Learning Particle Swarm Optimization Research Articles

Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization on cloud environment

Multi-objective energy aware task scheduling using Orthogonal Learning Particle Swarm Optimization on cloud environment

Deep contextual reinforcement learning algorithm for scalable power scheduling

This article introduces a deep contextual reinforcement learning (DCRL) optimization algorithm to tackle the NP-hard power scheduling problem. The algorithm is based on a multi-agent simulation environment that decomposes the power scheduling problem into sequential Markov decision processes (MDPs). The simulation environment inherently corrects incorrect decisions and adjusts supply capacities so that the MDPs adhere to the optimization constraints. A deep reinforcement learning (DRL) model is trained on these MDPs to provide optimal solutions. Demonstrating its applicability and effectiveness, the proposed method is evaluated on various test systems with different unit numbers, constraints, and production cost functions. The experimental results show that the proposed method has better performance relative to alternative methods, such as binary alternative moth-flame optimization (BAMFO), binary particle swarm optimization (BPSO), teaching learning-based optimization (TLBO), new binary particle swarm optimization (NBPSO), binary learning particle swarm optimization (BLPSO), quasi-oppositional teaching learning-based algorithm (QOTLBO), binary-real-coded genetic algorithm (BRCGA), hybrid genetic-imperialist competitive algorithm (HGICA), three-stage priority list (TSPL), and hybridized evolutionary algorithm and sequential quadratic programming (HEPSQP). The novelties of the proposed method lie in its adaptability to longer planning horizons and linear dimensionality complexity, rendering it suitable for large-scale power systems.

Wave spectrum fitting with multiple parameters based on optimization algorithms and its application

In the realm of ocean engineering and environmental research, the accuracy of the wave spectrum is paramount. Traditional models, constrained by the number of parameters, often struggle to accurately capture the intricacies of real-world wave spectra, especially when confronting the complexities of multi-peak spectral shapes shaped by wind-sea and swell systems. This research develops a novel multi-parameter wave spectrum model that substantially amplifies the capacity to describe the diversity of wave spectra by introducing more shape parameters. The proposed model includes more shape parameters than its predecessors. These parameters can be directly optimized and obtained through the Heterogeneous Comprehensive Learning Particle Swarm Optimizer (HCLPSO). This sophisticated algorithm leverages its robust global search capabilities and swift convergence to fine-tune the model’s parameters, ensuring a high degree of precision in fitting the measured wave spectra. Furthermore, the proposed model also shows great potential in wave spectrum prediction, even when there are fewer training samples, it can still yield relatively accurate predictive results. This research not only improves the applicability and accuracy of the wave spectrum model but also offers a new tool for ocean wave research and real-world applications, thereby contributing important research and practical value to the field.

Scheduling of twin automatic stacking cranes and automated guided vehicle considering buffer mode on automated container terminal

To improve the efficiency of automatic stacking crane (ASC) and automated guided vehicle (AGV) scheduling in synchronized import and export mode at automated container terminal (ACT), with the objective of minimizing the maximum ASC completion time and AGV wait time, a twin ASCs and AGV scheduling model is established, which considers both the size of handshake area and buffer, and the location constraints of handshake area. Longest transport time priority (LTTP) and traversal priority (TP) heuristics strategies are designed to adjust the execution order of ASCs to reduce the wait time of ASCs. Based on the comprehensive learning particle swarm optimization algorithm (CLPSO), the discrete coding CLPSO algorithm (CLDPSO) is developed by designed permutation coding for ASC execution order and integer coding for AGV numbering, and the convergence speed is improved by dynamically adjusting the weight parameters. The experimental results show that increasing the handshake area and buffer size can reduce the fitness value by 3.64 % and 5.58 % on average respectively, the selected optimal handshake area location can reduce the fitness value by 3.51 % on average compared with the conventional location, the TP strategy can reduce the waiting time of ASC by up to 16.89 %. Compared to the PSO and DPSO algorithms, the fitness value of CLDPSO can reduce the fitness value by 13.83 % and 7.80 %, and the computation time is reduced by 10.67 % and 7.43 % on average, respectively.

