Modified Salp Swarm Research Articles

Air supply subsystem efficiency optimization for fuel cell power system with layered control method

Efficient and stable operation is critical for the large-scale commercialization of the proton exchange membrane fuel cell power system. The effective control and optimization of the operating conditions, such as oxygen excess ratio and cathode pressure of the air supply system, is a solution to improve the overall system efficiency. This work proposes a novel layered control method to achieve rapid and stable control of the operating conditions. The control structure in this paper consists of the optimization and control layers. A two-dimensional objective optimization function for the optimization layer is established to characterize the system efficiency based on theoretical analysis and experimental testing on the fuel cell power generation process and air supply system power consumption pattern. Then, a modified salp swarm algorithm with adaptive inertia weight is proposed to quickly and accurately obtain the optimal operating conditions for the maximum efficiency under different load current densities. Meanwhile, the local optimal solutions are avoided by introducing mutation operations. For the control layer, a third-order state space equation is developed to accurately describe the operating characteristics of the air supply system according to its operating principles. A feedback linearization-based sliding mode controller is designed to achieve rapid and stable control of the optimal working conditions outputted from the optimization layer. Finally, the fuel cell system was tested in the lab and verified on the fuel cell city buses. The results show that the system's operating efficiency is improved by 0.6 %–2.6 % at different current densities, and the hydrogen consumption of all three city buses is reduced by more than 5 %. The optimization effect was enhanced significantly. Therefore, the layered control method is effective in solving the optimization and control problems of the fuel cell power system.

Modified salp swarm algorithm based on competition mechanism and variable shifted windows for feature selection

Modified salp swarm algorithm based on competition mechanism and variable shifted windows for feature selection

Optimizing the Architecture of Convolutional Neural Networks Using Modified Salp Swarm Algorithm

Deep learning is highly effective in dealing with complex tasks such as image classification and recognition. However, finding the optimal architecture's hyperparameters for Convolutional Neural Networks (CNNs) to achieve the best performance and parameter regularization can be challenging. Metaheuristic optimization algorithms can be utilized to find solutions in this context. In this research, a computerized CNN was adjusted using an improved Salp Swarm Algorithm (SSA) to enhance crucial CNN settings, like dropout rate, hidden units, learning rate, and batch size. The refined design was tested on two standard datasets. MNIST and Fashion MNIST. The outcomes displayed model performance achieving accuracy levels of 99.6% for MNIST and 94.08% for Fashion MNIST. This tuned system outperformed the existing practices by 0.2% and 0.04% for each dataset while also cutting down on computational expenses. The fusion of SSA with CNNs displayed adaptability and resilience opening up possibilities, in image classification and consistently delivering outstanding outcomes.

Advancing large-scale cement vehicle distribution: the modified salp swarm algorithm

The vehicle routing problem (VRP) is a paramount combinatorial optimisation challenge, extensively used across various transportation logistics and distribution systems. The capacity-utilised vehicle routing problem (CVRP) stands as a notable variant, necessitating a nuanced interplay between the exploration and exploitation phases due to its discrete nature. While the salp swarm algorithm (SSA) enjoys recognition in the optimisation domain for its streamlined design and efficacy, its foundational architecture is inherently suited for continuous optimisation tasks. Addressing this gap, our paper presents a refined iteration of SSA, termed mSSA. By ingeniously integrating the core principles of SSA with the opposition-based learning (OBL) approach and incorporating the roulette wheel selection (RWS) mechanism, mSSA is meticulously crafted to navigate the discrete challenges posed by expansive CVRP instances. To affirm the robustness of mSSA, our research undertook performance evaluations in three distinct CVRPs: initially, an 8-customer assignment to validate stability, followed by two practical tests involving the distribution of cement to 30 and 50 customers in Vietnam. Empirical findings consistently highlight mSSA's dominant performance against other meta-heuristic techniques tailored for CVRP. This positions mSSA as a formidable tool in decision-making processes, particularly for optimising cement delivery using limited-capacity vehicles.

