Hybrid GA-PSO Research Articles

Modular design and structural optimization of CubeSat separation mechanism

In order to achieve the design requirements of light weight and high stiffness of the CubeSat modular separation mechanism, a BPNN-GA-PSO size optimization method is proposed to optimize the design of the separation mechanism. Firstly, the separation mechanism of modularization and standardization is analyzed to select the optimization objects. Then, a hierarchical optimization strategy of topology optimization followed by size optimization is adopted to find the global optimum using a hybrid GA-PSO optimization algorithm. Meanwhile, the BPNN surrogate model is introduced to improve the optimization efficiency. The results show that the mass proportion of the optimized separation mechanism is reduced to 18 %, and the maximum deformation of the separation mechanism is 0.123 mm, which meets the design requirements of light weight and high stiffness of the separation mechanism. It proves the applicability of the optimization method to the optimal design of the separation mechanism. The CubeSat modular separation mechanism designed in this paper has been verified by ground verification with overload, vibration, and shock mechanical tests, and successfully deployed the BY-03 satellite in-orbit, which can provide reference for the design and development of subsequent CubeSat modular separation mechanisms.

Computational Morphogenesis of Lightweight Continous Concrete Shell Structures by Utilizing Metaheuristic Algorithms

While the hanging model and physical prototyping are reliable methods for form-finding continuous lightweight shell structures, they cannot explore various design possibilities and consider multiple criteria in the design. This research aims to employ metaheuristic algorithms as a search tool for simultaneous form-finding (form exploration) and optimization, known as computational morphogenesis. This workflow consists of a parametric model and metaheuristic algorithms, which were implemented through costume Python codes. To evaluate the workflow, a double-curvature footbridge was defined, and the forms that GA found were in line with the anticipation. The GA found a better solution (0.04022) than the SA (0.064) by considering elastic energy change. In case study II, the optimal form of a continuous lightweight shell was explored by utilizing GA, PSO, SA, and the hybrid algorithm of GAPSO. The GA improved the fitness solution by 35% in the second run, while PSO showed similar results, and the hybrid GAPSO algorithm did not yield better results. The results show that the optimum result based on different algorithms was not significantly different. Nevertheless, hyperparameters considerably affected finding the global minimum. Moreover, NSGA-II was utilized, which let the designer trade-off between alternatives while considering other criteria.

A modified multi-objective particle swarm optimization (M-MOPSO) for optimal sizing of a solar–wind–battery hybrid renewable energy system

This study proposes and utilizes a modified multi-objective particle swarm optimization (M-MOPSO) algorithm for the optimal sizing of a solar-wind-battery hybrid renewable energy system for a rural community in Rivers State, Nigeria. Unlike previous studies that primarily focused on minimizing total economic cost (TEC) and total annual cost (TAC), this research emphasizes minimizing the loss of power supply probability (LPSP) and levelized cost of energy (LCOE). The M-MOPSO algorithm introduces a dynamic inertia weight, a unique repository update mechanism, and a dominance-based personal best update strategy, which collectively enhance its performance. Comparative analysis with PSO, NSGA-II, MOPSO and hybrid GA-PSO demonstrates that M-MOPSO consistently achieves a lower LPSP, although its LCOE remains higher. The M-MOPSO optimal configuration when simulated under various climatic scenarios was able to meet the energy needs of the community irrespective of ambient condition.

New Methods for Optimal Power Allocation and Joint Resource Scheduling in 5G Network which Use Mobile Edge Computing

Mobile Edge Computing (MEC) is considered one of the enabling and promising technologies in 5G networks, especially with the massive data movement of various devices and the increased demand for computing. Here, computational offloading of tasks to edge clouds provides an effective, flexible, low-latency solution for mobile users in the network. However, the limited computing resources in edge clouds and the dynamic demands of mobile users make it difficult to schedule computing requests to appropriate edge clouds, and make the offloading process energetically expensive for devices. Therefore, it is very important to design an energy-efficient offloading strategy. To this end, we first formulate the transmission power allocation (PA) problem for mobile phone users to minimize power consumption. Using a quasi-convex technique, we address the (PA) problem using a (Hybrid GAPSO) algorithm resulting from combining the Genetic Algorithm (GA) with the Particle Swarm Optimization (PSO) algorithm. Next, we model the joint request offloading and resource scheduling (JRORS) problem as a mixed- nonlinear program to minimize the response delay of requests. The (JRORS) problem can be divided into two problems, namely the request offloading (RO) problem and the computing resource scheduling (RS) problem. Therefore, we analyze the JRORS problem as a dual decision problem and propose a multi-objective particle swarm optimization algorithm referred as (MO-PSO). The simulation results show that (HGAPSO) can save transmission power consumption and has good convergence property, and (MO-PSO) outperforms existing methods in terms of response rate and can maintain good performance in a dynamic network.

