Learning Particle Swarm Optimization Research Articles

Interaction Design of Wellness Building Space by Deep Learning and VR Technology in the Context of Internet of Things

This study explores the application of deep learning theory and virtual reality (VR) technology to the interactive behavior design of building space according to the interaction behavior of wellness building space in the context of the Internet of Things (IoT). Firstly, VR theory is made into an image-based 3-dimensional (3D) modeling process. Secondly, the interactive behavior information data is analyzed according to the theory of deep learning and edge computing. Finally, the particle swarm optimization (PSO) is used to analyze the predicted temperature with the wellness building space model, as well as to make a study based on the changes in the user’s psychological indicators. The results show that the model predictions of deep learning-edge computing are most like the actual environmental settings. Both PSO and deep learning algorithms have varying degrees of influence on the final prediction results. The average temperature of the wellness building space established by deep learning and edge computing is 24.58 degrees, the average measured value of the actual environment is 24.49 degrees, and the predicted values of the two are similar. While users experienced the interactive design of the health building, their heart rate dropped from 73.17 to 68.79 and gradually became stable. There is no obvious change in the user’s heart rate, which reflects the comfort of the wellness building space designed based on deep learning and VR interaction.

Forgetting velocity based improved comprehensive learning particle swarm optimization for non-convex economic dispatch problems with valve-point effects and multi-fuel options

Economic dispatch (ED) plays an essential role in the operation and planning of power systems. Mathematically, it turns to be a multi-constraint, multimodal, non-linear, and multivariate coupling optimization problem when considering the valve-point effects and multi-fuel options. In this paper, an improved comprehensive learning particle swarm optimization (CLPSO) named FV-ICLPSO is presented to solve it. FV-ICLPSO introduces three improved components to conquer the issue of slow convergence rate of CLPSO: (1) an adaptive strategy by using both the iteration and problem's dimensionality is presented to tune the learning probability; (2) an adaptive method is designed to give different particles in different levels different scopes to pick the source particles to construct their learning exemplars; and (3) an improved velocity updating formula based on forgetting the previous velocity is proposed to guide particles to fly towards more promising areas. FV-ICLPSO is first validated on thirty CEC2014 benchmark numerical functions and then applied to eight ED cases with different units from 10-Unit to 640-Unit. Simulation results demonstrate the strong competitiveness of FV-ICLPSO compared with CLPSO, other state-of-the-art algorithms, and the reported results of some recently published ED solution methods. Furthermore, the effect of the three improved components on FV-ICLPSO is also investigated.

Guest Editorial: Situational awareness of integrated energy systems

Guest Editorial: Situational awareness of integrated energy systems

Evolutionary self-organizing fuzzy system using fuzzy-classification-based social learning particle swarm optimization

A self-organizing algorithm based on an online cluster and fuzzy sets update algorithm (OCFU) and fuzzy-classification-based social learning particle swarm optimization (FC-SLPSO) is proposed to address the problem of rule initialization and fitness function evaluation. The OCFU algorithm is used to determine the structure of the fuzzy system and build a flexible partition of fuzzy sets in each input variable. The FC-SLPSO algorithm establishes a fuzzy K-Nearest Neighbor (KNN) classifier in each iteration. The fitness evaluation is performed only when the membership degree of the offspring particles belonging to potential particles is greater than that of the parent particles, which effectively reduces the number of fitness function evaluations and accelerates the PSO algorithm. The tracking results of three nonlinear systems show that the tracking accuracy of the proposed method is better. The Pioneer P3DX mobile robot model and simulation environment with a two-dimensional lidar are constructed based on the Coppeliasim robot simulation platform. Using the algorithms proposed in this paper, the tracking task of the pioneer p3dx mobile robot along a wall is achieved. The effectiveness of the proposed algorithm is verified by the cosimulation of Coppeliasim and MATLAB in multiple scenarios.

