Investigating dam reservoir operation optimization using metaheuristic algorithms

Abstract. The optimization of aerospace propulsion systems plays a pivotal role in enhancing performance and efficiency. This paper presents a comprehensive analysis of a 2D bypass dual throat nozzle, with a primary focus on optimizing two critical design parameters: expansion ratio and bypass width, to maximize the mass flow rate and facilitate thrust vectoring capabilities. An improved Harris Hawks Optimization (HHO) algorithm was leveraged in this research to achieve an optimal configuration for the nozzle. Furthermore, the complex relationship between design parameters and mass flow rate is approximated using a Radial Basis Function (RBF) surrogate model, allowing for effective optimization. Through extensive simulations and analyses, the effectiveness of the proposed methodology is demonstrated, showcasing significant improvements in nozzle performance compared to conventional approaches. Furthermore, the optimized configuration obtained through the HHO algorithm is systematically compared with other metaheuristic optimization algorithms, highlighting its superiority in achieving optimal solutions for thrust vectoring applications. This study advances aerospace propulsion technology by providing valuable insights into the optimization of bypass dual throat nozzles, thereby paving the way for enhanced performance and maneuverability in aerospace systems.

Whale Optimization Algorithm (WOA) proposed by Seyedali Mirjalili and Andrew Lewis in 2016 is popular and powerful metaheuristic algorithm to search the global solution of optimization problems. WOA is nature-inspired, metaheuristic (randomization and deterministic) algorithm, which has been widely used to solve various single objective, multi objective and multidimensional optimization problems. WOA and its variant have been introduced in engineering applications, bioinformatics, multi-level image segmentation, clustering applications, design of low pass filter, Email classification, Diabetes classification, heterogeneous networks, machine learning etc. WOA is gradient free, easy to represent, capable to explore, exploit the search space and able to avoid local optima. This paper presents overview of WOA, its variants and applications. The performance of WOA is enhanced by introducing hybridization of other methods with WOA such as WOA-PSO, WOA-Levy, WOA-BAT, WOA-ANN, WOA-SVM etc. Objective of metaheuristic algorithm is tofind best position or leader position X* which is near to optimal solution for target prey over successive iteration. Objective function could be based on minimization or maximization approach.

In the distribution system, proper placement of distributed generation (DG) is still a very challenging issue for getting their maximum potential benefits. Power system stability should be determined through load modeling, hybrid energy storage system (HESS), and photovoltaics (PV) modeling. This paper proposed the optimal sizing and location of photovoltaic using the Modified Harris Hawk Optimization (MHHO) algorithm. The energy generated from the photovoltaic (PV) is stored in the HESS, where the energy’s charging and discharging from the storage unit is framed with a reduced power loss (active and reactive power). The optimal sizing and placement of the PV system will provide better voltage stability. The Modified Harris Hawk Optimization Algorithm (MHHO) frames the system’s voltage stability. The Newton-Raphson load flow method is used to analyze the loading in the power system. The IEEE 33 and 69 bus systems are used to analyze the load flow to the consumers, thus analyzing the power system’s dynamic performance. The performance and voltage stability of the presented model are compared with the existing optimization techniques, which include the Firefly Algorithm (FA), Crow Search Optimization (CSO), Particle Swarm Optimization (PSO), Analytical PSO (APSO), Improved Cayote Optimization Algorithm (COA) and Whale optimization algorithm (WOA) through the MATLAB/Simulink platform.

The dynamic voltage restorer's (DVR) transient, steady-state, and dynamic responses are essential requirements for protecting sensitive loads against upstream voltage disturbances via the DVR's ride-through capabilities. DVRs also look after transient oscillation at the instant of entering, and /or exiting by the DVR. This paper presents an enhanced, optimized, and less complex DVR control system structure, which is capable of improving the transient, steady-state, and dynamic responses as well as eliminating inherent transient oscillations. The control system comprises a closed-loop feedback control signal and feedforward upstream disturbance detection signal. Incorporating the feedforward term helps, dramatically, in improving the system response and eliminating the transient oscillations in the load voltage. The error signals are adapted using a PI controller to make the load voltage faithfully track its predefined reference waveform. The controller is implemented in the dq synchronous rotating reference frame. The parameters of the PI controller are selected using modern population-based optimization called the Harris Hawks Optimization (HHO) technique. The results obtained using the HHO technique are compared with two other optimization algorithms, namely Particle Swarm Optimization (PSO) and Whale Optimization Algorithm (WOA). The results show that the HHO gives the best system response. The system is simulated using MATLAB/Simulink and the validation via Typhoon HIL402 real-time emulator. Both HIL402 validation and simulation results show that the proposed control scheme recovers normal operation against voltage disturbance within approximately 1.2 milliseconds without overshoot with steady-state error near zero and significantly dampens the inherent voltage oscillation that occurs at the instant of DVR entrance and/or exit.

