental results show that the BPSO-based model outperforms other traditional ML methods. The BPSO-XGBoost is more accurate than PSO-XGBoost and BPSO-RandomForest for predicting the speed. Also, it is verified that the hyper parameters optimized by the BPSO are better than those optimized by the original PSO. The comprehensive prediction performance ranking of models is as follows: BPSO-XGBoost > PSO-XGBoost > BPSO-RF > PSO-RF. Our models have preferable engineering application value.

A Survey of Algorithms, Applications and Trends for Particle Swarm Optimization

Survey/review study A Survey of Algorithms, Applications and Trends for Particle Swarm Optimization Jingzhong Fang 1, Weibo Liu 1,*, Linwei Chen 2, Stanislao Lauria 1, Alina Miron 1, and Xiaohui Liu 1 1 Department of Computer Science, Brunel University London, Uxbridge, Middlesex, UB8 3PH, United Kingdom 2 The School of Engineering, University of Warwick, Coventry CV4 7AL, United Kingdom * Correspondence: Weibo.Liu2@brunel.ac.uk Received: 18 October 2022 Accepted: 28 November 2022 Published: 27 March 2023 Abstract: Particle swarm optimization (PSO) is a popular heuristic method, which is capable of effectively dealing with various optimization problems. A detailed overview of the original PSO and some PSO variant algorithms is presented in this paper. An up-to-date review is provided on the development of PSO variants, which include four types i.e., the adjustment of control parameters, the newly-designed updating strategies, the topological structures, and the hybridization with other optimization algorithms. A general overview of some selected applications (e.g., robotics, energy systems, power systems, and data analytics) of the PSO algorithms is also given. In this paper, some possible future research topics of the PSO algorithms are also introduced.