Metaheuristic Optimization Algorithm Research Articles

Puma optimizer (PO): a novel metaheuristic optimization algorithm and its application in machine learning

Puma optimizer (PO): a novel metaheuristic optimization algorithm and its application in machine learning

Multi-Objective Optimal Allocation of Hybrid Photovoltaic Distributed Generators and Distribution Static Var Compensators in Radial Distribution Systems Using Various Optimization Algorithms

In recent years, considerable growth was about the integration of renewable energy sources in the Radial Distribution Systems (RDS), as Photovoltaic Distributed Generators (PVDG) due to their importance in achieving plenty desired technical and economic benefits. Implementation of the Distribution Static Var Compensator (DSVC) in addition to the PVDG would be one of the best choices that may provide the maximum of those benefits. Hence, it is crucial to determine the optimal allocation of the devices (PVDG and DSVC) into RDS to get satisfactory results and solutions. This paper is devoted to solve the allocation problem (locate and size) of hybrid PVDG and DSVC units into the standards test systems IEEE 33-bus and 69-bus RDSs. Solving the formulated problem of the optimal integration of hybrid PVDG and DSVC units is based on minimizing the proposed Multi-Objective Function (MOF) which is represented as the sum of the technical-economic parameters of Total Active Power Loss (TAPL), Total Reactive Power Loss (TRPL), Total Voltage Deviation (TVD), Total Operation Time (TOT) of the overcurrent relays (OCRs) installed in the RDS, the Investment Cost of PVDGs (ICPVDG) and the Investment Cost of DSVCs (ICDSVC), by applying various recent metaheuristic optimization algorithms. The simulation results reveal the superiority and the effectiveness of the Slime Mould Algorithm (SMA) in providing the minimum of MOF, including minimization of the power losses until 16.209 kW, and 12.11 kVar for the first RDS, 4.756 kW and 7.003 kVar for the second RDS, enhancing the voltage profiles and the overcurrent protection system. Moreover, the ability to reach the optimal allocation of PVDG and DSVC and maintain the voltage profiles in the allowable limit, whatever the load demand variation.

Applying machine learning techniques in the form of ensemble and hybrid models to appraise hardness properties of high-performance concrete

Accurately estimating concrete mechanical parameters using artificial intelligence-based methods can save time and energy. Existing nonlinear relationships between concrete components have entered uncertainty in the estimation of hardness properties of the slump and compressive strength as one of the most important parameters in concrete design. Employing regular approaches to use AI models individually in estimating dependent variables has been adopted in many studies. Therefore, the current study has aimed to develop predictive models in two categories of ensemble and hybrid frameworks to predict the hardness properties of high-performance concrete (HPC). In this regard, models based on Support Vector Regression, Decision Tree, and AdaBoost Machine learning were coupled with a metaheuristic optimization algorithm Chaos game optimizer (CGO). Linking three predictive models as well as tuning their internal settings via optimization algorithm could generate various types of hybrid and ensemble models. By assessing the results of the proposed models for compressive strength, the performance of ADA-CGO hybrid models was calculated higher than the ensemble model of SVR-ADA-DT, with 1.22% and 166% percent difference in terms of R2 and RMSE, respectively. Also, for predicting Slump, other hybrid models appeared with weaker performance than the ensemble model, with an average difference of 40.66% in terms of the MAE index. Generally, using advanced types of individual models, including ensemble and hybrid, indicated boosted performance accompanied by low-cost modeling processes.

