Elitist Genetic Algorithm Research Articles

Modeling demand responsive service for the elderly healthcare activities considering temporal and spatial variations

ABSTRACT This paper develops a cost-effective demand-responsive transportation (DRT) model aimed at enhancing the accessibility and convenience of clinical visits for the elderly by optimizing two NP-hard problems. First, a set of pick-up stops is optimized based on potential stop locations, spatial and temporal demand, and acceptable walking distance. Next, vehicle routing and scheduling are optimized, considering vehicle capacity, users’ desired arrival times, and travel companions, to minimize total costs. An elite genetic algorithm (EGA) is developed to effectively search for the optimal solution. In the case study, demands are generated from a survey on elderly clinical visits and population census data in Xi’an. The proposed EGA is applied to different clustered demands classified by time interval to identify optimal solutions. Sensitivity analysis is conducted to explore the relationships between model parameters and decision variables for the studied DRT system.

Towards maximum cost-effectiveness: multi-objective design optimisation of insulating glass flat-plate collectors

A significant challenge in the advancement of solar thermal heating systems lies in the unexplored techno-economic potential of insulating glass flat-plate collectors. These collectors are constructed in accordance with the specifications of standard insulating glass units and have emerged over the past decade as a promising design concept for enhancing the cost-effectiveness of solar thermal systems. However, substantial findings regarding the techno-economic viability of their production are still pending. The aim of this paper is to optimise insulating glass collector designs for solar district heating applications by identifying key design parameters that maximise cost-effectiveness. This study employed a five-stage methodology. It included thermo-hydraulic collector modelling using MATLAB/Simscape and the CARNOT Toolbox. The model was validated against experimental performance tests. A Latin hypercube computational design with 250,000 samples was set up to train supervised machine learning metamodels and perform a multi-objective optimisation using an elitist genetic algorithm. The study identified the argon concentration, collector length, and width as critical parameters influencing efficiency. Larger, thinner collectors demonstrated superior performance due to reduced convective losses and increased aperture-to-surface ratios. The optimisation revealed that the insulating glass collectors could achieve a 7.7 percentage point increase in efficiency, a 19.4 % reduction in material cost, and a 14.5 % decrease in weight compared to market-available flat-plate collectors. However, the direct economic comparison was not considered strong in evidence due to a lack of economic data from technology providers. The most cost-effective designs featured an argon concentration of 99 %, sealing thickness of 31.2 mm, and a glazing thickness of 4.1 mm, and 4.5 mm, while collector length and width varied more significantly. The research findings indicate the techno-economic potential of insulating glass collectors, demonstrating their ability to outperform conventional flat-plate collectors in terms of cost-effectiveness and efficiency. Future studies should focus on producing and testing larger modules and incorporating production costs to fully realise their potential for solar district heating applications. This study provides valuable guidelines for IGU designers and producers aiming to develop cost-effective and efficient solar thermal collectors for district heating systems.

A Robust Optimization Model for Emergency Location Considering the Uncertainty and Correlation of Transportation Network Capacity

Emergencies often lead to the impairment of infrastructure systems, including transportation systems. It is necessary to analyze the uncertainty and correlation of transportation network capacity caused by emergencies, aiming at the problems of emergency facilities’ location and matching in emergency contexts. This study introduces novel concepts, such as flow distribution betweenness centrality (FD-BC) and the transport capacity effect coefficient (TC-EC). Furthermore, we introduce the ellipsoidal uncertainty set to characterize uncertainties in transport capacity. We construct a multi-criteria decision-making (MCDM) model and a multi-strength elitist genetic algorithm (multi-SEGA) to ensure the lower limit of transport capacity between demand and emergency points while minimizing decision-making costs. By designing an uncertain scenario example, we analyze the effect of the perturbation ratio and the uncertainty level on the robust location model. The following results were drawn: (1) Indicators FD-BC and TC-EC effectively indicated the importance of each section in the emergency transportation network. (2) The optimal value of the model’s objective function changed more significantly as the perturbation ratio and uncertainty level increased. (3) After reaching a certain uncertainty level, the robust model with an ellipsoidal uncertainty set became more conservative than the robust model with a box uncertainty set, which lacked practical significance. The research results guarantee the robustness of the emergency support system in uncertain conditions.