Optimized Fixed-Time Synergetic Controller via a modified Salp Swarm Algorithm for Acute and Chronic HBV Transmission System

In this paper, we propose a Salp Swarm Algorithm (SSA) Optimized Fixed-Time Synergetic Control (FTSC) strategy for the spread of hepatitis B infection. The utilization of the SSA optimization algorithm for optimizing the Synergetic Control (SC) fraction parameters presents a non-trivial challenge due to the restriction that only odd numbers can be used for the fractional power. Therefore, an enhanced and adapted version of the SSA algorithm is proposed to effectively address this specific scenario. Our strategic approach centers on the reduction of susceptible, acutely infected, and chronically infected individuals by employing control parameters like isolation, treatment, and vaccination. The objective is to drive these target state variables to their smallest values in a fixed-time, thereby effectively controlling the epidemic. We support our proposal with numerical simulations to demonstrate the feasibility and effectiveness of the control strategy. A comparison is conducted between FTSC and SC in scenarios with and without optimization. The results indicated that FTSC holds a distinct advantage, consistently demonstrating significant progress, with up to 30\% reduction in the total convergence time to zero, outperforming SC in each case.

On the Best Fitness Function for the WSN Lifetime Maximization: A Solution Based on a Modified Salp Swarm Algorithm for Centralized Clustering and Routing

Wireless sensor networks (WSNs) have become increasingly important in recent years due to their ability to monitor and collect data in various environments. However, WSNs are often limited by their energy resources, making energy efficiency a critical concern in designing WSNs. Clustering and multi-hop routing are effective methods for maximizing the lifetime of WSNs. The energy efficient clustering and routing problem in WSNs can be formulated as a multi-dimensional knapsack problem (d-kp). This formulation can generalize all clustering and routing protocols in regard to energy efficiency. In this paper, we investigate the hardness of the energy-efficient clustering and routing problem in WSNs based on the d-kp formulation and introduce a modified Salp Swarm Algorithm (SSA) as a method to solve this problem. SSA is a metaheuristic algorithm inspired by the behavior of salps in the ocean. Moreover, we prove that it is impossible to design a polynomial time fitness function to maximize a long-term metric such as FND (time of first node death), which is a commonly used metric for network lifetime. Our results have implications for the design of energy-efficient WSNs and call for the development of more efficient algorithms that can handle the complexity of this problem. furthermore, we evaluate our proposed algorithm using simulation and compare it to existing algorithms. Our results show that using SSA with a carefully designed fitness function based on the theoretical findings and a unique one-to-one routing protocol to mitigate the energy hole problem, outperforms many of the existing algorithms in terms of energy efficiency and network lifetime.

Anomaly Detection for Internet of Things Security Attacks Based on Recent Optimal Federated Deep Learning Model

The mushrooming of IoTs (Internet of Things) and decentralised paradigm in cyber security have attracted a lot of interest from the government, academic, and business sectors in recent years. The use of MLT-assisted techniques in the IoT security arena has attracted a lot of attention in recent years. Many current studies presume that massive training data is readily accessible from IoT devices and transferable to main servers. However, since data is hosted on single servers, security and privacy concerns regarding this data also increase. It is suggested to use decentralised on-device data in OFDL (Optimal Federated Deep Learning) based anomaly detections to proactively identify infiltration in networks for IoTs. The GRUs (Gated Recurrent Units) used in OFDL's training rounds share only learned weights with the main OFDL servers, protecting data integrity on local devices. The model's training costs are reduced by the use of appropriate parameters, which also secures the edge or IoT device. In order to optimise the hyper-parameter environments for the limited OFDL environment, this paper suggests an MSSO (Modified Salp Swarm Optimisation) approach. Additionally, ensembles combine updates from multiple techniques to enhance accuracies. The experimental findings show that this strategy secures user data privacy better than traditional/centralized MLTs and offers the best accuracy rate for attack detection.

A MODIFIED SALP SWARM OPTIMIZATION ALGORITHM BASED ON THE LOAD FREQUENCY CONTROL OF MULTIPLE-SOURCE POWER SYSTEM

This work proposes a modified Salp Swarm Optimization Algorithm (SSA) for addressing a multi-source power state's Load Frequency Control (LFC). A controller parameter tuning of the SSA method and its application to the LFC of a multi-source power system with several power generating sources. Derive to the controller parameters, a single area telecommunications device that permits two power system with integrated controlles according to each unit is considered first, and the SSA approach is used. The tunned SSA algorithm is used to optimize the integral (I), proportional integral (PI), and proportional integral derivative (PID) parameters. The research is expanded to include a multi-area multi-source power system, as well as an HVDC link is proposed for connectivity of two regions in addition to the current AC point of intersection. This same tunned SSA method is used to improve the parameters of the Integral (I), Proportional Integral (PI), and Proportional - integral - derivative Derivative (PID). Consequently, the suggested system is shown to be resilient and unaffected by changes of the loading situation, system parameters, or SLP size.