Parameter estimation in single-phase transformers via the generalized normal distribution optimizer while considering voltage and current measurements

This research addresses, from a perspective of metaheuristic optimization, the problem regarding parametric estimation in single-phase transformers while considering voltage and current measures at the terminals of the transformer and weighing linear loads. Transformer parametric estimation is modeled as a nonlinear problem in order to minimize the mean square error between the calculated voltage and current variables and the measurements taken. The nonlinearities are associated with Kirchhoff's first and second laws applied to the equivalent electrical circuit of the single-phase transformer. The nonlinear optimization problem is solved by applying a metaheuristic optimization algorithm known as the generalized normal distribution optimizer (GNDO), which uses evolution rules that allow exploring and exploiting the solution space via the classical probability function based on normal distributions. Numerical results in three test transformers of 20, 45, and 112.5 kVA demonstrate the effectiveness and robustness of the proposed GNDO approach when compared to other optimizers reported in the literature, such as the crow search algorithm, the coyote optimization algorithm, and the exact solution of the nonlinear optimization model using the fmincon solver of the MATLAB software. All numerical simulations confirm the potential of the GNDO approach to deal with complex optimization problems in engineering and science with promising results and low computational effort.

Solving Traveling Salesman Problem Using Parallel River Formation Dynamics Optimization Algorithm on Multi-core Architecture Using Apache Spark

According to Moore’s law, computer processing hardware technology performance is doubled every year. To make effective use of this technological development, the algorithmic solutions have to be developed at the same speed. Consequently, it is necessary to design parallel algorithms to be implemented on parallel machines. This helps to exploit the multi-core environment by executing multiple instructions simultaneously on multiple processors. Traveling Salesman (TSP) is a challenging non-deterministic-hard optimization problem that has exponential running time using brute-force methods. TSP is concerned with finding the shortest path starting with a point and returning to that point after visiting the list of points, provided that these points are visited only once. Meta-heuristic optimization algorithms have been used to tackle TSP and find near-optimal solutions in a reasonable time. This paper proposes a parallel River Formation Dynamics Optimization Algorithm (RFD) to solve the TSP problem. The parallelization technique depends on dividing the population into different processors using the Map-Reduce framework in Apache Spark. The experiments are accomplished in three phases. The first phase compares the speedup, running time, and efficiency of RFD on 1 (sequential RFD), 4, 8, and 16 cores. The second phase compares the proposed parallel RFD with three parallel water-based algorithms, namely the Water Flow algorithm, Intelligent Water Drops, and the Water Cycle Algorithm. To achieve fairness, all algorithms are implemented using the same system specifications and the same values for shared parameters. The third phase compares the proposed parallel RFD with the reported results of metaheuristic algorithms that were used to solve TSP in the literature. The results demonstrate that the RFD algorithm has the best performance for the majority of problem instances, achieving the lowest running times across different core counts. Our findings highlight the importance of selecting the most suitable algorithm and core count based on the problem characteristics to achieve optimal performance in parallel optimization.

Football team training algorithm: A novel sport-inspired meta-heuristic optimization algorithm for global optimization

A more efficient optimization algorithm has always been the pursuit of researchers, but the performance of the current optimization algorithm in some complex test functions is not always satisfactory. In order to solve this problem, a new meta-heuristic optimization algorithm—Football Team Training Algorithm (FTTA) is proposed according to the training method of the football team, which simulates the three stages of the training session: Collective Training, Group Training and Individual Extra Training. By the test on two groups of test functions, CEC2005 and CEC2020, the proposed optimization algorithm (FTTA) achieves the best results, which far exceeds the traditional Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA) algorithms and so on. In the engineering application, a new hybrid wind speed prediction system is proposed based on FTTA. The FTTA is used to optimize variational mode decomposition (VMD) to improve the effect of data denoising. At the same time, based on unconstrained weighting algorithm, FTTA and combination prediction model build a new hybrid prediction strategy. Through the experiments on four groups of wind speed data in Dalian, the accuracy, stability, advancement, and CPU running speed of the system are verified. It is obvious that the practical application ability of the system is much better than previous methods, which can effectively improve the utilization efficiency of renewable energy.

