Gravitational Search Algorithm Research Articles

Innovative Optimal Nonstandard Tripping Protection Scheme for Radial and Meshed Microgrid Systems

The coordination of optimal overcurrent relays (OCRs) for modern power networks is nowadays one of the critical concerns due to the increase in the use of renewable energy sources. Modern grids connected to inverter-based distributed generations (IDGs) and synchronous distributed generations (SDGs) have a direct impact on fault currents and locations and then on the protection system. In this paper, a new optimal OCR coordination scheme has been developed based on the nonstandard time–current characteristics (NSTCC) approach. The proposed scheme can effectively minimize the impact of distributed generations (DGs) on OCR coordination by using two optimization techniques: genetic algorithm (GA) and hybrid gravitational search algorithm–sequential quadratic programming (GSA–SQP) algorithm. In addition, the proposed optimal OCR coordination scheme has successfully employed a new constraint reduction method for eliminating the considerable number of constraints in the coordination and tripping time formula by using only one variable dynamic coefficient. The proposed protection scheme has been applied in IEEE 9-bus and IEC MG systems as benchmark radial networks as well as IEEE 30-bus systems as meshed structures. The results of the proposed optimal OCR coordination scheme have been compared to standard and nonstandard characteristics reported in the literature. The results showed a significant improvement in terms of the protection system sensitivity and reliability by minimizing the operating time (OT) of OCRs and demonstrating the effectiveness of the proposed method throughout minimum and maximum fault modes.

A heterogeneous couplings and persuasive user/item information model for Next Basket recommendation

Next Basket Recommender Systems (NBRS) are session-based recommenders that leverage a user’s sequential behaviour and context to predict the next items they could buy during the next shop visit. This field is popular now. Current research works rely primarily on item–user relations, ignoring complicated heterogeneous couplings and persuasive item/user information, causing sparsity and cold-start, stifling NBRS performance. This research implements a Heterogeneous Coupling and Persuasive User/Item Information Model (HCPIM) comprising of heterogeneous couplings and a persuasive embedding layer (HCPEL), the consecutive basket layer, and a basket prediction layer. The HCPEL learns heterogeneous couplings (user–user, user–item, item–item) and persuasive user information for every basket to model the composite intra-basket associations across the items inside a basket given a user’s behaviour sequences. The consecutive basket layer learns inter-basket associations from the HCPEL using a Gated Recurrent Unit network. In the basket prediction layer, an improved Particle Swarm Optimization (PSO) algorithm optimizes the network’s weight and bias to iteratively learn heterogeneous couplings and persuasive information inside and across baskets to recommend the next basket. In PSO, we incorporate the exploratory Gravitation Search Algorithm to balance exploration and exploitation. Our architecture includes an Adaptive Response to Particle Adjustment Strategy to increase exploitation and prevent particles from being trapped. Extensive tests are run to evaluate HCPIM on TaFeng and the IJCAI 2015 dataset. The HCPIM improves performance by 27.87, 29.5, and 27.29 percent when density is 50, 100, and 150 on the IJCAI-15 dataset, and 8.53, 10.57, and 4.85 percent on the TaFeng dataset.

Fault Diagnosis Method of Circuit Breaker Based on CEEMDAN and PSO‐GSA‐SVM

Due to that the feature extraction of vibration signal to judge the mechanical fault process of circuit breaker affected by interference, a fault feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and support vector machine (SVM) is proposed. Several intrinsic modal function (IMF) components reflecting the mechanical state information of the circuit breaker during operation are extracted from the vibration signal through CEEMDAN. According to the correlation coefficient and energy distribution of each IMF, the first seven IMF components are denoised by wavelet packet soft threshold, and the sample entropy is calculated as the feature quantity. Finally, the improved gravitational search algorithm (GSA) based on particle swarm optimization (PSO) is used to optimize the SVM classifier to classify and identify the different operating states of the circuit breaker. The experimental results show that the entropy characteristics of CEEMDAN samples are insensitive to signal interference, and the PSO‐GSA‐SVM diagnosis method has a good effect on fault identification in the opening operation process of high voltage circuit breakers. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Fast Frequency Regulation Method for Power System With Two-Stage Photovoltaic Plants