Two-step machine learning-assisted label-free surface-enhanced Raman spectroscopy for reliable prediction of dissolved furfural in transformer oil

Accurate detection of dissolved furfural in transformer oil is crucial for real-time monitoring of the aging state of transformer oil-paper insulation. While label-free surface-enhanced Raman spectroscopy (SERS) has demonstrated high sensitivity for dissolved furfural in transformer oil, challenges persist due to poor substrate consistency and low quantitative reliability. Herein, machine learning (ML) algorithms were employed in both substrate fabrication and spectral analysis of label-free SERS. Initially, a high-consistency Ag@Au substrate was prepared through a combination of experiments, particle swarm optimization-neural network (PSO-NN), and a hybrid strategy of particle swarm optimization and genetic algorithm (Hybrid PSO-GA). Notably, a two-step ML framework was proposed, whose operational mechanism is classification followed by quantification. The framework adopts a hierarchical modeling strategy, incorporating simple algorithms such as kernel support vector machine (Kernel-SVM), k-nearest neighbors (KNN), etc., to independently establish lightweight regression models on each cluster, which allows each model to focus more effectively on fitting the data within its cluster. The classification model achieved an accuracy of 100%, while the regression models exhibited an average correlation coefficient (R2) of 0.9953 and the root mean square errors (RMSE) consistently below 10-2. Thus, this ML framework emerges as a rapid and reliable method for detecting dissolved furfural in transformer oil, even in the presence of different interfering substances, which may also have potentiality for other complex mixture monitoring systems.

Improved PID Algorithm-intelligent Detection System of Tightening Machine

As the level of automation in manufacturing industry continues to improve, intelligent tightening technology is widely used in many fields. Research on torque, force and angle control technology for tightening machines focuses on designing sensitive detection systems, constructing control models and implementing accurate control of tightening parameters. This article proposes an optimized PID algorithm to improve tightening accuracy and stability. At the same time, an intelligent tightening machine monitoring system will be designed and developed to achieve online monitoring and control, ensuring tightening quality and stability. The system will use the latest technologies, including big data, cloud computing and artificial intelligence, to further optimize the tightening effect. The overshoot of PID control optimized by PSO-GA hybrid algorithm is 8.367% , which is far less than that of PID control alone, it is shown that the PSO-GA hybrid algorithm has higher accuracy and better robustness.

Research on optimization model based on heliostat field

Tower solar power system (SPT) is a new type of clean energy technology with low carbon and environmental protection. In this context, it is very meaningful to explore how to arrange an efficient heliostat field and set the heliostat parameters, because the improvement here can improve the average optical efficiency of the heliostat field and collect thermal energy. In this paper, under the constraint of circular layout area, the solar energy transmission model of heliostat and the comprehensive optical efficiency model of heliostat field are established by coordinate system transformation method, Monte Carlo algorithm and HFLCAL calculation model. Then, considering the optimal layout scheme of the heliostat field, the EB layout is used to establish the basic layout of the heliostat field, and the heliostat with high comprehensive optical efficiency and meeting the actual use requirements is selected by the step-by-step traversal algorithm. Subsequently, the heliostat height, heliostat width, installation height and heliostat installation height difference between adjacent areas are introduced into the optimization model as particles, and then the PSO-GA hybrid optimization algorithm is used to approximate the optimal design of the SPT system. The goal of optimizing the comprehensive optical efficiency of the heliostat field and the output thermal power per unit area of the SPT system is achieved.

A hybrid cloud load balancing and host utilization prediction method using deep learning and optimization techniques