Solution of Inverse Problem for Diffusion Equation with Fractional Derivatives Using Metaheuristic Optimization Algorithm

The article focuses on the presentation and comparison of selected heuristic algorithms for solving the inverse problem for the anomalous diffusion model. Considered mathematical model consists of time-space fractional diffusion equation with initial boundary conditions. Those kind of models are used in modelling the phenomena of heat flow in porous materials. In the model, Caputo’s and Riemann-Liouville’s fractional derivatives were used. The inverse problem was based on identifying orders of the derivatives and recreating fractional boundary condition. Taking into consideration the fact that inverse problems of this kind are ill-conditioned, the problem should be considered as hard to solve. Therefore,to solve it, metaheuristic optimization algorithms popular in scientific literature were used and their performance were compared: Group Teaching Optimization Algorithm (GTOA), Equilibrium Optimizer (EO), Grey Wolf Optimizer (GWO), War Strategy Optimizer (WSO), Tuna Swarm Optimization (TSO), Ant Colony Optimization (ACO), Jellyfish Search (JS) and Artificial Bee Colony (ABC). This paper presents computational examples showing effectiveness of considered metaheuristic optimization algorithms in solving inverse problem for anomalous diffusion model.

Optimization of a Hybrid Renewable Energy System Based on Meta-Heuristic Optimization Algorithms

Optimization of a Hybrid Renewable Energy System Based on Meta-Heuristic Optimization Algorithms

CHAOS THEORY, ADVANCED METAHEURISTIC ALGORITHMS AND THEIR NEWFANGLED DEEP LEARNING ARCHITECTURE OPTIMIZATION APPLICATIONS: A REVIEW

Metaheuristic techniques are capable of representing optimization frames with their specific theories as well as objective functions owing to their being adjustable and effective in various applications. Through the optimization of deep learning models, metaheuristic algorithms inspired by nature, imitating the behavior of living and non-living beings, have been used for about four decades to solve challenging, complex, and chaotic problems. These algorithms can be categorized as evolution-based, swarm-based, nature-based, human-based, hybrid, or chaos-based. Chaos theory, as a useful approach to understanding neural network optimization, has the basic idea of viewing the neural network optimization as a dynamical system in which the equation schemes are utilized from the space pertaining to learnable parameters, namely optimization trajectory, to itself, which enables the description of the evolution of the system by understanding the training behavior, which is to say the number of iterations over time. The examination of the recent studies reveals the importance of chaos theory, which is sensitive to initial conditions with randomness and dynamical properties that are principally emerging on the complex multimodal landscape. Chaotic optimization, in this regard, accelerates the speed of the algorithm while also enhancing the variety of movement patterns. The significance of hybrid algorithms developed through their applications in different domains concerning real-world phenomena and well-known benchmark problems in the literature is also evident. Metaheuristic optimization algorithms have also been applied to deep learning or deep neural networks (DNNs), a branch of machine learning. In this respect, the basic features of deep learning and DNNs and the extensive use of metaheuristic algorithms are overviewed and explained. Accordingly, the current review aims at providing new insights into the studies that deal with metaheuristic algorithms, hybrid-based metaheuristics, chaos-based metaheuristics as well as deep learning besides presenting recent information on the development of the essence of this branch of science with emerging opportunities, applicability-based optimization aspects and generation of well-informed decisions.

Study on deconvolution of alpha-particle spectra using metaheuristic optimization and multivariate analysis

To find a global optimal solution and obtain further insight into the parameters of the peak shape fitting function, metaheuristic optimization algorithms, and multivariate analysis techniques are employed to study the deconvolution of alpha-particle spectra. An improved peak shape model composed of the Bortels-Collaers function and Lévy distribution function, which aims to handle the high-energy tailing, is proposed. A newly developed metaheuristic optimization method, Bonobo Optimizer (BO) is adopted to seek optimal parameters in the peak shape function. Multivariate analysis (MVA) techniques are used to find hidden information in the shape model. Pearson's correlation tells the mutual variation relationship among parameters, while Multidimensional scaling (MDS) shows similarities of parameters through a 2D plot. Effects of parameters upon the regression accuracy are obtained via the Student t-test. Self-organizing Mapping (SOM) is utilized to mine intrinsic relations among these parameters through visual images. AM243-1 test alpha spectra example is selected to examine the proposed methodology. The improved model is more accurate when handling the high-energy tailing features. Compared with traditional gradient-based optimization algorithms, BO can find global solutions without tedious work in initial solution setting and constraint handling. More information is mined through MVA and further understanding of the peak shape function is obtained.

