Showing papers on "Firefly algorithm published in 2019"
TL;DR: It has been observed that the reactive approaches are more robust and perform well in all terrain when compared to classical approaches and are used to improve the performance of the classical approaches as a hybrid algorithm.
450 citations
TL;DR: The proposed work, deploys filter and wrapper based method with firefly algorithm in the wrapper for selecting the features, and shows that 10 features are sufficient to detect the intrusion showing improved accuracy.
215 citations
TL;DR: PNGV and the exact algorithms are an ideal combination in the low SOC area and in the high SOC area, and PSO is an ideal identification algorithm for second-order RC models.
148 citations
TL;DR: A method for detecting rapid rice disease based on FCM-KM and Faster R-CNN fusion is proposed to address various problems with the rice disease images, such as noise, blurred image edge, large background interference and low detection accuracy.
Abstract: In this paper, a method for detecting rapid rice disease based on FCM-KM and Faster R-CNN fusion is proposed to address various problems with the rice disease images, such as noise, blurred image edge, large background interference and low detection accuracy. Firstly, the method uses a two-dimensional filtering mask combined with a weighted multilevel median filter (2DFM-AMMF) for noise reduction, and uses a faster two-dimensional Otsu threshold segmentation algorithm (Faster 2D-Otsu) to reduce the interference of complex background with the detection of target blade in the image. Then the dynamic population firefly algorithm based on the chaos theory as well as the maximum and minimum distance algorithm is applied for optimization of the K-Means clustering algorithm (FCM-KM) to determine the optimal clustering class k value while addressing the tendency of the algorithm to fall into the local optimum problem. Combined with the R-CNN algorithm for the identification of rice diseases, FCM-KM analysis is conducted to determine the different sizes of the Faster R-CNN target frame. As revealed by the application results of 3010 images, the accuracy and time required for detection of rice blast, bacterial blight and blight were 96.71%/0.65s, 97.53%/0.82s and 98.26%/0.53s, respectively, indicating clearly that the method is more capable of detecting rice diseases and improving the identification accuracy of Faster R-CNN algorithm, while reducing the time required for identification.
137 citations
TL;DR: A Discrete and Improved Bat Algorithm (DaIBA) is developed, which consists on the existence of two different neighborhood structures, which are explored depending on the bat's distance regarding the best individual of the swarm.
Abstract: The work presented in this paper is focused on the resolution of a real-world drugs distribution problem with pharmacological waste collection. With the aim of properly meeting all the real-world restrictions that comprise this complex problem, we have modeled it as a multi-attribute or rich vehicle routing problem (RVRP). The problem has been modeled as a Clustered Vehicle Routing Problem with Pickups and Deliveries, Asymmetric Variable Costs, Forbidden Roads and Cost Constraints. To the best of authors knowledge, this is the first time that such a RVRP problem is tackled in the literature. For this reason, a benchmark composed of 24 datasets, from 60 to 1000 customers, has also been designed. For the developing of this benchmark, we have used real geographical positions located in Bizkaia, Spain. Furthermore, for the proper dealing of the proposed RVRP, we have developed a Discrete and Improved Bat Algorithm (DaIBA). The main feature of this adaptation is the use of the well-known Hamming Distance to calculate the differences between the bats. An effective improvement has been also contemplated for the proposed DaIBA, which consists on the existence of two different neighborhood structures, which are explored depending on the bat's distance regarding the best individual of the swarm. For the experimentation, we have compared the performance of our presented DaIBA with three additional approaches: an evolutionary algorithm, an evolutionary simulated annealing and a firefly algorithm. Additionally, with the intention of obtaining rigorous conclusions, two different statistical tests have been conducted: the Friedman's non-parametric test and the Holm's post-hoc test. Furthermore, an additional experimentation has been performed in terms of convergence. Finally, the obtained outcomes conclude that the proposed DaIBA is a promising technique for addressing the designed problem.
110 citations
TL;DR: A novel scheme based on firefly (FA) optimization and chaotic map to construct cryptographically efficient S-box is proposed in this paper, and the obtained experimental results are compared with some recently investigated S-boxes to demonstrate that the proposed scheme has better proficiency of constructing efficientS-boxes.
