Gravitational Search Algorithm Research Articles

Parameter optimization of laser displacement sensor based on gravitational search algorithm

Parameter optimization of laser displacement sensor based on gravitational search algorithm

Addressing a Collaborative Maintenance Planning Using Multiple Operators by a Multi-Objective Metaheuristic Algorithm

Selective maintenance has a significant impact on the sustainable management of maintenance operations. The collaboration of multiple maintenance teams/operators is helpful to achieve sustainability for selective maintenance sequence planning. For products with a large number of components, a single maintenance team/operator is inefficient due to a long completion time which is not acceptable for emergency planning. Providing specific and efficient maintenance sequence planning is critical to effectively handle different types of emergencies (e.g., wartime) while avoiding vague task assignments to multiple maintenance teams/operators. For scheduling many maintenance jobs while improving the efficiency and quality of maintenance operations, this study proposes a collaborative maintenance planning based on the concept of imperfect maintenance. In this regard, this study develops a multi-objective optimization model to optimize parallel maintenance sequences considering maintenance profit, maintenance cost, maintenance team, and resource limitations. We show the feasibility of the proposed multi-objective optimization model through a real case of maintenance practice for the components of an assistor device. For analyzing the complexity of the proposed maintenance sequence planning problem, this study introduces a new multi-objective metaheuristic algorithm which is an enhanced multi-objective gravitational search algorithm (EMOGSA) to find high-quality Pareto solutions for the proposed problem. Different multi-objective evaluation metrics are used to study the performance of the proposed algorithm. From the results, the proposed model and developed solution algorithm can help maintenance decision-makers to determine complex maintenance planning. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper deals product with a maintenance and proposes gravitational search algorithm based on only maintenance task, which maintenance task. The goal of this paper is to analyze the maintenance problem from the perspective of collaboration of multiple maintenance teams/operators.

IGSA-PNN-based Methods for Power Transformer Fault Diagnosis

To enhance the precision of power transformer fault diagnosis, it is necessary to make improvements. Aiming at the shortcomings of Probabilistic Neural Network (PNN) network experience selection smoothing factor and avoiding the shortcomings of traditional Gravitational Search Algorithm (GSA) easy 0to fall into local optimum and convergence speed slow, a Probabilistic Neural Network (PNN) model using chaos sequence to improved GSA for power transformer fault diagnosis is proposed. Firstly, chaos sequence is used to increase the diversity of gravitational particles to avoid falling into local optimum during the training process. Then, the improved GSA algorithm is used to optimize the parameters of the PNN model itself to improve the prediction accuracy of the model. Finally, the prediction results are compared with the prediction results of other traditional diagnostic models. The results show that IGSA-PNN fault diagnosis model performs better in generalization ability and classification accuracy.

Wireless sensor network data gathering using a multi-fold gravitational search algorithm with a mobile agent

Wireless sensor network data gathering using a multi-fold gravitational search algorithm with a mobile agent

Cluster‐based context‐aware route service management for smart intelligent autonomous vehicles with industrial transport system

SummaryIndustrial transport system refers to the movement of goods, raw materials, and finished products within and between industrial facilities such as factories, warehouses, and distribution centers. It includes a variety of modes of transport such as trucks, forklifts, conveyor belts, and automated guided vehicles (AGVs). Context‐aware route service management refers to system that can dynamically manage and optimize the routes taken by vehicles in transportation system based on contextual information. Our proposed framework for industrial transport systems and smart intelligent autonomous vehicles utilizes cluster‐based context‐aware routing (CCAR), which includes several significant contributions. Firstly, modified elephant herding optimization (MEHO) algorithm is used to efficiently group autonomous vehicles for routing. Secondly, an improved gravitational search (IGS) algorithm is used for cluster head (CH) selection responsible for transferring context information between vehicles (V2V). Thirdly, a deep hybrid multi‐graph neural network (DHMG‐NN) is designed for optimal neighboring roadside unit (RSU) node selection through different design constraints to ensure data dissemination between vehicles and infrastructure (V2I). Finally, we validate the effectiveness of our CCAR framework using various simulation scenarios. Our framework achieves a reduction of up to 78% in computation time and an improvement of up to 25% in customer satisfaction ratio and 15% higher than the overall performance ratio compared to the existing frameworks.

