Multiple Objective Genetic Algorithm Research Articles

Orca hydrofoil shape optimization using Bezier curve and Artificial Neural Network – Multiple objective Genetic Algorithm for low flow velocity

Tidal energy is a clean and predictable power source that is commonly harnessed by using horizontal axis tidal turbines. The power generating process of tidal turbines is influenced by various elements, one of which is the hydrofoil performance. This includes the lift coefficient, drag coefficient, and lift-to-drag ratio. This study introduces the utilization of the Orcinus Orca hydrofoil for horizontal axis tidal turbines. The Orcinus Orca geometry is obtained by modified the NACA0021 airfoil. Subsequently, Bezier curve parameterization is employed to make a smooth hydrofoil profile. The study further deploy an Artificial Neural Network coupled with a Multi-Objective Genetic Algorithm, specifically targeting optimization of the hydrofoil shape optimization at a low flow velocity, specifically at an inlet velocity of 0.5 m/s. The aim of this optimization is to augment the lift coefficient and diminish the drag coefficient in order to amplify the lift to drag ratio. The findings reveal a significant enhancement in performance, as the optimized Orcinus Orca hydrofoil exhibits a remarkable increase of 42.78 % and 27.93 % compared to the original Orcinus Orca and the Bezier-modified Orcinus Orca hydrofoils, respectively.

Design of a precision planter chassis using computer-aided engineering and experimental validation

The application of X-section beams in the modular and strength-based design of a precision planter chassis was investigated numerically and experimentally in a case study. This study deals with the feasibility of a special section design with a systematic engineering approach. Mechanical tests were performed for the beam evaluated in a mounting system. The X-section beam model and the mounting elements on this beam were created using computer-aided engineering software, and the compatibility of the design with the mass criterion was investigated. This model was edited as a 2D and 3D mixed model and analyzed with the finite element method to analyzing studies of the system. Stress measurement was conducted using strain gauges at specified points in the system whose prototype was produced. These strain data were processed with nCode DesignLife software, and nonlinear FEA analyses were validated using these stress measurements. The fatigue damage of the X-section beam under dynamic loading conditions was investigated using the FE model solution and experimental measurement data (CAE-based fatigue analysis) with nCode software. The X-section beam design adopted a multiple-objective genetic algorithm technique for optimization by means of ANSYS. The maximum stress value was 121.83 MPa, and a 7.77 kg material was saved correlated to the prototype with the help of optimization solved 400 iterations. It has been determined that the X-section beam is safe by 1.06 × 106 cycles under these loading conditions and can carry a load of 1600 kg. The X-section beam can be successfully applied in similar systems owing to its assemblability and functionality.

EMI Minimization from Stacked Radiation Sources by Means of Multiple Objective Genetic Algorithm

The containment of unwanted electromagnetic radiation and interference is a relevant topic for the system design of any electrical system, and even more for data centers. In this context, the racks hosting piles of servers are one of the main sources of electromagnetic noise. Such unwanted radiation can couple and interact with other computing machines, but also with sensitive electronic devices needed for the management and/or maintenance of the center. The aim of this work is to show how the proper stack-up of the trays in the rack gives rise to a decrease in the unwanted physical electromagnetic radiation. Based on the application of the spherical wave expansion technique, a multi-objective genetic algorithm is developed to evaluate the optimal set of rack configurations that allows for a reduction of the external radiated field. The algorithm and the implemented constraints are described, and the results are discussed.

Discrete-time simulation for performance modelling of FIFO single-server queuing system

Optimal queue management is crucial for improving the network operation since packet loss is commonly attributed to the likelihood of buffer overflow at intermediate routers on end-to-end communication path. In this paper, a transient discrete-time simulation model is proposed based on queuing theory served by single-server system and single first-in first-out (FIFO) queue. This queuing service framework effectively enforces the best-effort service to the streams of incoming data packets across the network with disparate quality of service (QoS) requirements. We plot the network performance measures such as queue length, delay, server utilisation and packet lifetime to validate the practical wireless systems. Besides, we employ conventional multiple-objective genetic algorithm to model the trade-off among key queuing system parameters including queuing delay, packet drop rate and network bandwidth. Finally, the efficiency of our queuing optimisation model is significantly compared with previous works in terms of bandwidth utilisation, delay, and packet loss rate.