Abstract: Substitution boxes are essential nonlinear components responsible to impart strong confusion and security in most of modern symmetric ciphers. Constructing efficient S-boxes has been a prominent topic of interest for security experts. With an aim to construct cryptographically efficient S-box, a novel scheme based on firefly (FA) optimization and chaotic map is proposed in this paper. The anticipated approach generates initial S-box using chaotic map. The meta-heuristic FA is applied to find notable configuration of S-box that satisfies the criterions by guided search for near-optimal features by minimizing fitness function. The performance of proposed approach is assessed through well-established criterions such as bijectivity, nonlinearity, strict avalanche criteria, bit independence criteria, differential uniformity, and linear approximation probability. The obtained experimental results are compared with some recently investigated S-boxes to demonstrate that the proposed scheme has better proficiency of constructing efficient S-boxes.
105 citations
TL;DR: A new hybrid FA is proposed, called CVRP-FA, to solve capacitated vehicle routing problem, which is integrated with two types of local search and genetic operators to enhance the solution’s quality and accelerate the convergence.
95 citations
TL;DR: A meta-heuristic optimization algorithm known as Whale Optimization Algorithm (WOA) is introduced to perform the optimization of the BESS to reduce the power losses in the distribution grid.
Abstract: This paper proposes an approach for optimal placement and sizing of battery energy storage system (BESS) to reduce the power losses in the distribution grid. A meta-heuristic optimization algorithm known as Whale Optimization Algorithm (WOA) is introduced to perform the optimization. In this paper, two different approaches are presented to achieve the optimal allocation of the BESS. The first approach is to obtain the optimal location and sizing in two steps while the second approach optimizes both location and sizing simultaneously. The performance of the proposed technique has been validated by comparing with two other algorithms namely firefly algorithm and particle swarm optimization. The results show that WOA has outstanding performance in attaining the optimal location and sizing of BESS in the distribution network for power losses reduction.
91 citations
TL;DR: Simulation results indicate that the improved basic versions of the tree growth algorithm and the elephant herding optimization swarm intelligence metaheuristics can obtain more consistent and accurate locations of the unknown target nodes in wireless sensor networks topology than other approaches that have been proposed in the literature.
Abstract: Wireless sensor networks, as an emerging paradigm of networking and computing, have applications in diverse fields such as medicine, military, environmental control, climate forecasting, surveillance, etc. For successfully tackling the node localization problem, as one of the most significant challenges in this domain, many algorithms and metaheuristics have been proposed. By analyzing available modern literature sources, it can be seen that the swarm intelligence metaheuristics have obtained significant results in this domain. Research that is presented in this paper is aimed towards achieving further improvements in solving the wireless sensor networks localization problem by employing swarm intelligence. To accomplish this goal, we have improved basic versions of the tree growth algorithm and the elephant herding optimization swarm intelligence metaheuristics and applied them to solve the wireless sensor networks localization problem. In order to determine whether the improvements are accomplished, we have conducted empirical experiments on different sizes of sensor networks ranging from 25 to 150 target nodes, for which distance measurements are corrupted by Gaussian noise. Comparative analysis with other state-of-the-art swarm intelligence algorithms that have been already tested on the same problem instance, the butterfly optimization algorithm, the particle swarm optimization algorithm, and the firefly algorithm, is conducted. Simulation results indicate that our proposed algorithms can obtain more consistent and accurate locations of the unknown target nodes in wireless sensor networks topology than other approaches that have been proposed in the literature.
86 citations
TL;DR: It has been observed that the designed hIFA-PS based fuzzy logic PID controller performs satisfactorily with varied conditions and the superiority of proposed AGC approach over some recently published AGC approaches is also demonstrated.
Abstract: This article deals with frequency control of five area power systems employing a technique which based on the hybridization of improved Firefly optimization Algorithm and Pattern Search technique (hIFA-PS) to tune the parameters of fuzzy aided PID controller. The performance of original firefly algorithm (FA) is improved by adding memory, newborn fireflies and using a new updating formula of fireflies which eliminate the wandering movement of the fireflies during the iteration process. The proposed hIFA-PS technique gets the benefits of FA's global explore capability and local search ability of PS. At first, an interconnected five area thermal power system with appropriate Generation Rate Constraints (GRC) and Dead Bands (DB) is considered and the integral constants are optimized by FA. To demonstrate the superiority of the proposed hIFA-PS algorithm results are compared with other soft computing approaches. To improve the dynamic performance, different controller structures are considered and a comparative study of hIFA-PS optimized I/PI/PID/Fuzzy aided PID is presented. The proposed design method is also applied to a five area ten unit system consisting of diverse generation sources such as thermal, hydro, wind, diesel, gas turbine. Performance analysis of the designed controller has been carried out for different system parameters and loading conditions. It has been observed that the designed hIFA-PS based fuzzy logic PID controller performs satisfactorily with varied conditions. The superiority of proposed AGC approach over some recently published AGC approaches is also demonstrated.