An Optimal Model and Application of Hydraulic Structure Regulation to Improve Water Quality in Plain River Networks

The proper dispatching of hydraulic structures in water diversion projects is a desirable way to maximize project benefits. This study aims to provide a reliable, optimal scheduling model for hydraulic engineering to improve the regional water environment. We proposed an improved gravitational search algorithm (IPSOGSA) based on multi-strategy hybrid technology to solve this practical problem. The opposition-based learning strategy, elite mutation strategy, local search strategy, and co-evolution strategies were employed to balance the exploration and exploitation of the algorithm through the adaptive evolution of the elite group. Compared with several other algorithms, the preponderance of the proposed algorithm in single-objective optimization problems was demonstrated. We combined the water quality mechanism model, an artificial neural network (ANN), and the proposed algorithm to establish the optimal scheduling model for hydraulic structures. The backpropagation neural network (IGSA-BPNN) trained by the improved algorithm has a high accuracy, with a coefficient of determination (R2) over 0.95. Compared to the two traditional algorithms, the IGSA-BPNN model was, respectively, improved by 1.5% and 0.9% on R2 in the train dataset, and 1.1% and 1.5% in the test dataset. The optimal scheduling model for hydraulic structures led to a reduction of 46~69% in total power consumption while achieving the water quality objectives. With the lowest cost scheme in practice, the proposed intelligent scheduling model is recommended for water diversion projects in plain river networks.

Q-LEARNING, POLICY ITERATION AND ACTOR-CRITIC REINFORCEMENT LEARNING COMBINED WITH METAHEURISTIC ALGORITHMS IN SERVO SYSTEM CONTROL

This paper carries out the performance analysis of three control system structures and approaches, which combine Reinforcement Learning (RL) and Metaheuristic Algorithms (MAs) as representative optimization algorithms. In the first approach, the Gravitational Search Algorithm (GSA) is employed to initialize the parameters (weights and biases) of the Neural Networks (NNs) involved in Deep Q-Learning by replacing the traditional way of initializing the NNs based on random generated values. In the second approach, the Grey Wolf Optimizer (GWO) algorithm is employed to train the policy NN in Policy Iteration RL-based control. In the third approach, the GWO algorithm is employed as a critic in an Actor-Critic framework, and used to evaluate the performance of the actor NN. The goal of this paper is to analyze all three RL-based control approaches, aiming to determine which one represents the best fit for solving the proposed control optimization problem. The performance analysis is based on non-parametric statistical tests conducted on the data obtained from real-time experimental results specific to nonlinear servo system position control.

Drum boiler system water level control: A study of existing hybrid optimization algorithms

In this research, we use a variety of optimization techniques to perfect the settings of a PID controller that manages the water level in a boiler's drum. In this study, Particle Swarm Optimization (P_S OPTIMIZATION) is used alongside other optimization techniques and compared to each other. Optimization that combines bacterial foraging with Particle swarms (BFP_S) and Hybridising the Gravitational Search Algorithm along with Particle swarm (GSAP_S) seeks to improve search results. The forementioned methods were tested, and their results were compared, utilising metrics such as IS ERROR, IA ERROR, ITA ERROR, and time domain specifications.

Analysis of Distribution Static Compensator Control Strategies for Mitigating Voltage Dip Impact on Distribution Network

Voltage dip, over-voltage, load unbalanced, and current and voltage harmonics distortions are the key characteristics of poor power quality (PQ) issues on the power distribution network with a significant negative impact. The performance of a custom power device, distribution static compensator (D-STATCOM), in reducing current total harmonic distortion (THD) during the mitigation process of voltage dip with fault is investigated in this study. To control the load side voltage, the D-STATCOM utilizes a three-phase voltage source converter and is coupled at the point of common coupling (PCC). To mitigate voltage dip effects, this study implements and compares the effectiveness of the conventional PI controller with an intelligent optimization-based PI controller using the dynamic gravitational search algorithm (DGSA). The performance of these controllers is validated by the MATLAB/Simulink simulation results obtained. Analysis of the results demonstrates that D-STATCOM operates flawlessly with an intelligently optimized PI control strategy reducing the current THD from 11.68% to 3.74%.