Surrogate-assisted constrained hybrid particle swarm optimization algorithm for propane pre-cooled mixed refrigerant LNG process optimization

The propane pre-cooled mixed refrigerant (C3MR) process is one of the most widely used and efficient natural gas liquefaction processes. However, optimization of this process involves various design and operational constraints, complex thermodynamics, and hence nonconvex in nature. Therefore, it's computationally expensive, often involving trial and error approaches. Existing optimization algorithms often possess flaws such as insufficient accuracy and premature convergence, leading to suboptimal solutions that may violate essential process constraints. This article proposes a novel method to optimize the C3MR process that handles the computational complexity, meets the constraints, and achieves feasible solutions quickly. The proposed method includes modified feasibility-based constraint handling and radial basis function network-assisted surrogate modeling and optimization, where the power consumption is optimized using a hybrid of the particle swarm optimization (PSO) and social learning PSO algorithm. The proposed algorithm achieves the optimum power consumption (121109.31 kW), which is 21.5 % less than the base case (154200 kW). The optimization results are compared with similar optimization algorithms, where the proposed algorithm outperformed the other algorithm regarding optimal solution, convergence, and speed. The results from this study are compared to previous studies from the literature, which validate the accuracy and applicability of the proposed method.

Heterogeneous pbest-guided comprehensive learning particle swarm optimization

The balance between exploration and exploitation in the particle swarm optimization (PSO) algorithm is often discussed but has not been well solved. To further improve the capabilities of exploration and exploitation in the search space, the aim of this study is to focus on a novel comprehensive learning strategy for the PSO algorithm, which is named the heterogeneous pbest-guided comprehensive learning particle swarm optimizer (HPBPSO). In this algorithm, the population is divided into two subpopulations. In the exploration subpopulation, a pbest-guided mechanism is designed for obtaining better particles’ personal best information. Meanwhile, the non-elite personal best particles learn from elite personal best particles by using dynamic crossover strategy. In the exploitation subpopulation, in order to fully leverage the benefits of learning from high-quality individuals, the learning process is divided into two distinct categories: elite individual learning and intragroup learning. Furthermore, intergroup perturbation is designed to accelerate convergence performance. The experiments on classical functions are firstly used to verify the effectiveness and mutuality of the proposed strategies. Moreover, the performance of the proposed algorithm is evaluated on two well-known benchmarks and medical image segmentation problem. According to the statistical results, the HPBPSO algorithm is not only better than the other existing state-of-the-art PSO variants and metaheuristic evolutionary algorithms, but also applicable to real-world optimization problems.

A multi-strategy surrogate-assisted social learning particle swarm optimization for expensive optimization and applications

Evolutionary algorithms (EAs) require extensive fitness evaluations, which constitutes a barrier to solving computationally complex problems. In contrast, surrogate-assisted evolutionary algorithms (SAEAs) have the potential to solve complex expensive optimization problems. This paper proposes a surrogate-assisted social learning particle swarm optimization (SASLPSO) to handle expensive optimization problems. An adaptive local surrogate (ALS) strategy introduced in SASLPSO is introduced to accurately fit the landscape near the global optimum. ALS consists of two layers of surrogate, the part of the particles closest to the optimal particle and the closest to the optimal particle among the particles that have been eliminated historically. The proposed SASLPSO effectively combines global surrogate (GS) and adaptive local surrogate (ALS) to balance global exploration and local exploitation. Furthermore, a novel random group-based pre-screening (RGBPS) strategy is proposed to screen promising particles for real function evaluation. The proposed SASLPSO is compared with four other state-of-the-art SAEAs on 30D, 50D, and 100D benchmark functions. In addition, the significance of the SASLPSO algorithm was also verified using the Wilcoxon rank test. The test results on the benchmark function show that the SASLPSO algorithm performs better than other comparison algorithms, especially when dealing with high-dimensional benchmark functions. To further validate the effectiveness of the SASLPSO algorithm in solving expensive optimization problems, it was also applied to feature selection problems and real-world engineering problems. In addition, in the real application of node deployment in 3D wireless sensor networks, the highest coverage rate of the SASLPSO algorithm can reach 99.96%, confirming its performance advantages in solving real application problems. Finally, in the application of network intrusion detection, SASLPSO has shown more advantages in multiple metrics, proving its versatility.

