Search Results (51)

Solar energy is a promising and sustainable green energy source, showing significant advancements in photovoltaic (PV) system deployment. To maximize PV efficiency, robust maximum power point tracking (MPPT) methods are essential, as the maximum power point (MPP) shifts with changing irradiance and temperature. This paper proposes a novel MPPT control strategy for a 100 kW grid-connected PV system, based on the incremental conductance (IC) method and enhanced by a cascaded Fractional Order Proportional–Integral (FOPI) and conventional Proportional–Integral (PI) controller. The controller parameters are optimally tuned using the recently introduced RUNge Kutta optimizer (RUN). MATLAB/Simulink simulations have been conducted on the 100 kW benchmark PV model integrated into a medium-voltage grid, with the objective of minimizing the integral square error (ISE) to improve efficiency. The performance of the proposed IC-MPPT-(FOPI-PI) controller has been benchmarked against standalone PI and FOPI controllers, and the RUN optimizer is here compared with recent metaheuristic algorithms, including the Gorilla Troops Optimizer (GTO) and the African Vultures Optimizer (AVO). The evaluation covers five different environmental scenarios, including step, ramp, and realistic irradiance and temperature profiles. The RUN-optimized controller achieved exceptional performance with 99.984% tracking efficiency, sub-millisecond rise time (0.0012 s), rapid settling (0.015 s), and minimal error (ISE: 16.781), demonstrating outstanding accuracy, speed, and robustness. Full article

To address the issue of rolling bearing fault diagnosis, this paper proposes a novel model combining the Improved Gorilla Troop Optimization (IGTO) algorithm, Variational Mode Decomposition (VMD), Permutation Entropy (PE), and Long Short-Term Memory (LSTM) networks. The IGTO algorithm is used to optimize the parameters of VMD and LSTM, enhancing signal decomposition and feature extraction. The proposed model achieves fault classification accuracies of 96.67% and 98.96% in the testing and training phases, respectively, on the Case Western Reserve University dataset, with minimal accuracy fluctuations. Furthermore, on the Jiangnan University dataset, the model reaches an average testing accuracy of 98.85%, with the highest accuracy reaching 99.48%. The results also demonstrate high stability, as indicated by low standard deviations (1.2148 and 1.3217) and narrow 95% confidence intervals ([95.75%, 97.58%] and [96.73%, 97.49%]). Despite a longer average runtime of 13.88 s per sample, the model’s superior accuracy justifies the computational cost. These results demonstrate the model’s excellent diagnostic performance, adaptability to different datasets, and practical applicability for rolling bearing fault diagnosis. This approach provides a valuable reference for predictive maintenance and fault detection systems in industrial applications. Full article

The Artificial Gorilla Troops Optimizer (GTO) has emerged as an efficient metaheuristic technique for solving complex optimization problems. However, the conventional GTO algorithm has a critical limitation: all individuals, regardless of their roles, utilize identical search equations and perform exploration and exploitation sequentially. This uniform approach neglects the potential benefits of labor division, consequently restricting the algorithm’s performance. To address this limitation, we propose an enhanced Labor Division Gorilla Troops Optimizer (LDGTO), which incorporates natural mechanisms of labor division and outcome allocation. In the labor division phase, a stimulus-response model is designed to differentiate exploration and exploitation tasks, enabling gorilla individuals to adaptively adjust their search equations based on environmental changes. In the outcome allocation phase, three behavioral development modes—self-enhancement, competence maintenance, and elimination—are implemented, corresponding to three developmental stages: elite, average, and underperforming individuals. The performance of LDGTO is rigorously evaluated through three benchmark test suites, comprising 12 unimodal, 25 multimodal, and 10 combinatorial functions, as well as two real-world engineering applications, including four-bar transplanter mechanism design and color image segmentation. Experimental results demonstrate that LDGTO consistently outperforms three variants of GTO and seven state-of-the-art metaheuristic algorithms in most test cases. Full article