Drought Prediction with Feature Enhanced LSTM Model using Metaheuristic Optimization Algorithms

The impact of drought builds on all three fronts of economy, environment, and society is devastating. Predicting its arrival and duration is highly important to arrange any sort of mitigation plans. The association of detailed relationship between multiple variables makes drought prediction a highly complex task. Especially influence of global warming, polar sea extent variations and their influence on overall ocean temperature have altered the seasonal rainfall behaviors all over the world. In the midst of it, predictions centered on the history of rainfall levels become inaccurate. The proposed system is an optimized deep learning prediction model integrating indigenous knowledge (IK) is proposed to predict the drought. IK expressed in human language is translated using fuzzy function and fed to an improved Long Short Term Memory (LSTM) model. The LSTM model hyperparameters are optimized using a hybrid of Particle Swarm Optimization (PSO) with firefly to produce the meta-heuristics algorithm which will provide the best performance in presence of integration of IK features into modern meteorological features which solves the problem of local minima in LSTM hyperparameter optimization. The performance of the proposed results were tested compared with the meteorological information gathered by the Karnataka Natural Disaster Monitoring Centre (KNDMC) for the district named Chitradurga of the Karnataka state in India. The proposed system which is Indigenous Knowledge merged along the cross model attention network can produce at least 1.4% higher Nash–Sutcliffe model efficiency coefficient (NSE) and 30% lower Mean Absolute Error (MAE) in the prediction of Standard Precipitation Index (SPI) compared to Convolution Neural Networks (CNN) and LSTM based time series prediction models.

A Comparative Analysis of Metaheuristic Algorithms Tuned Supper Twisting Sliding Mode Control of a Self-balancing Segway

A self-balancing two-wheel Segway is a multivariable, nonlinear, coupled and unstable personal transport that is among the benchmarks of under-actuated systems to test different control schemes. The proper operation of the system needs stable and robust controllers for the balancing and direction of the Segway. Stable and robust performance of such systems can be achieved using adaptive, optimal and non-linear control schemes. A conventional sliding mode controller is a nonlinear controller, considered a robust controller except for the chattering problem that can be solved using higher order sliding mode controllers such as a supper twisted sliding mode controller (STSMC). In this research, STSMC is proposed for balancing and PID controller for direction control of a self-balancing Segway. To solve the impacts of design technique, skill, and experience of the designer on the control schemes, controllers are tuned using metaheuristic optimization algorithms, namely Grey wolf algorithm (GWO), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) technique. The overall system has been implemented in MATLAB/Simulink, and performance evaluations have been executed for the time domain specifications of settling and rise times as comparison criteria for the Segway operating conditions of variable driver mass and tilt angles. The results show relatively quick responses - for initial pitch angel of 0.3 rad, and initial yaw angle of 0.1 rad – of GWO-STSMC and GWO-PID controllers. For variable driver mass and constant initial tilt angles, the pitch response is found to be less sensitive to the increase in mass of the driver for GWO-STSMC, while the yaw angle response shows a slight sensitivity decrease for GWO-PID controller. For variable initial tilt angles and constant mass of the drive, both GWO-STSMC and GWO-PID controllers show the capability of tracking the reference pitch and yaw angles.