Predicting anti-trypanosome effect of carbazole-derived compounds by powerful SVM with novel kernel function and comprehensive learning PSO.

In order to predict the anti-trypanosome effect of carbazole-derived compounds by quantitative structure-activity relationship, five models were established by the linear method, random forest, radial basis kernel function support vector machine, linear combination mix-kernel function support vector machine, and nonlinear combination mix-kernel function support vector machine (NLMIX-SVM). The heuristic method and optimized CatBoost were used to select two different key descriptor sets for building linear and nonlinear models, respectively. Hyperparameters in all nonlinear models were optimized by comprehensive learning particle swarm optimization with low complexity and fast convergence. Furthermore, the models' robustness and reliability underwent rigorous assessment using fivefold and leave-one-out cross-validation, y-randomization, and statistics including concordance correlation coefficient (CCC), [Formula: see text] , [Formula: see text] , and [Formula: see text] . Among all the models, the NLMIX-SVM model, which was established by support vector regression using a nonlinear combination of radial basis kernel function, sigmoid kernel function, and linear kernel function as a new kernel function, demonstrated excellent learning and generalization abilities as well as robustness: [Formula: see text] = 0.9581, mean square error (MSE) = 0.0199 for the training set and [Formula: see text] = 0.9528, MSE = 0.0174 for the test set. [Formula: see text] , [Formula: see text] , CCC, [Formula: see text] , [Formula: see text], and [Formula: see text] are 0.9539, 0.8908, 0.9752, 0.9529, 0.9528, and 0.9633, respectively. The NLMIX-SVM method proved to be a promising way in quantitative structure-activity relationship research. In addition, molecular docking experiments were conducted to analyze the properties of new derivatives, and a new potential candidate drug molecule was ultimately found. In summary, this study will provide help for the design and screening of novel anti-trypanosome drugs.

“Reinforcement learning particle swarm optimization based trajectory planning of autonomous ground vehicle using 2D LiDAR point cloud”

The advent of autonomous mobile robots has spurred research into efficient trajectory planning methods, particularly in dynamic environments with varied obstacles. This study focuses on optimizing trajectory planning for an Autonomous Ground Vehicle (AGV) using a novel Reinforcement Learning Particle Swarm Optimization (RLPSO) algorithm. Real-time mobile robot localization and map generation are introduced through the utilization of the Hector-SLAM algorithm within the Robot Operating System (ROS) platform, resulting in the creation of a binary occupancy grid. The present research thoroughly investigates the performance of the RLPSO algorithm, juxtaposed against five established Particle Swarm Optimization (PSO) variants, within the context of four distinct physical environments. The experimental design is tailored to emulate real-world scenarios, encompassing a spectrum of challenges posed by static and dynamic obstacles. The AGV, equipped with LiDAR sensors, navigates through diverse environments characterized by obstacles of different geometries. The RLPSO algorithm dynamically adapts its strategies based on feedback, enabling adaptable trajectory planning while effectively avoiding obstacles. Numerical results obtained from extensive experimentation highlight the algorithm's efficacy. The navigational model's validation is achieved within a MATLAB 2D virtual environment, employing 2D Lidar mapping point data. Transitioning to physical experiments with an AGV, RLPSO continues to demonstrate superior performance, showcasing its potential for real-world applications in autonomous navigation. On average, RLPSO achieves a 10–15 % reduction in path distances and traversal time compared to the following best-performing PSO variant across diverse scenarios. The adaptive nature of RLPSO, informed by feedback from the environment, distinguishes it as a promising solution for autonomous navigation in dynamic settings, with implications for practical implementation in real-world scenarios.