Improved adaptive neuro-fuzzy inference system based on modified salp swarm algorithm and golden eagle optimizer algorithm for intrusion detection in networks

With the increase in the growth of computer networks throughout the past years, network security has become an essential issue. Among the numerous network security measures, intrusion detection systems play a dynamic function with integrity, confidentiality, and accessibility of resources. An Intrusion Detection System (IDS) is a software program or hardware device which monitors computer system and/or network activities for malicious activities and produces alerts to security experts. In IDS there are three major problems namely generating many alerts, a huge rate of false positive alerts, and unknown attack types per generated alerts. Alert management methods are used to manage these problems. One of the methods of alert management is alert reduction and alert classification. The proposed approach focuses on enhancing the efficiency of the adaptive neuro-fuzzy inference system (ANFIS) using a modified salp swarm algorithm (SSA) and Golden Eagle optimizer (GEOSSA). The present study uses the Golden Eagle optimization algorithm to improve SSA behaviors. The proposed model (GEO-SSA-ANFIS) intends to determine the appropriate parameters using the GEO-SSA algorithm because these parameters are considered the main component affecting the ANFIS forecasting process. The results of the intrusion detection based on the NSL-KDD dataset were better and more efficient compared with those models because the detection rate was 96.68% and the FAR result was 0.438%.

A Novel EA-Based Techno–Economic Analysis of Charging System for Electric Vehicles: A Case Study of Qassim Region, Saudi Arabia

Because of the fast expansion of electric vehicles (EVs) in Saudi Arabia, a massive amount of energy will be needed to serve these vehicles. In addition, the transportation sector radiates a considerable amount of toxic gases in the form of SO2 and CO2. The national grid must supply a huge amount of electricity on a regular basis to meet the increasing power demands of EVs. This study thoroughly investigates the technical and economic benefits of an off-grid and grid-connected hybrid energy system with various configurations of a solar, wind turbine and battery energy storage system for the electric vehicle charging load in the Qassim region, Saudi Arabia. The goal is to decrease the cost of energy while reducing the chance of power outages in the system. This is achieved by using a new optimization algorithm called the modified salp swarm optimization algorithm (MSSOA), which is based on an evolutionary algorithm approach. MSSOA is an improved version of SSOA, which addresses its shortcomings. It has two search strategies to enhance its efficiency: first, it uses Levy flight distribution (LFD) to help individuals reach new positions faster, and second, it instructs individuals to spiral around the optimal solution, improving the exploitation phase. The MSSOA’s effectiveness is confirmed by comparing its results with those of the conventional salp swarm optimization algorithm and particle swarm optimization (PSO). According to simulation findings, MSSOA has excellent accuracy and robustness. In this region, the SPV/WT/BESS-based EV charging station is the optimal option for EV charging stations. The SPV/WT/BESS design has the lowest LCOE of all feasible configurations in the region under study. The optimum values for the LCOE and TNPC using MSSOA are USD 0.3697/kWh and USD 99,928.34, which are much lower than the optimized values for the LCOE (USD 0.4156) and TNPC (USD 1,12,671.75) using SSOA. Furthermore, a comprehensive techno–economic analysis of optimized hybrid systems is assessed by incorporating the grid-connected option. The grid connected system results in optimized values of the LCOE (USD 0.0732/kWh) and TNPC (USD 1,541,076). The impact of different grid purchase prices on the levelized cost of energy is also studied. Our results will assist the researchers to determine the best technique for the optimization of an optimal energy system.