Virtual machine (VM) integration methods have effectively proven an optimized load balancing in cloud data centers. The main challenge with VM integration methods is the trade-off among cost effectiveness, quality of service, performance, optimal resource utilization and compliance with service level agreement violations. Deep Learning methods are widely used in existing research on cloud load balancing. However, there is still a problem with acquiring noisy multilayered fluctuations in workload due to the limited resource-level provisioning. The long short-term memory (LSTM) model plays a vital role in the prediction of server load and workload provisioning. This research presents a hybrid model using deep learning with Particle Swarm Intelligence and Genetic Algorithm (“DPSO-GA”) for dynamic workload provisioning in cloud computing. The proposed model works in two phases. The first phase utilizes a hybrid PSO-GA approach to address the prediction challenge by combining the benefits of these two methods in fine-tuning the Hyperparameters. In the second phase, CNN-LSTM is utilized. Before using the CNN-LSTM approach to forecast the consumption of resources, a hybrid approach, PSO-GA, is used for training it. In the proposed framework, a one-dimensional CNN and LSTM are used to forecast the cloud resource utilization at various subsequent time steps. The LSTM module simulates temporal information that predicts the upcoming VM workload, while a CNN module extracts complicated distinguishing features gathered from VM workload statistics. The proposed model simultaneously integrates the resource utilization in a multi-resource utilization, which helps overcome the load balancing and over-provisioning issues. Comprehensive simulations are carried out utilizing the Google cluster traces benchmarks dataset to verify the efficiency of the proposed DPSO-GA technique in enhancing the distribution of resources and load balancing for the cloud. The proposed model achieves outstanding results in terms of better precision, accuracy and load allocation.

Estimation of land subsidence using coupled particle swarm optimization and genetic algorithm: The case of Damghan aquifer

Abstract Land subsidence, which is mainly caused by over-extraction of groundwater, is one of the most important problems in arid and semi-arid regions. In the present study, seven factors affecting the land subsidence, i.e., types of subsoil, land use, pumping, recharge, thickness of the plain aquifer, distance to the fault, and groundwater depletion were considered as input data for the ALPRIFT framework and intelligence models to map both Subsidence Vulnerability Index (SVI) and prediction of land subsidence, respectively. The hybrid of particle swarm optimization (PSO) and genetic algorithm (GA) (Hybrid PSO-GA) was then used to optimize the weights of the input layers and the estimation of the land subsidence. The capability of the PSO-GA at predictions of land subsidence compared with the typical GA model, and Gene Expression Programming (GEP). The statistical indices R2, RMSE, and MAE were used to assess the accuracy and reliability of the applied models. The results showed that the Hybrid PSO-GA model had R2, RMSE, and MAE equal to 0.91, 1.11 (cm), and 0.94 (cm), respectively. In comparison with the GA, and GEP models, the Hybrid PSO-GA model improved the prediction of land subsidence and reduced RMSE by 24.30 and 16.80%, respectively.

A comparative study on hybrid GA-PSO performance for stand-alone hybrid energy systems optimization

A comparative study on hybrid GA-PSO performance for stand-alone hybrid energy systems optimization

A Hybrid GAPSO Optimization Approach

In this work, the hybrid techniques of genetic algorithm (GA) and particle swarm optimization (PSO) are presented. PSO and GA are two population-based heuristic search methods that can be applied to the channel allocation optimization problem. GAPSO is based on a mixture of particle swarm optimization (PSO) and genetic algorithms (GA). Individuals of a new generation are produced in GAPSO by PSO in addition to crossover and mutation operations as in GA. In order to reduce the number of blocked calls and handoff failures in the mobile network, the Hybrid GAPSO algorithm is used to allocate tasks to resources efficiently. The proposed strategy optimizes the channel allocation using the GAPSO.

Optimizing Distributed Generation Resources for Power Grid Quality Improvement Using Hybrid Optimization Technique

Distributed generation (DG) integration is a critical requirement in modern distribution networks to enhance power grid quality. An essential aspect of this endeavor involves strategically placing and sizing various DG resources optimally. The primary objective of this study is to determine an efficient approach for allocating Photovoltaic (PV) and Wind Turbine resources to minimize overall power losses within the grid. To achieve this goal, we introduce a novel hybrid optimization technique that combines Particle Swarm Optimization (PSO) with Genetic Algorithms (GAs). Furthermore, we explore the influence of factors such as variations in PV daily consumption, load profile fluctuations, penetration levels, and changing climatic conditions on the optimization process across two comprehensive case studies presented in this research. Our modeling results reveal that the hybrid PSO-GA approach outperforms traditional PSO in terms of integration speed, power loss reduction, and enhancements to grid quality, including voltage and frequency profiles. Additionally, this study highlights the dynamic impact of load curve fluctuations and climate changes on the optimal location and capacity of DG resources, leading to a substantial reduction in grid power losses.