Predominant Cognitive Learning Particle Swarm Optimization for Global Numerical Optimization

Particle swarm optimization (PSO) has witnessed giant success in problem optimization. Nevertheless, its optimization performance seriously degrades when coping with optimization problems with a lot of local optima. To alleviate this issue, this paper designs a predominant cognitive learning particle swarm optimization (PCLPSO) method to effectively tackle complicated optimization problems. Specifically, for each particle, a new promising exemplar is constructed by letting its personal best position cognitively learn from a better personal experience randomly selected from those of others based on a novel predominant cognitive learning strategy. As a result, different particles preserve different guiding exemplars. In this way, the learning effectiveness and the learning diversity of particles are expectedly improved. To eliminate the dilemma that PCLPSO is sensitive to the involved parameters, we propose dynamic adjustment strategies, so that different particles preserve different parameter settings, which is further beneficial to promote the learning diversity of particles. With the above techniques, the proposed PCLPSO could expectedly compromise the search intensification and diversification in a good way to search the complex solution space properly to achieve satisfactory performance. Comprehensive experiments are conducted on the commonly adopted CEC 2017 benchmark function set to testify the effectiveness of the devised PCLPSO. Experimental results show that PCLPSO obtains considerably competitive or even much more promising performance than several representative and state-of-the-art peer methods.

Adaptive heterogeneous comprehensive learning particle swarm optimization with history information and dimensional mutation

Adaptive heterogeneous comprehensive learning particle swarm optimization with history information and dimensional mutation

Differential Elite Learning Particle Swarm Optimization for Global Numerical Optimization

Although particle swarm optimization (PSO) has been successfully applied to solve optimization problems, its optimization performance still encounters challenges when dealing with complicated optimization problems, especially those with many interacting variables and many wide and flat local basins. To alleviate this issue, this paper proposes a differential elite learning particle swarm optimization (DELPSO) by differentiating the two guiding exemplars as much as possible to direct the update of each particle. Specifically, in this optimizer, particles in the current swarm are divided into two groups, namely the elite group and non-elite group, based on their fitness. Then, particles in the non-elite group are updated by learning from those in the elite group, while particles in the elite group are not updated and directly enter the next generation. To comprise fast convergence and high diversity at the particle level, we let each particle in the non-elite group learn from two differential elites in the elite group. In this way, the learning effectiveness and the learning diversity of particles is expectedly improved to a large extent. To alleviate the sensitivity of the proposed DELPSO to the newly introduced parameters, dynamic adjustment strategies for parameters were further designed. With the above two main components, the proposed DELPSO is expected to compromise the search intensification and diversification well to explore and exploit the solution space properly to obtain promising performance. Extensive experiments conducted on the widely used CEC 2017 benchmark set with three different dimension sizes demonstrated that the proposed DELPSO achieves highly competitive or even much better performance than state-of-the-art PSO variants.

부배열이 적용된 Thinned 위상배열안테나 설계

In this paper, a 36×36 design of a thinned phased array antenna with subarrays is proposed. Binary-genetic learning particle swarm optimization (GLPSO) was used to design a thinned phased array antenna with a thinning factor of 60 % to 65 %, and continuous-GLPSO was used to apply 36 subarray shapes. The RF beam steering range was an azimuth/elevation of 40°, the sidelobe levels (SLLs) were 26.67 dB and 28.43 dB, and the half-power beamwidths (HPBWs) were 4.6° and 4.7°. When the subarrays were applied, the digital beam steering range was HPBW/2° in the azimuth/elevation direction. SLLs were 22.52 dB and 22.53 dB respectively, and the HPBWs were all 3.5°. When RF beam and digital beam steering are simultaneously performed in the azimuth/elevation direction by 40°+HPBW/2°, the SLLs are 20.16 dB and 21.25 dB respectively, and the HPBWs are all 5°.

Dynamic neighborhood genetic learning particle swarm optimization for high-power-density electric propulsion motor

To maximize the power density of the electric propulsion motor in aerospace application, this paper proposes a novel Dynamic Neighborhood Genetic Learning Particle Swarm Optimization (DNGL-PSO) for the motor design, which can deal with the insufficient population diversity and non-global optimal solution issues. The DNGL-PSO framework is composed of the dynamic neighborhood module and the particle update module. To improve the population diversity, the dynamic neighborhood strategy is first proposed, which combines the local neighborhood exemplar generation mechanism and the shuffling mechanism. The local neighborhood exemplar generation mechanism enlarges the search range of the algorithm in the solution space, thus obtaining high-quality exemplars. Meanwhile, when the global optimal solution cannot update its fitness value, the shuffling mechanism module is triggered to dynamically change the local neighborhood members. The roulette wheel selection operator is introduced into the shuffling mechanism to ensure that particles with larger fitness value are selected with a higher probability and remain in the local neighborhood. Then, the global learning based particle update approach is proposed, which can achieve a good balance between the expansion of the search range in the early stage and the acceleration of local convergence in the later stage. Finally, the optimization design of the electric propulsion motor is conducted to verify the effectiveness of the proposed DNGL-PSO. The simulation results show that the proposed DNGL-PSO has excellent adaptability, optimization efficiency and global optimization capability, while the optimized electric propulsion motor has a high power density of 5.207 kW/kg with the efficiency of 96.12%.