PSO Training Neural Network MPPT with CUK Converter Topology for Stand-Alone PV Systems Under Varying Load and Climatic Conditions

Temperature and irradiance levels are two examples of environmental variables that affect the power value produced by photovoltaic panels. Therefore, in order to transfer the maximum power value from the PV panel to the load under varying climatic conditions, maximum power point tracking (MPPT) algorithms and DC-DC converter topologies are used. In this study, the performances of boost converter and CUK converter circuit topologies are investigated under variable irradiance and variable load conditions by using a neural network-based MPPT algorithm learning particle swarm optimization (PSO). As the first scenario, it is analyzed assuming that the temperature and irradiance values coming to the panel are constant. As the second scenario, the performance evaluation of the converter topologies according to the current, voltage and power parameters is made for the variable load situation. As the last scenario, the difference in the irradiance value coming to the panel depending on the sun's condition during the day has been examined. Canadian Solar CS6P-250P PV panel is used in the study. 50 kHz is selected as the switching frequency. According to the results obtained, it has been observed that the CUK converter circuit topology reaches the maximum power point faster than the boost converter circuit topology both in dynamic environmental conditions and load change, and the oscillation at this point is less. It is aimed to increase the performance of this method, which uses boost converter topology and MPPT in the literature, by applying CUK converter topology.

Comprehensive Learning Particle Swarm Optimization Based on Optimal Particle Recombination

Particle swarm optimization (PSO) algorithm has been widely used in large-scale complex problems such as resource allocation in recent years because of its simple implementation and easy operation. However, the slow convergence speed and low solution accuracy of the algorithm also restrict its further application. To solve the above problems, this paper introduces the chromosome crossing characteristics of genetic algorithm (GA), and proposes a comprehensive learning particle swarm optimization based on optimal particle recombination. With the help of the ability of comprehensive learning strategy to efficiently explore the solution space, this method organically combines the excellent information explored by each particle through the optimal particle recombination, so as to obtain a better individual, speed up the convergence speed of the algorithm, and improve the solution accuracy of the problem. The experimental results of benchmark function show that the proposed algorithm has faster convergence speed and optimization accuracy than the original algorithm, and the results of Friedman test and Wilcoxon signed-rank test prove the feasibility of the optimal particle recombination operation in particle swarm optimization.

Self-adaptive learning particle swarm optimization-based path planning of mobile robot using 2D Lidar environment

AbstractThe loading and unloading operations of smart logistic application robots depend largely on their perception system. However, there is a paucity of study on the evaluation of Lidar maps and their SLAM algorithms in complex environment navigation system. In the proposed work, the Lidar information is finetuned using binary occupancy grid approach and implemented Improved Self-Adaptive Learning Particle Swarm Optimization (ISALPSO) algorithm for path prediction. The approach makes use of 2D Lidar mapping to determine the most efficient route for a mobile robot in logistical applications. The Hector SLAM method is used in the Robot Operating System (ROS) platform to implement mobile robot real-time location and map building, which is subsequently transformed into a binary occupancy grid. To show the path navigation findings of the proposed methodologies, a navigational model has been created in the MATLAB 2D virtual environment using 2D Lidar mapping point data. The ISALPSO algorithm adapts its parameters inertia weight, acceleration coefficients, learning coefficients, mutation factor, and swarm size, based on the performance of the generated path. In comparison to the other five PSO variants, the ISALPSO algorithm has a considerably shorter path, a quick convergence rate, and requires less time to compute the distance between the locations of transporting and unloading environments, based on the simulation results that was generated and its validation using a 2D Lidar environment. The efficiency and effectiveness of path planning for mobile robots in logistic applications are validated using Quanser hardware interfaced with 2D Lidar and operated in environment 3 using proposed algorithm for production of optimal path.

