Meta-heuristic Optimization Technique Research Articles

Optimizing Machine Learning Algorithms for Landslide Susceptibility Mapping along the Karakoram Highway, Gilgit Baltistan, Pakistan: A Comparative Study of Baseline, Bayesian, and Metaheuristic Hyperparameter Optimization Techniques.

Algorithms for machine learning have found extensive use in numerous fields and applications. One important aspect of effectively utilizing these algorithms is tuning the hyperparameters to match the specific task at hand. The selection and configuration of hyperparameters directly impact the performance of machine learning models. Achieving optimal hyperparameter settings often requires a deep understanding of the underlying models and the appropriate optimization techniques. While there are many automatic optimization techniques available, each with its own advantages and disadvantages, this article focuses on hyperparameter optimization for well-known machine learning models. It explores cutting-edge optimization methods such as metaheuristic algorithms, deep learning-based optimization, Bayesian optimization, and quantum optimization, and our paper focused mainly on metaheuristic and Bayesian optimization techniques and provides guidance on applying them to different machine learning algorithms. The article also presents real-world applications of hyperparameter optimization by conducting tests on spatial data collections for landslide susceptibility mapping. Based on the experiment's results, both Bayesian optimization and metaheuristic algorithms showed promising performance compared to baseline algorithms. For instance, the metaheuristic algorithm boosted the random forest model's overall accuracy by 5% and 3%, respectively, from baseline optimization methods GS and RS, and by 4% and 2% from baseline optimization methods GA and PSO. Additionally, for models like KNN and SVM, Bayesian methods with Gaussian processes had good results. When compared to the baseline algorithms RS and GS, the accuracy of the KNN model was enhanced by BO-TPE by 1% and 11%, respectively, and by BO-GP by 2% and 12%, respectively. For SVM, BO-TPE outperformed GS and RS by 6% in terms of performance, while BO-GP improved results by 5%. The paper thoroughly discusses the reasons behind the efficiency of these algorithms. By successfully identifying appropriate hyperparameter configurations, this research paper aims to assist researchers, spatial data analysts, and industrial users in developing machine learning models more effectively. The findings and insights provided in this paper can contribute to enhancing the performance and applicability of machine learning algorithms in various domains.

Self-adaptive metaheuristic optimization technique for multi-objective reservoir operation

Abstract Multi-objective reservoir operation presents a number of critical challenges that must be overcome for efficient management of water resources. The inherent contradiction between several goals, such as satisfying irrigation demand and maximizing hydropower generation, is one of the major issues. Trade-offs and compromises must be carefully considered to balance these objectives. To solve this problem, a study was carried out to optimize the operation of multi-objective reservoirs with two primary goals: minimizing irrigation deficits and maximizing hydropower generation. This study employs the self-adaptive multipopulation multi-objective Jaya algorithm (SAMP-MOJA), an improved version of the Jaya algorithm, to construct an optimal Pareto Front utilizing an a priori approach. The performance of SAMP-MOJA is compared to that of other algorithms such as multi-objective particle swarm optimization, multi-objective invasive weed optimization, and multi-objective Jaya algorithm. The results of this study demonstrate that the hydropower generated by the developed model surpasses 80% of the actual generation. The study's findings will aid in designing the most effective Pareto front possible.

Comparative Analysis of Firefly and Modified Firefly Algorithms in Multimodal Biometric Authentication Systems

Abstract: This research focuses on addressing the challenges of high-dimensional feature spaces and selecting significant features in multimodal biometric systems. Feature-level fusion poses persistent issues that require extensive investigation due to its potential for enhancing biometric recognition accuracy. This study proposes the integration of meta-heuristic optimization techniques into the feature selection phase of a multimodal biometric system, prior to the classification phase, to identify the most relevant features from two distinct biological traits. To determine the authorization status of an individual, the fused feature vectors are inputted into a Support Vector Machine (SVM) classifier. The study leverages the physiological biometrics of the face and iris to validate the findings of previous research, highlighting the exceptional accuracy of iris recognition and the natural acceptability of face recognition for identity verification purposes.