The full utilization of solar energy is of great significance in reducing carbon emissions and alleviating environmental problems. Fast frequency regulation plays an important role in the power system with grid-connected two-stage photovoltaic (PV) plants. The presented fast frequency regulation method is composed of droop control, virtual inertia control and de-loading control. This work focuses on improving droop control and virtual inertia control for PV plants connected to grid. Due to non-Gaussian disturbance induced by solar irradiance, an adaptive control strategy is proposed by minimizing an improved performance index which combines the mean square error (MSE) and the minimum error entropy (MEE) criteria. Based on the collected frequency deviation series data, the entropy of the frequency deviation is estimated with the aid of a quantizer. The droop control coefficient and inertia gain are then solved by an improved gravitational search algorithm (IGSA). Finally, the effectiveness of the proposed strategy is testified by an illustrative power system with a two-stage grid-connected PV plant.

Study on the operating condition diagnosis method of hydropower station equipment based on fuzzy clustering analysis

The current operation status diagnosis of hydropower station equipment is mainly based on the independent analysis of the equipment, ignoring the correlation between the equipment, resulting in a large diagnostic error. In order to improve the above problems, a diagnosis method based on fuzzy clustering analysis is studied. This paper deals with association analysis and error data discrimination of equipment state data in operation collection of hydropower station, and selects operation data preliminarily. Using gravitational search algorithm for fuzzy c-means algorithm of the initial fuzzy membership degree matrix, improved fuzzy clustering algorithm is used to analyze the running status data clustering at a time. After using the encoder to extract data, secondary cluster, the abnormal data and equipment state match, the final diagnosis results are obtained. In the case verification experiment, the diagnostic accuracy rate of the method is as high as 94.83%, and the diagnostic efficiency is higher and the real-time performance is better.

Meta-Heuristics Based Inverse Kinematics of Robot Manipulator’s Path Tracking Capability Under Joint Limits

In robot-assisted manufacturing or assembly, following a predefined path became a critical aspect. In general, inverse kinematics offers the solution to control the movement of manipulator while following the trajectory. The main problem with the inverse kinematics approach is that inverse kinematics are computationally complex. For a redundant manipulator, this complexity is further increased. Instead of employing inverse kinematics, the complexity can be reduced by using a heuristic algorithm. Therefore, a heuristic-based approach can be used to solve the inverse kinematics of the robot manipulator end effector, guaranteeing that the desired paths are accurately followed. This paper compares the performance of four such heuristic-based approaches to solving the inverse kinematics problem. They are Bat Algorithm (BAT), Gravitational Search Algorithm (GSA), Particle Swarm Optimization (PSO), and Whale Optimization Algorithm (WOA). The performance of these algorithms is evaluated based on their ability to accurately follow a predefined trajectory. Extensive simulations show that BAT and GSA outperform PSO and WOA in all aspects considered in this work related to inverse kinematic problems.

Adaptation of Number of Filters in the Convolution Layer of a Convolutional Neural Network Using the Fuzzy Gravitational Search Algorithm Method and Type-1 Fuzzy Logic

This paper presents a model of the search for adaptation of parameters and the creation of the membership functions of various fuzzy systems created using the fuzzy gravitational algorithm (FGSA). These fuzzy systems were created to find the optimal number of filters to enter a convolutional neural network (CNN) with an architecture of two convolution layers, as well as two pooling layers respectively and a classification layer, which is responsible for recognizing images. With this model, the results obtained by optimizing this CNN with the FGSA algorithm and the adaptation of parameters using this same algorithm are compared to form the membership functions of fuzzy systems. Both methods and their results are comparing with each other.