86 citations
TL;DR: The empirical results indicate that the proposed FA models demonstrate statistically significant superiority in both distance and performance measures for clustering tasks in comparison with conventional K-means clustering, five classical search methods, and five advanced FA variants.
TL;DR: In this article, a Firefly algorithm based approach is used to find the optimal hybrid system configuration based on minimum cost of energy (COE) while satisfying a specified reliability criteria identified with loss of load probability (LOLP) reliability index.
10 May 2019
TL;DR: This paper presents firefly algorithm framework for designing convolutional neural network architecture, and obtained empirical results showed that the proposed framework achieves promising performance in this domain.
Abstract: This paper presents firefly algorithm framework for designing convolutional neural network architecture. Convolutional neural networks can be classified as a special category of deep neural networks that in most cases consist of several convolution, fully connected (dense) and pooling layers. Wide set of image classification tasks and problems from the computer vision domain were successfully tackled by convolutional neural networks. One of the most challenging tasks from this domain is to find the convolutional neural network architecture that obtains the best performance for the specific application. The values of network's hyper-parameters have significant influence on the overall network performance. Research shown in this paper deals with convolutional neural network hyper-parameters optimization that define the network's architecture and structure. The hyper-parameters that were taken into account for this research include the number of convolutional and dense layers, the number of kernels per layer and the kernel size. We performed hyper-parameters optimization by the well-known firefly algorithm that belongs to the group of swarm intelligence metaheuristis. Solution's quality, robustness and performance of our proposed framework was tested against the MNIST dataset. Obtained empirical results showed that the proposed framework achieves promising performance in this domain.
TL;DR: F fuzzy logic controllers (FLC) are designed for maximum power point tracking (MPPT) in a photovoltaic system and then fuzzy membership functions of the fuzzy controller are optimized using Firefly Algorithm (FA) to generate the proper duty cycle.
TL;DR: The hybridization of MLP with nature-inspired optimization algorithms boosted the estimation accuracy that is clearly owing to the tuning robustness, and the applied methodology showed very convincing results for both inspected climate zones.
Abstract: Dew point temperature (DPT) is known to fluctuate in space and time regardless of the climatic zone considered. The accurate estimation of the DPT is highly significant for various applications of hydro and agro–climatological researches. The current research investigated the hybridization of a multilayer perceptron (MLP) neural network with nature-inspired optimization algorithms (i.e., gravitational search (GSA) and firefly (FFA)) to model the DPT of two climatically contrasted (humid and semi-arid) regions in India. Daily time scale measured weather information, such as wet bulb temperature (WBT), vapor pressure (VP), relative humidity (RH), and dew point temperature, was used to build the proposed predictive models. The efficiencies of the proposed hybrid MLP networks (MLP–FFA and MLP–GSA) were authenticated against standard MLP tuned by a Levenberg–Marquardt back-propagation algorithm, extreme learning machine (ELM), and support vector machine (SVM) models. Statistical evaluation metrics such as Nash Sutcliffe efficiency (NSE), root mean square error (RMSE), and mean absolute error (MAE) were used to validate the model efficiency. The proposed hybrid MLP models exhibited excellent estimation accuracy. The hybridization of MLP with nature-inspired optimization algorithms boosted the estimation accuracy that is clearly owing to the tuning robustness. In general, the applied methodology showed very convincing results for both inspected climate zones.
TL;DR: The obtained results prove the excellence of the proposed method in predicting the noise of APP considering four different valve seat materials and five speed levels, and six system pressures.
Abstract: In this paper, an alternative method to predict the noise of a submersible Axial Piston Pump (APP) for different valve seat materials is presented. The proposed method is composed of an Artificial Neural Network (ANN) model trained using experimental data and integrated with a hybrid algorithm consists of Cat Swarm Optimization (CSO) and Firefly Algorithm (FA) algorithms. The hybrid CSFA algorithm is used as a subroutine in the ANN model to estimate the ANN weights. The FA is used as local operator to improve the exploitation ability of CSO. The obtained results prove the excellence of the proposed method in predicting the noise of APP considering four different valve seat materials (Polytetrafluoroethylene (PTFE), Polyetheretherketone (PEEK), Aliphatic polyamides (NYLON), and stainless steel (316 L)), five speed levels, and six system pressures. Moreover, the effects of different mechanical properties of the valve seat materials as well as operating conditions (speed and system pressure) have been investigated.
