Self-adaptive Genetic Algorithm Research Articles

Aerodynamic optimization of double S-duct caret intake by self-adapting non-dominated sorting genetic algorithm

The caret intake could not only provide compressed airflow to the aircraft engine stably but also should have applicable radar stealth performance. Radar stealth means that the echo intensity of the intake should be low when detected by radar, which could be measured by radar cross section (RCS). The airflow distribution of the double S-duct caret intake was numerically optimized to improve aerodynamic performance, with radar stealth performance as constraints. Self-adaptive genetic algorithm and Kriging model were used to improve the optimization efficiency. There could be multiple boundary-layer separations in the S-duct caret intake, resulting in obvious total pressure distortion at the outlet and secondary flow. To suppress these adverse airflow phenomena, the optimization of the double S-duct intake was defined as a problem with two targets and multiple constraints. By defining the probabilities of selection and variation as functions of the iteration number and the fitness, the self-adapting non-dominated sorting genetic algorithm can be applicable for such a problem. Using the Kriging model, which was proven to have satisfactory accuracy in predicting performance parameters, an optimized intake with both excellent aerodynamic and stealth performance was obtained, with a 30% reduction in DC60 value and a 47% reduction in SC60 value compared to the intake before optimization.

HRMF-DRP: A next-generation solution for overcoming provisioning challenges in cloud environments

The cloud computing infrastructure is a distributed environment and the existing research works have some provisioning problems such as suboptimal resource utilization and high execution time. The Heterogeneity Resource Management Framework for Dynamic Resource Provisioning (HRMF-DRP) is proposed for focusing on task scheduling and workload management. This framework incorporates advanced algorithms for dataset preprocessing, task clustering, workload prediction, and dynamic resource provisioning. For data preprocessing, the real-world workload traces were captured from the Planet Lab dataset that are taken as input for the preprocessing stage. The data preprocessing is responsible for ensuring data quality and reliability by using different models like missing data handling, outlier detection and removal as well as standardization and normalization. In this paper, the tasks are grouped into clusters by utilizing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model and this model categorizes the data points into border points, core points and noise points based on their density. The temporal dependencies are captured for the workload prediction by using Long Short-Term Memory (LSTM) neural network model. A Gaussian Mixture Model (GMM) model is responsible for estimating the number of Virtual machines (VMs) present in the workload prediction process. The Self-Adaptive Genetic Algorithm (SAGA) is implemented for task mapping that adjusts the parameters to change workload patterns for contributing adaptability and robustness. The different experimental evaluations are conducted based on the task completion time, workload balance index, resource utilization efficiency and workload prediction accuracy. The proposed model achieved the workload prediction accuracy of 98.5%, cost of $89.6, execution time of 125ms, Task Completion Time (TCT) of 40ms, Workload Balance Index (WBI) of 0.96 and Resource Utilization Efficiency (RUE) of 0.93. The quantitative results collectively position HRMF-DRP as a practical and efficient solution, promising advancements in dynamic resource provisioning for cloud computing, particularly within the Infrastructure as a Service (IaaS) cloud model.

Retraction Note: A self-adaptive genetic algorithm with improved mutation mode based on measurement of population diversity

Retraction Note: A self-adaptive genetic algorithm with improved mutation mode based on measurement of population diversity

Wind farm power density optimization according to the area size using a novel self-adaptive genetic algorithm

This work studies the power density (PD) optimization in wind farms, and its sensitivity to the available area size. A novel genetic algorithm (PDGA) is introduced, which optimizes PD and the turbine layout, by self-adapting to the PD and to the solutions diversity. PDGA uses the levelized cost of energy (LCOE) as cost function, which in turn employs the EPFL analytical wake model to derive the power output. For the baseline area size, PDGA reduces 2.25% the original LCOE, 2.6 times more than optimizing with constant PD. PDGA-driven solutions provide 11% and 6% LCOE reductions against the default layout for the smallest (6.4 km2) and largest (386 km2) scaled wind farm areas, respectively. Specially relevant for the industry, PDGA solutions depict convex fronts for area vs. LCOE or vs. PD, which allows determining the required area or turbine number given a target LCOE. Unlike default layouts, optimized ones reveal a linear relationship between LCOE and PD. The mean turbine spacing tends to 8-9D for very large areas. The economics-optimized PDs are below the estimated PD available in the atmosphere. This work is limited to a simplified, offshore wind climatology, a specific wind turbine model, and the LCOE specifications used herein.