Chaos embedded opposition based learning for gravitational search algorithm

Due to its robust search mechanism, Gravitational search algorithm (GSA) has achieved a lot of popularity in different research communities. However, stagnation reduces its searchability towards global optima for rigid and complex multi-modal problems. This paper proposes a GSA variant that incorporates chaos-embedded opposition-based learning into the basic GSA for the stagnation-free search. Additionally, a sine-cosine based chaotic gravitational constant is introduced to balance the trade-off between exploration and exploitation capabilities more effectively. The proposed variant is tested over 23 classical benchmark problems, 15 test problems of CEC 2015 test suite, and 15 test problems of CEC 2014 test suite. Different graphical, as well as empirical analyses, reveal the superiority of the proposed algorithm over conventional meta-heuristics and most recent GSA variants.

Optimized Takagi–Sugeno Fuzzy Mixed H2/H∞ Robust Controller Design Based on CPSOGSA Optimization Algorithm for Hydraulic Turbine Governing System

The hydraulic turbine governing system (HTGS) is a complex nonlinear system that regulates the rotational speed and power of a hydro-generator set. In this work, an incremental form of an HTGS nonlinear model was established and the Takagi–Sugeno (T-S) fuzzy linearization and mixed H2/H∞ robust control theory was applied to the design of an HTGS controller. A T-S fuzzy H2/H∞ controller for an HTGS based on modified hybrid particle swarm optimization and gravitational search algorithm integrated with chaotic maps (CPSOGSA) is proposed in this paper. The T-S fuzzy model of an HTGS that integrates multiple-state space equations was established by linearizing numerous equilibrium points. The linear matrix inequality (LMI) toolbox in MATLAB was used to solve the mixed H2/H∞ feedback coefficients using the CPSOGSA intelligent algorithm to optimize the weighting matrix in the process so that each mixed H2/H∞ feedback coefficients in the fuzzy control were optimized under the constraints to improve the performance of the controller. The simulation results show that this method allows the HTGS to perform well in suppressing system frequency deviations. In addition, the robustness of the method to system parameter variations is also verified.

Multi-objective scheduling of priority-based rescue vehicles to extinguish forest fires using a multi-objective discrete gravitational search algorithm

The implementation of emergency scheduling of priority-based rescue vehicles for extinguishing forest fires is a complex optimization problem facing with many challenges and difficulties to optimize the operational costs and to improve the efficiency to make robust decisions. The main challenges are to minimize the number of fire engines while minimizing firefighting time and firefighting delay time, simultaneously. The main difficulties to make these decisions are to consider the severity of each fire point with regards to the limited resources of vehicles. Hence, this paper motivates to develop a new multi-objective scheduling model for extinguishing the fire of forests considering rescue priority with the limited rescue resources. To make an efficient and robust solution for the proposed problem, another novelty is to propose a hybrid optimization algorithm which is a modified discrete gravitational search algorithm. To confirm the applicability of the proposed problem, an actual forest fire emergency scheduling in Heilongjiang Province, China, is simulated. The proposed hybrid optimization algorithm is tested to check the feasibility the Pareto solutions and it is compared with a set of well-known and recent algorithms to show its efficiency. Finally, after a comprehensive discussion, the results prove that this work provides an accurate and effective tool for performing the emergency scheduling for extinguishing the forest fire.