Finite control set model predictive control (FCS-MPC) is an attractive control method for electric drives. This is primarily due to the ease of implementation and robust responses. When applied to rotor current control of the Doubly Fed Induction Generator (DFIG), FCS-MPC has thus far exhibited promising results when compared to the conventional Proportional Integral control strategy. Recently, there has been research conducted regarding the reduction in switching frequency of FCS-MPC. Preliminary studies indicate that a reduction in switching frequency will result in larger current ripples and a greater total harmonic distortion (THD). However, research in this area is limited. The aim of this study is two-fold. Firstly, an indication into the effect of weighting factor magnitude on current ripple is provided. Thereafter, the research work provides insight into the effect of such weighting factor on the overall current ripple of FCS-MPC applied to the DFIG and attempts to determine an optimal weighting factor which will simultaneously reduce the switching frequency and keep the current ripple within acceptable limits. To tune the relevant weighting factor, the utilization of swam intelligence is deployed. Three swarm intelligence techniques, particle swarm optimization, the African Vulture Optimization Algorithm, and the Gorilla Troops Optimizer (GTO), are applied to achieve the optimal weighting factor. When applied to a 2 MW DFIG, the results indicated that owing to their strong exploitation capability, these algorithms were able to successfully reduce the switching frequency. The GTO exhibited the overall best results, boasting steady-state errors of 0.03% and 0.02% for the rotor direct and quadrature currents whilst reducing the switching frequency by up to 0.7%. However, as expected, there was a minor increase in the current ripple. A robustness test indicated that the use of metaheuristics still produces superior results in the face of changing operating conditions. The results instill confidence in FCS-MPC as the control strategy of choice, as wind energy conversion systems continue to penetrate the energy sector. Full article

This study utilized a multi-stage constant current (MSCC) charge protocol to identify the optimal current pattern (OCP) for effectively charging lithium-ion batteries (LiBs) using a Dandelion optimizer (DO). A Thevenin equivalent circuit model (ECM) was implemented to simulate an actual LiB with the ECM parameters estimated from the offline time response data obtained through a hybrid pulse power characterization (HPPC) test. For the first time, DO was applied to metaheuristic optimization algorithms (MOAs) to determine the OCP within the MSCC protocol. A composite objective function that incorporates both charging time and charging temperature was constructed to facilitate the use of DO in obtaining the OCP. To verify the performance of the proposed method, various algorithms, including the constant current-constant voltage (CC-CV) technique, formula method (FM), particle swarm optimization (PSO), war strategy optimization (WSO), jellyfish search algorithm (JSA), grey wolf optimization (GWO), beluga whale optimization (BWO), levy flight distribution algorithm (LFDA), and African gorilla troops optimizer (AGTO), were introduced. Based on the OCP extracted from the simulations using these MOAs for the specified ECM model, a charging experiment was conducted on the Panasonic NCR18650PF LiB to evaluate the charging performance in terms of charging time, temperature, and efficiency. The results demonstrate that the proposed DO technique offers superior charging performance compared to other charging methods. Full article

Nowadays, standalone microgrids that make use of renewable energy sources have gained great interest. They provide a viable solution for rural electrification and decrease the burden on the utility grid. However, because standalone microgrids are nonlinear and time-varying, controlling and managing their energy can be difficult. A fractional-order proportional integral (FOPI) controller was proposed in this study to enhance a standalone microgrid’s energy management and performance. An ultra-capacitor (UC) and a battery, called a hybrid energy storage scheme, were employed as the microgrid’s energy storage system. The microgrid was primarily powered by solar and wind power. To achieve optimal performance, the FOPI’s parameters were ideally generated using the gorilla troop optimization (GTO) technique. The FOPI controller’s performance was contrasted with a conventional PI controller in terms of variations in load power, wind speed, and solar insolation. The microgrid was modeled and simulated using MATLAB/Simulink software R2023a 23.1. The results indicate that, in comparison to the traditional PI controller, the proposed FOPI controller significantly improved the microgrid’s transient performance. The load voltage and frequency were maintained constant against the least amount of disturbance despite variations in wind speed, photovoltaic intensity, and load power. In contrast, the storage battery precisely stores and releases energy to counteract variations in wind and photovoltaic power. The outcomes validate that in the presence of the UC, the microgrid performance is improved. However, the improvement is very close to that gained when using the proposed controller without UC. Hence, the proposed controller can reduce the cost, weight, and space of the system. Moreover, a Hardware-in-the-Loop (HIL) emulator was implemented using a C2000™ microcontroller LaunchPad™ TMS320F28379D kit (Texas Instruments, Dallas, TX, USA) to evaluate the proposed system and validate the simulation results. Full article