Groundwater Level Prediction Using a Multiple Objective Genetic Algorithm-Grey Relational Analysis Based Weighted Ensemble of ANFIS Models

Predicting groundwater levels is critical for ensuring sustainable use of an aquifer’s limited groundwater reserves and developing a useful groundwater abstraction management strategy. The purpose of this study was to assess the predictive accuracy and estimation capability of various models based on the Adaptive Neuro Fuzzy Inference System (ANFIS). These models included Differential Evolution-ANFIS (DE-ANFIS), Particle Swarm Optimization-ANFIS (PSO-ANFIS), and traditional Hybrid Algorithm tuned ANFIS (HA-ANFIS) for the one- and multi-week forward forecast of groundwater levels at three observation wells. Model-independent partial autocorrelation functions followed by frequentist lasso regression-based feature selection approaches were used to recognize appropriate input variables for the prediction models. The performances of the ANFIS models were evaluated using various statistical performance evaluation indexes. The results revealed that the optimized ANFIS models performed equally well in predicting one-week-ahead groundwater levels at the observation wells when a set of various performance evaluation indexes were used. For improving prediction accuracy, a weighted-average ensemble of ANFIS models was proposed, in which weights for the individual ANFIS models were calculated using a Multiple Objective Genetic Algorithm (MOGA). The MOGA accounts for a set of benefits (higher values indicate better model performance) and cost (smaller values indicate better model performance) performance indexes calculated on the test dataset. Grey relational analysis was used to select the best solution from a set of feasible solutions produced by a MOGA. A MOGA-based individual model ranking revealed the superiority of DE-ANFIS (weight = 0.827), HA-ANFIS (weight = 0.524), and HA-ANFIS (weight = 0.697) at observation wells GT8194046, GT8194048, and GT8194049, respectively. Shannon’s entropy-based decision theory was utilized to rank the ensemble and individual ANFIS models using a set of performance indexes. The ranking result indicated that the ensemble model outperformed all individual models at all observation wells (ranking value = 0.987, 0.985, and 0.995 at observation wells GT8194046, GT8194048, and GT8194049, respectively). The worst performers were PSO-ANFIS (ranking value = 0.845), PSO-ANFIS (ranking value = 0.819), and DE-ANFIS (ranking value = 0.900) at observation wells GT8194046, GT8194048, and GT8194049, respectively. The generalization capability of the proposed ensemble modelling approach was evaluated for forecasting 2-, 4-, 6-, and 8-weeks ahead groundwater levels using data from GT8194046. The evaluation results confirmed the useability of the ensemble modelling for forecasting groundwater levels at higher forecasting horizons. The study demonstrated that the ensemble approach may be successfully used to predict multi-week-ahead groundwater levels, utilizing previous lagged groundwater levels as inputs.

Simplified Steady-State Representation of Slot Synthetic Jet Actuators to Enable Numerical Optimization With Steady RANS Simulations

To address the growing energy use of data centers, waste heat recuperation offers a solution to better integrate these facilities into the broader energy system, thus facilitating a transition to the decarbonization of the energy system. The use of liquid coolants for full immersion cooling or local heat extraction from high power density components is considered for this purpose. However, heat can also be extracted by novel air cooling approaches, perhaps in combination with localized liquid cooling. To optimize heat extraction from air-cooled systems and maximize the heat grade, synthetic jets (SJs) can be used for targeted adaptive cooling in conjunction with air ducting to facilitate maximum heat recuperation potential in rack or server-mounted air-to-liquid heat exchangers. Internal server layouts can be optimized numerically, e.g., using a multiple objective genetic algorithm approach based on minimization of entropy generation rates. However, since SJs are inherently transient flow phenomena, this would require transient flow simulations, which forms a bottleneck in a numerical optimization loop. This research aims to develop a simplified steady-state representation of a synthetic jet actuator (SJA) with slot orifice using a localized body force to generate a similar time-averaged flow field to a real SJA, suitable for steady Reynolds-averaged Navier–Stokes simulations within a numerical optimization loop. Both flow fields are compared in terms of the mean flow field, jet spreading rate, and turbulence intensity distributions.