Robust energy storage system for stable in wind and solar

Energy storage systems (ESS) have become a conspicuous research hotspot since they store power and supply it during peak hours. Existing storage systems must be replaced by advanced energy storage with improved performance, energy management, and a control interface due to issues with size, dependability, and charging/discharging. The suggested robust energy retention system uses a battery and a super-capacitor to generate power from wind and solar energy. A Multiport DC converter with a buck-boost capacitor is used to properly discharge the stored energy to DC loads via a DC bus. The inverter is then delivered to a Power Flow Controller (PFC) and a Voltage Source Inverter (VSI). The Gravitational Search Algorithm (GSA) method optimizes the power controller settings based on the fluctuation of the system's active and reactive power. The optimization method ensures improved power flow while dealing with the least amount of power variance in imbalanced load situations. Based on the power variation, the proposed method generates appropriate control signals for the inverter system. The covers convert the inverter and reduce harmonics with a controller. Furthermore, the inverter AC supplied to the AC bus is converted into reactive power by an inductive load, and unwanted signals and harmonics are extracted using a Cascaded C-type filter. As a result, the described method has preserved total harmonic distortion, electrical efficiency, and finer transient stability.

An atom search optimization approach for IIR system identification

ABSTRACT Filtering, or digital signal processing, is a significant and fundamental requirement in fields such as signal systems and computers. The process of designing optimal digital filters is difficult, which has led researchers to design filters using emerging evolutionary computations. Metaheuristics have emerged as the most promising tool for solving optimization problems, with excellent development and improvement. However, it has not been clear how to select the best performing metaheuristic to design an optimal digital filter. In this paper, a digital infinite impulse response (IIR) filter is constructed using the atom search optimization (ASO) algorithm impressed by the physical motion of atoms in nature based on molecular dynamics. The simulation results obtained are extensively compared with the results of other optimization algorithms such as moth flame optimization, gravitational search algorithm and artificial bee colony optimization. ASO was found to have the highest percentage of improvement. Furthermore, eight cases are analyzed across four numerical filter instances with the same degree and four with reduced degree, and the results are validated by outperforming several different algorithm-based approaches in the literature. The stability analysis on the basis of pole zero diagrams further cements the efficacy of the ASO for IIR system identification problem.

Optimal Design of Heliostat Field Power Based on Whale Optimization Algorithm and Gravitational Search Algorithm

With the deterioration of global climate and the worsening of energy crisis, the construction of a new power system mainly based on new energy is an important measure for China to realize the goal of "carbon peak" and "carbon neutrality". In order to maximize the power generation efficiency of the mirror field, the layout design of the heliostat is particularly important. In this paper, we constructed a model to calculate each optical efficiency loss component, cosine efficiency, atmospheric transmittance, and discretized the points on the heliostat, and calculated the shadow masking efficiency by coordinate transformation, and finally obtained the collector truncation efficiency. Next, the optimal design of the heliostat field in different cases is obtained using the whale optimization algorithm and the gravitational search algorithm.

Optimal energy trading in cooperative microgrids considering hybrid renewable energy systems

This study presents a novel method for optimal energy trading within microgrids considering renewable energy (RE) integration. The proposed approach uses the hybridization of particle swarm optimization and gravitational search algorithms (PSO-GSA) with Nash Bargaining to optimize power flow and energy trading between interconnected MGs and the main utility grid. Unlike existing solutions, the proposed model promotes cooperative energy trading among MGs and the main grid, considering network constraints and RE's inherent uncertainty; consequently, it addresses key challenges related to model design, pricing fairness, power flow optimization, and network constraints. The proposed method is implemented in MATLAB® considering the interconnection of four different MGs, called cooperative MGs, which optimally enable energy trading within the cooperative MGs and main utility. Simulation results, case studies and comparisons demonstrate the relevance of the proposed hybrid PSO-GSA in terms of maximizing the RE utilization, reducing load burden on the main grid and substantial cost reductions, with monthly energy costs decreased by $60,720 compared to the base case of $94,551. Also, the robustness and efficiency of the proposed PSOGSA algorithm are evaluated by comparing it with other well-established metaheuristic optimization methods under the same system data, control variables, and constraints. This research significantly contributes to MG energy trading by proactively optimizing economic operations and increasing RE utilization while adapting cooperation among interconnected MGs.