A new power system active rescheduling method considering the dispatchable plug-in electric vehicles and intermittent renewable energies

The significant penetration of renewable power generations (RGs) and the large-scale use of plug-in electric vehicles (PEVs) have brought tangible impacts in tackling the climate change challenge the mankind has been facing due to substantive green-house gas and pollutant emissions from fossil-fuel based thermal power generation plants. However, the uncertainty of RGs has also exerted significant challenges to the grid operation and control. Therefore, dynamic power system scheduling to accommodate the intermittent RGs and mass roll-out of PEVs has become extremely important. In this paper, a novel power system rescheduling strategy is proposed to tackle this problem. Considering the uncertainty of the wind energy, a set of indices according to different wind power application scenarios is proposed to initiate a rescheduling scheme for power generations. In addition, a social learning particle swarm optimization algorithm based on real-value and binary parallel is proposed to schedule the output of generator units and the charging and discharging of the PEV. The effectiveness of the proposed active rescheduling framework and solving algorithm has been verified by extensive experiments considering different number of generating units and scenarios, achieving up to over 5.3% cost reduction. The experimental results have also shown that through expropriate management of the charging and discharging of PEVs would be significantly alleviate the negative impact on the grid stability caused by the intermittent wind power generations.

Two-phase ESO and comprehensive learning PSO method for structural optimization with discrete steel sections

This paper proposes the novel two-phase metaheuristic method that combines the distinctive features provided by evolutionary structural optimization (ESO) and comprehensive learning particle swarm optimization (CLPSO) for the design of steel structures with standard sections. The approach overcomes the challenges associated with local optima pitfalls in processing the mixed integer nonlinear programming problem, and hence determines the accurate solutions at modest computing efforts. In essence, the first-phase ESO design incorporates the constraint relaxations to fast eliminate the ineffective (infeasible) sections from initial discrete variable domains. This advantageously provides a significant reduction in the search spaces performed in the second-phase CLPSO scheme. The comprehensive learning technique enhances a standard particle swarm optimization algorithm by enabling the cooperative responses among swarm populations. The learning probability function defines the comprehensive cross-positions between the sets of best particles constructed from the reducing sets of steel sections specified in the preliminary ESO phase leading to the computation of optimal solutions. Various benchmarks (subjected to infinite design combinations) illustrate robustness and accuracy of the proposed design method (viz., generating the smaller number of particles) as compared to conventional metaheuristic algorithms.

Learning Competitive Swarm Optimization.

Particle swarm optimization (PSO) is a popular method widely used in solving different optimization problems. Unfortunately, in the case of complex multidimensional problems, PSO encounters some troubles associated with the excessive loss of population diversity and exploration ability. This leads to a deterioration in the effectiveness of the method and premature convergence. In order to prevent these inconveniences, in this paper, a learning competitive swarm optimization algorithm (LCSO) based on the particle swarm optimization method and the competition mechanism is proposed. In the first phase of LCSO, the swarm is divided into sub-swarms, each of which can work in parallel. In each sub-swarm, particles participate in the tournament. The participants of the tournament update their knowledge by learning from their competitors. In the second phase, information is exchanged between sub-swarms. The new algorithm was examined on a set of test functions. To evaluate the effectiveness of the proposed LCSO, the test results were compared with those achieved through the competitive swarm optimizer (CSO), comprehensive particle swarm optimizer (CLPSO), PSO, fully informed particle swarm (FIPS), covariance matrix adaptation evolution strategy (CMA-ES) and heterogeneous comprehensive learning particle swarm optimization (HCLPSO). The experimental results indicate that the proposed approach enhances the entropy of the particle swarm and improves the search process. Moreover, the LCSO algorithm is statistically and significantly more efficient than the other tested methods.