Strengthened elitist genetic algorithm for aeroengine blade arrangement optimisation

Strengthened elitist genetic algorithm for aeroengine blade arrangement optimisation

Bio-Inspired Hyperparameter Tuning of Federated Learning for Student Activity Recognition in Online Exam Environment

Nowadays, online examination (exam in short) platforms are becoming more popular, demanding strong security measures for digital learning environments. This includes addressing key challenges such as head pose detection and estimation, which are integral for applications like automatic face recognition, advanced surveillance systems, intuitive human–computer interfaces, and enhancing driving safety measures. The proposed work holds significant potential in enhancing the security and reliability of online exam platforms. It achieves this by accurately classifying students’ attentiveness based on distinct head poses, a novel approach that leverages advanced techniques like federated learning and deep learning models. The proposed work aims to classify students’ attentiveness with the help of different head poses. In this work, we considered five head poses: front face, down face, right face, up face, and left face. A federated learning (FL) framework with a pre-trained deep learning model (ResNet50) was used to accomplish the classification task. To classify students’ activity (behavior) in an online exam environment using the FL framework’s local client device, we considered the ResNet50 model. However, identifying the best hyperparameters in the local client ResNet50 model is challenging. Hence, in this study, we proposed two hybrid bio-inspired optimized methods, namely, Particle Swarm Optimization with Genetic Algorithm (PSOGA) and Particle Swarm Optimization with Elitist Genetic Algorithm (PSOEGA), to fine-tune the hyperparameters of the ResNet50 model. The bio-inspired optimized methods employed in the ResNet50 model will train and classify the students’ behavior in an online exam environment. The FL framework trains the client model locally and sends the updated weights to the server model. The proposed hybrid bio-inspired algorithms outperform the GA and PSO when independently used. The proposed PSOGA not only outperforms the proposed PSOEGA but also outperforms the benchmark algorithms considered for performance evaluation by giving an accuracy of 95.97%.

Optimization of Clustering and Trajectory for Minimizing Age of Information in Unmanned Aerial Vehicle-Assisted Mobile Edge Computing Network.

With the development of the Internet of Things (IoT) technology, massive amounts of sensor data in applications such as fire monitoring need to be transmitted to edge servers for timely processing. However, there is an energy-hole phenomenon in transmitting data only through terrestrial multi-hop networks. In this study, we focus on the data collection task in an unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) network, where a UAV is deployed as the mobile data collector for the ground sensor nodes (SNs) to ensure high information freshness. Meanwhile, the UAV is equipped with an edge server for data caching. We first establish a rigorous mathematical model in which the age of information (AoI) is used as a measure of information freshness, related to both the data collection time and the UAV's flight time. Then a mixed-integer non-convex optimization problem is formulated to minimize the peak AoI of the collected data. To solve the problem efficiently, we propose an iterative two-step algorithm named the AoI-minimized association and trajectory planning (AoI-MATP) algorithm. In each iteration, the optimal SN-collection point (CP) associations and CP locations for the parameter ε are first obtained by the affinity propagation clustering algorithm. The optimal UAV trajectory is found using an improved elite genetic algorithm. Simulation results show that based on the optimized ε, the AoI-MATP algorithm can achieve a balance between data collection time and flight time, reducing the peak AoI of the collected data.

Predictive Control Plane Balancing in SD-IoT Networks Based on Elitism Genetic Algorithm and Non-Cooperative Game Theory

Predictive Control Plane Balancing in SD-IoT Networks Based on Elitism Genetic Algorithm and Non-Cooperative Game Theory

Healthcare prognosis: GradiLearn-driven elitist genetic algorithm for disease predictions

Healthcare prognosis: GradiLearn-driven elitist genetic algorithm for disease predictions

Elite Genetic Algorithm Based Self-Sufficient Energy Management System for Integrated Energy Station

Elite Genetic Algorithm Based Self-Sufficient Energy Management System for Integrated Energy Station

Combining genetic algorithm and deep learning to optimize a chemical kinetic mechanism of ammonia under high pressure

Ammonia is a potential zero-carbon fuel, but the difficulties of experimenting at high pressure limit its development of application in power engineering. In this work, deep learning and genetic algorithm are combined to optimize the chemical reaction kinetics mechanism of ammonia under high pressure. The result shows that deep learning model is able to regress experimental data of ignition delay time in the range of less than 0.2% |Elog| (logarithmic absolute error). At the same time, the trained model can be applied to the trend prediction of ignition delay time at high pressure, enriching combustion data of ammonia fuel that is not available from experiments. Optimization of PLOG reactions with a large population size was performed by strengthen elitist genetic algorithm, and the prediction accuracy of ammonia chemical reaction kinetics mechanism was improved by about 5% finally. The application value of artificial intelligence in combustion science is demonstrated.