Techno-Economic Analysis and Optimization of Hybrid Renewable Energy System with Energy Storage under Two Operational Modes

Access to cheap, clean energy has a significant impact on a country’s ability to develop sustainably. Fossil fuels have a major impact on global warming and are currently becoming less and less profitable when used to generate power. In order to replace the diesel generators that are connected to the university of Debre Markos’ electrical distribution network with hybrid renewable energy sources, this study presents optimization and techno-economic feasibility analyses of proposed hybrid renewable systems and their overall cost impact in stand-alone and grid-connected modes of operation. Metaheuristic optimization techniques such as enhanced whale optimization algorithm (EWOA), whale optimization algorithm (WOA), and African vultures’ optimization algorithm (AVOA) are used for the optimal sizing of the hybrid renewable energy sources according to financial and reliability evaluation parameters. After developing a MATLAB program to size hybrid systems, the total current cost (TCC) was calculated using the aforementioned metaheuristic optimization techniques (i.e., EWOA, WOA, and AVOA). In the grid-connected mode of operation, the TCC was 4.507 × 106 EUR, 4.515 × 106 EUR, and 4.538 × 106 EUR, respectively, whereas in stand-alone mode, the TCC was 4.817 × 106 EUR, 4.868 × 106 EUR, and 4.885 × 106 EUR, respectively. In the grid-connected mode of operation, EWOA outcomes lowered the TCC by 0.18% using WOA and 0.69% using AVOA, and by 1.05% using WOA and 1.39% using AVOA in stand-alone operational mode. In addition, when compared with different financial evaluation parameters such as net present cost (NPC) (EUR), cost of energy (COE) (EUR/kWh), and levelized cost of energy (LCOE) (EUR/kWh), and reliability parameters such as expected energy not supplied (EENS), loss of power supply probability (LPSP), reliability index (IR), loss of load probability (LOLP), and loss of load expectation (LOLE), EWOA efficiently reduced the overall current cost while fulfilling the constraints imposed by the objective function. According to the result comparison, EWOA outperformed the competition in terms of total current costs with reliability improvements.

Optimal Load Sharing between Lithium-Ion Battery and Supercapacitor for Electric Vehicle Applications

There has been a suggestion for the best energy management method for an electric vehicle with a hybrid power system. The objective is to supply the electric vehicle with high-quality electricity. The hybrid power system comprises a supercapacitor (SC) bank and a lithium-ion battery. The recommended energy management plan attempts to maintain the bus voltage while providing the load demand with high-quality power under various circumstances. The management controller is built on a metaheuristic optimization technique that enhances the flatness theory-based controller’s trajectory generation parameters. The SC units control the DC bus while the battery balances the power on the common line. This study demonstrates the expected contribution using particle swarm optimization and performance are assessed under various optimization parameters, including population size and maximum iterations. Their effects on controller performance are examined in the study. The outcomes demonstrate that the number of iterations significantly influences the algorithm’s ability to determine the best controller parameters. The results imply that combining metaheuristic optimization techniques with flatness theory can enhance power quality. The suggested management algorithm ensures power is shared efficiently, protecting power sources and providing good power quality.

Comparison of Metaheuristic Optimization Techniques for the Optimal Placement and Sizing of Shunt Flexible Alternating Current Transmission Systems Device Considering Load Increase

Comparison of Metaheuristic Optimization Techniques for the Optimal Placement and Sizing of Shunt Flexible Alternating Current Transmission Systems Device Considering Load Increase

A Novel Hybrid Algorithm Based on Jellyfish Search and Particle Swarm Optimization