Three-learning strategy particle swarm algorithm for global optimization problems

Social Learning Particle Swarm Optimization (SL-PSO) greatly improves the optimization performance of PSO. In solving complex optimization problems, however, it still has some deficiencies, such as poor search ability and low search efficiency. Hence, an improved SL-PSO, namely, Three-Learning Strategy PSO (TLS-PSO) is proposed in this paper. Firstly, a med-point-example learning strategy and a random learning strategy are proposed to replace the imitation component and social influence component of SL-PSO to enhance the exploitation and exploration, respectively. Secondly, the two learning strategies are combined cleverly into an updating equation to balance exploration and exploitation. Finally, a worst-best example learning strategy is merged skillfully to construct TLS-PSO with hybrid learning mechanism and further enhance the search ability. The experimental results on the complex functions from CEC2013 and CEC2017 test sets indicate that TLS-PSO has better performance compared with state-of-the-art PSO variants and other algorithms. For example, TLS-PSO has an advantage over SL-PSO on 50 of the 56 functions from CEC2013, its running time is less than SL-PSO’s and it has higher search efficiency. Simulation results on the 10 engineering problems also show that TLS-PSO outperforms 7 excellent algorithms, such as IUDE and iLSHADE∊. It is expected to solve practical problems better.

Balancing exploitation and exploration: A novel hybrid global-local optimization strategy for hydrological model calibration

Optimization problems in hydrological modeling are frequently solved using local or global search strategies, which either maximize exploitation or exploration. Thus, the elevated performance of one strategy for one class of problems is often offset by poor performance for another class. To overcome this issue, we propose a hybrid strategy, G-CLPSO, that combines the global search characteristics of the Comprehensive Learning Particle Swarm Optimization (CLPSO) with the exploitation capability of the Marquardt-Levenberg (ML) method and implement it into the hydrological model, HYDRUS. Benchmarks involving optimizing non-separable unimodal and multimodal functions demonstrate that G-CLPSO outperforms CLPSO in terms of accuracy and convergence. Synthetic modeling scenarios involving the inverse estimation of soil hydraulic properties are used to compare the G-CLPSO against the original HYDRUS ML solver, the gradient-based algorithm PEST, and the stochastic SCE-UA strategy. Results demonstrate the superior performance of the G-CLPSO, suggesting a potential use in other environmental problems.

Model Identification and Human-robot Coupling Control of Lower Limb Exoskeleton with Biogeography-based Learning Particle Swarm Optimization

Model Identification and Human-robot Coupling Control of Lower Limb Exoskeleton with Biogeography-based Learning Particle Swarm Optimization

A Novel UAV Path Planning Algorithm Based on Double-Dynamic Biogeography-Based Learning Particle Swarm Optimization

Particle swarm optimization (PSO), one of the classical path planning algorithms, has been considered for unmanned aerial vehicle (UAV) path planning more frequently in recent years. A large amount of studies on UAV path planning based on modified PSO have been reported. However, most UAV path planning algorithms still optimize only one kind terrain problem which is mountain terrain. At the same time, many modified PSO algorithms also have some problems, such as insufficient convergence and unsatisfactory efficiency. In this paper, six kinds of terrain functions of UAV path planning are proposed to simulate real-world application. The terrain functions contain city, village without houses, village with houses, mountainous area without houses, mountainous area with houses, and mountainous area with a huge building. Inspired by CLPSO and BLPSO, we proposed a new double-dynamic biogeography-based learning particle swarm optimization (DDBLPSO) algorithm to solve these problems. The double-dynamic biogeography-based learning strategy replacing the traditional learning mechanism from the personal and global best particles is used to select the learning particles. In this strategy, each particle will learn from the better one of two selected particles which are not worse than itself. However, one random component of particle will replaced by corresponding component of other particle if all components of the particle only learn from itself. In this way, particles sufficiently learn from better objects and maintain the ability of jumping out of local optimality. The superiority of our algorithm is verified with four relevant algorithms, a PSO variant, and a BBO variant on the benchmark suite of CEC2015. Real-world application demonstrates that the algorithm we proposed outperforms four relevant algorithms, a PSO variant, and a BBO variant both in small-scale problems and large-scale problems. This paper shows a good application of our novel algorithm.

