Swarm Size Research Articles

Investigation on performance of particle swarm optimization (PSO) algorithm based fuzzy inference system (PSOFIS) in a combination of CFD modeling for prediction of fluid flow

Herein, a reactor of bubble column type with non-equilibrium thermal condition between air and water is mechanistically modeled and simulated by the CFD technique. Moreover, the combination of the adaptive network (AN) trainer with the fuzzy inference system (FIS) as the artificial intelligence method calling ANFIS has already shown potential in the optimization of CFD approach. Although the artificial intelligence method of particle swarm optimization (PSO) algorithm based fuzzy inference system (PSOFIS) has a good background for optimizing the other fields of research, there are not any investigations on the cooperation of this method with the CFD. The PSOFIS can reduce all the difficulties and simplify the investigation by elimination of the additional CFD simulations. In fact, after achieving the best intelligence, all the predictions can be done by the PSOFIS instead of the massive computational efforts needed for CFD modeling. The first aim of this study is to develop the PSOFIS for use in the CFD approach application. The second one is to make a comparison between the PSOFIS and ANFIS for the accurate prediction of the CFD results. In the present study, the CFD data are learned by the PSOFIS for prediction of the water velocity inside the bubble column. The values of input numbers, swarm sizes, and inertia weights are investigated for the best intelligence. Once the best intelligence is achieved, there is no need to mesh refinement in the CFD domain. The mesh density can be increased, and the newer predictions can be done in an easier way by the PSOFIS with much less computational efforts. For a strong verification, the results of the PSOFIS in the prediction of the liquid velocity are compared with those of the ANFIS. It was shown that for the same fuzzy set parameters, the PSOFIS predictions are closer to the CFD in comparison with the ANFIS. The regression number (R) of the PSOFIS (0.98) was a little more than that of the ANFIS (0.97). The PSOFIS showed a powerful potential in mesh density increment from 9477 to 774,468 and accurate predictions for the new nodes independent of the CFD modeling.

Particle swarm optimization for solving a scan-matching problem based on the normal distributions transform

In this paper, an evolutionary scan-matching approach is proposed to solve an optimization issue in simultaneous localization and mapping (SLAM). A rich literature has been invested in this direction, however, most of the proposed approaches lack fast convergence and simplicity regarding the optimization process, which should directly affect the accuracy of the environment’s map and the estimated pose. It is a line of research that is always active, offering various solutions to this issue. Among many SLAM methods, the normal distributions transform approach (NDT) has shown high performances, where numerous works have been published up to date and many studies demonstrate its efficiency wrt other methods. Nevertheless, few works have been interested to solve the optimization issue. The proposed solution is based on NDT scan-matching using particle swarm optimization (PSO) and it is dubbed NDT-PSO. The main contribution is to solve the pose estimation problem based on PSO and iterative NDT maps. The performances of the NDT-PSO approach have been proven in real experiments performed on a car-like mobile robot in both static and dynamic environments. NDT-PSO is tested for different swarm sizes, and the results show that 70 particles are more than enough to find the best particle while avoiding local minima even in loop closing. The algorithm is also suitable for real time applications, with an average runnnig time of $$145 \rm{ms}$$ for 70 particles and 70 iterations of the optimization process. This value can be further reduced using fewer particles and iterations. The accuracy of the proposed approach is also evaluated wrt other SLAM methods widely used among the robot operating system community and it has been shown that NDT-PSO outperforms these algorithms.

Novel Fuzzy-Swarm Optimization for Sizing of Hybrid Energy Systems Applying Smart Grid Concepts

A hybrid energy system (HES) is a perfect option for supplying electric energy to remote areas. A HES normally uses renewable energy sources such as wind and PV. Owing to the intermittent nature of these sources, HES should have batteries and/or conventional energy sources. HES proposed in this study is having wind, PV, batteries, and diesel generators. The design and operation of HES are considerably improved with the use of smart grid concepts. This study introduced a fuzzy logic controller to implement a new demand response strategy (DRS) where the electricity tariff is determined based on the state of charge of the battery, the charging/discharging power from the battery, and the previous response from the customers. A modified cuckoo search (MCS) optimization algorithm is introduced for sizing HES components for the lowest cost of energy (CoE) and loss of load probability (LOLP). A multiobjective function consisting of the CoE and LOLP is used to get the optimal design of HES. The MCS reduces the number of times that the optimization algorithm executes the objective function. The continuous reduction of the swarm size proposed in this paper enhances the exploration in the beginning and enhances exploitation at the final stage. The MCS is compared with 10 state-of-the-art optimization algorithms. The results from using MCS reduced the convergence time to 25-63% of the time needed by other optimization algorithms and the DRS introduced in this study reduced the CoE by 34% compared with the flat-rate pricing.