Metaheuristic optimization is considered one of the most efficient and powerful techniques of recent decades as it can deal effectively with complex optimization problems. The performance of the optimization technique relies on two main components: exploration and exploitation. Unfortunately, the performance is limited by a weakness in one of the components. This study aims to tackle the issue with the exploration of the existing jellyfish search optimizer (JSO) by introducing a hybrid jellyfish search and particle swarm optimization (HJSPSO). HJSPSO is mainly based on a JSO structure, but the following ocean current movement operator is replaced with PSO to benefit from its exploration capability. The search process alternates between PSO and JSO operators through a time control mechanism. Furthermore, nonlinear and time-varying inertia weight, cognitive, and social coefficients are added to the PSO and JSO operators to balance between exploration and exploitation. Sixty benchmark test functions, including 10 CEC-C06 2019 large-scale benchmark test functions with various dimensions, are used to showcase the optimization performance. Then, the traveling salesman problem (TSP) is used to validate the performance of HJSPSO for a nonconvex optimization problem. Results demonstrate that compared to existing JSO and PSO techniques, HJSPSO contributes in terms of exploration and exploitation improvements, where it outperforms other well-known metaheuristic optimization techniques that include a hybrid algorithm. In this case, HJSPSO secures the first rank in classical and large-scale benchmark test functions by achieving the highest hit rates of 64% and 30%, respectively. Moreover, HJSPSO demonstrates good applicability in solving an exemplar TSP after attaining the shortest distance with the lowest mean and best fitness at 37.87 and 36.12, respectively. Overall, HJSPSO shows superior performance in solving most benchmark test functions compared to other optimization techniques, including JSO and PSO. As a conclusion, HJSPSO is a robust technique that can be applied to solve most optimization problems with a promising solution.

Northern Goshawk Optimization Algorithm for Optimal Power Flow with FACTS Devices in Wind Power Integrated Electrical Networks

Power-operational problems must be resolved with flexible AC transmission systems (FACTS) and optimum power flow (OPF). The complexity of power flow analysis in modern power network models is increased by the unpredictability of renewable energy generating sources in addition to the challenge of determining the appropriate locations and ratings for FACTS devices. FACTS devices can increase the thermal capacity of power transmission lines, enabling the network to accommodate more electricity from renewable sources. The major goals of this study are to lower production costs, decrease power losses, enhance the voltage profile of the system, and enhance load capability. To solve a variety of optimization issues optimally, optimization meta-heuristics approaches have been created in response to the increased emphasis on renewable energy sources, such as wind power. Wind energy is an important component of modern power systems due to its affordability and clean nature. This article presents an OPF method for efficiently scheduling energy from wind farms using the Northern Goshawk Optimization (NGO) meta-heuristic technique. The Weibull probability distribution function is used to represent wind speed and estimate the cost of electricity produced by wind turbines based on the planned power. To validate the NGO approach and its results compared with those of other meta-heuristic optimization techniques, such as Chef-Based Optimization Algorithm, Dingo Optimization Algorithm, and Chameleon Swarm Algorithm, the IEEE system 30-bus is used to solve the OPF problem.

Enhancing the Hybrid Microgrid Performance with Jellyfish Optimization for Efficient MPPT and THD Estimation by the Unscented Kalman Filter

Power management in advanced grid systems requires the seamless integration of diverse renewable energy sources. This study investigates the optimization of a grid-connected system comprising a photovoltaic (PV) solar panel, energy storage system, fuel cell (FC), and diesel generator (DG) using the bioinspired metaheuristic technique called jellyfish optimization (JF). The objective is to maximize power generation from the PV system under normal and partial shading conditions. The performance of JF is compared against particle swarm optimization (PSO) using various parameters. As India heavily relies on solar PV, the results highlight JF’s exceptional effectiveness in extracting maximum power during partial shading scenarios. Inspired by the active and passive motions of jellyfish in the ocean, the JF algorithm is utilized. To further optimize the power output, the system is integrated with an efficient battery management system, PEM fuel cell stacking, and diesel generators. The system’s performance is analyzed using fast Fourier transform (FFT) to evaluate harmonic distortions, which consistently meet the limits specified in IEEE STD 1547-2018. Furthermore, unscented Kalman filter-based analysis is employed to assess total harmonic distortion (THD) and power rating for the grid system across various renewable energy scenarios. The contribution of the jellyfish optimization (JF) algorithm lies in its ability to efficiently and effectively maximize power generation from the PV system, regardless of normal or partial shading conditions. JF, a bioinspired metaheuristic optimization technique, successfully emulates the collective behavior of jellyfish in the ocean to identify optimal solutions. In this study, JF outperforms particle swarm optimization (PSO) in terms of power generation under partial shading conditions. Notably, JF exhibits remarkable capability in exploring the search space and discovering the global optimum, even when the system operates under challenging conditions. Overall, this study demonstrates the tremendous potential of JF in maximizing power generation in grid-connected systems with renewable energy sources while also highlighting the benefits of integrating additional components to further enhance the system performance.