Extracting Micro-Doppler Features from Multi-Rotor Unmanned Aerial Vehicles Using Time-Frequency Rotation Domain Concentration

This study addresses the growing concern over the impact of small unmanned aerial vehicles (UAVs), particularly rotor UAVs, on air traffic order and public safety. We propose a novel method for micro-Doppler feature extraction in multi-rotor UAVs within the time-frequency transform domain. Utilizing competitive learning particle swarm optimization (CLPSO), our approach divides population dynamics into three subgroups, each employing unique optimization mechanisms to enhance local search capabilities. This method overcomes limitations in traditional Particle Swarm Optimization (PSO) algorithms, specifically in achieving global optimal solutions. Our simulation and experimental results demonstrate the method’s efficiency and accuracy in extracting micro-Doppler features of rotary-wing UAVs. This advancement not only facilitates UAV detection and identification but also significantly contributes to the fields of UAV monitoring and airspace security.

Robot Path Planning Based on Generative Learning Particle Swarm Optimization

Robot Path Planning Based on Generative Learning Particle Swarm Optimization

Multi-body dynamic evolution sequence-assisted PSO for interval analysis

<p>To enhance the efficiency and accuracy of response analysis in practical multivariable complex engineering problems, we introduced a new interval analysis method—multi-body dynamic evolution sequence-assisted particle swarm optimization (DES-PSO) is introduced in this research. This method optimizes the heterogeneous comprehensive learning particle swarm optimization algorithm (HCLPSO) by incorporating a dynamic evolution sequence (DES), addressing the difficulty of HCLPSO in covering the search space, which makes this method suitable for solving multivariable interval analysis problems. The results of two numerical examples prove that both DES-PSO and HCLPSO can give the accurate upper and lower bounds of the response interval. Compared with HCLPSO, DES-PSO improves the computing speed by about 50%.</p>

Fractional-order modified heterogeneous comprehensive learning particle swarm optimizer for intelligent disease detection in IoMT environment

This paper presents an alternative early disease detection technique based on the Internet of Medical Things (IoMT) to improve the healthcare system. Since it is necessary to address different aspects to help healthcare organizations to improve their efficiency. Early disease detection using a fast and efficient test, such as chest X-ray images, is one of the most important issues. In this paper, we develop an efficient model to allocate abnormalities in medical chest X-ray images. The developed model consists of a set of stages; the first stage is to segment the images using a multilevel thresholding technique to determine the lung inside the image, then extracting the features from the segmented objects using different extractor methods. Then, we proposed a Fractional-order modified Heterogeneous comprehensive learning particle swarm optimizer (FMHCLPSO) as a feature selection method to determine the relevant features used to improve the detection process. To evaluate the performance of the developed IoMT model, a set of three medical datasets is used, called Covid-19 & Pneumonia, X-raycovid, and Radiography. The results illustrate the high efficiency of the developed model to detect diseases based on performance measures. Furthermore, We compared the proposed method to several existing methods, and it showed significant performance.

A neighborhood comprehensive learning particle swarm optimization for the vehicle routing problem with time windows

Vehicle routing problem with time windows (VRPTW), which is a typical NP-hard combinatorial optimization problem, plays an important role in modern logistics and transportation systems. Recent years, heuristic and meta-heuristic algorithms have attracted many researchers’ attentions to solve the VRPTW problems. As an outstanding meta-heuristic algorithm, particle swarm optimization (PSO) algorithm exhibits very promising performance on continuous problems. However, how to adapt PSO to efficiently deal with VRPTW is still challenging work. In this paper, we propose a neighborhood comprehensive learning particle swarm optimization (N-CLPSO) to solve VRPTW. To improve the exploitation capability of N-CLPSO, we introduce a new remove-reinsert neighborhood search mechanism, which consists of the removed operator and the reinsert operator. When performing the removed operator, the probability of adjacency between two customers is calculated by an information matrix (IM), which is constructed based on the customers’ time-space information and elite individuals’ local information. When executing the reinsert operator, the IM and a cost matrix (CM), which is introduced to record the cost of customer insertion, are used to find an optimal insert position. Moreover, to enhance the exploration of N-CLPSO, a semi-random disturbance strategy is proposed, in which elites’ longest common sequences (LCS) are saved, aiming to prevent population degradation. The N-CLPSO algorithm is tested on 56 Solomon benchmark instances, and it attains the optimal solutions on 29 instances. The simulation results and comparison results illustrate that the proposed algorithm outperforms or can compete with the majority of other 3 PSO variants as well as other 12 state-of-the-art algorithms.