To address the issue of intelligent optimization algorithms being prone to local optima, resulting in insufficient feature extraction and low fault-type recognition rates when optimizing Variational Mode Decomposition and Support Vector Machine parameters, this paper proposes a fault diagnosis method based on an improved Artificial Gorilla Troops Optimization algorithm. The Artificial Gorilla Troops Optimization algorithm was enhanced using Logistic chaotic mapping, a linear decreasing weight factor, the global exploration strategy of the Osprey Optimization Algorithm, and the Levy flight strategy, improving its ability to escape local optima, adaptability, and convergence accuracy. This algorithm was used to optimize the parameters of Variational Mode Decomposition and Support Vector Machine for fault diagnosis. Experiments on fault diagnosis with two datasets of different sample sizes showed that the proposed method achieved a diagnostic accuracy of no less than 98% for samples of varying sizes, with stable and reliable results. Full article

Recently, Alzheimer’s disease (AD) is one of the common neurodegenerative disorders, which primarily occurs in old age. Structural magnetic resonance imaging (sMRI) is an effective imaging technique used in clinical practice for determining the period of AD patients. An efficient deep learning framework is proposed in this paper for AD detection, which is inspired from clinical practice. The proposed deep learning framework significantly enhances the performance of AD classification by requiring less processing time. Initially, in the proposed framework, the sMRI images are acquired from a real-time dataset and two online datasets including Australian Imaging, Biomarker and Lifestyle flagship work of ageing (AIBL), and Alzheimer’s Disease Neuroimaging Initiative (ADNI). Next, a fuzzy-based superpixel-clustering algorithm is introduced to segment the region of interest (RoI) in sMRI images. Then, the informative deep features are extracted in segmented RoI images by integrating the probabilistic local ternary pattern (PLTP), ResNet-50, and Visual Geometry Group (VGG)-16. Furthermore, the dimensionality reduction is accomplished by through the modified gorilla troops optimizer (MGTO). This process not only enhances the classification performance but also diminishes the processing time of the capsule network (CapsNet), which is employed to classify the classes of AD. In the MGTO algorithm, a quasi-reflection-based learning (QRBL) process is introduced for generating silverback’s quasi-refraction position for further improving the optimal position’s quality. The proposed fuzzy based superpixel-clustering algorithm and MGTO-CapsNet model obtained a pixel accuracy of 0.96, 0.94, and 0.98 and a classification accuracy of 99.88%, 96.38%, and 99.94% on the ADNI, real-time, and AIBL datasets, respectively. Full article

Wireless sensor networks have gained significant attention in recent years due to their wide range of applications in environmental monitoring, surveillance, and other fields. The design of a groundwater quality and quantity monitoring network is an important aspect in aquifer restoration and the prevention of groundwater pollution and overexploitation. Moreover, the development of a novel localization strategy project in wireless sensor groundwater networks aims to address the challenge of optimizing sensor location in relation to the monitoring process so as to extract the maximum quantity of information with the minimum cost. In this study, the improved hybrid butterfly artificial gorilla troop optimizer (iHBAGTO) technique is applied to optimize nodes’ position and the analysis of the path loss delay, and the RSS is calculated. The hybrid of Butterfly Artificial Intelligence and an artificial gorilla troop optimizer is used in the multi-functional derivation and the convergence rate to produce the designed data localization. The proposed iHBAGTO algorithm demonstrated the highest convergence rate of 99.6%, and it achieved the lowest average error of 4.8; it consistently had the lowest delay of 13.3 ms for all iteration counts, and it has the highest path loss values of 8.2 dB, with the lowest energy consumption value of 0.01 J, and has the highest received signal strength value of 86% for all iteration counts. Overall, the Proposed iHBAGTO algorithm outperforms other algorithms. Full article