Implementation of a Novel Tabu Search Optimization Algorithm to Extract Parasitic Parameters of Solar Panel

The aging of PV cells reduces their electrical performance i.e., the parasitic parameters are introduced in the solar panel. The shunt resistance (RSh), series resistance (RS), photo current (IPh), diode current (Id), and diffusion constant (a1) are known as parasitic or extraction parameters. Cracks and hotspots reduce the performance of PV cells and result in poor V–I characteristics. Certain tests are carried out over a long period of time to determine the quality of solar cells; for example, 1000 h of testing is comparable to 20 years of operation. The extraction of solar parameters is important for PV modules. The Tabu Search Optimization (TSO) algorithm is a robust meta-heuristic algorithm that was employed in this study for the extraction of parasitic parameters. Particle Swarm Optimization (PSO) and a Genetic lgorithm (GA), as well as other well-known optimization methods, were used to test the proposed method’s correctness. The other approaches included the lightning search algorithm (LSA), gravitational search algorithm (GSA), and pattern search (PS). It can be concluded that the TSO approach extracts all six parameters in a reasonably short period of time. The work presented in this paper was developed and analyzed using a MATLAB-Simulink software environment.

A Two-Stage Hybrid Extreme Learning Model for Short-Term Traffic Flow Forecasting

Credible and accurate traffic flow forecasting is critical for deploying intelligent traffic management systems. Nevertheless, it remains challenging to develop a robust and efficient forecasting model due to the nonlinear characteristics and inherent stochastic traffic flow. Aiming at the nonlinear relationship in the traffic flow for different scenarios, we proposed a two-stage hybrid extreme learning model for short-term traffic flow forecasting. In the first stage, the particle swarm optimization algorithm is employed for determining the initial population distribution of the gravitational search algorithm to improve the efficiency of the global optimal value search. In the second stage, the results of the previous stage, rather than the network structure parameters randomly generated by the extreme learning machine, are used to train the hybrid forecasting model in a data-driven fashion. We evaluated the trained model on four real-world benchmark datasets from highways A1, A2, A4, and A8 connecting the Amsterdam ring road. The RMSEs of the proposed model are 288.03, 204.09, 220.52, and 163.92, respectively, and the MAPEs of the proposed model are 11.53%, 10.16%, 11.67%, and 12.02%, respectively. Experimental results demonstrate the superior performance of our proposed model.

Fractional memetic computing paradigm for reactive power management involving wind-load chaos and uncertainties

Optimal reactive power dispatch (ORPD) with integration of renewable energy resources has a growing interest in research community due to its utmost requirements during the operation, planning and design of the modern electrical power networks. The objective of ORPD is to improve the performance of power network by means of reducing the losses in transmission line, improving the voltage profile, and decreasing the overall cost of operation through optimal tuning of the operational variables such as tap position of transformers, generator output voltages and capacitor banks. However, the nonlinear, non-stationary and complex nature of power network, presence of load uncertainties, and dynamic behavior of wind generation introduces a complex optimization task which cannot be readily solved in an efficient manner. In this research work, a new fractional memetic computing paradigm, i.e., the fractional particle swarm optimization gravitational search algorithm with entropy evolution (FPSOGSA-EE), is designed to solve the ORPD problems in power system adopting wind power plants (WPPs) and load uncertainties. The proposed optimization framework FPSOGSA-EE integrates the concept of fractional calculus and Shannon entropy to strengthen the optimization characteristics of canonical algorithm. The exhaustive experimentation endorse the efficacy of FPSOGSA-EE by providing minimum gauge of fitness evaluation function, namely, the line loss and voltage deviation index minimization, in IEEE 30 and 57 bus networks. The stability, consistency and reliability of proposed FPSOGSA-EE is ascertained through statistical interpretations by means of boxplots, probability measures for cumulative distribution function, and histogram illustrations.