Techno-economic assessment of grid and renewable powered electric vehicle charging stations in India using a modified metaheuristic technique

Renewable energy technologies have left an indelible impression on the global electrical market by supplying customers with uninterrupted electricity. Utilizing renewable energy sources to satisfy the load requirements of electric vehicle charging stations is one of the most significant areas of study in developing nations. This research investigates the technical and financial viability of grid and renewable-powered energy systems for an environmentally sustainable electric vehicle charging station in three distinct regions across India. The presented setup is subjected to an economic analysis for satisfying the charging requirement of the electric vehicle load. The system is designed in such a way that the power exchange takes place between the grid network and different components of the energy system. The assigned places are selected so that wind and solar prospects are contrary in these areas. The charging hours of electric vehicles are different in the specific sites. The optimal sizing of the system component is performed to minimize the levelized cost of electricity and total net present cost while keeping the probability of power supply failure within acceptable limits using a novel metaheuristic-based optimization algorithm i.e., modified salp swarm algorithm. The achievement of the designed system demonstrates that New Delhi has a lower total net present cost of $ 14853.63 and levelized cost of electricity of 0.0051 $/kWh. The optimum number of solar panels and wind turbines needed to meet the EV load demand in the New Delhi region is 120 with 325 W rated capacity and 310 with 650 W rated capacity. The optimal solution for the hybrid system consists of 64.5% wind energy, 33.5% solar energy and 1.94% grid purchase with annual electricity production is 5,91,117 kWh. Similarly, the optimum values of the total net present cost and levelized cost of electricity for the city of Ahmedabad are 222762.80 $ and 0.023 kWh, respectively. The total net present cost and levelized cost of electricity in the Madurai area are 37.44% and 8.17% higher than in the New Delhi region, respectively. The envisaged system could help to reduce the dependence on the overstrained grid, especially in developing nations.

A modified Salp Swarm Algorithm for parameter estimation of fractional-order chaotic systems

For the parameter estimation problem in research related to the fractional-order chaotic systems (FOCSs), a modified optimization algorithm based on Salp Swarm Algorithm (SSA) was developed in this paper. The proposed algorithm introduced several improvements on SSA: adding a grouping step, introducing “betrayal” behavior, and improving the update method of the followers. We applied multiple classical optimization algorithms to conduct the parameter estimation experiments on the fractional-order Lorenz chaotic system (Lorenz-FOCS) and the fractional-order Financial chaotic system (Financial-FOCS). In addition, we explored the impact of searching space on parameters estimation through experiments. The experimental results confirmed the feasibility of the modified Salp Swarm Algorithm (MSSA). The MSSA performed better than the SSA and other classical optimization algorithms in terms of the estimation accuracy and convergence rate.

Underwater image illumination estimation via an evolving extreme learning machine by an improved salp swarm algorithm.

Underwater images have chromatic aberrations under different light sources and complex underwater scenes, which can lead to the wrong choice when using an underwater robot. To solve this problem, this paper proposes an underwater image illumination estimation model, which we call the modified salp swarm algorithm (SSA) extreme learning machine (MSSA-ELM). It uses the Harris hawks optimization algorithm to generate a high-quality SSA population, and uses a multiverse optimizer algorithm to improve the follower position that makes an individual salp carry out global and local searches with a different scope. Then, the improved SSA is used to iteratively optimize the input weights and hidden layer bias of ELM to form a stable MSSA-ELM illumination estimation model. The experimental results of our underwater image illumination estimations and predictions show that the average accuracy of the MSSA-ELM model is 0.9209. Compared to similar models, the MSSA-ELM model has the best accuracy for underwater image illumination estimation. The analysis results show that the MSSA-ELM model also has high stability and is significantly different from other models.

Size optimization of planar truss systems using the modified salp swarm algorithm

This work evaluates the performance of the salp swarm algorithm (SSA) for truss system optimization problems and presents a novel method called the modified salp swarm algorithm (MSSA). Five truss structures, previously optimized by metaheuristics and containing discrete and continuous variables, were used for the evaluations. Size and size–shape optimization types were considered. Although the SSA performs poorly and has convergence issues in initial random solutions, it reaches comparable solutions to previously published results, particularly in continuous problems. In contrast, the MSSA achieves the best solutions for discrete problems and is relatively close to the best results in the reference literature on continuous problems. Moreover, the MSSA convergence curves exhibit a modest increase in convergence rates, especially for discrete problems. It is envisaged that the findings will contribute to improving solution performance, convergence speed and security for future real-world applications.