Impact Behaviour Modelling of Magnetorheological Elastomer Using a Non-Parametric Polynomial Model Optimized with Gravitational Search Algorithm

This paper presents an approach to model the impact behaviour of a dual-acting magnetorheological elastomer (MRE) damper using 4th-order polynomial functions optimized with a gravitational search algorithm. MRE is a type of smart material that can change its mechanical properties in response to an injected current, making it well-suited for a wide range of applications such as vibration absorption, noise cancellation, and shock mitigation. The proposed model uses a combination of polynomial functions designed to predict the nonlinearity of MRE during compression and extension stages. The model is tuned and validated using experimental data from impact tests conducted on the MRE damper under various currents. The results indicate that the developed model can accurately track the impact behaviour of MRE with minimum error. Additionally, an interpolation model is proposed to estimate the appropriate forces for median currents. The interpolation model predicts the force between the upper and lower currents, demonstrating the model's ability to predict MRE behaviour accurately. The main contribution of this study is proposing a non-parametric model of MRE that is able to identify the hysteretic behaviour of the MRE based on specific current applied. In addition, an interpolation model is introduced in this study to cover not only the input current starting from 0 A to 2 A but also the intermediate current such as 0.3 A, 0.7 A, 1.3 A and 1.7 A.

Net Zero Energy cost Building system design based on Artificial Intelligence

This paper presents a solution to the energy planning problem in buildings by implementing the net Zero Energy cost Building (nZEcB), a new concept that refers to buildings with zero or almost zero annual energy costs, using Artificial Intelligence (AI) techniques such as bidirectional long short-term memory, ordinary least squares linear regression, K-means, Pearson’s correlation, decision tree, and binary gravitational search algorithm. AI techniques are used to design the optimal structure of a distributed generation system. The system includes wind and photovoltaic renewable energy sources, a battery bank, and an automated capacitor bank for power factor compensation. A case study was conducted in a real public building with an annual consumption of 1.748 GWh, which resulted in the specification of a distributed generation system with a generation of 2.805 GWh per year. This system meets approximately 160.5% of the building’s electrical demand and 99.999% of annual energy costs, i.e., attending the nZEcB concept. The excess production of approximately 60% of the energy is necessary because the exported energy (feed-in tariff) has a lower value than that imported from the network, having to deduct costs with demand, in addition to having to compensate for losses in the battery banks. The project has a payback period of 6.79 years. This novel study demonstrates the feasibility and effectiveness of using AI techniques to achieve nZEcBs more efficiently, economically and sustainably.

Optimized gravitational search algorithm for feature fusion in a multimodal biometric system

In recent years, multimodal biometric systems have gained significant attention due to their capacity to enhance recognition accuracy and robustness. The integration of multiple biometric traits, such as face, fingerprint, iris, and voice, has shown promising results in addressing the limitations of unimodal systems. However, achieving efficient and accurate feature fusion remains a critical challenge in the development of multimodal biometric systems. This study proposes an optimized approach utilizing the Gravitational Search Algorithm (GSA) for feature fusion in a multimodal biometric system. The objective is to enhance recognition performance by effectively combining complementary information from multiple biometric traits. The evaluation performance to determine the effect of the optimization at threshold values of 0.22, 0.35, 0.5, 0.8 and 1.0 was compared with the traditional GSA and presented. This study achieved the highest GWGSA accuracy at 0.8 and 1.0 thresholds to outperform other thresholds as shown in T able 1. The proposed approach is tested with real-world datasets and compared against existing fusion techniques, demonstrating its superiority in terms of recognition accuracy and computational efficiency.

Fractional-PID and Its Parameter Optimization for Pumped Storage Units Considering the Complicated Conduit System

Speed governing control is significant in ensuring the stable operation of pumped storage units. In this study, a state-space equation mathematical model of the pumped storage governing system considering the complex hydraulic pipeline structure of the pumped storage plant is proposed to describe the system’s dynamic behaviors under small disturbance conditions. Considering the frequent operating condition transitions and the complicated nonlinear dynamic characteristics of the pumped storage units, the fractional-order PID (FOPID) scheme that possesses a higher degree of control freedom than the traditional PID scheme is discussed in detail. To optimize the control parameters of the unit governor, an improved gravitational search algorithm (IGSA) that combines the basic searching mechanisms of the gravitational search algorithm and chaotic search, elastic sphere boundary treatment, and elite guidance strategy is developed. Comparative studies have been carried out under frequency and load disturbance conditions. Simulation results indicate that the control performance of FOPID is better than that of PID under diverse operating conditions and the proposed IGSA has satisfactory parameter optimization capability.