Optimization of Biofilter Size for Aquaponics Using Genetic Algorithm

Unlike a media-filled aquaponic system, the nutrient film technique (NFT) and deep water culture (DWC) require the installation of an external biofilter to provide sufficient area for nitrifying bacteria colonization, which is essential for the conversion of toxic ammonia from fish waste into nitrate that is easily assimilated by plants. Given the importance of biofilters, it is imperative to properly design this tank to effectively support the nitrification process. Several factors need to be considered for the biofilter design. Thus, an optimization algorithm can be used to obtain combinations of the design parameters. The genetic algorithm (GA) is a heuristic solution search or optimization technique based on the Darwinian principle of genetic selection. The main goal of this study was to obtain the optimal biofilter size for a given fishpond volume and the amount of ammonia to be treated. The conversion coefficient in the Michaelis–Menten equation was used as the fitness function in this study. The parameters optimized using GA include the hydraulic loading rate, height of the biofilter, and predicted ammonia concentration. For the given assumption of a 60 kg feed introduced to the system and a 1500 L fishpond, the hydraulic loading rate, biofilter height, and final concentration of ammonia were 0.17437 m, 0.58585 m, and 0.01026 ppm, respectively. Using the values obtained from running the GA, the optimum biofilter volume for the system was 0.4608 m3, whereas the water flow rate was 0.03 L/min. For recommendations, multiple objective GAs can be used to add cost-related variables in the optimization because they have not yet been considered in the computation.

A multi-hop routing algorithm for WSNs based on compressive sensing and multiple objective genetic algorithm

Energy-efficiency and reliability are vital metrics of the robustness of Wireless Sensor Networks (WSNs). Various data reduction techniques are used to improve them, among them compressive sensing (CS) is a data reduction technique used to recover extensive data from fewer samples in case of sparse representation of sensor-readings. Unfortunately, energy-efficiency and accuracy are contradictory metrics, as increased accuracy requires a large number of measurements, and data transmissions. Therefore, in this paper, a CS-based algorithm is proposed for efficient data transfer through WSNs, which uses multiple objective genetic algorithms (MOGA) to optimize the number of measurements, transmission range, and the sensing matrix. The algorithm aims at striking the right balance between energy-efficiency and accuracy. It constructs a path in a multi hop manner based on the optimized values. Numerical simulations and experiments show that Pareto-front, which is the output of MOGA, helps the user to select the right combination of the number of measurements and the transmission range fitting the application at hand, and to strike a good balance between energy efficiency and accuracy. The results also demonstrate the existence of measurement matrices which lower mutual coherency improve the accuracy of CS.

Dynamic dispatching for interbay automated material handling with lot targeting using improved parallel multiple-objective genetic algorithm

With the growth of wafer size from 200 mm to 300 mm and then to 450 mm in recent years, automatic material handling system (AMHS) has played an indispensable role in semiconductor wafer fabrication systems, and improving the overall efficiency of interbay AMHS has therefore received considerable attention. This study investigates the integrated scheduling problem in an interbay AMHS that combines vehicle scheduling with lot targeting. However, the large-scale, dynamic, and stochastic production environment significantly substantiates the complexity of the scheduling problem. To meet the demands of adaptive adjusting, efficient scheduling, and multiple-objective optimization, this study develops an improved parallel multiple-objective genetic algorithm with full use of parallel strategy, multi-objective evolutionary process, and local search strategy. Simulation experiments have been conducted and the numerical results illustrate the superiority of the algorithm in terms of comprehensive performance of multiple sub-objectives.