Modified Salp Swarm Algorithm With Deep Learning Based Gastrointestinal Tract Disease Classification on Endoscopic Images

Nowadays, the analysis of gastrointestinal (GI) tract disease utilzing endoscopic image classification becomes an active research activity from the biomedical sector. The latest technology in medical imaging is Wireless Capsule Endoscopy (WCE) for diagnosing gastrointestinal diseases namely bleeding, ulcer, polyp, and so on. Manual diagnoses will be time taking and tough for the medical practitioner; thus, the authors have designed computerized approaches for classifying and detecting such diseases. Many research groups presented various machine learning (ML) and image processing methods for classifying GI tract diseases in recent times. Conventional data augmentation and image processing methods are integrated with adjusted pre-trained deep convolutional neural networks (CNNs) for classifying diseases in the GI tract from WCI images. This study presents a Modified Salp Swarm Algorithm with Deep Learning based Gastrointestinal Tract Disease Classification (MSSADL-GITDC) on Endoscopic Images. The presented MSSADL-GITDC technique mainly focuses on the examination of WCE images for GIT classification. To accomplish this, the presented MSSADL-GITDC technique applies median filtering (MF) technique for image smoothening. The presented MSSADL-GITDC technique designs improved capsule network (CapsNet) model for feature extraction where the CapsNet model is modified by the class attention layer (CAL). Moreover, MSSA based hyperparameter tuning process is performed to improve the efficiency of the improved CapsNet model. For GIT classification, deep belief network with extreme learning machine (DBN-ELM) was used. Finally, backpropagation is applied for supervised fine tuning of the DBN-ELM model. The experimental validation of the MSSADL-GITDC technique takes place on Kvasir-V2 database reported the betterment of the MSSADL-GITDC technique on GIT classification with maximum accuracy of 98.03%.

Availability Capacity Evaluation and Reliability Assessment of Integrated Systems Using Metaheuristic Algorithm

Contemporarily, the development of distributed generations (DGs) technologies is fetching more, and their deployment in power systems is becoming broad and diverse. Consequently, several glitches are found in the recent studies due to the inappropriate/inadequate penetrations. This work aims to improve the reliable operation of the power system employing reliability indices using a metaheuristic-based algorithm before and after DGs penetration with feeder system. The assessment procedure is carried out using MATLAB software and Modified Salp Swarm Algorithm (MSSA) that helps assess the Reliability indices of the proposed integrated IEEE RTS79 system for seven different configurations. This algorithm modifies two control parameters of the actual SSA algorithm and offers a perfect balance between the exploration and exploitation. Further, the effectiveness of the proposed schemes is assessed using various reliability indices. Also, the available capacity of the extended system is computed for the best configuration of the considered system. The results confirm the level of reliable operation of the extended DGs along with the standard RTS system. Specifically, the overall reliability of the system displays superior performance when the tie lines 1 and 2 of the DG connected with buses 9 and 10, respectively. The reliability indices of this case namely SAIFI, SAIDI, CAIDI, ASAI, AUSI, EUE, and AEUE shows enhancement about 12.5%, 4.32%, 7.28%, 1.09%, 4.53%, 12.00%, and 0.19%, respectively. Also, a probability of available capacity at the low voltage bus side is accomplished a good scale about 212.07 times/year.

Urban Rail Substation Parameter Optimization by Energy Audit and Modified Salp Swarm Algorithm

Auditing the energy consumption in urban rail is vital for energy consumption evaluation and system parameter design. There are multiple ways to audit energy consumption, but a universal and global approach is missing. The system-level traction energy consumption (STEC) is proposed. Compared to the main substation energy consumption (MSEC), STEC is more accurate by eliminating the influence of step-down loads based on field test studies. An optimization parameter designing model is built, which takes the system cost as the optimal object considering the life span of energy feedback system (EFS)s. The modified salp swarm algorithm (MSSA) is proposed as the optimization algorithm. The numerical tests show that MSSA has better converge performance than salp swarm algorithm (SSA) and particle swarm optimization (PSO). The impact factors of STEC are analyzed. Compared with SSA and PSO, the initial value of the MSSA is improved and it evolves faster. Compared with the case that does not take the no-load voltage of rectifiers and start voltage of EFSs as optimal parameters, the composite cost of the case that takes the abovementioned parameters as optimal parameters is 3.49% less. Compared to the system without EFSs, the optimal system with EFSs can save costs by 29.47%.