Accurate parameter estimation methodology applied to model proton exchange membrane fuel cell

One of the essential phases in delivering a precise simulation of the fuel cell system behavior is estimating the model parameters. A novel identification approach based on the bald eagle search algorithm (BES) is suggested in this study to reliably extract the best PEM fuel cell (PEMFC) characteristics. BES is a modern metaheuristic algorithm with outstanding performance in various applications. Furthermore, this method delivers an accurate result because of its unique convergence mechanism. The paremeter identification of PEMFC is an optimization problem to minimize the sum square error (SSE) of the model and measurements. The unknown parameters are used as decision variables. To assess the effectiveness of the suggested method, two different types of PEMFCs were used: BCS 500 W and NedStack PS6. To approve the excellence of BES, a comparison was performed to those achieved using various optimizers, including gravitational search algorithm (GSA), grey wolf optimizer (GWO), differential evolution (DE), sine cosine algorithm (SCA), RSA encryption algorithm, and arithmetic optimization algorithm (AOA). The achieved results approve the advantage of BES in comparison with other algorithms. The SSE for NedStack PS6 employing the proposed method has been reduced to 2.07974 and 0.01136 for the BCS 500 W type. An accurate fitting for the measured datasets with the least deviation between the estimated and the experimental one.

Optimal placement and sizing of FACTS devices for optimal power flow using metaheuristic optimizers

This paper proposes the implementation of various metaheuristic algorithms in solving the optimal power flow (OPF) with the presence of Flexible AC Transmission System (FACTS) devices in the power system. OPF is one of the well-known problems in power system operations and with the inclusion of the FACTS devices allocation problems into OPF will make the solution more complex. Thus, seven metaheuristic algorithms: Barnacles Mating Optimizer (BMO), Marine Predators Algorithm (MPA), Moth–Flame Optimization (MFO), Particle Swarm Optimization (PSO), Gravitational Search Algorithm (GSA), Teaching–Learning-Based Optimization (TLBO) and Heap-Based Optimizer (HBO) are used to solve two objective functions: power loss and cost minimizations. These algorithms are selected from the different metaheuristics classification groups, where the implementation of these algorithms into the said problems will be tested on the modified IEEE 14-bus system. From the simulation results, it is suggested that TLBO and HBO perform better compared to the rest of algorithms.

An optimized deep learning architecture for breast cancer diagnosis based on improved marine predators algorithm

Breast cancer is the second leading cause of death in women; therefore, effective early detection of this cancer can reduce its mortality rate. Breast cancer detection and classification in the early phases of development may allow for optimal therapy. Convolutional neural networks (CNNs) have enhanced tumor detection and classification efficiency in medical imaging compared to traditional approaches. This paper proposes a novel classification model for breast cancer diagnosis based on a hybridized CNN and an improved optimization algorithm, along with transfer learning, to help radiologists detect abnormalities efficiently. The marine predators algorithm (MPA) is the optimization algorithm we used, and we improve it using the opposition-based learning strategy to cope with the implied weaknesses of the original MPA. The improved marine predators algorithm (IMPA) is used to find the best values for the hyperparameters of the CNN architecture. The proposed method uses a pretrained CNN model called ResNet50 (residual network). This model is hybridized with the IMPA algorithm, resulting in an architecture called IMPA-ResNet50. Our evaluation is performed on two mammographic datasets, the mammographic image analysis society (MIAS) and curated breast imaging subset of DDSM (CBIS-DDSM) datasets. The proposed model was compared with other state-of-the-art approaches. The obtained results showed that the proposed model outperforms the compared state-of-the-art approaches, which are beneficial to classification performance, achieving 98.32% accuracy, 98.56% sensitivity, and 98.68% specificity on the CBIS-DDSM dataset and 98.88% accuracy, 97.61% sensitivity, and 98.40% specificity on the MIAS dataset. To evaluate the performance of IMPA in finding the optimal values for the hyperparameters of ResNet50 architecture, it compared to four other optimization algorithms including gravitational search algorithm (GSA), Harris hawks optimization (HHO), whale optimization algorithm (WOA), and the original MPA algorithm. The counterparts algorithms are also hybrid with the ResNet50 architecture produce models named GSA-ResNet50, HHO-ResNet50, WOA-ResNet50, and MPA-ResNet50, respectively. The results indicated that the proposed IMPA-ResNet50 is achieved a better performance than other counterparts.