Discrete-time simulation for performance modelling of FIFO single-server queuing system

Optimal queue management is crucial for improving the network operation since packet loss is commonly attributed to the likelihood of buffer overflow at intermediate routers on end-to-end communication path. In this paper, a transient discrete-time simulation model is proposed based on queuing theory served by single-server system and single first-in first-out (FIFO) queue. This queuing service framework effectively enforces the best-effort service to the streams of incoming data packets across the network with disparate quality of service (QoS) requirements. We plot the network performance measures such as queue length, delay, server utilisation and packet lifetime to validate the practical wireless systems. Besides, we employ conventional multiple-objective genetic algorithm to model the trade-off among key queuing system parameters including queuing delay, packet drop rate and network bandwidth. Finally, the efficiency of our queuing optimisation model is significantly compared with previous works in terms of bandwidth utilisation, delay, and packet loss rate.

Modelling and management of saltwater intrusion in a coastal aquifer system: A regional-scale study

Increasing saltwater intrusion in the Barguna aquifer due to unplanned groundwater abstraction is a concern for the people of Barguna district, Bangladesh. A sustainable groundwater abstraction strategy capable of confining saltwater concentrations in the aquifer within acceptable limits is required for the Barguna aquifer system. In this study, a regional-scale integrated simulation-optimization (S–O) approach was used to prescribe an optimal groundwater abstraction strategy for the aquifer. The flow and transport processes were simulated by a calibrated and validated numerical simulation model using the available hydrogeological data. The simulation model was then used within the integrated S–O based management model to evolve ideal groundwater abstraction patterns to restraint saltwater intrusion in the study area. Computational efficiency of the management model was achieved by using a Multivariate Adaptive Regression Spline (MARS) based meta-model emulating the density dependent salinity transport processes of the study area. The developed MARS-based emulators were then externally linked with a Controlled Elitist Multiple Objective Genetic Algorithm (CEMOGA) as a replacement of the numerical model. The study area comprised of a set of production wells for abstracting groundwater for beneficial purposes. Barrier extraction wells placed along the coastline were also considered as a management option to control saltwater intrusion hydraulically. Grey Relational Analysis was utilized as a quick decision-making tool for selecting a relatively better solution from a large number of non-dominated solutions from the Pareto front. The proposed MARS-CEMOGA based saltwater intrusion management methodology was capable of obtaining accurate solutions for optimal groundwater abstractions from a combination of production and barrier extraction bores in a real-life coastal aquifer system. This study demonstrates the efficiency of the MARS meta-model, together with an integrated S–O approach, to solve real-life complex coastal aquifer management problems.

A Cost-Effective In Situ Zooplankton Monitoring System Based on Novel Illumination Optimization.

A cost-effective and low-power-consumption underwater microscopic imaging system was developed to capture high-resolution zooplankton images in real-time. In this work, dark-field imaging was adopted to reduce backscattering and background noise. To produce an accurate illumination, a novel illumination optimization scheme for the light-emitting diode (LED) array was proposed and applied to design a lighting system for the underwater optical imaging of zooplankton. A multiple objective genetic algorithm was utilized to find the best location of the LED array, which resulted in the specific illumination level and most homogeneous irradiance in the target area. The zooplankton imaging system developed with the optimal configuration of LEDs was tested with Daphnia magna under laboratory conditions. The maximal field of view was 16 mm × 13 mm and the optical resolution was 15 μm. The experimental results showed that the imaging system developed could capture high-resolution and high-definition images of Daphnia. Subsequently, Daphnia individuals were accurately segmented and their geometrical characters were measured by using a classical image processing algorithm. This work provides a cost-effective zooplankton measuring system based on an optimization illumination configuration of an LED array, which has a great potential for minimizing the investment and operating costs associated with long-term in situ monitoring of the physiological state and population conditions of zooplankton.

A Generic Design of Driver Drowsiness and Stress Recognition Using MOGA Optimized Deep MKL-SVM.