Renewable energy (RE) resources such as wind and PV solar power are crucial for transitioning to carbon-free and sustainable energy systems, especially for agricultural and domestic applications in the desert and rural areas. However, implementing RE resources may lead to frequency penetrations, especially in isolated microgrids (µGs). This study proposes an adaptive load frequency control (LFC) technique for power systems. An integral controller can be tuned online using an artificial gorilla troops optimization algorithm (GTO), which is supported using a balloon effect (BE) identifier. Adaptive control is used to control the system frequency in case of variable loads and fluctuation due to 6 MW photovoltaic (PV). Three other optimization methods have been compared with the GTO + BE technique, namely the Grey Wolf Optimization method (GWO), the standard artificial gorilla troops optimization (GTO) and the Jaya technique. Digital simulation tests approved the efficiency of (GTO + BE) during system difficulties such as load disturbance and system parameter variations. In addition, the same test conditions have been repeated using a real-time simulation platform. The real-time simulation results supported the digital outcomes. Full article

The development of wave energy converter (WEC) arrays is an effective way to reduce the cost of levelized energy and facilitate the commercialization of WECs. This study proposes a hydraulic power take-off (PTO) system for an array of point absorber wave energy converters (PA-WECs) and designs a control system using a novel algorithm called the improved simplified universal intelligent PID (ISUIPID) controller and the adaptive matching controller including an improved artificial gorilla troops optimizer (IGTO) to improve and stabilize the output power of PA-WEC arrays. Simulations under varying irregular wave states have been carried out to verify the validity of the mathematical model and the control system. The results show that the designed IGTO has faster convergence speed and better convergence accuracy in solving the optimal linear damping coefficient of the generator, and the proposed ISUIPID controller provides superior performance in tracking the speed of the hydraulic motor under the changing sea states. In addition, the capture power and output power of the array of PA-WECs are improved and the electrical energy can be output stably under the designed control system. The array of PA-WECs with the proposed control system will become an independent, stable, efficient, and sustainable power supply system. Full article

One of the most prevalent cancers is oral squamous cell carcinoma, and preventing mortality from this disease primarily depends on early detection. Clinicians will greatly benefit from automated diagnostic techniques that analyze a patient’s histopathology images to identify abnormal oral lesions. A deep learning framework was designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely, normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed swarm intelligence technique called the Modified Gorilla Troops Optimizer. While there are many optimization algorithms used in the literature for feature selection, weight updating, and optimal parameter identification in deep learning models, this work focuses on using optimization algorithms as an intermediate layer to convert extracted features into features that are better suited for classification. Three datasets comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures, namely, InceptionV2, MobileNetV3, and EfficientNetB3, are investigated as feature extraction layers. Two fully connected Neural Network layers, batch normalization, and dropout are used as classification layers. With the best accuracy of 0.89 among the examined feature extraction models, MobileNetV3 exhibits good performance. This accuracy is increased to 0.95 when the suggested Modified Gorilla Troops Optimizer is used as an intermediary layer. Full article