An efficient RBF‐DCNN based DOA estimation in multipath and impulse noise wireless environment

AbstractThe typical MultiPath (MP) propagation environment attains lots of MP signals as of the antenna array, and the Impulse Noise (IPN) accompanies these MP signals. The Directions‐of‐Arrivals (DOA) of an MP signal is tough to be assessed because of these IPN. Though numerous existing techniques were generated to assess the MP signal's DOA, they cannot attain a desirable output. To achieve robust and accurate DOA estimation (DOAE) in multipath and IPN wireless environment, this work proposes an efficient Radial Basis Function based Deep Convolutional Neural Network (RBF‐DCNN) centered DOAE. Here, initially, the noises in the inputted signal are eradicated utilizing Improved Particle Filter (IPF). After denoising, the imperative features are extracted as of that signal. Next, the required features are selected as of that signal, which is utilized for Dimension Reduction (DR). The Modified Salp Swarm Optimization Algorithm (MSSOA) is employed for feature selection. Then, the dimension reduced signal is inputted to the RBF‐DCNN, which estimated the DOA centered upon the received signal's SNR value. Numerical simulation outcomes are rendered to exemplify the proposed method's effectiveness.

A Comparative Analysis of a Hybrid System with Hybrid Methodologies

Economic Load Dispatch (ELD) is an important optimization problem in the energy system. Economic Dispatch (ED) is a short-term determination of the optimal performance of a set of power generation assets to meet the system load at the lowest possible cost, taking into account transmission and operational constraints. Economic dispatch problems are solved by dedicated computer software that needs to take into account the operational and system limitations of available resources and corresponding transmission functions. Economic load balancing provides optimal cost savings for power plant operations where methodologies can be applied in a variety of ways, from traditional to advanced. To achieve this, traditional methods have been used from the last few years to the 90's, but in the last few decades AI methods have met their needs and validated satisfactory results. Some advanced hybrid techniques used are the Modified Salp Swarm Optimization Algorithm (MSSA) with Artificial Intelligent (AI) technique aided with Particle Swarm Optimization (PSO) technique, Improved Moth-Fly Optimization Algorithm (IMFOA) with the Recurrent Neural Network (RNN), the Improved Fruit Fly Optimization Algorithm (IFOA) with Artificial Neural Network (ANN) system and Lightning Search Algorithm (LSA) with Genetic Algorithm (GA) which will encourage the researches for providing better solution for economic load dispatch problem is presented in this paper.

Techno-Economic and Environmental Analysis of Grid-Connected Electric Vehicle Charging Station Using AI-Based Algorithm

The rapid growth of electric vehicles in India necessitates more power to energize such vehicles. Furthermore, the transport industry emits greenhouse gases, particularly SO2, CO2. The national grid has to supply an enormous amount of power on a daily basis due to the surplus power required to charge these electric vehicles. This paper presents the various hybrid energy system configurations to meet the power requirements of the electric vehicle charging station (EVCS) situated in the northwest region of Delhi, India. The three configurations are: (a) solar photovoltaic/diesel generator/battery-based EVCS, (b) solar photovoltaic/battery-based EVCS, and (c) grid-and-solar photovoltaic-based EVCS. The meta-heuristic techniques are implemented to analyze the technological, financial, and environmental feasibility of the three possible configurations. The optimization algorithm intends to reduce the total net present cost and levelized cost of energy while keeping the value of lack of power supply probability within limits. To confirm the solution quality obtained using modified salp swarm algorithm (MSSA), the popularly used HOMER software, salp swarm algorithm (SSA), and the gray wolf optimization are applied to the same problem, and their outcomes are equated to those attained by the MSSA. MSSA exhibits superior accuracy and robustness based on simulation outcomes. The MSSA performs much better in terms of computation time followed by the SSA and gray wolf optimization. MSSA results in reduced levelized cost of energy values in all three configurations, i.e., USD 0.482/kWh, USD 0.684/kWh, and USD 0.119/kWh in configurations 1, 2, and 3, respectively. Our findings will be useful for researchers in determining the best method for the sizing of energy system components.