A Comparative Study of Metaheuristic Optimization Algorithms for Solving Engineering Design Problems

Metaheuristic optimization algorithms (Nature-Inspired Optimization Algorithms) are a class of algorithms that mimic the behavior of natural systems such as evolution process, swarm intelligence, human activity and physical phenomena to find the optimal solution. Since the introduction of meta-heuristic optimization algorithms, they have shown their profound impact in solving the high-scale and non-differentiable engineering problems. This paper presents a comparative study of the most widely used nature-inspired optimization algorithms for solving engineering classical design problems, which are considered challenging. The teen metaheuristic algorithms employed in this study are, namely, Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Biogeography Based Optimization Algorithm (BBO), Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES), Cuckoo Search algorithm (CS), Differential Evolution (DE), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Gravitational Search Algorithm (GSA) and Particle Swarm Optimization (PSO). The efficiency of these algorithms is evaluated on teen popular engineering classical design problems using the solution quality and convergence analysis, which verify the applicability of these algorithms to engineering classical constrained design problems. The experimental results demonstrated that all the algorithms provide a competitive solution.

A Novel Hybrid IGSA-BPSO Optimized FOPID Controller for Load Frequency Control of Multi-source Restructured Power System

Background: An investigation of Automatic Generation Control (AGC) for a two-area, multi-source, interconnected power system under deregulation is presented in this article. For a more realistic approach, physical constraints namely Generation Rate Constraints (GRC) and Time Delay (TD) are incorporated into the system. Objective: This article proposed a novel hybrid Improved Gravitational Search Algorithm – Binary Particle Search Optimization (IGSA-BPSO) optimized Fractional Order Proportional-Integral- Derivative (FOPID) controller to regulate the frequency of a multi-area multi-source (thermalhydro- gas) interconnected power system in a deregulated environment. Methods: Integral Time Multiplied by Absolute Error (ITAE) is used as the objective function to be minimized by optimization techniques for getting optimum parameters of FOPID controllers installed in each area. Results: To inspect the efficacy of the suggested method, the dynamics of the system are investigated for poolco, bilateral and contract violation cases and the comparative results are also presented and analyzed. The supremacy of the recommended technique is studied by comparing with other well-known techniques namely GSA and PSO. Conclusion: The robustness of the proposed system is examined by sensitivity analysis after variations in different system parameters. In this paper, the AC-DC tie-line model is incorporated for the AGC mechanism. Dynamic load changes condition is also tested and verified. The study found that the proposed controller provides improved system dynamics in all competitive electricity market contract situations under varied system uncertainties.

Agile gravitational search algorithm for cyber-physical path-loss modelling in 5G connected autonomous vehicular network

Based on the characteristics of the 5 G standard defined in Release 17 by 3GPP and that of the emerging Beyond 5 G (or the so-called 6 G) network, cyber-physical systems (CPSs) used in smart transport network infrastructures, such as connected autonomous vehicles (CAV), will significantly depend on the cellular networks. The 5 G and Beyond 5 G (or 6 G) will operate over millimetre-wave (mmWave) bands. These network standards require suitable path loss (PL) models to guarantee effective communication over the network standards of CAV. The existing PL models suffer heavy signal losses and interferences at mmWave bands and may not be suitable for cyber-physical (CP) signal propagation. This paper develops an Agile Gravitational Search Algorithm (AGSA) that mitigates the PL and signal interference problems in the 5G–NR network for CAV. On top of that, a modified Okumura-Hata model (OHM) suitable for deployment in CP terrestrial mobile networks is derived for the CAV-CPS application. These models are tested on the real-world 5 G infrastructure. Results from the simulated models are compared with measured data for the modified, enhanced model and four other existing models. The comparative evaluation shows that the modified OHM and AGSA performed better than existing OHM, COST, and ECC-33 models by 90%. Also, the modified OHM demonstrated reduced signal interference compared to the existing models. In terms of optimisation validation, the AGSA scheme outperforms the Genetic algorithm, Particle Swarm Optimisation, and OHM models by at least 57.43%. On top of that, the enhanced AGSA outperformed existing PL (i.e., Okumura, Egli, Ericson 999, and ECC-33 models) by at least 67%, thus presenting the potential for efficient service provisioning in 5G-NR driverless car applications.