Bi-directional learning particle swarm optimization for large-scale optimization

Large-scale optimization problems (LSOPs) are an essential research topic in the evolutionary computation (EC) community with two challenges: slow convergence in the huge search space and the trap in massive locally optimal solutions. To tackle these two challenges, this paper proposes a bi-directional learning particle swarm optimization (BLPSO) with two learning strategies, called diversity learning strategy (DLS) and convergence learning strategy (CLS). In DLS, we first propose a diversity evaluation mechanism based on locally sensitive hashing (LSH) to measure the diversity of individuals. Then the density individuals will learn from other dispersed individuals with good diversity to enhance the diversity of the population. In CLS, the inferior individuals will learn from other superior individuals with excellent evolution information to help the population accelerate convergence speed. These two learning strategies act in different roles and complement each other. With these two learning strategies, BLPSO achieves a balance between sufficient diversity and fast convergence in solving LSOPs. Two large-scale test suites, IEEE CEC2010 and IEEE CEC2013, are used to test the performance between BLPSO and other state-of-the-art algorithms. The experimental results show that BLPSO outperforms other algorithms on both test suites, including the winner algorithms of the IEEE CEC2010 and IEEE CEC2012 competitions. Finally, BLPSO is applied to a large-scale portfolio optimization problem to illustrate its application capability.

Recuperation based multi-objective generation expansion planning for a real-world power system

This paper proposed a multi-objective-based Generation Expansion Planning (GEP) for the real-word power generation system of Tamil Nadu, an Indian state. GEP aims to solve numerous conflicting problems for constructing new power plants. The proposed approaches are Multi-Objective Comprehensive Learning Particle Swarm Optimization (MOCLPSO) and Circle Search algorithm. The key objectives of the proposed method is to reduce budget, to maximize reliability and to minimize the pollutant discharge. Therefore, the apt formulations are modeled and solved to establish the conflicting facets of GEP problem. This paper implements MOCLPSO algorithm to solve Multi-Objective GEP (MOGEP) problem for 7-year and 14-year planning horizon. By then, the proposed model is implemented at MATLAB/Simulink platform and the implementation is calculated. The proposed method shows better results in all approaches like Seagull Optimization Algorithm (SOA), Particle Swarm Optimization (PSO) and Cuckoo Search algorithm. The outcomes establish the competence of MOCLPSO and Circle Search Algorithm to offer good-ranged Pareto optimal non-dominated solutions.

A Novel Black Widow Optimized Controller Approach for Automatic Generation Control in Modern Hybrid Power Systems

This research paper demonstrates an application of the Black Widow Optimization (BWO) approach to address the issue of load-frequency control (LFC) in networked power systems. BWO is an innovative metaheuristic method that quickly suggests technique is initially evaluated on a non-reheat thermal-thermal (NRTT) power system spanning two areas of interconnection, and then it is applied to two different actual power systems: (a) a two-area thermal-thermal considering Generation Rate Constraint (GRC); and (b) a two-area having thermal, hydro, wind, solar, and gas systems. The BWO method uses two fitness functions based on integral time multiplied absolute error (ITAE) and integral square error (ISE) to optimize controller gains. The suggested BWO algorithm's performance has been compared to that of existing meta-heuristic optimization methods, such as grey wolf optimization (GWO), comprehensive learning particle swarm optimization (CLPSO), and an ensemble of parameters in differential evolution (EPSDE). The simulation results show that BWO's tuning skills are better than other population-based planning methods like CLPSO, EPSDE, and GWO. The ITAE value is enhanced by 33.28% (GWO), 40.28% (EPSDE), and 43.27% (CLPSO) when the BWO algorithm is used in conjunction with the PID Controller for thermal system.