Research on the optimization and practice of mathematical modeling curriculum systems based on the perspective of big data

Abstract Today’s society is undergoing rapid changes from the information age to the big data age and the intelligence age, and some new requirements and challenges are faced by mathematical modeling curriculum teaching in talent training in the big data age. In this paper, we propose a self-adaptive genetic algorithm scheme for the optimization of a mathematical modeling curriculum system, which is mainly reflected in re-planning and designing the constraints for the optimization of the mathematical modeling curriculum, optimizing and improving the initialization population, selection operator, crossover operator, and variation operator processes. The crossover probability at 0.8, the optimal value of individual fitness and the average value of fitness of the group are both maximum, and the variation probability at 0.01, the optimal value of individual fitness and the average value of fitness of mathematical modeling are both maximum, which indicates that this crossover probability and variation probability are better in the quality of the self-adaptive genetic algorithm. This Study is a guiding reference for the research on the optimization and practical exploration of mathematical modeling curriculum systems in colleges and universities and thus is of historical importance to promote the development of Chinese mathematics.

Construction of a personalized learning platform based on genetic algorithm for specialized education in industrial colleges in the context of industry-education integration

Abstract Under the progress trend of the information technology period environment of deepening study curriculum reform, personalized learning in specialized education of industrial colleges has become one of its key contents. This paper mainly studies the necessary system design based on characteristics of genetic calculation for specialized education in industrial colleges under industry-education integration. This paper first introduces the principle of genetic algorithm. It then proceeds to introduce in detail the shortcomings of The advantage of this calculation method is that the standard calculation tendency is unable to move forward in an area extremes, the iteration is relatively slow, and the low accuracy when dealing with optimization problems. Then the design and construction ideas of the personalized platform and the database design from Learners, educators (teachers), and administrators are compared by experimentally analyzing the data diversity and convergence of the three algorithms on the database. Experimentally, the diversity of the self-adaptive genetic algorithm is maintained at 0.8, and the diversity, iteration time, and convergence standard are better compared with the comparison subject. Using a self-adaptive genetic algorithm to evaluate and rank learners’ personality differences and to provide and recommend suitable learning methods for learners helps develop education and improve teaching quality and has great historical significance for China’s development and international status.

Hybrid Electric Vehicle Energy Control System based on Minimum Energy Use Rate

This research proposes an energy control method for hybrid electric automobiles with the objective of minimizing energy consumption rate. The method involves three main steps: (1) measuring energy source parameters under various driving conditions in a real automobile, (2) optimizing the efficiency of three energy sources based on power and energy consumption rate using a self-adaptive genetic algorithm, and (3) implementing an energy switching system to distribute energy during real-world driving based on State of Charge (SOC) and power demands of the hybrid system. The proposed method allows for rapid adaptation to real-world conditions, ensuring optimal operation of the multi-energy automobile and offering significant practical engineering value.

Genetic algorithms with self-adaptation for predictive classification of Medicare standardized payments for physical therapists

