Adaptive Inertia Weight Strategy Research Articles

Multi-subswarm cooperative particle swarm optimization algorithm and its application

Particle swarm optimization (PSO) is a classical evolutionary algorithm and has been widely used to solve continuous optimization problems. However, the performance of the PSO algorithm is highly sensitive to its control parameters and learning strategies. To address this problem, a multi-subswarm cooperative particle swarm optimization algorithm (MSC-PSO) is proposed in this paper. In MSC-PSO, firstly, a population muti-subswarm division method is designed to enhance the global exploration capability. Secondly, a level-based particle adaptive inertia weight strategy is introduced to adjust control parameters. Finally, a level-based update learning mechanism is used for particles adaptive selection learning strategy. The performance of the MSC-PSO is evaluated by the CEC2020 test suite, and five heuristic algorithms are compared with the MSC-PSO in the experiments. The experimental results demonstrate that the proposed MSC-PSO algorithm has significant advantages in terms of convergence speed and solving optimal solutions. Furthermore, the proposed MSC-PSO algorithm is used to solve the plant protection unmanned aerial vehicles (UAV) path planning problem. The experimental results proved that the proposed MSC-PSO algorithm effectively solves the real-world UAV path planning problem, and achieves at most a 34 % reduction in round-trip distance and a 24.1 % reduction in total non-spraying time compared to classical PSO.

Time–jerk optimal trajectory planning for industrial robots with coupled interpolation function selection

AbstractIn the contemporary field of optimal trajectory planning for industrial robots, it is customary to construct trajectories through the manual predefinition of interpolation functions. Unfortunately, this method frequently overlooks the influence of the interpolation function itself on the optimization objectives, resulting in suboptimal outcomes. To remedy this limitation, an optimal trajectory planning method with coupled interpolation function selection is proposed, in which the total task time and the integral squared jerk are defined as optimization objectives. This method minimizes the optimization objectives while also factoring in the optimal interpolation function, and avoiding subjective interference. To address the aforementioned biobjective optimization problem better, an Improved MultiObjective Golden Eagle Optimizer is introduced. Population diversity and the ability to escape local optima are enhanced through the incorporation of Chaotic Mapping, Opposition‐Based Learning, Differential Evolution, and adaptive inertia weight strategy into the algorithm. The superiority of the algorithm is validated through a series of simulations on 17 benchmark functions. In the context of the robotic stirring operation within the automated block cast charging process, the proposed method is utilized to derive the time–jerk optimal trajectory. The results demonstrate the effectiveness of the proposed method.

Low light image enhancement algorithm based on improved multi-objective grey wolf optimization with detail feature enhancement

This article aims to enhance low-light images by proposing a novel algorithm called MoGDF. It departs from the traditional approach of using deep learning with low-light and normal images as training data. Instead, exposure images at five different exposure scales are generated using a proposed model called EIPM, which consists of an improved Gamma function. Then it introduces a feature extraction network called FMEM, which leverages an improved PFPN structure to enhance the fusion of multi-scale information and strengthen the connection between high-level and low-level semantic information. Finally, it optimizes the fusion weights using an improved multiple-objective grey wolf optimization algorithm with comprehensive improvements in the convergence factor updating strategy, adaptive inertia weight strategy, and individual position strategy. The experiments show that the MoGDF outperforms the current state-of-the-art algorithms in terms of color restoration and detail preservation, and has significant advantages in objective and subjective evaluation metrics, with improvements of 5.69%, 2.60%, 1.11%, and 6.67% in PSNR, SSIM, NIQE, and LPIPS, respectively.

Design of Electric Vehicle’s Wireless Power Transfer System Based on Deep Learning Combined With Multi-Objective Optimization

During the wireless power transmission of an electric vehicle (EV), due to the influence of the compensation circuit’s manufacturing process, the driver’s operating technique, and other factors, the wireless power transfer (WPT) efficiency features strong uncertainty. The article chooses the coil group’s spatial parameters as well as the compensation circuit’s parameters as input variables, and then builds the deep learning network as the framework of uncertainty quantification, so as to obtain the relevant statistical characteristic parameters of WPT efficiency, through comparing with the calculation results of classical Monte Carlo (MC), it can be verified that the uncertainty quantification based on deep learning has almost the same solution accuracy and higher computational efficiency. At the same time, the article adopts tent chaotic mapping and adaptive inertia weight strategy to improve the traditional Aquila Optimization (AO) algorithm, then uses the improved multiobjective AO algorithm to accomplish the optimization of the WPT system’s structure. Through the comparison of improved AO and other optimization algorithms, it can be concluded that the improved AO can search out the optimal design parameter group with faster speed and higher accuracy, which provides effective guidance for the actual optimized design of the EVs WPT system.