TL;DR: The proposed node localization scheme is proposed based on a recent bioinspired algorithm called Salp Swarm Algorithm (SSA), which is compared to well-known optimization algorithms, namely, particle swarm optimization (PSO), Butterfly optimization algorithm (BOA), firefly algorithm (FA), and grey wolf optimizer (GWO) under different WSN deployments.
Abstract: Nodes localization in a wireless sensor network (WSN) aims for calculating the coordinates of unknown nodes with the assist of known nodes. The performance of a WSN can be greatly affected by the localization accuracy. In this paper, a node localization scheme is proposed based on a recent bioinspired algorithm called Salp Swarm Algorithm (SSA). The proposed algorithm is compared to well-known optimization algorithms, namely, particle swarm optimization (PSO), Butterfly optimization algorithm (BOA), firefly algorithm (FA), and grey wolf optimizer (GWO) under different WSN deployments. The simulation results show that the proposed localization algorithm is better than the other algorithms in terms of mean localization error, computing time, and the number of localized nodes.
TL;DR: A hybrid firefly algorithm (hybrid-FA) method, combining the weighted least squares (WLS) algorithm and FA, which can reduce computation as well as achieve high accuracy is proposed.
Abstract: Time difference of arrival (TDoA) based on a group of sensor nodes with known locations has been widely used to locate targets. Two-step weighted least squares (TSWLS), constrained weighted least squares (CWLS), and Newton–Raphson (NR) iteration are commonly used passive location methods, among which the initial position is needed and the complexity is high. This paper proposes a hybrid firefly algorithm (hybrid-FA) method, combining the weighted least squares (WLS) algorithm and FA, which can reduce computation as well as achieve high accuracy. The WLS algorithm is performed first, the result of which is used to restrict the search region for the FA method. Simulations showed that the hybrid-FA method required far fewer iterations than the FA method alone to achieve the same accuracy. Additionally, two experiments were conducted to compare the results of hybrid-FA with other methods. The findings indicated that the root-mean-square error (RMSE) and mean distance error of the hybrid-FA method were lower than that of the NR, TSWLS, and genetic algorithm (GA). On the whole, the hybrid-FA outperformed the NR, TSWLS, and GA for TDoA measurement.
TL;DR: The result shows that some of the modified versions of firefly algorithm produce superior results with a tradeoff of high computational time, which will help practitioners to decide which modified version to apply based on the computational resource available and the sensitivity of the problem.
Abstract: Firefly algorithm is a swarm based metaheuristic algorithm designed for continuous optimization problems. It works by following better solutions and also with a random search mechanism. It has been successfully used in different problems arising in different disciplines and also modified for discrete problems. Unlike its easiness to understand and to implement; its effectiveness is highly affected by the parameter values. In addition modifying the search mechanism may give better performance. Hence different modified versions are introduced to overcome its limitations and increase its performance. In this paper, the modifications done on firefly algorithm for continuous optimization problems will be reviewed with a critical analysis. A detailed discussion on the modifications with possible future works will also be presented. In addition a comparative study will be conducted using forty benchmark problems with different dimensions based on ten base functions. The result shows that some of the modified versions produce superior results with a tradeoff of high computational time. Hence, this result will help practitioners to decide which modified version to apply based on the computational resource available and the sensitivity of the problem.
TL;DR: A novel approach for forecasting stock prices by combining the SVR with the firefly algorithm (FA) and the proposed MFA-SVR prediction procedure can be considered as a feasible and effective tool for forecastingStock prices.
Abstract: The support vector regression (SVR) has been employed to deal with stock price forecasting problems. However, the selection of appropriate kernel parameters is crucial to obtaining satisfactory forecasting performance. This paper proposes a novel approach for forecasting stock prices by combining the SVR with the firefly algorithm (FA). The proposed forecasting model has two stages. In the first stage, to enhance the global convergence speed, a modified version of the FA, which is termed the MFA, is developed in which the dynamic adjustment strategy and the opposition-based chaotic strategy are introduced. In the second stage, a hybrid SVR model is proposed and combined with the MFA for stock price forecasting, in which the MFA is used to optimize the SVR parameters. Finally, comparative experiments are conducted to show the applicability and superiority of the proposed methods. Experimental results show the following: (1) Compared with other algorithms, the proposed MFA algorithm possesses superior performance, and (2) The proposed MFA-SVR prediction procedure can be considered as a feasible and effective tool for forecasting stock prices.