Feature selection can be defined as one of the pre-processing steps that decreases the dimensionality of a dataset by identifying the most significant attributes while also boosting the accuracy of classification. For solving feature selection problems, this study presents a hybrid binary version of Harris Hawks Optimization algorithm (HHO) and Salp Swarm Optimization (SSA) (HHOSSA). The HHOSSA was tested against two well-known optimization algorithms, the Whale Optimization Algorithm (WOA) and the grey wolf optimizer (GWO), utilizing 280 2D X-ray images from the Posteroanterior (PA) chest view dataset for normal and covid-19 patients. A total of three performance metrics (Recall, Precision, F1) were employed in the studies with Support vector machines (SVMs), k-Nearest Neighbor (KNN), and XGBoost as classifiers. The suggested algorithm outperforms SVM by 96%, and two classifiers, XGboost and KNN, by 98%.

Intrusion Detection and Prevention Systems (IDPSs) play a crucial role in safeguarding online connections against unauthorized access and malicious activities. To enable efficient and effective detection and mitigation, IDPSs must continuously improve their performance due to the constantly developing nature of cyber threats. However, an IDPS is more difficult to use and less reliable when it deals with huge amounts of data. This study aimed to improve the performance of IDPSs by employing optimization algorithms to reduce the data size. Particularly, the Harris Hawks Optimization (HHO) and Whale Optimization Algorithm (WOA) were combined for feature selection. The experimental results showed that the performance of the proposed IDPS was greatly improved by combining the HHO and WOA algorithms. Combining a Random Forest classifier with the suggested HHO/WOA feature selection method achieved very high results in accuracy (99.17%), recall (98.76%), precision (98.76%), and F1-score (98.43%).

<span lang="EN-US">One of the primary concerns of governments, corporations, and even individual users is their level of online protection. This is because a large number of attacks target their primary assets. A firewall is a critical tool that almost every organization uses to protect its assets. However, firewalls become less reliable when they deal with large amounts of data. One method for reducing the amount of data and enhancing firewall performance is feature selection. The main aim of this study is to enhance the firewall's performance by proposing a new feature selection method. The proposed feature selection method combines the strengths of Harris Hawks optimization (HHO) and whale optimization algorithm (WOA). Experiments were performed utilizing the NSL-KDD dataset to measure the effectiveness of the proposed method. The experiments employed the decision trees (DTs) as a machine classifier. The experimental results show that the achieved accuracy is 98.46% when using HHO/WOA for feature selection and DT for classification, outperforming the HHO and WOA when used separately for feature selection. The study's findings offer insightful information for researchers and practitioners looking to improve firewall effectiveness and efficiency in defending internet connections against changing threats.</span>

With the wide application of mobile robots, mobile robot path planning (MRPP) has attracted the attention of scholars, and many metaheuristic algorithms have been used to solve MRPP. Swarm-based algorithms are suitable for solving MRPP due to their population-based computational approach. Hence, this paper utilizes the Whale Optimization Algorithm (WOA) to address the problem, aiming to improve the solution accuracy. Whale optimization algorithm (WOA) is an algorithm that imitates whale foraging behavior, and the firefly algorithm (FA) is an algorithm that imitates firefly behavior. This paper proposes a hybrid firefly-whale optimization algorithm (FWOA) based on multi-population and opposite-based learning using the above algorithms. This algorithm can quickly find the optimal path in the complex mobile robot working environment and can balance exploitation and exploration. In order to verify the FWOA’s performance, 23 benchmark functions have been used to test the FWOA, and they are used to optimize the MRPP. The FWOA is compared with ten other classical metaheuristic algorithms. The results clearly highlight the remarkable performance of the Whale Optimization Algorithm (WOA) in terms of convergence speed and exploration capability, surpassing other algorithms. Consequently, when compared to the most advanced metaheuristic algorithm, FWOA proves to be a strong competitor.