We present a self-adaptive genetic algorithm for the problem of predicting if a Medicare standardized payment to a physical therapist will be above or below the national median. The percentage of Americans 65 and over is expected to increase in the coming years, increasing the need for physical therapy services. As a result, accurate prediction of expected Medicare payments based on local factors will be of increasing importance. A self-adaptive genetic algorithm is an evolutionary algorithm in which some or all of the algorithm’s parameters are evolved over the course of its execution. Self-adaptation is a useful tool both for improving the performance of evolutionary algorithms, as well as improving usability through lessening the amount of parameter tuning required of the algorithm’s user. While other self-adaptive approaches tend to focus on self-adaptation of only a few parameters, our approach self-adapts all of the parameters related to crossover and mutation. We compare the performance of our self-adaptive genetic algorithm with that of logistic regression and a canonical genetic algorithm on the problem of predicting Medicare payments. Logistic regression is a commonly used benchmark for this type of problem and a canonical genetic algorithm is included to allow us to see if any performance costs arise from the self-adaptive mechanisms. Results show that our self-adaptive genetic algorithm is effective at the classification of Medicare standardized payments to physical therapists, achieving accuracies of over 93%. Performance remains strong with training sets as small as 5% of the full data set. The problem representation used by our method allows for the identification of the relevant features for classification which means that our approach is capable of simultaneously performing classification and feature selection.

Short-Term Hydro-Thermal-Solar Scheduling with CCGT Based on Self-Adaptive Genetic Algorithm

This paper presents a new metaheuristic approach based on a self-adaptive genetic algorithm (SAGA) for solving the short-term hydro-thermal-solar scheduling with combined-cycle (CCGT) units. First of all, the proposed approach is applied to a test system with different characteristics, considering the valve-point effect. The simulation results obtained from the new SAGA are compared with the results obtained from some other metaheuristic methods, such as AIS, DE, and EP to reveal the validity and verify the feasibility of the proposed approach. The test results show that the proposed metaheuristic approach proves the effectiveness and superiority of the SAGA algorithm for solving the short-term hydro-thermal-solar scheduling (SHTSS) problem.

Wind farm layout and unconstrained hub height optimization using genetic algorithms applied to different power densities

LES and wind tunnel studies have shown significant benefit when allowing turbines (T) in a wind farm to adopt different heights. This work presents two new genetic algorithms (GA) that perform wind farm layout optimization (WFLO) involving continuous and top-unconstrained Z-coordinate (XYZ-WFLO), applied to different power densities (PD) and using Horns Rev 1 as case study. One provides each turbine the possibility to adopt any height (XYZInd ). The other is a self-adaptive GA allowing turbines to automatically cluster into a fixed number of maximum heights (XYZClus). When considering 80T, compared to the baseline the levelized cost of energy (LCOE) is reduced up to 2.3% (XYZInd ), vs. a 0.88% improvement obtained through XY-WFLO. XYZClus shows performances close to XYZInd even with just 2 Z-clusters (2%), which can entail a more feasible solution for the industry. The allowance for different heights exerts the main role in the performance improvement, in contrast to merely allowing turbines to increase their height. Results considering different PD yield the optimum XYZ-WFLO performance through 70T (2.5% LCOE decrease), while XY-WFLO provides best results considering 60T (1.5%). This indicates that the most efficient XYZ-WFLO solution also allows for bigger power productions. The benefit of XYZ-WFLO against XY-WFLO increases with PD. The optimized solutions arrange turbines into very few different heights, whose amount is positively related to PD. Finally, it is verified that the solutions attained reproduce the vertically staggered patterns proposed in conceptual studies (LES, wind tunnel).

Focusing through disturbed multimode optical fiber based on self-adaptive genetic algorithm

In terms of the imaging resolution and miniaturization, multimode fiber outperforms single-mode fiber bundles. However, fiber disturbance has always been a challenge to multimode fiber imaging. The great majority of existing algorithms are incapable of dealing with abrupt and strong perturbations from outside. In this paper, a self-adaptive genetic algorithm is proposed. When the environment changes rapidly, additional new elements can be introduced, preventing the optimization from being trapped in a local optimum. The effectiveness of the algorithm is verified by simulation. The experimental results indicate that it enables the speckle pattern to refocus better when the fiber is perturbed. The algorithm can also be used to transmit images. Our research will facilitate the advancement of detection technology using multimode optical fiber in the industrial and medical domains.