TL;DR: Two hybrid intelligence predictive models that rely on an adaptive neuro-fuzzy inference system (ANFIS) and two metaheuristic optimization algorithms, i.e., genetic algorithm (GA) and firefly algorithm (FA), for the spatially explicit prediction of wildfire probabilities are described.
TL;DR: The improved performance of the EFA in comparison with the FA, EM as well as other optimization algorithms in the literature is demonstrated by six popular truss optimization problems with discrete variables.
TL;DR: Results of various evaluations show superiority of the proposed method in finding the optimal solution with minimum function evaluations and can be applied to applications like automatic evolution of robotics, automatic control of machines and innovation of machines in finding better solutions with less cost.
Abstract: Increase in complexity of real world problems has provided an area to explore efficient methods to solve computer science problems. Meta-heuristic methods based on evolutionary computations and swarm intelligence are instances of techniques inspired by nature. This paper presents a novel social mimic optimization (SMO) algorithm inspired by mimicking behavior to solve optimization problems. The proposed algorithm is evaluated using 23 test functions. Obtained results are compared with 14 known optimization algorithms including Whale optimization algorithm (WOA), Grasshopper optimization algorithm (GOA), Particle Swarm Optimization (PSO), Stochastic fractal search (SFS), Grey Wolf Optimizer (GWO), Optics Inspired Optimization (OIO), League Championship Algorithm (LCA), Wind Driven Optimization (WDO), Harmony search (HS), Firefly Algorithm (FA), Artificial Bee Colony (ABC), Biogeography Based Optimization (BBO), Bat Algorithm (BA), and Teaching Learning Based Optimization (TLBO). Obtained results indicate higher capability of the SMO algorithm in solving high-dimensional decision variables. Furthermore, SMO is used to solve two classic engineering design problems. Three important features of SMO are simple implementation, solving optimization problems with minimum population size and not requiring control parameters. Results of various evaluations show superiority of the proposed method in finding the optimal solution with minimum function evaluations. This superiority is achieved based on reducing number of initial population. The proposed method can be applied to applications like automatic evolution of robotics, automatic control of machines and innovation of machines in finding better solutions with less cost.
TL;DR: Rigorous sensitivity analysis has been conducted to evaluate the superiority of BOA-optimised PFOID controller towards preserving system stability of ImGS with ±25% change in synchronising tie-line coefficients and bias values, and +20%change in loading condition without resetting the nominal condition gain values.
Abstract: This work presents a maiden approach of coordinated frequency control of novel solar tower (ST)-Archimedes wave energy conversion (AWEC)-geothermal energy conversion (GEC)-biodiesel driven generator (BDDG)-energy storage (ES) units and direct current (DC) links based independent three-area interconnected microgrid system (ImGS). A recent metaheuristic technique, named butterfly optimisation algorithm (BOA) is applied to obtain the optimal gains of the controllers employed with the ImGS and system participation factors. The dynamic performance of proportional–integral derivative (PID), PID with filter (PIDN), proportional–fractional-order integral derivative (PFOID) controllers with their gains tuned by different algorithms such as particle swarm optimisation (PSO), firefly algorithm (FA), whale optimisation algorithm (WOA), and BOA have been compared. Further, the effect of ES units and DC links in all the areas is analysed first time in ImGS. The results have established the superiority of the BOA-based PFOID controllers under different real-world scenarios in terms of frequency deviation, tie-line power, and objective functions. Finally, rigorous sensitivity analysis has been conducted to evaluate the superiority of BOA-optimised PFOID controller towards preserving system stability of ImGS with ±25% change in synchronising tie-line coefficients and bias values, and +20% change in loading condition without resetting the nominal condition gain values.
TL;DR: Four optimization algorithms are presented in this paper for optimizing fuzzy membership functions (MFs) and generating proper duty cycle for MPPT and simulation results indicate that TLBO and FFA based asymmetric fuzzyMFs not only increase MPPT convergence speed but also enhance tracking accuracy in comparison with symmetric fuzzy MFs and asymmetric furry MFs based on BBO and PSO.
TL;DR: A multi-objective decision making method named PROMETHEE method is applied in this work in order to select a particular solution out-of the multiple Pareto-optimal solutions provided by MO-Jaya algorithm which best suits the requirements of the process planer.