There are mainly two components in almost every visual object tracking algorithm, which are the object presentation and the searching mechanism. In the literature, metaheuristic algorithms have been recently, widely used as searching method in visual tracking. In fact, the more discriminative is their combined object presentation the better is their precision. Salient background information is often inside the first detected region of the object, which may decrease considerably the tracking performance. In this work, we combine a powerful metaheuristic searching method, whale optimization algorithm (WOA), with the discriminative presentation named as corrected background weighted histogram (CBWH) to improve the tracking accuracy in difficult environments. WOA algorithm is used because of its strong searching ability, which enable it avoid being trapped in local optimum, and also its lowest computation cost compared to other metaheuristic algorithms. The WOA sensitivity parameters are studied experimentally to be adjusted in visual tracking. For a fair assessment of the proposed approach, its performance has been evaluated on 20 video sequences, from the famous object tracking benchmark OTB15, and compared with six (6) other state-of-art trackers. The evaluations were carried quantitatively and qualitatively on challenging situations and have provided satisfying results. The experimental results shows that WOA combined with CBWH can lead to further improvement, and better success rate in tracking.

Sensor technology advancements have provided a viable solution to fight COVID and to develop healthcare systems based on Internet of Things (IoTs). In this study, image processing and Artificial Intelligence (AI) are used to improve the IoT framework. Computed Tomography (CT) image‐based forecasting of COVID disease is among the important activities in medicine for measuring the severity of variability in the human body. In COVID CT images, the optimal gamma correction value was optimised using the Whale Optimisation Algorithm (WOA). During the search for the optimal solution, WOA was found to be a highly efficient algorithm, which has the characteristics of high precision and fast convergence. Whale Optimisation Algorithm is used to find best gamma correction value to present detailed information about a lung CT image, Also, in this study, analysis of important AI techniques has been done, such as Support Vector Machine (SVM) and Deep‐Learning (Deep‐Learning (DL)) for COVID disease forecasting in terms of amount of data training and computational power. Many experiments have been implemented to investigate the optimisation: SVM and DL with WOA and without WOA are compared by using confusion matrix parameters. From the results, we find that the DL model outperforms the SVM with WOA and without WOA.

Bearing is one of the most fundamental components of rotary machinery, and its fatigue life is a crucial factor in designing. The design optimization of tapered roller bearing (TRB) is a complex design problem because various arrays of designing parameters and functional requirements should be fulfilled. Since there are many design variables and nonlinear constraints, presenting an optimal design of TRBs poses some challenges for metaheuristic algorithms. The Harris hawks optimization (HHO) algorithm is a robust nature-inspired method with unique exploitation and exploration phases due to its time-varying structure. However, this metaheuristic algorithm may still converge to local optima for more challenging problems such as the design of TRBs. Therefore, this study aims to improve the accuracy and efficiency of the shortcomings of this algorithm. The performance of the proposed algorithm is first evaluated for the TRB optimization problem. The TRB optimization design has nine design variables and 26 constraints because of geometrical dimensions and strength conditions. The productivity of the proposed method is compared with diverse metaheuristic algorithms in the literature. The results demonstrate the significant development of dynamic load capacity in comparison to the standard value. Furthermore, the enhanced version of the HHO algorithm presented in this study is benchmarked with various well-known engineering problems. For supplementary materials regarding algorithms in this research, readers can refer to https://aliasgharheidari.com.