Bus routing fine-tuning for integrated network-based demand and bus bridging for a disrupted railway system

Unanticipated commuter railway disruptions inevitably tend to result in passenger bunching and frustration with considerable delays. Bus bridging strategy is a timely response approach to operationally handle and ease these scheduling disturbance issues. Conventional strategies, in this case, are apt to adding new/temporary bus routes, or, alternatively, sharply amending existing routes. Nonetheless, previous approaches have mainly been dedicated to reducing the delay of stranded passengers. This was done without integrating and considering the ordinary demand with the stranded demand through optimally handling time-dependent total passenger demand based on available service capacity. Consequently, this study creates a method on how to fine-tune bus-routing changes to handle these railway disruptions. This method allows for adjusting partial bus routes to optimally solve the combined problem of the railway passengers with bus bridging and to service all the network-based bus stops. We propose a mixed integer nonlinear programming model with multitype vehicles using a rolling horizon method to minimize total passenger delay from integrated bus bridging and existing bus services. Considering the extensive problem of the bus network with variable headways, we use a customized branch-and-bound algorithm incorporating an elitist genetic algorithm and the Monte Carlo simulation method to solve the model. A case study of the Shanghai Jinshan Railway shows that the result of total passenger delay of the proposed bus bridging modeling with rolling horizon is less by 37.23% than without rolling horizon for representing the advance of knowledge, and less by 60.7% than the do-nothing situation for representing the advance over practice.

Structural optimization of composite corrugated cores with variable stiffness

Outstanding progress in manufacturing technology of fiber-reinforced composite materials, allows designers to go beyond classical design rules. Composites with variable stiffness are an innovative division of composite materials that provide more efficient designs for engineers due to their diverse design parameters. In this study, a straightforward methodology is presented for the design of sandwich panels with corrugated variable stiffness core. Based on the homogenization method, a unit-cell of the sandwich panel is used as a representative volume element for the sandwich panel with corrugated core. Due to multiple design variables, conventional numerical and analytical methods cannot be applied to variable stiffness composites, thus PYTHON/ABAQUS framework is developed to determine the extensional and bending behavior of unit-cells. Details of this framework including PYTHON scripting and ABAQUS finite element solver are given along with their corresponding functions. Furthermore, the elitist genetic algorithm is incorporated into a framework for the optimum design of variable stiffness cores. Two optimization problems, namely composites with variable thickness and variable angle are considered for unit-cells, and associated constraints, boundary conditions, and fitness functions are discussed in detail. In addition to the benefits of the proposed framework, the obtained results reveal notable enhancement in the extensional and bending behavior of unit-cell. Results reveal that corresponding displacements are significantly improved (up to 80%) when using the optimum variable thickness case. For variable angle cases, the improvement of displacements is up to about 28%.

Bottom-up approaches for rapid on-demand design of modular metaporous structures with tailored absorption

As a new trend in the studies on sound-absorbing structures design, customizable metaporous structures (MPSs) have drawn a great deal of interest due to their distinct advantages, which include designable broadband absorption, light weight, and low thickness. Conventional finite element-based design methods, such as trial-and-error and iterative optimization, are inefficient and expensive in terms of computational resources. Inspired by the widely used bottom-up method, in this study, we develop a data-driven metaheuristic optimization framework to accomplish the rapid on-demand design for a novel modular metaporous structure (MMPS) of only 30mm thickness from the local to the global level. Two cascade variants of the genetic algorithm (GA) are employed for local optimization and global customized design, accordingly. The local design level involves the development of a surrogate-assisted genetic algorithm (SAGA) for design space optimization. On the basis of the structural dataset, a well-tuned convolutional neural network (CNN) model is developed for expediting the forward prediction of the acoustic properties of the two-dimensional (2D) MPS. In the subsequent phase, the validated CNN model is combined with SAGA to expedite the fitness evaluation for optimizing the structural units. At the global design stage, the developed SAGA is coupled with the population initialization process of an elitist genetic algorithm (EGA) to achieve inverse design for the MMPS with customizable broadband absorption based on the optimized design space. Furthermore, an acoustic measurement is performed on the fabricated MMPS samples to validate the finite element method (FEM) simulation and impedance design method. The utilization of this optimization method opens up fresh possibilities not solely for the customized design of sound-absorbing structures, but also for optimization processes in various other domains. Meanwhile, the proposed MMPS with customizable broadband absorption in a thickness of 30mm could well be utilized for noise reduction in a variety of practical applications.