Imperialist competitive algorithm hybridized with multilayer perceptron to predict the load-settlement of square footing on layered soils

To forecast the value of bearing capacity in shallow footings, a total of 2430 finite element modelling (FEM) simulation is performed. In this regard and to optimize the performance of the artificial neural network (ANN), it is combined with the imperialist competitive algorithm (ICA). The new combined technique is called ICA-MLP (multi-layer perceptron). To develop the ICA-MLP model, the input parameters were the soil type (i.e., having particular soil properties for each of the sandy soil types) installed at the top, the soil type installed at the bottom, the first-layer thickness ratio (h/B) and the applied stress on the footing (kPa), while the output was the vertical settlement (mm) under the square footing. The estimations were compared with a predeveloped ANN model to demonstrate the ability of the ICA-MLP hybrid model. The results showed a high ability of ICA metaheuristic ensembles for understanding the non-linear relationship between the influential factors and the selected target. Meanwhile, a comparison between the used models revealed that the best-combined structure is when the ICA algorithm is followed by the swarm size equal to 350. In this sense, the results from the predeveloped ANN model, based on R2 values, were 0.83 and 0.89 for the training and testing data sets, respectively, whereas the R2 and RMSE values for the ICA-MLP model for the training and testing datasets were 0.983, 0.062 and 0.977, 0.070, respectively. Therefore, the ICA-MLP model can be regarded as a new model that is superior to the conventional MLP technique.

Numerical Study of Optimal Location of Non-Circular Segmented Failure Surface in Soil Slope With Weak Soil Layer

The article addresses stability analysis of complicated slopes having weak soil layer sandwiched between two strong layers. The search for critical failure surface and associated optimum/minimum factor of safety (FOS) among all potential failure surfaces can be posed as an optimization problem. Two different variants of particle swarm optimization (PSO) models, namely inertia weight-based PSO (IW-PSO) and contemporary standard PSO (CS-PSO), are used to obtain optimum global solution. Detailed comparison between the global optimum solutions obtained from two PSO variants and the effect of swarm size is studied. The performance of IW-PSO and CS-PSO are studied by observing the convergence behavior of the respective algorithms with respect to iteration count. The influence of velocity clamping on the optimized solution is investigated and its use is found beneficial as it prevents the solution from overflying the region with global best solution. The studies related to swarm diversity demonstrating the exploitation and exploration behaviors of the algorithms are also presented.

Fast and improved PSO (FIPSO)‐based deterministic and adaptive MPPT technique under partial shading conditions

Partial shading in photovoltaic (PV) power generating systems is practically unavoidable and is a menace to the PV system. Non-uniform shading can be caused due to clouds, tree branches, buildings or other nearby items. The non-linear output characteristics of a PV source varies with temperature and solar insolation. During partial shading condition, the conventional hill-climbing methods of maximum power point tracking (MPPT) prove to be inefficient. In partial shading, the power–voltage curve exhibits multiple peaks. Conventional MPPT methods get stuck on one of the local maxima and fail to attain the global maximum power point (GMPP). Particle swarm optimisation (PSO) has proved to be a very accurate and powerful technique to find GMPP. In this study, the authors improved the conventional PSO by reducing swarm size, as well as, the number of iterations to achieve MPP at a fast pace with remarkable accuracy, thus making the system more efficient with less computational effort. Simulation and hardware implementation for performance evaluation of the proposed technique is carried out to verify various qualities under different partial shading conditions, such as flexibility, reliability, system-independence and high accuracy in tracking the GMPP under non-uniform insolations.

Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field

Drilling fluid loss of circulation is a challenging issue to resolve for many oil and gas wells as drilling progresses. It imposes enormous expenses on drilling industry. One of the common practices to solve this problem or make it less severe is introducing various loss circulation materials (LCM) into the circulating drilling fluid. The ability to predict the amount of mud loss before drilling a particular formation would provide engineers with invaluable information to assist them in selecting appropriate LCM properties such as particle size distribution. In this study, a number of heuristic search algorithms including genetic algorithm (GA), particle swarm size (PSO), and cuckoo search algorithm (COA) are combined with two machine-learning techniques namely multilayer perception (MLP) neural network and least square support vector machine (LSSVM) to present different hybrid algorithms in prediction of lost circulation. The established database consists of 2820 cases (datasets) extracted from available drilling reports of 305 drilled wells in the Marun oil field. These datasets are associated with drilling operation variables, formation specifications, and drilling mud characteristics which totally include 18 input variables and 1 output. Pre-processing of data involves filtering with Savitzky-Golay (SG) filter and ranking features using wrapper method. Results show that hybrid intelligent models are highly capable of predicting lost circulation before drilling a certain formation. Furthermore, LSSVM-COA and LSSVM-PSO achieve coefficients of determination of 0.9424 and 0.9391, respectively, making them the two most accurate models. GA cannot match the prediction performance of the other two algorithms in enhancing machine-learning techniques for this purpose. MLP-GA with a coefficient of determination (R2) and RMSE of 0.9304 and 25.26 (bbl/hr), respectively, yields the weakest prediction performance. Hybrid intelligent models, coupling optimizers and machine learning algorithms show themselves to be superior to applying standalone machine-learning methodologies for predicting loss of circulation.

Indoor 3D visible light positioning system based on adaptive parameter particle swarm optimisation

Visible light positioning has become a new research hotspot in recent years. In this study, a new Gaussian model of hybrid noise and multipath reflection is established for noise interference in line-of-sight (LOS) communication and multipath reflection in non-LOS (NLOS) communication. First, the likelihood function of the ranging error is established according to the Gaussian hybrid model, and the analytical expression of Cramer–Rao lower bound is derived. Second, the novel adaptive parameter particle swarm optimisation (AP-PSO) algorithm is proposed to calculate the three-dimensional (3D) coordinates of the target. In order to avoid falling into the local optimal solution, a novel particle adaptive mutation algorithm, namely AP-PSO-M algorithm is also proposed. Simulation results show that if the NLOS propagation probability is 0.3 and the swarm size is 20, compared with Newton–Raphson (NR), particle swarm optimisation (PSO), dissipative PSO (DPSO) and simulated annealing PSO (SA-PSO) algorithms, the average positioning error based on AP-PSO-M algorithm can be reduced by 45.43, 38.98, 25.37 and 26.42%, respectively. If similar positioning accuracy is obtained, compared with PSO, DPSO and SA-PSO algorithms, the average calculation time required by the AP-PSO-M algorithm can be reduced by 48.16, 30.24 and 26.14%, respectively.

Development of a Coupled TRNSYS-MATLAB Simulation Framework for Model Predictive Control of Integrated Electrical and Thermal Residential Renewable Energy System

An integrated electrical and thermal residential renewable energy system consisting of solar thermal collectors, gas boiler, fuel cell combined heat and power, a photovoltaic system with battery, inverter, and thermal storage for a single-family house of Sonnenhaus standard is investigated with a model predictive controller (MPC). The main focus of this article is to define a multi-objective mathematical function, develop a coupled simulation framework for the nonlinear time-varying deterministic discrete-time problem of the energy system using TRNSYS and MATLAB. With the developed methodology, a sensitivity analysis of maximum optimization time, swarm (or population or mesh) size of a typical spring day and a typical summer day assuming a 100% accurate weather and load forecast with three different algorithms: particle swarm optimization (PSO), genetic algorithm (GA) and global pattern search (GPS) are analyzed. Finally, the obtained results are compared with a status quo controller. Results show that the PSO algorithm optimizer performs the best in this MPC for such a complex and time-consuming MPC model in both the spring day and the summer day. The obtained results show that the PSO with swarm size 50 in the selected typical spring day and the PSO with swarm size 40 in the selected summer day reduces the objective function’s fitness value from 413 to −177 within 6 h optimization time and from 1396 to 1090 in 4 h optimization time respectively.

A Fuzzy Cooperative Localisation Framework for Underwater Robotic Swarms.