Whale Optimization Algorithm (WOA) and Grey Wolf Optimizer (GWO) are well-perform metaheuristic algorithms used by various researchers in solving feature selection problems. Yet, the slow convergence speed issue in Whale Optimization Algorithm and Grey Wolf Optimizer could demote the performance of feature selection and classification accuracy. Therefore, to overcome this issue, a modified WOA (mWOA) and modified GWO (mGWO) for wrapper-based feature selection were proposed in this study. The proposed mWOA and mGWO were given a new inversed control parameter which was expected to enable more search area for the search agents in the early phase of the algorithms and resulted in a faster convergence speed. The objective of this comparative study is to investigate and compare the effectiveness of the inversed control parameter in the proposed methods against the original algorithms in terms of the number of selected features and the classification accuracy. The proposed methods were implemented in MATLAB where 12 datasets with different dimensionality from the UCI repository were used. kNN was chosen as the classifier to evaluate the classification accuracy of the selected features. Based on the experimental results, mGWO did not show significant improvements in feature reduction and maintained similar accuracy as the original GWO. On the contrary, mWOA outperformed the original WOA in terms of the two criteria mentioned even on high-dimensional datasets. Evaluating the execution time of the proposed methods, utilizing different classifiers, and hybridizing proposed methods with other metaheuristic algorithms to solve feature selection problems would be future works worth exploring.

Whale optimization algorithm (WOA) is one of the popular swarm-based algorithms (SA), inspired by nature. The WOA was determined by mimicking the pattern of navigation of whales while encircling preys. The humpback whale is considered in this context. These set of whales can recognize and surround the location of the prey strategically. Identifying the exact position in the a priori search space in whale is usually not imaginable. It is assumed by the WOA that the target prey is the best candidate solution. This model was implemented in MATLAB by considering 30 search agents (n = 30) and the maximum number of iterations was set to 1000. The best solution obtained by WOA is [3.0015 1.9969] and the best optimal value of the objective function found by WOA is 0.00015167. The parameter space and the objective space presented, demonstrate the problem solving capability of WOA in complex domain.

The 0/1 Knapsack problem is one of the most popular real-world optimization problems that arise in searching space and finding the most optimum solution. Theoretically, the optimum solution problem of the 0/1 Knapsack requires suitable technique to explore the search space effectively. Practically, as many metaheuristic algorithms, Whale Optimization Algorithm (WOA) may fail in local optimum solution. This paper proposes Opposition-based Whale Optimization Algorithm (OWOA) to optimize solution problem in 0/1 Knapsack. The OWOA has been tested original WOA by using twenty cases of Knapsack problem and against other metaheuristic algorithms such as (CGMA) and HS-Jaya. The experimental results indicate a significant performance of the optimization solution and stabilization with minimal standard deviation value. This shows that the OWOA improved the original version WOA and has promising result in comparison with other existing algorithms.

The inherent variability and uncertainty of solar radiation, influenced by factors such as seasons, weather, and cloud cover, pose significant challenges in accurately forecasting energy output from solar power systems. Robust forecasting models that can capture the dynamic behavior of solar radiation are crucial for optimizing energy generation, distribution, and storage processes. This study proposes an integrated approach that combines neural networks, metaheuristic optimization algorithms, and principal component analysis (PCA) for precise solar radiation forecasting. The methodology uses one year of solar radiation data from November 2022 to October 2023 from Vellore district, India. PCA is employed for dimensionality reduction, mitigating the curse of dimensionality. The reduced dataset is segregated into winter, summer, and monsoon subsets to capture distinct seasonal patterns. Neural networks are trained on these seasonal datasets, with their weights optimized by metaheuristic algorithms, including particle swarm optimization (PSO), gray wolf optimization (GWO), whale optimization algorithm (WOA), and coati optimization algorithm (COA). A comprehensive comparative study evaluated the performance of ANN-PSO, ANFIS-GWO, ANN-WOA, ANN-COA, and traditional ANN models. The ANN-COA model, integrating ANN with COA for weight optimization and PCA for dimensionality reduction, achieved the most accurate forecasts, outperforming other approaches. It attained optimal RMSE of 12.06 for winter, 6.72 for summer, and 9.49 for monsoon season, MAE of 6.66, 5.50, and 6.25, MAPE of 3.58 %, 1.68 %, and 2.31 %, and R2 of 0.973, 0.982, and 0.985 for winter, summer, and monsoon seasons respectively, demonstrating its robustness and suitability for time-series solar radiation forecasting.