Abstract: In this work, the process parameters optimization problems of abrasive waterjet machining process are solved using a recently proposed metaheuristic optimization algorithm named as Jaya algorithm and its posteriori version named as multi-objective Jaya (MO-Jaya) algorithm. The results of Jaya and MO-Jaya algorithms are compared with the results obtained by other well-known optimization algorithms such as simulated annealing, particle swam optimization, firefly algorithm, cuckoo search algorithm, blackhole algorithm and bio-geography based optimization. A hypervolume performance metric is used to compare the results of MO-Jaya algorithm with the results of non-dominated sorting genetic algorithm and non-dominated sorting teaching–learning-based optimization algorithm. The results of Jaya and MO-Jaya algorithms are found to be better as compared to the other optimization algorithms. In addition, a multi-objective decision making method named PROMETHEE method is applied in this work in order to select a particular solution out-of the multiple Pareto-optimal solutions provided by MO-Jaya algorithm which best suits the requirements of the process planer.
TL;DR: Eigenvalue and overshoot based multi objective function is used to enhance damping of electromechanical oscillations in the system and it is seen that Firefly optimization technique based PSS converges faster as compared to conventional PSS and GAPSS.
Abstract: The proposed approach focuses on investigating the optimum values of Power System Stabilizer (PSS) parameters by the implementation of Firefly algorithm (FFA) based optimization technique. It minimizes the low frequency oscillations such that both maximum overshoot and settling time are reduced simultaneously, since the reduction of both these parameters will considerably improve the stability of the power system. In this paper, eigenvalue and overshoot based multi objective function is used to enhance damping of electromechanical oscillations in the system. Firstly, the conventional lead-lag structure of PSS, which has its design based on phase compensation technique, was applied to the systems under study. Then, Firefly optimization technique is implemented on three different standard test systems and a comparative analysis is carried out with the classical techniques (under the disturbances). Moreover, the performance of FFA tuned PSS is also compared with PSS tuned using Genetic algorithm (GA). Based on the simulations, it is seen that Firefly optimization technique based PSS converges faster as compared to conventional PSS and GAPSS. Thus, the implementation and evaluation of firefly algorithm has emerged as an evolving platform and can be considered as a very impressive catalytic method to tune the PSS parameters.
TL;DR: The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu’s criterion was used as the fitness function and achieved better segmentation considering standard segmentation quality metrics.
Abstract: During the past few decades digital images have become an important part of numerous scientific fields. Digital images used in medicine enabled tremendous progress in the diagnostics, treatment determination process as well as in monitoring patient recovery. Detection of brain tumors represents one of the active research fields and an algorithm for brain image segmentation was developed with an aim to emphasize four different primary brain tumors: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma and sarcoma from PET, MRI and SPECT images. The proposed image segmentation method is based on the firefly algorithm whose solutions are improved by the k-means clustering algorithm when Otsu’s criterion was used as the fitness function. The proposed combined algorithm was tested on commonly used images from Harvard Whole Brain Atlas and the results were compared to other method from literature. The method proposed in this paper achieved better segmentation considering standard segmentation quality metrics such as normalized root square mean error, peak signal to noise and structural similarity index metric.
TL;DR: Two chaotic firefly algorithms based on Logistic map and Gaussian map have been presented to improve basic FA, showing a desirable performance of the algorithms in both obtaining lower weight and having a higher convergence rate.
TL;DR: Three different modified algorithms of WOA have been proposed to improve its explorative ability, and opposition- and exponential-based WOA is the best among all the proposed variants.
Abstract: Whale optimization algorithm (WOA) is a recently developed swarm intelligence-based algorithm which is inspired from the social behavior of humpback whale This algorithm mimics the bubble-net hunting strategy of whales and has been applied to optimization problems But the algorithm suffers from the problem of poor exploration and local optima stagnation In this paper, three different modified algorithms of WOA have been proposed to improve its explorative ability The modified versions are based on the concepts of opposition-based learning, exponentially decreasing parameters and elimination or re-initialization of worst particles These properties have been added to improve the explorative properties of WOA by maintaining diversity among the search agents The proposed algorithms have been tested on CEC2005 benchmark problems for variable population and dimension sizes Statistical testing and scalability testing of the best algorithm have been carried out to prove its significance over other algorithms such as with well-known algorithms such as bat algorithm, bat flower pollinator, differential evolution, firefly algorithm, flower pollination algorithm It has been found from the experimental results that the performance of all the proposed versions is better than the original WOA Here, opposition- and exponential-based WOA is the best among all the proposed variants Statistical testing and convergence profiles further validate the results