This article proposes a holistic localisation framework for underwater robotic swarms to dynamically fuse multiple position estimates of an autonomous underwater vehicle while using fuzzy decision support system. A number of underwater localisation methods have been proposed in the literature for wireless sensor networks. The proposed navigation framework harnesses the established localisation methods in order to provide navigation aids in the absence of acoustic exteroceptive sensors navigation aid (i.e., ultra-short base line) and it can be extended to accommodate newly developed localisation methods by expanding the fuzzy rule base. Simplicity, flexibility, and scalability are the main three advantages that are inherent in the proposed localisation framework when compared to other traditional and commonly adopted underwater localisation methods, such as the Extended Kalman Filter. A physics-based simulation platform that considers environment’s hydrodynamics, industrial grade inertial measurement unit, and underwater acoustic communications characteristics is implemented in order to validate the proposed localisation framework on a swarm size of 150 autonomous underwater vehicles. The proposed fuzzy-based localisation algorithm improves the entire swarm mean localisation error and standard deviation by 16.53% and 35.17%, respectively, when compared to the Extended Kalman Filter based localisation with round-robin scheduling.

Autonomous and Cooperative Design of the Monitor Positions for a Team of UAVs to Maximize the Quantity and Quality of Detected Objects

This paper tackles the problem of positioning a swarm of UAVs inside a completely unknown terrain, having as objective to maximize the overall situational awareness. The situational awareness is expressed by the number and quality of unique objects of interest, inside the UAVs' fields of view. YOLOv3 and a system to identify duplicate objects of interest were employed to assign a single score to each UAVs' configuration. Then, a novel navigation algorithm, capable of optimizing the previously defined score, without taking into consideration the dynamics of either UAVs or environment, is proposed. A cornerstone of the proposed approach is that it shares the same convergence characteristics as the block coordinate descent (BCD) family of approaches. The effectiveness and performance of the proposed navigation scheme were evaluated utilizing a series of experiments inside the AirSim simulator. The experimental evaluation indicates that the proposed navigation algorithm was able to consistently navigate the swarm of UAVs to "strategic" monitoring positions and also adapt to the different number of swarm sizes. Source code is available at https://github.com/dimikout3/ConvCAOAirSim.

Population size in Particle Swarm Optimization

Abstract Particle Swarm Optimization (PSO) is among the most universally applied population-based metaheuristic optimization algorithms. PSO has been successfully used in various scientific fields, ranging from humanities, engineering, chemistry, medicine, to advanced physics. Since its introduction in 1995, the method has been widely investigated, which led to the development of hundreds of PSO versions and numerous theoretical and empirical findings on their convergence and parameterization. However, so far there is no detailed study on the proper choice of PSO swarm size, although it is widely known that population size crucially affects the performance of metaheuristics. In most applications, authors follow the initial suggestion from 1995 and restrict the population size to 20–50 particles. In this study, we relate the performance of eight PSO variants to swarm sizes that range from 3 up to 1000 particles. Tests are performed on sixty 10- to 100-dimensional scalable benchmarks and twenty-two 1- to 216-dimensional real-world problems. Although results do differ for the specific PSO variants, for the majority of considered PSO algorithms the best performance is obtained with swarms composed of 70–500 particles, indicating that the classical choice is often too small. Larger swarms frequently improve efficiency of the method for more difficult problems and practical applications. For unimodal problems slightly lower swarm sizes are recommended for the majority of PSO variants, but some would still perform best with hundreds of particles.

Comparison of swarming, mating performance and longevity of males Anopheles coluzzii between individuals fed with different natural fruit juices in laboratory and semi-field conditions