A Novel Simulation-Optimization Model Built by FloPy: Pollutant Traceability in a Chemical Park in China

Heavy metal pollution of groundwater will not only destroy the ecological environment but also negatively affect the functioning of the human liver. Tracing the source of groundwater pollution is an important way to protect groundwater resources. FloPy is promoting the use of big data in the groundwater field, especially in groundwater resource planning and management and contaminant traceability. This paper takes Mn as an example and codes a simulation-optimization model for solving the groundwater pollutant traceability problem using FloPy. The Bayesian optimization and strengthen elitist genetic algorithm (SEGA) algorithms are then used to optimize the hydraulic conductivity and pollutant sources in the study area. The results show that the model runs in 411 s, which is an acceptable amount of time spent, the slope of the fitted curve between the model-calculated water level and the actual observed water level is 0.914, and the contaminant traceability results can successfully locate the contaminant sources in real engineering problems. The numerical groundwater flow model and solute transport model can be quickly built, modified, and run by writing code, and can be easily and efficiently coupled with various optimization algorithms with FloPy.

Partitioning multi-layer edge network for neural network collaborative computing

There is a trend to deploy neural network on edge devices in recent years. While the mainstream of research often concerns with single edge device processing and edge-cloud two-layer neural network collaborative computing, in this paper, we propose partitioning multi-layer edge network for neural network collaborative computing. With the proposed method, sub-models of neural network are deployed on multi-layer edge devices along the communication path from end users to cloud. Firstly, we propose an optimal path selection method to form a neural network collaborative computing path with lowest communication overhead. Secondly, we establish a time-delay optimization mathematical model to evaluate the effects of different partitioning solutions. To find the optimal partition solution, an ordered elitist genetic algorithm (OEGA) is proposed. The experimental results show that, compared with traditional cloud computing, single-device edge computing and edge-cloud collaborative computing, the proposed multi-layer edge network collaborative computing has a smaller runtime delay with limited bandwidth resources, and because of the pipeline computing characteristics, the proposed method has a better response speed when processing large number of requests. Meanwhile, the OEGA algorithm has better performance than conventional methods, and the optimized partitioning method outperforms other methods like random and evenly partition.

Optimizing a monitoring scheme for CO2 geological sequestration: An environmentally sustainable and cost-efficient approach

CO2 geological storage in depleted oil and gas reservoirs is recognized as a vital approach to combat anthropogenic CO2 emissions. However, the associated challenges of high operational costs and potential CO2 leakage necessitate the development of a cost-effective and environmentally sustainable monitoring program. This study presents a multi-objective optimization model aimed at designing an efficient CO2 monitoring program that meets both economic and environmental requirements. The model is applied to a case study of a Carbon Capture and Storage project in Shaanxi, utilizing an enhanced strengthen elitist genetic algorithm to solve the model under various scenarios. The analysis results demonstrate that in any scenario, a 10 % increase in the required monitoring technology precision leads to an average 1 % rise in monitoring costs, highlighting the cost-effectiveness of the CO2 monitoring scheme developed using our model. Furthermore, when environmental targets are raised by 10 times, monitoring costs show an average increase of 0.92 times, further illustrating the environmentally sustainable nature of our proposed CO2 monitoring scheme. In conclusion, this study provides a cost-effective and environmentally sustainable method framework for the development of CO2 geologic sequestration monitoring scheme, which can contribute to the practical implementation of Carbon Capture and Storage projects to a certain extent.