Study on Meta-heuristics techniques for shade dispersion to enhance GMPP of PV array systems under PSCs

Reconfiguring the photovoltaic modules in an array is one option for reducing the influence of partial shadowing circumstances, which shows the shade dispersion property on the entire photovolatic array. This paper proposes a novel meta-heuristic optimization technique named Vommi that resolves the reconfiguration process of shaded modules in a photovoltaic array. Using the proposed objective function, the major goal of this unique optimization technique is to maximize the power extracted from the shaded PV array during shading conditions. The proposed meta-heuristic Vommi optimization algorithm is compared to conventional total cross-tied, and particle swarm optimization algorithm-based configurations in terms of power at the global maximum power point, improved fill factor, power losses, execution ratio, etc. The global maximum power point of the Vommi optimization algorithm configuration delivers such as 990 W, 1283 W, 1181 W, and 1173 W, which are higher than conventional approaches during all four partial shodowing circumstances and smoother power-voltage characteristics..

Integration of Superconducting Magnetic Energy Storage for Fast-Response Storage in a Hybrid Solar PV-Biogas with Pumped-Hydro Energy Storage Power Plant

Electric distribution systems face many issues, such as power outages, high power losses, voltage sags, and low voltage stability, which are caused by the intermittent nature of renewable power generation and the large changes in load demand. To deal with these issues, a distribution system has been designed using both short- and long-term energy storage systems such as superconducting magnetic energy storage (SMES) and pumped-hydro energy storage (PHES). The aim of this paper is to propose a metaheuristic-based optimization method to find the optimal size of a hybrid solar PV-biogas generator with SMES-PHES in the distribution system and conduct a financial analysis. This method is based on an efficient algorithm called the “enhanced whale optimization” algorithm (EWOA), along with the proposed objective functions and constraints of the system. The EWOA is employed to reduce the hybrid system’s life cycle cost (LCC) and improve its reliability, both of which serve as performance indicators for the distribution system. The proposed method for sizing a grid-connected hybrid solar PV-biogas generator with SMES-PHES is compared with other metaheuristic optimization techniques, including the African vulture optimization algorithm (AVOA), grey wolf optimization algorithm (GWO), and water cycle algorithm (WCA). The numerical results of the EWOA show that the combination of a hybrid solar PV-biogas generator with SMES-PHES can successfully reduce the LCC and increase reliability, making the distribution system work better.

On Employing a Constrained Nonlinear Optimizer to Constrained Economic Dispatch Problems

Recently, different metaheuristic techniques, their variants, and hybrid forms have been extensively used to solve economic load dispatch (ELD) problems with and without valve point loading (VPL) effects. Due to the randomization involved in these metaheuristic techniques, one has to perform extensive runs for each experiment to get an optimal solution. The process may sometimes become laborious and time-consuming to converge to an optimal solution. On the other hand, advanced calculus-based techniques, being deterministic, perform iteration systematically and come up with the same solution on each run of the experiment. Since ELD problems are constrained optimization problems, we are proposing the constrained (deterministic) optimization algorithm for their solutions. Various 13-unit, 38-unit, and 40-unit thermal test systems are considered. Valve point loading (VPL) effects are also considered in some cases. Computer-based numerical results depict that the constrained optimization algorithm shows evidence of being almost as competitive in a total fuel cost as the metaheuristic optimization techniques, especially for the less-constrained ELD problems but with far reduced computation time. This finding validates the application of the constrained optimization technique to solve the economic dispatch problem.