Towards improved multifactorial particle swarm optimization learning of fuzzy cognitive maps: A case study on air quality prediction

Fuzzy cognitive map (FCM) is a very simple, efficient, and powerful soft computing tool for modeling and analysis of a complex system. Due to its simplicity and transparency, FCM has been widely utilized in engineering, environment, medicine, and other complex systems. However, it remains challenging to handle dynamic, non-stationary, and noisy time series, such as air quality monitoring data, which is with typical temporal periodicity, cross-interference, low-quality, and great noise. Concerning the above challenges, we propose an improved multifactorial particle swarm optimization learning algorithm of FCM, termed as IMFPSO-FCM. Within the framework of IMFPSO-FCM, the learning of an FCM is regarded as a multitask optimization problem. Every task represents learning local connections of a node, and a single population is adopted to process these tasks simultaneously. The task selection mechanism is used to automatically select appropriate target tasks, thereby suppressing negative transfer and enabling useful information to be transferred between tasks. In addition, a multi-dimensional adaptive inertia weight strategy and a local search strategy are employed to further improve the performance of the model. The performance of IMFPSO-FCM is validated on several public datasets and real-world air quality monitoring datasets. The experimental results demonstrate the performance of the development method and emphasize its practicality.

Optimization of Oil Pipeline Operations to Reduce Energy Consumption Using an Improved Squirrel Search Algorithm

To achieve the goal of achieving carbon-neutral by 2060, the government of China has put forward higher requirements for energy conservation and consumption reduction in the energy industry. Therefore, it is necessary to reduce energy consumption in the process of transporting oil. In this paper, an optimization model that minimizes the total energy consumption of the entire pipeline system is proposed and the squirrel search algorithm (SSA) is used to solve the optimization model. Meanwhile, to improve the performance of the SSA, two strategies are proposed. One is the adaptive inertia weight strategy, and the other is the multi-group co-evolution strategy. The adaptive inertia weight can adjust the step size of the flying squirrels according to the difference of the objective function value and multi-group co-evolution is introduced to improve population diversity. The improved SSA is named multigroup coevolution-adaptive inertia weight SSA (MASSA). A total of 20 benchmark functions are used to test the performance of MASSA, including unimodal functions and multimodal functions. Compared with the other four algorithms, MASSA has better performance and convergence capabilities. In the case study experiment, an optimization model of the oil pipeline is built, which takes the minimum energy consumption of the whole pipeline as the objective function. Compared with the actual operating conditions, the electricity consumption optimized by MASSA decreases by 399,018.94 kgce, and the thermal energy dissipation decreases by 113,759.25 kgce. The total energy consumption is reduced by 512,778.19 kgce, which is 9.62%. These results indicate that the two improvement strategies are significant, and optimizing the operating parameters can reduce energy consumption.

An enhanced whale optimization algorithm with improved dynamic opposite learning and adaptive inertia weight strategy

Whale Optimization Algorithm (WOA), as a newly proposed swarm-based algorithm, has gradually become a popular approach for optimization problems in various engineering fields. However, WOA suffers from the poor balance of exploration and exploitation, and premature convergence. In this paper, a new enhanced WOA (EWOA), which adopts an improved dynamic opposite learning (IDOL) and an adaptive encircling prey stage, is proposed to overcome the problems. IDOL plays an important role in the initialization part and the algorithm iterative process of EWOA. By evaluating the optimal solution in the current population, IDOL can adaptively switch exploitation/exploration modes constructed by the DOL strategy and a modified search strategy, respectively. On the other hand, for the encircling prey stage of EWOA in the latter part of the iteration, an adaptive inertia weight strategy is introduced into this stage to adaptively adjust the prey’s position to avoid falling into local optima. Numerical experiments, with unimodal, multimodal, hybrid and composition benchmarks, and three typical engineering problems are utilized to evaluate the performance of EWOA. The proposed EWOA also evaluates against canonical WOA, three sub-variants of EWOA, three other common algorithms, three advanced algorithms and four advanced variants of WOA. Results indicate that according to Wilcoxon rank sum test and Friedman test, EWOA has balanced exploration and exploitation ability in coping with global optimization, and it has obvious advantages when compared with other state-of-the-art algorithms.

Improved Adaptive Multi-Objective Particle Swarm Optimization of Sensor Layout for Shape Sensing with Inverse Finite Element Method.