In the domain of network security, intrusion detection systems (IDSs) play a vital role in data security. While the utilization of the internet amongst consumers is increasing on a daily basis, the significance of security and privacy preservation of system alerts, due to malicious actions, is also increasing. IDS is a widely executed system that protects computer networks from attacks. For the identification of unknown attacks and anomalies, several Machine Learning (ML) approaches such as Neural Networks (NNs) are explored. However, in real-world applications, the classification performances of these approaches are fluctuant with distinct databases. The major reason for this drawback is the presence of some ineffective or redundant features. So, the current study proposes the Network Intrusion Detection System using a Lion Optimization Feature Selection with a Deep Learning (NIDS-LOFSDL) approach to remedy the aforementioned issue. The NIDS-LOFSDL technique follows the concept of FS with a hyperparameter-tuned DL model for the recognition of intrusions. For the purpose of FS, the NIDS-LOFSDL method uses the LOFS technique, which helps in improving the classification results. Furthermore, the attention-based bi-directional long short-term memory (ABiLSTM) system is applied for intrusion detection. In order to enhance the intrusion detection performance of the ABiLSTM algorithm, the gorilla troops optimizer (GTO) is deployed so as to perform hyperparameter tuning. Since trial-and-error manual hyperparameter tuning is a tedious process, the GTO-based hyperparameter tuning process is performed, which demonstrates the novelty of the work. In order to validate the enhanced solution of the NIDS-LOFSDL system in terms of intrusion detection, a comprehensive range of experiments was performed. The simulation values confirm the promising results of the NIDS-LOFSDL system compared to existing DL methodologies, with a maximum accuracy of 96.88% and 96.92% on UNSW-NB15 and AWID datasets, respectively. Full article

In a smart grid (SG) system with load uncertainties and the integration of variable solar and wind energies, an effective frequency control strategy is necessary for generation and load balancing. Cyberattacks are emerging threats, and SG systems are typical cyber-attack targets. This work suggests an improved gorilla troops optimizer (iGTO)-based fuzzy PD-(1+PI) (FPD-(1+PI)) structure for the frequency control of an SG system. The SG contains a diesel engine generator (DEG), renewable sources like wind turbine generators(WTGs), solar photovoltaic (PV), and storage elements such as flywheel energy storage systems (FESSs) and battery energy storage systems (BESSs) in conjunction with electric vehicles (EVs). Initially, the dominance of the projected iGTO over the gorilla troops optimizer (GTO) and some recently suggested optimization algorithms are demonstrated by considering benchmark test functions. In the next step, a traditional PID controller is used, and the efficacy of the GTO method is compared with that of the GTO, particle swarm optimization (PSO), and genetic algorithm (GA) methods. In the next stage, the superiority of the proposed FPD-(1+PI) structure over fuzzy PID (FPID) and PID structures is demonstrated under various symmetry operating conditions as well as under different cyberattacks, leading to a denial of service (DoS) and delay in signal transmission. Full article

The early detection of oral cancer is pivotal for improving patient survival rates. However, the high cost of manual initial screenings poses a challenge, especially in resource-limited settings. Deep learning offers an enticing solution by enabling automated and cost-effective screening. This study introduces a groundbreaking empirical framework designed to revolutionize the accurate and automatic classification of oral cancer using microscopic histopathology slide images. This innovative system capitalizes on the power of convolutional neural networks (CNNs), strengthened by the synergy of transfer learning (TL), and further fine-tuned using the novel Aquila Optimizer (AO) and Gorilla Troops Optimizer (GTO), two cutting-edge metaheuristic optimization algorithms. This integration is a novel approach, addressing bias and unpredictability issues commonly encountered in the preprocessing and optimization phases. In the experiments, the capabilities of well-established pre-trained TL models, including VGG19, VGG16, MobileNet, MobileNetV3Small, MobileNetV2, MobileNetV3Large, NASNetMobile, and DenseNet201, all initialized with ’ImageNet’ weights, were harnessed. The experimental dataset consisted of the Histopathologic Oral Cancer Detection dataset, which includes a ’normal’ class with 2494 images and an ’OSCC’ (oral squamous cell carcinoma) class with 2698 images. The results reveal a remarkable performance distinction between the AO and GTO, with the AO consistently outperforming the GTO across all models except for the Xception model. The DenseNet201 model stands out as the most accurate, achieving an astounding average accuracy rate of 99.25% with the AO and 97.27% with the GTO. This innovative framework signifies a significant leap forward in automating oral cancer detection, showcasing the tremendous potential of applying optimized deep learning models in the realm of healthcare diagnostics. The integration of the AO and GTO in our CNN-based system not only pushes the boundaries of classification accuracy but also underscores the transformative impact of metaheuristic optimization techniques in the field of medical image analysis. Full article