QoS-aware placement of microservices-based IoT applications in Fog computing environments

The Fog computing paradigm, offering cloud-like services at the edge of the network, has become a feasible model to support computing and storage capabilities required by latency-sensitive and bandwidth-hungry Internet of Things (IoT) applications. As fog devices are distributed, heterogeneous and resource-constrained, efficient application scheduling mechanisms are required to harvest the full potential of such computing environments. Due to the rapid evolution in IoT ecosystems and also to better suit fog environment characteristics, IoT application development has moved from the monolithic architecture towards the microservices architecture that enhances scalability, maintainability and extensibility of the applications. This architecture improves the granularity of service decomposition, thus providing scope for improvement in QoS-aware placement policies. Existing application placement policies lack proper utilisation of these features of microservices architecture, thus failing to produce efficient placements. In this paper, we harvest the characteristics of microservice architecture to propose a scalable QoS-aware application scheduling policy for batch placement of microservices-based IoT applications within fog environments. Our proposed policy, QoS-aware Multi-objective Set-based Particle Swarm Optimisation (QMPSO), aims at maximising the satisfaction of multiple QoS parameters (makespan, budget and throughput) while focusing on the utilisation of limited fog resources. Besides, QMPSO adapts and improves the Set-based Comprehensive Learning Particle Swarm Optimisation (S-CLPSO) algorithm to achieve better convergence in the fog application placement problem. We evaluate our policy in a simulated fog environment. The results show that compared to the state-of-the-art solutions, our placement algorithm significantly improves QoS in terms of makespan satisfaction (up to 35% improvement) and budget satisfaction (up to 70% improvement) and ensures optimum usage of computing and network resources, thus providing a robust approach for QoS-aware placement of microservices-based heterogeneous applications within fog environments.

RAFL: A hybrid metaheuristic based resource allocation framework for load balancing in cloud computing environment

This paper proposes a hybrid metaheuristic based resource allocation framework named RAFL for load balancing in cloud computing environment. The objective is to proactively minimize the load imbalance across active physical machines and among their considered resource capacities (e.g., CPU and RAM). This prevents overloading/underloading of active physical machines and utilizes their considered resource capacities in a balanced manner. In the proposed framework, a phasor particle swarm optimization and dragonfly algorithm based hybrid optimization algorithm named PPSO-DA is used to generate an optimal resource allocation plan for balancing the load. Simulation experiments are performed using CloudSim simulator to measure the metrics of load imbalance across active physical machines and among their considered resource capacities. Results show that the proposed PPSO-DA algorithm outperforms phasor particle swarm optimization, dragonfly algorithm, comprehensive learning particle swarm optimization, memory based hybrid dragonfly algorithm, sine cosine algorithm, and elephant herding optimization, in finding an optimal resource allocation for balancing the load. The statistical analysis and benchmark testing also validates the relative superiority of PPSO-DA.

Combined Subset Simulation and Comprehensive Learning Particle Swarm Optimization in Reliability-Based Structural Optimization

Reliability-based design optimization (RBDO) addresses the cost-effective integrity design of structures in the presence of inherent uncertain parameters. Processing this class of problem is challenging from the computational burden to determine the failure probability of structures violating the limit-state function. This paper proposes an efficient decoupling RBDO method that advantageously couples a comprehensive learning particle swarm optimization (CLPSO) algorithm with a subset simulation (SS), termed as SS-CLPSO approach. In essence, the proposed method iteratively performs the CLPSO assuming deterministic parameters based on the most probable point underpinning limit-state functions updated within the reliability evaluation process. Based on the CLPSO design data, the SS approximates the spectrum of limit-state functions under uncertain parameters, and hence enables the significant reduction of Monte-Carlo simulations for the failure probability prediction. The SS map outs the failure probability from the conditional samples constructed at each intermediate event. The proposed SS-CLPSO terminates the optimal solution to the RBDO problem as when the resulting failure probability converges to the permissible threshold. The applications of the present approach are illustrated through the steel truss design under probabilistic uncertain parameters and constraints.

Multimodal Optimization Algorithm for Torque Ripple Reduction in Synchronous Reluctance Motors

An accurate analytical model is adopted to estimate the torque ripple of a synchronous reluctance motor (SynRM). Desired behavior of the torque ripple functionin this motor is obtained by changing the angles of one and two flux barriers per pole (FBs) in the rotor. The torque ripple function of the SynRM serves as the multiple and close local optima. By identifying the behavior of this function, a comprehensive learning particle swarm optimization (CLPSO) algorithm (typically applied in solving multimodal functions), is adopted to reduce the torque ripple. The results indicate that compared to PSO (i.e. global optimization algorithms) the CLPSO algorithm is more efficient in torque ripple reduction and finding more local optima. Among the available optimal solutions with four FBs per pole, a sample is selected for motor construction. Finite element analysis and laboratory tests are performed to validate the results.