Hybrid GA-PSO method with local search and image clustering for automatic IFS image reconstruction of fractal colored images

AbstractOver the past few decades, the application of iterated function systems (IFS) in reconstructing fractal images has been a challenging research area. Numerous methods have been proposed to address this issue. However, they generally focus on binary or grayscale images, neglecting the color component of the process. Consequently, they are unsuitable for reconstructing colored images. In a previous paper presented at the ISCMI 2021 conference, the authors introduced a novel approach that utilizes the cuckoo search algorithm and k-means clustering for IFS fractal reconstruction of colored images. Building upon that work, this paper introduces an enhanced and extended method by combining genetic algorithms (GAs) and particle swarm optimization (PSO) with local search and image clustering. In this approach, GA and PSO are mutually coupled to automatically determine the color of the contractive functions and the IFS parameters, respectively. The output of each method serves as the input for the other in an iterative manner. Main contributions of this method are: (1) it computes automatically the optimal number and IFS code of the contractive functions; (2) the color of the contractive functions is determined automatically through an optimization process using GA; (3) a local refinement step is performed to further enhance the final solution. Overall, this new method yields highly accurate results in reconstructing the geometry and color of input fractal images, without requiring any additional information about the target beyond the bitmap image.

A Novel Hybrid GA-PSO Algorithm-Based Optimization of Transmission and Expansion Planning

A Novel Hybrid GA-PSO Algorithm-Based Optimization of Transmission and Expansion Planning

Modeling and Verification of Electromagnetic-Thermal Coupling for Electromagnetic Track Launch Considering the Dynamic Conductivity

In order to solve the problems of insufficient precision of the armature velocity and inductance gradient in the process of finite element calculation of the electromagnetic track launcher, an improved dynamic conductivity electromagnetic-thermal coupling model is proposed to make the calculated results closer to the actual working condition. Firstly, the finite element analysis for the electromagnetic-thermal field is carried out. Then, considering the influence of dynamic conductivity on the armature velocity and inductance gradient, an improved dynamic conductivity electromagnetic-thermal coupling model based on finite element analysis is established, whose parameters are identified by the proposed PSO-GA hybrid algorithm. Moreover, the predicted values of armature velocity and inductance gradient are also obtained. Finally, the experimental platform of the electromagnetic track launcher is built to verify the improved model. By comparing the predicted value of the improved model with the experimental test value, it is found that the improved model can further reduce the calculated error from 5.79% to 1.18%, which provides a certain theoretical basis for the full true simulation of the electromagnetic track launch.

Discrete grey wolf optimization algorithm for solving k-coverage problem in directional sensor networks with network lifetime maximization viewpoint

Unlike the traditional wireless sensor networks (WSNs) which apply omni-directional sensors, the directional sensor networks (DSNs) utilize directional sensor nodes. Each directional sensor in DSN is a self-configured in one direction and one coverage range at a same time. In critical industries, the target coverage problem in which every target should be observed by k different sensors increases the reliability and leads the fault tolerant observation. In this case, the huge amount of energy is consumed in comparison with one coverage problem. Since the business continuity in such industries strongly depends on the network lifetime, the energy management and lifetime maximization of such resource-limited networks are still of the most important challenges. To address the issue, this paper formulates the k-coverage challenge to a discrete optimization problem with the network lifespan expansion viewpoint which is an NP-Hard problem. To solve this combinatorial problem, a discrete grey wolf optimization algorithm (D-GWA) is presented. This D-GWA proposes abundant novel exploration and exploitation procedures which permutes discrete search space efficiently. In this regard, the new fitness function is also defined which steers solutions in the directions to engage sensors uniformly in different rounds. It potentially improves network lifetime because of uniform battery usage. During the course of optimization, it utilizes temperature concept of simulated annealing algorithm to running away from local trap. To verify the proposed algorithm in solving k-coverage problem in DSNs, twelve scenarios are conducted. The simulation results experimentally prove that the totally dominance of the proposed algorithm against state-of-the-arts HTOH, LA-based, GWA, and hybrid PSO-GA approaches respectively are the amount of 31.37%, 20.97%, 14.12%, and 7.93% improvement in term of network lifetime expansion. Furthermore, the behavior of D-GWA shows the high potential of scalability in the larger search space.