The inverse finite element method (iFEM) is one of the most effective deformation reconstruction techniques for shape sensing, which is widely applied in structural health monitoring. The distribution of strain sensors affects the reconstruction accuracy of the structure in iFEM. This paper proposes a method to optimize the layout of sensors rationally. Firstly, this paper constructs a dual-objective model based on the accuracy and robustness indexes. Then, an improved adaptive multi-objective particle swarm optimization (IAMOPSO) algorithm is developed for this model, which introduces initialization strategy, the adaptive inertia weight strategy, the guided particle selection strategy and the external candidate solution (ECS) set maintenance strategy to multi-objective particle swarm optimization (MOPSO). Afterwards, the performance of IAMOPSO is verified by comparing with MOPSO applied on the existing inverse beam model. Finally, the IAMOPSO is employed to the deformation reconstruction of complex plate-beam model. The numerical and experimental results demonstrate that the IAMOPSO is an excellent tool for sensor layout in iFEM.

A Node Deployment Optimization Algorithm of WSNs Based on Improved Moth Flame Search

Wireless sensor networks, one of the basic technologies of remote environmental monitoring, can provide efficient sensing and communication services under limited energy supply. Coverage control is an important method to ensure efficient communication and reliable data transmission. Given the complex physical environments, which impede the energy supplement and recovery of sensor nodes, the motivation of our research is to repair the coverage holes and reduce the energy consumption during the deployment of sensor nodes. Firstly, the variable spiral position update and the adaptive inertia weight strategy are adopted to improve local development and global search ability of the moth flame algorithm. Secondly, we analyze the virtual force of nodes, including the attractive force of uncovered grid points, the virtual force between adjacent sensor nodes and the repulsive force of boundary. The node resultant force is used as the disturbance factor of moth position updating to optimize the path, which effectively avoids the “premature” problem of the algorithm and accelerates global convergence. Finally, moth search is used to guide nodes to move to the area with coverage holes to achieve coverage optimization. In addition, we limit the random walking range of moths to reduce the moving distance. The simulation results show that compared with VFPSO, VFA and MFO algorithms, the coverage rate of VF-IMFO algorithm is increased by 7.16%, 3.85% and 22.2%, and the average moving distance of nodes is reduced by 9.01 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textbf {m}$ </tex-math></inline-formula> , 0.51 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textbf {m}$ </tex-math></inline-formula> and 32.46 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textbf {m}$ </tex-math></inline-formula> respectively. Moreover, under different deployment environments, the VF-IMFO algorithm still maintains remarkable performance advantages.

AdPSO: Adaptive PSO-Based Task Scheduling Approach for Cloud Computing.

Cloud computing has emerged as the most favorable computing platform for researchers and industry. The load balanced task scheduling has emerged as an important and challenging research problem in the Cloud computing. Swarm intelligence-based meta-heuristic algorithms are considered more suitable for Cloud scheduling and load balancing. The optimization procedure of swarm intelligence-based meta-heuristics consists of two major components that are the local and global search. These algorithms find the best position through the local and global search. To achieve an optimized mapping strategy for tasks to the resources, a balance between local and global search plays an effective role. The inertia weight is an important control attribute to effectively adjust the local and global search process. There are many inertia weight strategies; however, the existing approaches still require fine-tuning to achieve optimum scheduling. The selection of a suitable inertia weight strategy is also an important factor. This paper contributed an adaptive Particle Swarm Optimisation (PSO) based task scheduling approach that reduces the task execution time, and increases throughput and Average Resource Utilization Ratio (ARUR). Moreover, an adaptive inertia weight strategy namely Linearly Descending and Adaptive Inertia Weight (LDAIW) is introduced. The proposed scheduling approach provides a better balance between local and global search leading to an optimized task scheduling. The performance of the proposed approach has been evaluated and compared against five renown PSO based inertia weight strategies concerning makespan and throughput. The experiments are then extended and compared the proposed approach against the other four renowned meta-heuristic scheduling approaches. Analysis of the simulated experimentation reveals that the proposed approach attained up to 10%, 12% and 60% improvement for makespan, throughput and ARUR respectively.