Interfacial behavior of hybrid-bonded CFRP-to-concrete joints

Hybrid-bonded (HB) systems are employed to anchor carbon fibre reinforced polymer (CFRP) laminates to concrete structures and delay their premature debonding failure mode by generating compressive stresses on the joint. However, although previous research on these strengthening systems exists, the optimum parameters that minimize the potential for premature debonding failure and maximize the ultimate load still need to be investigated.In this work, the feasibility of decoupling the effect of decohesion and friction of a HB CFRP-to-concrete joint is assessed through experimental and numerical analysis. To this end, single shear tests are performed on concrete specimens strengthened with externally bonded reinforcement (EBR) and HB-CFRP precured laminate. Besides, a numerical procedure, based on the finite difference method and a metaheuristic optimization algorithm, is utilized to obtain the bond-slip law that describes the constitutive behaviour of both systems. Moreover, the separated contributions of the cohesion of the adhesive joint and the friction induced by the external compressive stresses normal to the composite surface are analysed separately, and separated cohesive and friction stress-slip laws are obtained. The experimental behaviour of the full anchoring system is compared against that obtained by combination of the separated cohesive and friction contributions. The method represents progress in examining how different anchoring parameters, including the size (width and thickness) of the anchor plate and the torque applied to the bolts, influence the performance of the anchoring system in an efficient and systematic manner.

Improving the Prediction of Student Performance by Integrating a Random Forest Classifier with Meta-Heuristic Optimization Algorithms

Improving the Prediction of Student Performance by Integrating a Random Forest Classifier with Meta-Heuristic Optimization Algorithms

A review on the microgrid sizing and performance optimization by metaheuristic algorithms for energy management strategies

A growing concern over climate change and the depletion of conventional energy resources have led to the urgent need for sustainable and resilient energy solutions. The optimization of the size of renewable sources is crucial to maximizing their effectiveness. In contrast to conventional single-objective optimization, the multi-objective technique aims to achieve a trade-off between energy cost and power supply reliability. Due to this need, microgrids (MG) have emerged as a promising paradigm, allowing for localized and decentralized energy generation and distribution. Consequently, the conventional techniques for modelling and optimizing exhibit numerous limitations as the power grid continues to produce substantial volumes of high-dimensional and diverse data types. This review paper examines the use of metaheuristic algorithms in the context of multi-objective energy optimization for hybrid renewable energy-integrated microgrids. A comparative analysis of diverse metaheuristic algorithms for microgrid optimization is provided in this paper, which emulates natural phenomena, such as evolutionary processes and swarm dynamics. Based on the findings of case studies, it can be concluded that trade-offs exist between various objectives, eventually leading to the development of both resilient and efficient microgrid designs. By reviewing sustainable energy solutions, and advocating microgrids as viable alternatives to conventional centralized power systems, the review enhances the advancement of sustainable energy solutions.

A Comparison of Metaheuristic Algorithms for Structural Optimization: Performance and Efficiency Analysis

A Comparison of Metaheuristic Algorithms for Structural Optimization: Performance and Efficiency Analysis

Optimization of Home Energy Management Systems in Smart Cities Using Bacterial Foraging Algorithm and Deep Reinforcement Learning for Enhanced Renewable Energy Integration