GA-ABC hybridization for profit maximization of green 4DTSPs with discrete and continuous variables

A medical or business representative visits and spends some time (termed ‘stay time’) at different cities(nodes) for optimum return. With the rapid development of infrastructures worldwide, several vehicles and routes are available for transport between nodes. Road logistic transportation contributes 10.5% of the total emitted carbon emission (CE)11https://rb.gy/zlohdl.,22https://rb.gy/yjbdev.,33https://doi.org/10.1051/e3sconf/202233600060.. Heuristic method is applied to solve NP-hard problems with continuous/discrete variables. With these facts, here, CE/tour-time constrained profit maximization of green four-dimensional Travelling Salesman Problems (PMG4DTSPs) with both discrete (travel times between nodes) and continuous (stay-times at nodes) variables are formulated. A travelling salesman visits all cities using the appropriate routes and conveyances, spend some time at each node, and some revenues are earned and spent depending upon the stay time at those visiting places. There are toll plazas on the roads, where three types of fixed charges (online, offline, mixed online–offline) are collected as road taxes to maintain the roads. A green constraint is incorporated in the form of limited emission. Several connecting routes between the cities and conveyances at each city are available for travel. Thus, these (PMG4DTSPs) are mixed integer linear programming problems (NP-hard), and to solve them, two hybrid heuristic methods, GA-ABC and GA-PSO, are developed and used. Here, GA and ABC/PSO are used for optimum routing plan and stay time, respectively. The models are illustrated numerically. Multi-path justification, online payment advantage and tour time limitation effect on profit are presented. Some behavioural studies of Green models and managerial decisions are presented.

A hybrid GA-PSO strategy for computing task offloading towards MES scenarios.

As a new type of computing paradigm closer to service terminals, mobile edge computing (MEC), can meet the requirements of computing-intensive and delay-sensitive applications. In addition, it can also reduce the burden on mobile terminals by offloading computing. Due to cost issues, results in the deployment density of mobile edge servers (MES) is restricted in real scenario, whereas the suitable MES should be chosen for better performance. Therefore, this article proposes a task offloading strategy under the sparse MES density deployment scenario. Commonly, mobile terminals may reach MES through varied access points (AP) based on multi-hop transmitting mode. The transmission delay and processing delay caused by the selection of AP and MES will affect the performance of MEC. For the purpose of reducing the transmission delay due to system load balancing and superfluous multi-hop, we formulated the multi-objective optimization problem. The optimization goals are the workload balancing of edge servers and the completion delay of all task offloading. We express the formulated system as an undirected and unweighted graph, and we propose a hybrid genetic particle swarm algorithm based on two-dimensional genes (GA-PSO). Simulation results show that the hybrid GA-PSO algorithm does not outperform state-of-the-art GA and NSA algorithms in obtaining all task offloading delays. However, the workload by standard deviation approach is about 90% lower than that of the GA and NSA algorithms, which effectively optimizes the performance of load balancing and verifies the effectiveness of the proposed algorithm.

Development of two stage optimization-based demand response technique for smart homes under real time pricing

Residential load management deals with two major objectives viz. minimizing the cost of monthly electricity bill and peak demand of power consumption. Both objectives can be achieved by effective operational scheduling of smart home appliances. These two objectives are conflicting in nature because rescheduling of appliances in order to minimize one objective may result in the rise of another. To achieve both objectives concurrently, an algorithm is suggested in this paper based on artificial intelligent techniques like cuckoo search, hybrid GA-PSO, and adaptive cuckoo search. The proposed algorithm is tested successfully on seven households of different monthly power consumption and real data of dynamic pricing options for electricity applicable in two utilities. To reduce the risk associated with real-time price, a cost function based on inclining block rates (IBR) is also suggested for both the utilities. A novel approach to find the threshold limit of hourly power consumption is also suggested in this paper. The proposed algorithm solves the optimization problem in two stages and validates its performance by successfully achieving both objectives simultaneously.

Long Short-Term Memory Network Hyperparameter Optimization using Hybrid Algorithm GA-PSO on LQ45 Stock Prediction

Stock is a good investment tool, keeping money from inflation, and very trendy to earn a living nowadays by becoming a trader. There is always a risk, especially when trading, because stocks can fluctuate easily depending on the company. One of the data science capabilities, prediction modeling, can help lower the risk by predicting the stock price movement. This research proposed a prediction sequential data model, an optimized hyperparameter LSTM Network using hybrid GA-PSO (LSTM-GA-PSO). Hybrid GA-PSO aims to overcome the GA problem in terms of slow execution time and PSO that tend to be trapped in the local optimum. With the characteristics of both algorithms, the hybrid algorithm can solve each other algorithms downside. The low fluctuation stock of the Indonesian Index LQ45 dataset will be used to train and test the model and compare the proposed model with LSTM-GA and LSTM-PSO. Experiment results show that the hybrid LSTM-GA-PSO has a promising performance. Hybrid GA-PSO improved 18.18% of its time execution to GA and 29.07% accuracy to PSO.