Research on Prediction of Oxygen Consumption in Converter Steelmaking Based on IGWO-SVM Model

The oxygen supply for converter steelmaking is the main factor affecting the quality of molten steel. To improve the accuracy of the oxygen consumption prediction model for converter steelmaking, an improved gray wolf optimization algorithm is proposed to optimize support vector machines to establish an oxygen consumption prediction model (IGWO-SVM), effectively improving the prediction accuracy of oxygen consumption in converter steelmaking. Firstly, aiming at the problem of slow convergence of the standard gray wolf algorithm and easy to fall into local optimality, Bernoulli chaotic initialization is introduced to enhance the uniformity and ergodicity of the initial population; and an adaptive decreasing convergence factor is introduced to balance the global search of the gray wolf algorithm and local search capability, while adopting adaptive inertia weight strategy to update the population position and speed up the convergence speed. Secondly, the benchmark function is used for testing, and the results show that the improved gray wolf optimization algorithm has improved convergence speed and search accuracy. Finally, based on the measured data of a steel plant to predict the oxygen consumption of converter steelmaking, the simulation results show that the oxygen consumption prediction model of converter steelmaking based on IGWO optimized SVM has high accuracy and strong generalization ability.

A Multi-swarm Competitive Algorithm Based on Dynamic Task Allocation Particle Swarm Optimization

This paper presents a novel multi-swarm competitive algorithm based on the dynamic task allocation particle swarm optimization (MSCPSO-DTA) to solve global optimization problems. The MSCPSO-DTA consists of three main steps. Firstly, we propose a multi-swarm competitive (MSC) schedule to help the stagnant sub-swarm to jump out of local optima. When a certain condition is matched, the stagnant sub-swarm will be reinitialized with a chaotic strategy to begin a new search process in a different part of the search space. Secondly, in order to serve the MSC strategy which will reinitialize the stagnant sub-swarms and need the inertia weight to be increased correspondingly, a novel adaptive inertia weight strategy is proposed based on the maximum distance between the particles. Thirdly, a modified dynamic task allocation (DTA) strategy is adopted to make a better control of the balance between exploitation and exploration; specifically, with the help of the cumulative distribution function of normal distribution, the swarm is automatically divided into two labors to serve different tasks according to the position diversity. A set of benchmark functions are employed to test the performance of the proposed algorithm, as well as the contribution of each strategy employed in improving the performance of the algorithms. Experimental results demonstrate that, compared with other seven well-established optimization algorithms, the MSCPSO-DTA significantly performs the greatest improvement in terms of searching reliability, searching efficiency, convergence speed, and searching accuracy on most of the problems.

Heterogeneous multi-subswarm particle swarm optimisation for numerical and parameter estimation of PMSM

A heterogeneous multi-subswarm coevolution particle swarm optimisation (HMSCPSO) is proposed for numerical optimisation and parameters identification of PMSM. To improve the algorithm's dynamic optimal performance, the HMSCPSO consists of one adaptive subswarm and several basic subswarms. During the iteration, the best individual in basic subswarm and adaptive subswarm are selected as candidate to construct the elite subswarm. Heterogeneous search strategy was adopted in basic subswarm and adaptive subswarm. The migration scheme is employed for the information exchange between subswarms. The adaptive inertia weight strategy can maintain a balance between exploration and exploitation to ensure the algorithm converges to stable point. To accelerate the convergence rate, immune clonal selection operator with wavelet mutation is applied to elite subswarm. The performance of the proposed algorithm is extensively evaluated on suite of numerical optimisation functions. The results demonstrate good performance of the HMSCPSO in solving numerical problems when compared with others recent variants PSO. The performance of HMSCPSO is further evaluated by its application to the parameters identification of PMSM. The experimental results show that the HMSCPSO can simultaneously identify stator resistance, dq axis inductances and the permanent magnet flux accurately.

Prepositioning emergency earthquake response supplies: A new multi-objective particle swarm optimization algorithm

The development of an efficient emergency response plan to provide critical daily supplies to affected people facilitates efficient relief operations. In this study, we propose a multi-objective stochastic programming model for developing an earthquake response plan, which integrates pre-and post-disaster decisions. This three-objective model attempts to maximize the total expected demand coverage, to minimize the total expected cost, and to minimize the difference in the satisfaction rates between nodes. We develop a new multi-objective particle swarm optimization (MOPSO) algorithm to solve this model. Genotype-phenotype-based binary particle swarm optimization (PSO) and continuous PSO are designed to deal with the binary location and other continuous decision variables, respectively. A new strategy is employed to select two types of guides in order to enhance the search ability. Furthermore, a new adaptive inertia weight strategy and two mutation operators are used to ensure that the diversity is sufficient and to regulate the exploration and exploitation capacities, respectively. We present an illustrative real-world case study and some randomly generated instances for computational applications. The results obtained by the proposed MOPSO algorithm were compared with those obtained using a modified time-variant MOPSO, the non-dominated sorting genetic algorithm, strength Pareto evolutionary algorithm, and the exact solution method where possible.