BackgroundIt is assumed that malaria vectors feed on locally available nectar sources to obtain energy. Sugar feeding is energetically critical for the Anopheles male swarming and mating activities. However, little is known about the impact of local nectar feeding on male physiological development and its consequences on male mosquito life traits in the malaria control context. This study aimed to evaluate the influence of local fruit juices on the life traits of males Anopheles coluzzii.MethodsSwarming characteristics (number of males in swarm, number of mating pairs, and swarm duration) in semi-field conditions; mating rate and longevity in a laboratory setting were compared between males An. coluzzii fed exclusively with mango, papaya or banana juices. The trophic preference was investigated in semi-field conditions.ResultsThe results of this study showed that in the laboratory, mosquitoes fed with papaya juices lived on average longer (10 days) than those fed with banana or mango juices (5 days) and had higher a mating rate (53%) than those fed with banana juice (40%). In the semi-field, the swarm size of mosquitoes fed with banana juice (85 males) was larger than that of mosquitoes fed with mango juice (60 males). The number of mating pairs formed from banana-fed male swarms (17 mating pairs) was higher than that formed from mango-fed male swarm (8 mating pairs). There was no difference in swarming duration between male treatments. Male mosquitoes had a preference for papaya and banana juices.ConclusionsThe results indicate that the origin of plant-derived feeding is an important factor in the survival and reproduction of mosquitoes. This calls for further investigations of chemical contents of nectars and their impact on the physiological development of mosquitoes.

Walk, Stop, Count, and Swap: Decentralized Multi-Agent Path Finding With Theoretical Guarantees

For multi-agent path finding (MAPF) problems, finding the optimal solution has been shown to be NP-Complete. Here we present WSCaS (Walk, Stop, Count, and Swap), a decentralized multi-agent path-finding algorithm that can provide theoretical completeness and optimality guarantees. That is, WSCaS is able to deliver a worst case $\mathbf {\mathcal {O}(1)}$ -approximate distance-optimal solution to MAPF instances on square grids without narrow passages. Moreover, the algorithm‘s cost is independent of the swarm's size with respect to computation complexity, memory complexity, as well as communication complexity, therefore the algorithm can scale well with the number of agents in practice. The algorithm is executed on 1024 simulated agents as well as 100 physical robots, the results show that the WSCaS is robust to real-world non-idealitys.

Optimization of non-circular failure surface in slope based on particle swarm models

This article presents results of slope analyses employing a simple technique of generating segmented non-circular failure surfaces. The formulation of slope analysis is performed as an optimization problem with four constrained control variables characterizing the failure surface. In this study, different variants of particle swarm optimization (PSO) methods such as inertia weight equipped and contemporary standard PSO (CS-PSO) are utilized to obtain optimum control variables and associated critical failure surface. The factor of safety of the slope or the objective function of the constrained optimization problem is determined by Morgenstern–Price method. To explore the competence of proposed method with different PSO models, three benchmark problems are analysed for different maximum number of function evaluations such as 1000, 2500 and 5000. A series of sensitivity analyses are performed for various parameters such as swarm size with maximum iteration count of 100. The swarm diversity behaviour is also studied in relation with converged or promising global optimum solution. It is found that contemporary standard PSO (CS-PSO) with or without velocity clamping maintains better swarm diversity and preserves the balance between swarm “exploration” and “exploitation” efficiently. Velocity clamping and positional clamping are recommended as they prevent the solution/control variable from overflying the swarm best position.

Swarming of micron-sized hematite cubes in a rotating magnetic field – Experiments

Energy input by under-field rotation of particles drives the systems to emergent non-equilibrium states. Here we investigate the suspension of rotating magnetic cubes. Micron-sized hematite cubes are synthesized and observed microscopically. When exposed to a rotating magnetic field, they form rotating swarms that interact with each other like liquid droplets. We describe the swarming behaviour and its limits and characterize the swarm size and angular velocity dependence on the magnetic field strength and frequency. A quantitative agreement with a theoretical model is found for the angular velocity of swarms as a function of the field frequency.

Reinforcement learning based two-level control framework of UAV swarm for cooperative persistent surveillance in an unknown urban area

Persistent surveillance in a complex unknown urban area by an unmanned aerial vehicle (UAV) swarm is a low-cost, promising future application for anti-terrorism, disaster monitoring, and battlefield situational awareness. Based on over-simplified simulated surroundings and a UAV dynamic model, a few remarkable approaches have been proposed; however, they typically rely on non-sensor-based inputs and prior knowledge on the environment or targets. To overcome these limitations, based on simulated city blocks, a two-level quasi-distributed control framework is proposed for realizing the continuous control of a UAV swarm in two defined surveillance phases. With the support of a well-trained and corrected artificial neural network (ANN) in low-level UAV manoeuvre control for target homing and collision avoidance, several preliminary high-level target allocation strategies are designed for a cooperative overall objective based on the synchronization of local surveillance data. Then, via a series of numerical simulations, an optimal high-level strategy combination is identified. Finally, the surveillance performance of this strategy combination is evaluated under various swarm sizes and UAV launching patterns. The simulation results demonstrate that the proposed control framework is applicable for UAV swarm control in the persistent surveillance of unknown urban areas.