Intelligent and Improved Self-Adaptive Anomaly based Intrusion Detection System for Networks

With the advent of digital technology, computer networks have developed rapidly at an unprecedented pace contributing tremendously to social and economic development. They have become the backbone for all critical sectors and all the top Multi-National companies. Unfortunately, security threats for computer networks have increased dramatically over the last decade being much brazen and bolder. Intrusions or attacks on computers and networks are activities or attempts to jeopardize main system security objectives, which called as confidentiality, integrity and availability. They lead mostly in great financial losses, massive sensitive data leaks, thereby decreasing efficiency and the quality of productivity of an organization. There is a great need for an effective Network Intrusion Detection System (NIDS), which are security tools designed to interpret the intrusion attempts in incoming network traffic, thereby achieving a solid line of protection against inside and outside intruders. In this work, we propose to optimize a very popular soft computing tool prevalently used for intrusion detection namely Back Propagation Neural Network (BPNN) using a novel machine learning framework called “ISAGASAA”, based on Improved Self-Adaptive Genetic Algorithm (ISAGA) and Simulated Annealing Algorithm (SAA). ISAGA is our variant of standard Genetic Algorithm (GA), which is developed based on GA improved through an Adaptive Mutation Algorithm (AMA) and optimization strategies. The optimization strategies carried out are Parallel Processing (PP) and Fitness Value Hashing (FVH) that reduce execution time, convergence time and save processing power. While, SAA was incorporated to ISAGA in order to optimize its heuristic search. Experimental results based on Kyoto University benchmark dataset version 2015 demonstrate that our optimized NIDS based BPNN called “ANID BPNN-ISAGASAA” outperforms several state-of-art approaches in terms of detection rate and false positive rate. Moreover, improvement of GA through FVH and PP saves processing power and execution time. Thus, our model is very much convenient for network anomaly detection.

Automatic Building of a Powerful IDS for The Cloud Based on Deep Neural Network by Using a Novel Combination of Simulated Annealing Algorithm and Improved Self- Adaptive Genetic Algorithm

Cloud computing (CC) is the fastest-growing data hosting and computational technology that stands today as a satisfactory answer to the problem of data storage and computing. Thereby, most organizations are now migratingtheir services into the cloud due to its appealing features and its tangible advantages. Nevertheless, providing privacy and security to protect cloud assets and resources still a very challenging issue. To address the aboveissues, we propose a smart approach to construct automatically an efficient and effective anomaly network IDS based on Deep Neural Network, by using a novel hybrid optimization framework “ISAGASAA”. ISAGASAA framework combines our new self-adaptive heuristic search algorithm called “Improved Self-Adaptive Genetic Algorithm” (ISAGA) and Simulated Annealing Algorithm (SAA). Our approach consists of using ISAGASAA with the aim of seeking the optimal or near optimal combination of most pertinent values of the parametersincluded in building of DNN based IDS or impacting its performance, which guarantee high detection rate, high accuracy and low false alarm rate. The experimental results turn out the capability of our IDS to uncover intrusionswith high detection accuracy and low false alarm rate, and demonstrate its superiority in comparison with stateof-the-art methods.

Short-Term Hydro-Thermal-Solar Scheduling with Ccgt Based on a Novel Self-Adaptive Genetic Algorithm

Short-Term Hydro-Thermal-Solar Scheduling with Ccgt Based on a Novel Self-Adaptive Genetic Algorithm

Automated defect detection and classification for fiber-optic coil based on wavelet transform and self-adaptive GA-SVM.

The quality monitoring of fiber-optic coil (FOC) in winding systems is usually done manually. Aiming at the problem of inefficient and low accuracy of manual detection, this article is dedicated to researching a defect detection framework based on machine vision, which provides a reliable method for automatic defect detection of FOC. For this purpose, a defect detection scheme that integrates wavelet transform and nonlocal means filtering is proposed to accurately locate the defect region. Then, based on the features constructed by wavelet coefficients, a support vector machine (SVM) is used as the classifier. Additionally, a self-adaptive genetic algorithm is proposed to optimize the parameters of the SVM to form the final classifier. Through experiments on the data set obtained by our designed imaging system, the results show that our method has good defect detection performance and high classification accuracy, which provides an optimal solution for the automatic detection of FOC.