This paper presents a pioneering exploration into the optimization of Home Energy Management Systems (HEMS) through the novel application of the Bacterial Foraging Metaheuristic Optimization (BFMO) algorithm and Deep Reinforcement Learning (DRL). The study systematically addresses the pressing challenge of enhancing residential energy efficiency, focusing on dynamic appliance scheduling within HEMS. A robust methodology is established, encompassing data collection from smart homes, implementation details of the BFMO algorithm, DRL techniques, and a comprehensive evaluation framework. The unique contribution of this research lies in the effective integration of the BFMO algorithm and DRL to orchestrate energy‐conscious scheduling of home appliances within HEMS. The BFMO algorithm demonstrates its adaptability to fluctuating energy costs and consumption patterns by simulating the foraging behaviour of bacteria. At the same time, DRL enhances the system’s ability to learn and optimize scheduling decisions over time, showcasing their combined efficacy in real‐world scenarios. The algorithms’ iterative application of chemotaxis, reproduction, elimination‐dispersal, swarming, and learning consistently yields optimized appliance schedules. The main focus of this study resides in the evaluation metrics illustrating the tangible benefits of BFMO and DRL compared to traditional HEMS. Significant reductions in total energy consumption and cost, accompanied by improved peak demand management, exemplify the algorithms’ impact. Furthermore, the study delves into enhancing user comfort, integrating renewable energy sources, and the overall robustness of HEMS, all demonstrating the multifaceted advantages of the BFMO and DRL approaches. This research contributes methodologically by introducing and detailing these algorithms and provides a valuable dataset and evaluation metrics for future research in the domain. The findings underscore the immediate and long‐term relevance of optimizing HEMS with BFMO and DRL, catering to researchers, practitioners, and policymakers involved in advancing smart grid technologies and sustainable residential energy management. In summary, this work establishes the BFMO algorithm and DRL as pioneering and versatile tools for energy‐conscious appliance scheduling in HEMS, offering a substantial leap forward in the quest for efficient and sustainable residential energy management.

Stability-Based Optimum Design of Tuned Mass Damper using Chaos Game Optimization in Pole Placement Scheme

The present work investigates the optimization of Tuned Mass Dampers (TMDs) for improving the seismic behavior of structures by considering system stability using a well-known robust Chaos Game Optimization (CGO) metaheuristic algorithm. In this regard, a new approach was introduced to locate the system’s poles as an objective function in the optimum design of TMDs. In this scheme, the mechanical parameters of TMD are designed to find the pole placement of the structural system with more stability. This research presents a dynamic analysis and comparative evaluation of various cost functions—including relative controlled drift response, the transfer function (TF) of acceleration response, and pole placement scheme—to determine the most effective design for TMD parameter optimization. Structural control performance indexes are used to compare the seismic behavior of each design. The results demonstrate the cost function based on the pole placement scheme’s capability to enhance TMD design, suggesting valuable theoretical and practical understandings for more resilient and efficient structural designs.

Моделювання логістичних процесів імпорту морепродуктів в умовах пошкодженої інфраструктури

The article is devoted to issues of modeling the processes of finding solutions to logistical problems in fish and seafood supply to the population of Ukraine. The paper analyzes the numerous publications of Ukrainian and foreign researches on topics related to issues of marketing and logistics of fish products. The modern conditions’ assessment in which the supply of seafood is carried out is given. The problems faced by product carriers are considered, among which the main ones are hostilities, constant shelling, damage and destruction of infrastructure and energy networks of Ukraine. The Gray Wolf Optimization (GWO) metaheuristic algorithm is used to solve the given problem, which helps to solve NP-complex problems that are difficult to solve by any traditional exact methods, or these methods do not exist at all. Productivity of such type algorithms is evaluated based on five indicators: solution quality, convergence speed, computational efficiency, robustness, and flexibility. The proposed GWO-based model enabled the optimization of several objectives, including the minimization of total supply chain costs, maximization of customer satisfaction, and reduction of harmful environmental impacts, enabling an integrated approach to supply chain management.

An Efficient Metaheuristic algorithm for optimization for Location of Optimum Connectivity Services with Drones in Healthcare

Drones are being extensively used for a variety of practical purposes, including providing medical care. For instance, giving vaccinations, healthcare equipment, and samples of blood to individuals in isolated locations as well as during calamities. This study examined an efficient metaheuristic algorithm called MAP-LOCS, which optimizes the location of optimal connectivity amenities using drones. The use of drones in relation to facility placement and navigation is the issue. Within certain drone range limits, it entails choosing drone launch spots to optimize patient care availability. This work develops a heuristic called Location of Optimal Connection Services. The algorithm's basic premise is to start by randomly selecting a few services to open from among those that are most capable of meeting patient requests. Following that, patients are matched with the nearest open facility that can accommodate them.