Improved PSO Performance using LSTM based Inertia Weight Estimation

Particle Swarm Optimization (PSO) is first introduced in the year 1995. It is mostly an applied population-based meta-heuristic optimization algorithm. PSO is diversely used in the areas of sciences, engineering, technology, medicine, and humanities. Particle Swarm Optimization (PSO) is improved its performance by tuning the inertia weight, topology, velocity clamping. Researchers proposed different Inertia Weight based PSO (IWPSO). Every Inertia Weight based PSO in excelling the existing PSOs. A Long Short Term Memory (LSTM) predicting inertia weight based PSO (LSTMIWPSO) is proposed and its performance is compared with constant, random, and linearly decreasing Inertia Weight PSO. Tests are conducted on swarm sizes 50, 75, and 100 with dimensions 10, 15, and 25. The experimental results show that LSTM based IWPSO supersedes the CIWPSO, RIWPSO, and LDIWPSO.

A Novel Bat Algorithm Strategy for Maximum Power Point Tracker of Photovoltaic Energy Systems Under Dynamic Partial Shading

Power versus voltage curves of partial shading photovoltaic (PV) systems contain several local peaks (LPs) and one global peak (GP). Most conventional maximum power point tracker (MPPT) techniques may not follow the GP under partial shading conditions (PSC). The use of metaheuristic techniques such as the bat algorithm (BA) and particle swarm optimization (PSO) can overcome these obstacles. All problems inherent in the using of BA as MPPT of PV systems has been discussed and solved in this paper. The first problem is the random initial values of bats that may cause premature convergence. Therefore, the initial values of bats were modified to be close to the anticipated positions of peaks to reduce the convergence time and improve the chance of capturing the GP. The second problem occurs when shading pattern changes the value and position of the GP which is not configurable because all bats are concentrated at the previous GP; this can be resolved by BA re-initialization. The the third problem is the GP memorized in the execution of the BA code forces the PV system to work at the duty ratio of the highest GP ever seen, which may not be the real GP. This problem is solved by updating the memorized GP. This paper also proposes a new criterion for selecting the optimal swarm size against number of peaks to reduce the convergence time and improve the chance of capturing the GP. To the authors' knowledge, most of these problems inherent in the BA have hitherto not been addressed in the literature. The simulation and experimental results obtained from the proposed modified BA (MBA) with re-initialization have been compared to the PSO and grey wolf optimization (GWO) techniques which show the superiority of using MBA strategy in the MPPT of partial shading PV systems.

Robust mission planning for Autonomous Marine Vehicle fleets

Mission planning for Autonomous Marine Vehicles (AMVs) is non-trivial because significant uncertainty is present when profiling the operating environment, especially for underwater missions. Mission complexity is compounded for each vehicle added to the mission. In practice, fleet operations are formulated as separate temporal problems by the operator and solved using a temporal planner. This paper proposes a planning method that uses energy as the base planning resource instead of time. Unlike temporal planners, energy planners account for physical loads endured by the vehicles. The extent of uncertainty in the vehicle loads is clarified by using the vehicle dynamics model and Monte Carlo simulation on the model parameters. The planning method is a multistage procedure to decompose operator specified task, obstacle, and vehicle data into an energy formulation of the Team Orienteering Problem (TOP) which is then solved using Discrete Strengthened PSO (DStPSO). The DStPSO algorithm has been modified to include a selective swarm size decay method that allows for larger initial swarm sizes to promote early exploration and preserves a percentage of the best performing particles on each iteration to save computational resources. The planner produces near-optimal routes containing feasible trajectories for individual vehicles that maximise tasks completed according to individual vehicle energy constraints. A case-study mission for long-term, large-scale, underwater inspection of a wind turbine array was converted into input data to evaluate the planner. Energy planning presents the opportunity for vehicles to actively monitor the feasibility of their individual plan against their current energy consumption, allowing for advanced reasoning and fault handling to occur in situ without operator assistance.