ASEAN logistics network model and algorithm

Reasonable layout of logistics centers in the ASEAN countries has important practical significance for improving logistics network efficiency and reducing logistics transportation costs. This paper based on the current status of the ASEAN logistics network and the characteristics of the hub-and-spoke network, taking the minimum total cost as the optimization goal, establishing the central location model, and the design self-adaptive genetic algorithms to solve it. Therefore, the number of central nodes in the ASEAN logistics network has been determined, the radiation range between nodes, and route allocation. The results indicate that the ASEAN network layout model is a hub-and-spoke logistics network. With Singapore as the logistic center hub node. Jakarta logistics development belt will form the main radiating logistics demand cities of Kuching and Ho Chi Minh city. Kuala Lumpur logistics development belt’s main radiating logistics demand cities will be East Kalimantan and Da Nang city. Chon Buri logistics development belt mainly radiates the cities of Phnom Penh and Riau city. Bangkok logistics development belt mainly radiates the cities of Hanoi, Vientiane, and Yangon city.

An approximation to the use of self-adaptive genetic algorithms in weight optimization of 3-D steel trusses

An approximation to the use of self-adaptive genetic algorithms in weight optimization of 3-D steel trusses

Designing and Modelling of Delta Wing Genetic-Based Prediction Model

The designing and modeling of delta wing is one of the interesting topics. A number of researchers has contributed different works on modeling the same. This paper comes out with a new delta wing modeling with the inclusion of optimization concept. The obtained data from the investigation is integrated and given as the input to the classifier for predicting the drag and lift coefficients. This paper uses neural network (NN) classifier for predicting the drag and lift coefficients. Moreover, the weight of the NN is optimized using a proposed genetic algorithm. After the implementation, the performance of proposed model is compared to other conventional methods like individual adaptive genetic algorithm (IAGA-NN), deterministic adaptive genetic algorithm (DAGA-NN), self-adaptive genetic algorithm (SAGA-NN), genetic algorithm (GA-NN), gradient descendent (GD-NN), and Levenberg masquerade (LM-NN), respectively, in terms of drag and lift coefficient.

An Improved Anti-counterfeiting Printed QR Watermarking Algorithm Based on Self-Adaptive Genetic Algorithm

To solve watermarking parameters optimization problem and enhance anti-counterfeiting performance, a self-adaptive genetic algorithm is proposed and introduced to improve robust QR code watermarking scheme. In the improved scheme, we adaptively change the genetic algorithm procedure according to the relation between the maximum fitness value and the average fitness value of a population. With the improved genetic algorithm procedure, it is easier to get better diveisity. In addition, mutation probability as well as crossover probability is adaptively modified to quickly seek out the optimal watermarking parameters. The tests indicate that the decoding rate of QR code noticeably increases without degrading detecting rate of digital watermark with the improved anti-counterfeiting printed QR code watermarking scheme.

A Collaborative Optimization Strategy for Energy Reduction in Ironmaking Digital Twin

The expenses of pig iron manufacturing stay in a relatively high level due to the large consumption of coke and ore. There are a variety of methods to optimize the ironmaking process, including multi-indexes method, production-oriented approach, and cost control strategy. In order to reduce the production cost, we optimize the raw materials supply schedule of an ironmaking plant with five sintering machines and seven blast furnaces. The ironmaking plant used to fix the feeding system, leading to an inefficient operation and mismatched connection between these two procedures. At first, the physical characteristics of each blast furnace is captured by linear regression model. Then, a self-adaptive genetic algorithm with variable population size is constructed under distribution system. Finally, the improved genetic algorithm is applied to optimize the total production cost represented by the aggregation of seven coke ratios on a cloud computing platform. With the application of this cloud collaborative optimization framework, the mean coke ratio of the ironmaking factory has decreased 13.96kg/t Fe.