Power Quality Alleviation of a Grid-Integrated Photovoltaic System Based on Novel Meta-Heuristic Optimization Technique Using OPAL-RT Real-Time Platform

Power Quality Alleviation of a Grid-Integrated Photovoltaic System Based on Novel Meta-Heuristic Optimization Technique Using OPAL-RT Real-Time Platform

A Comprehensive Review of Diabetic Retinopathy Detection and Grading Based on Deep Learning and Metaheuristic Optimization Techniques

A Comprehensive Review of Diabetic Retinopathy Detection and Grading Based on Deep Learning and Metaheuristic Optimization Techniques

Firefly Algorithm Optimization-Based LQR Controller for 1/4 Vehicle Active Suspension System: Design and Performance Evaluation

The outcomes of this research significantly contribute to the existing body of knowledge on metaheuristic optimization techniques for active suspension systems. By conducting thorough investigations and analyses, the study effectively demonstrates the remarkable advantages of the Firefly algorithm in optimizing the performance of both conventional and intelligent controllers for active suspension systems. These findings highlight the algorithm's potential to revolutionize the field and pave the way for more efficient and robust control strategies. The demonstrated effectiveness of the Firefly algorithm in minimizing the error between the car's displacements and the disturbances of the road is particularly noteworthy. This achievement ensures a more precise and accurate tracking of the desired trajectory, regardless of the input signal used, whether it be an impulse, sine wave, or step-wise graded signal.

A Backstepping Control Strategy for Power System Stability Enhancement

Secure power system operation relies extensively on the analysis of transient stability and control. The dynamics involved in power system control are often complex and nonlinear. Most of the currently existing works approach these frequent problems with nonlinear control techniques, leading to a requirement for specific controller parameter adjustments. In these veins, this paper proposes a new method for stabilizing electric power systems, using nonlinear backstepping control by optimizing the controller’s parameters. The Jaya algorithm and Genetic algorithm are utilized as a powerful meta-heuristic optimization technique to search parameters of an optimal controller. Improvement in system damping, transient stability, and voltage regulation has been achieved by minimizing the integral time absolute error (ITAE) as the objective function. Numerical simulations on an SMIB power system under different fault conditions showed that the proposed method outperforms classical power system stabilizer (PSS) methods, reducing overshoots and settling times and eliminating steady-state errors. These findings highlight the effectiveness of the proposed approach and its potential contribution to the development of advanced nonlinear control techniques for electric power systems. The suggested optimization methods demonstrate superior performance, compared to classical methods, and achieve a reduction of 27.5% in overshoot and 87% in transient time in addition to complete elimination of static error.

Feature Selection Using Golden Jackal Optimization for Software Fault Prediction

A program’s bug, fault, or mistake that results in unintended results is known as a software defect or fault. Software flaws are programming errors due to mistakes in the requirements, architecture, or source code. Finding and fixing bugs as soon as they arise is a crucial goal of software development that can be achieved in various ways. So, selecting a handful of optimal subsets of features from any dataset is a prime approach. Indirectly, the classification performance can be improved through the selection of features. A novel approach to feature selection (FS) has been developed, which incorporates the Golden Jackal Optimization (GJO) algorithm, a meta-heuristic optimization technique that draws on the hunting tactics of golden jackals. Combining this algorithm with four classifiers, namely K-Nearest Neighbor, Decision Tree, Quadrative Discriminant Analysis, and Naive Bayes, will aid in selecting a subset of relevant features from software fault prediction datasets. To evaluate the accuracy of this algorithm, we will compare its performance with other feature selection methods such as FSDE (Differential Evolution), FSPSO (Particle Swarm Optimization), FSGA (Genetic Algorithm), and FSACO (Ant Colony Optimization). The result that we got from FSGJO is great for almost all the cases. For many of the results, FSGJO has given higher classification accuracy. By utilizing the Friedman and Holm tests, to determine statistical significance, the suggested strategy has been verified and found to be superior to prior methods in selecting an optimal set of attributes.