Optimal solution of PM synchronous motor obtained by gravitational search algorithm

This paper presents a novel approach to the efficiency improvement of permanent magnet synchronous motor using gravitational search algorithm as an optimization tool. The gravitational search algorithm (GSA) is a recently developed meta-heuristic optimization algorithm, which so far has proven to be quite suitable for solving power engineering optimization problems. The aim of this research work is to implement this novel optimization algorithm for the efficiency improvement of permanent magnet synchronous motor, where the objective function in the optimization process is the efficiency of the investigated motor. Comparative analysis of the initial and a number of optimized solutions of the motor model is performed.

Damage identification of thin plates using multi-stage PSOGSA and incomplete modal data

ABSTRACT The present work proposes a multi-stage optimization technique for damage detection of the thin plate-like structure using sparse modal data collected from the limited sensors. The response of the thin plate structures is obtained from a finite element model, which is developed with constant strain triangle elements. The iterated improved reduction system (IIRS) is applied to simulate the state of sparse sensors numerically. Next, the damage identification problem is formulated as a constrained optimization problem. A weighted linear combination of the natural frequencies and modes shapes of the structure is used to construct the objective function. The damage extent of each element is considered as the design variable. The formulated objective function is minimized by the proposed multi-stage strategy employing a hybrid metaheuristic algorithm, which is based on particle swarm optimization and gravitational search algorithm (PSOGSA). The algorithm identifies the healthy elements in each stage and eliminates them from the search space of the next stage. Thus, the search space dimension of the optimization problem reduces in each stage, and actual damaged elements are identified effectively. The efficiency of the proposed method is demonstrated through three numerical examples with different damage scenarios.

A bio‐inspired AlexNet‐DrpXLm architype for an effective brain stroke lesion detection and classification

SummaryIn this article, a bio‐inspired AlexNet‐DrpXLm architype is proposed for an effective brain stroke lesion detection and classification within a short period. Here, the input CT image datasets are collected from Himalayan Institute of Medical Sciences, then the images are preprocessed to take away the noises and also enhance the quality of the images. After that, the input images are trained and the features are extracted with the help of AlexNet model, and then classified as the brain images of normal and abnormal. The last three layers of the AlexNet model are replaced with the dropout extreme learning machine (DrpXLM) classifier to classify the images in efficient manner. The DrpXLM weight parameters are tuned by improved dolphin swarm optimization algorithm. The proposed method attains higher accuracy 99.54%, high precision 90.43%, high F‐score 89.40%, higher specificity 93.56%, higher sensitivity 93.56%, lower computational time 0.02 s, and the proposed method is compared to the existing methods, like random decision forest with gravitational search algorithm, hybrid native Bayes and sample weighted with random forest classification algorithm, and random forest with fractional‐order Darwinian particle swarm optimization.

Lamb wave-based damage localization and quantification algorithms for CFRP composite structures

Accurately and quantitatively monitoring the damages in complicated composite structures is very challenging, but essential for assessing their integrity. In this paper, an innovative damage monitoring method based on Lamb wave is proposed for large-scale complicated composite laminates. A combination of a resource-constraint Levenberg-Marquardt algorithm associated with a quantum-inspired gravitational search algorithm is introduced to identify the damage location. A damage contour algorithm using convex envelope of damage reflection points and maximum inscribed n-polygon is developed to determine the quantitative damage size. Meanwhile, a singular loci removal scheme based on an automatically updated boundary region constraint and bivariate normal distribution is utilized to separate the correctly positioned points on the damage periphery from those associated with noise. Experiments on two large-scale composite panels with multiple damage cases are conducted to substantiate the proposed algorithms. Sensor layers with embedded piezoelectric transducer (PZT) sensor networks mounted on the structures are employed to excite and receive Lamb wave signals because of their superiority of flexibility, electrical stability and apt for complex structures. The results demonstrate that the proposed technique is capable of pinpointing both location and size of the damage in the complicated composite structures.