An efficient evolutionary algorithm for high-speed train rescheduling under a partial station blockage

This paper investigates the high-speed train rescheduling (HSTR) problem under a partial station blockage and proposes an efficient problem-specific strengthen elitist genetic algorithm (PS-SEGA) for HSTR. Firstly, a HSTR model subject to train operation constraints is established to minimize the total train delay. A permutation-based encoding method is developed to define an efficient search space based on the train departure sequence. A heuristic decoding method is employed to eliminate all train operation constraints and output the rescheduled timetable. Moreover, a hybrid initialization method involving an efficient heuristic strategy (EHS) is put forward to accelerate the convergence speed of PS-SEGA. Using problem-specific knowledge, EHS generates an efficient and feasible solution for the initial population. Finally, a restart strategy is presented to maintain genetic diversity. Compared with other advanced evolutionary algorithms and their improved variants also using the improvements of PS-SEGA, experimental results demonstrate the effectiveness of the proposed PS-SEGA for addressing HSTR scenarios under the partial station blockage. As for the scenarios that CPLEX cannot obtain optimal solutions within 10 min, PS-SEGA can provide quasi-optimal solutions in real time. Furthermore, compared with the other two heuristics algorithms (i.e., First-Scheduled-First-Served and EHS), PS-SEGA can give the train departure sequence with a smaller total train delay.

Sewer Network Multi-objective Optimization using Genetic Algorithms

This paper focuses on the multi-objective optimization of a sewer network that serves a medium-sized Romanian city, with a population of 250,000 residents. The sewer network is modeled using BSMSewer software package. The obtained results are based on numerical simulations with the optimization algorithm considering two performance criteria: the volume of overflow and the quality of the overflowed wastewater. For optimization, two approaches that use a controlled elitist genetic algorithm were employed: a multi-objective optimization and a two-steps multi-objective optimization. Results analysis involved comparing them with a scenario where each performance criterion was separately minimized. Additionally, a comparison was made to the situation where the sewer network operated without a control system, meaning the valves were fully open and the pumps were running at maximum capacity.

A method based on elitist genetic algorithm for calibrating the thermo-physical surface indicators: Its principles, validation and application to bioswales

Pavement is closely linked to the hydrological characteristics of the surface, which affects the infiltration and retention of surface runoff, leading to changes in thermo-physical surface indicators such as surface albedo, surface emissivity, volumetric heat capacity, thermal diffusivity, average soil temperature and surface humidity. Green drainage facilities, particularly bioswales, can mitigate runoff and improve microclimates by altering the flow path of water and thermo-physical surface indicators. While the thermo-physical indicators of artificial pavement surfaces such as sand, asphalt, cement, brick and stone have been studied and applied, those of bioswales have yet to be thoroughly investigated, and there is a dearth of scientific evaluation methods for their thermal effect. In this study, a genetic algorithm-based method for calibrating thermo-physical surface indicators was established, and its reliability was validated by comparing the thermo-physical indicators of asphalt pavement surfaces with existing literature. Two bioswales covering 200 m2 were designed and constructed, and their surface air temperature (1.5-meter from the surface) was monitored under irrigating and non-irrigated scenarios, and the thermo-physical indicators of two bioswales surface were determined. The temperature of bioswales in relevant literature was calculated by using the calibration results, and compared with the measured air temperature. The calibration method exhibited an error range of −9.6% to + 4.3%, and the surface temperature error resulting from the application of calibration parameters was 0.9133 to 0.9338. By establishing a method for determining the thermo-physical indicators of surface pavement and obtaining the thermo-physical indicators of bioswale surfaces using the surface temperature data, this study provides essential support for evaluating the thermal environment effect of bioswales.

Opportunistic maintenance optimisation for offshore wind farm with considering random wind speed

ABSTRACT A joint maintenance decision-making framework is proposed to optimise the long-term maintenance plan and lower the maintenance cost for offshore wind farms. The historical wind speed data are screened by using the method of k-means clustering, and Markov chains are established for the wind speed in different seasons. On this basis, the approach of Markov chain Monte Carlo is applied to simulate the distribution of repair vessel's waiting time for maintenance, where the impact of wind speed on maintenance availability is considered. Moreover, the components in wind turbines are divided into four states according to their effective ages, i.e. young, mature, old and failed, respectively. A maintenance decision model is established, with the objective to minimise maintenance cost. Besides, three types of opportunistic maintenance are considered, i.e. failure-based opportunistic maintenance (FBOM), event-based opportunistic maintenance (EBOM) and age-based opportunistic maintenance (ABOM), respectively. The enhanced elitist genetic algorithm (SEGA) is adopted to solve the optimisation problem. The results indicate that among the three types of opportunistic maintenance, ABOM can reduce maintenance cost more effectively, and it is more suitable for long-term maintenance plans of offshore wind farm.