A novel integrated approach of RUNge Kutta optimizer and ANN for estimating compressive strength of self-compacting concrete

In this study machine learning models are used that forecast the compressive strength of self-compacting concrete (SCC) depending on percentage replacement of cement by supplementary cementitious material. In order to predict the mechanical property of SCC, a hybrid artificial neural network (ANN) along with metaheuristic optimization techniques and two traditional models were employed which comprised of 300 datasets. Several input factors are employed in the modelling process, including cement, the water-binder ratio, coarse aggregate, fine aggregate, fly ash (FA) and the superplasticizer. ANN hybridised with RUNge Kutta optimizer (RUN) was chosen as one of the top predictive models based on coefficient of determination ((R2 = 0.933 (in training) and R2 = 0.9203 (in testing))) findings and model validation. According to the rank analysis, the ANN-RUN surpassed other models with a score of 128. Permutation feature importance, statistical analysis, and comparisons amongst regression models are used to determine the models' efficacy. The best input parameters were selected based on person correlation and density plot. Also, the use of Taylor diagrams and accuracy matrices was also examined for the visual comprehension of the data which has shown similar results as discussed above. The results show that the suggested machine learning models attained consistent accuracy and can be used as a robust technique to predict the compressive strength of SCC.

Optimal Design and Mathematical Modeling of Hybrid Solar PV–Biogas Generator with Energy Storage Power Generation System in Multi-Objective Function Cases

This study demonstrates how to use grid-connected hybrid PV and biogas energy with a SMES-PHES storage system in a nation with frequent grid outages. The primary goal of this work is to enhance the HRES’s capacity to favorably influence the HRES’s economic viability, reliability, and environmental impact. The net present cost (NPC), greenhouse gas (GHG) emissions, and the likelihood of a power outage are among the variables that are examined. A mixed solution involves using a variety of methodologies to compromise aspects of the economy, reliability, and the environment. Metaheuristic optimization techniques such as non-dominated sorting whale optimization algorithm (NSWOA), multi-objective grey wolf optimization (MOGWO), and multi-objective particle swarm optimization (MOPSO) are used to find the best size for hybrid systems based on evaluation parameters for financial stability, reliability, and GHG emissions and have been evaluated using MATLAB. A thorough comparison between NSWOA, MOGWO, and MOPSO and the system parameters at 150 iterations has been presented. The outcomes demonstrated NSWOA’s superiority in achieving the best optimum value of the predefined multi-objective function, with MOGWO and MOPSO coming in second and third, respectively. The comparison study has focused on NSWOA’s ability to produce the best NPC, LPSP, and GHG emissions values, which are EUR 6.997 × 106, 0.0085, and 7.3679 × 106 Kg reduced, respectively. Additionally, the simulation results demonstrated that the NSWOA technique outperforms other optimization techniques in its ability to solve the optimization problem. Furthermore, the outcomes show that the designed system has acceptable NPC, LPSP, and GHG emissions values under various operating conditions.

GW optimization based MPPT for solar photovoltaic system

The most efficient and cleanest form of renewable energy source for effective power generation is the solar photovoltaic (PV) system. In recent years, solar energy generation has become an essential part of electric power applications. The power produced by the solar PV system is unstable, as it depends upon illumination and global climatic change. So as to get the uttermost efficacy the solar PV system must be guided at the maximum point. An efficient MPP tracking method has a vital function to play in upgrading the efficacy of a solar PV system. The operational point of the perturb and observe (P&O) approach swings about MPP at a steady state, resulting in power output variations. In this work, the Grey Wolf (GW) optimization-based MPPT is proposed. The GW is a Metaheuristic optimization technique that extracts the highest amount of energy from a solar PV system. The PV module’s voltage and current are utilized as inputs and the duty ratio is the indeed output that has been obtained and it is been tested under different operating conditions. Depending on the fluctuations in input power, a DC/DC boost converter is utilized to increase the wattage of the output. To estimate the usefulness of this MPPT, the outcomes of GW are correlated with the P&O approach and outcomes demonstrate the GW MPPT gives better power output and its convergence time is faster than the P&O method for change in irradiation levels.