Driver drowsiness and stress are major causes of traffic deaths and injuries, which ultimately wreak havoc on world economic loss. Researchers are in full swing to develop various algorithms for both drowsiness and stress recognition. In contrast to existing works, this paper proposes a generic model using multiple-objective genetic algorithm optimized deep multiple kernel learning support vector machine that is capable to recognize both driver drowsiness and stress. This algorithm simplifies the research formulations and model complexity that one model fits two applications. Results reveal that the proposed algorithm achieves an average sensitivity of 99%, specificity of 98.3% and area under the receiver operating characteristic curve (AUC) of 97.1% for driver drowsiness recognition. For driver stress recognition, the best performance is yielded with average sensitivity of 98.7%, specificity of 98.4% and AUC of 96.9%. Analysis also indicates that the proposed algorithm using multiple-objective genetic algorithm has better performance compared to the grid search method. Multiple kernel learning enhances the performance significantly compared to single typical kernel. Compared with existing works, the proposed algorithm not only achieves higher accuracy but also addressing the typical issues of dataset in simulated environment, no cross-validation and unreliable measurement stability of input signals.

Path optimization of taxi carpooling

The problem that passengers are hard to take taxis while empty driving rate is high widely exists under the traditional taxi operation mode. The implementation of taxi carpooling mode can alleviate the problem in a certain extent. The objective of this study is to optimize the taxi carpooling path. Firstly, the taxi carpooling path optimization model with single objective and its extended model with multiple objectives are built respectively. Then, the single objective path optimization model of taxi carpooling is solved based on the improved single objective genetic algorithm, and the multiple-objective path optimization model of taxi carpooling is solved based on the improved multiple-objective genetic algorithm. Finally, a case study is carried out based on a road network with 24 nodes. The case study results show the path optimization models and algorithms of taxi carpooling proposed in the paper can quickly get the taxi carpooling path, and can increase the income of taxi driver while reduce the cost for passengers.

Optimization of Operation Parameters for Direct Spring Loaded Pressure Relief Valve in a Pipeline System

A direct spring loaded pressure relief valve (DSLPRV) is an efficient hydraulic structure used to control a potential water hammer in pipeline systems. The optimization of a DSLPRV was explored to consider the instability issue of a valve disk and the surge control for a pipeline system. A surge analysis scheme, named the method of characteristics, was implemented into a multiple-objective genetic algorithm to determine the adjustable factors in the operation of the DSLPRV. The forward transient analysis and multi-objective optimization of adjustable factors, such as the spring constant, degree of precompression, and disk mass, showed substantial relaxation in the surge pressure and oscillation of valve disk in a hypothetical pipeline system. The results of the regression analysis of surge were compared with the optimization results to demonstrate the potential of the developed method to substantially reduce computational costs.

VNF-FG design and VNF placement for 5G mobile networks

Network function virtualization (NFV) is envisioned as one of the critical technologies in 5th-Generation (5G) mobile networks. This paper investigates the virtual network function forwarding graph (VNF-FG) design and virtual network function (VNF) placement for 5G mobile networks. We first propose a two-step method composed of flow designing and flow combining for generating VNF-FGs according to network service requests. For mapping VNFs in the generated VNF-FG to physical resources, we then modify the hybrid NFV environment with introducing more types of physical nodes and mapping modes for the sake of completeness and practicality, and formulate the VNF placement optimization problem for achieving lower bandwidth consumption and lower maximum link utilization simultaneously. To resolve this problem, four genetic algorithms are proposed on the basis of the frameworks of two existing algorithms (multiple objective genetic algorithm and improved non-dominated sorting genetic algorithm). Simulation results show that Greedy-NSGA-II achieves the best performance among our four algorithms. Compared with three non-genetic algorithms (random, backtracking mapping and service chains deployment with affiliation-aware), Greedy-NSGA-II reduces 97.04\%, 87.76\% and 88.42\% of the average total bandwidth consumption, respectively, and achieves only 13.81\%, 25.04\% and 25.41\% of the average maximum link utilization, respectively. Moreover, using our VNF-FG design method and Greedy-NSGA-II together can also reduce the total bandwidth consumption remarkably.

Fuzzy MOGA for supply chain models with Pareto decision space at different α-cuts

Today’s global environment is highly competitive. The competition between two firms means the competition in their supply chain. The prime objective of decision makers are to optimize the supply chain. In every stage of supply chain, the cost and delivery time are involved. These criteria are uncertain in nature. We express these criteria in either the triangular or trapezoidal fuzzy numbers. While optimizing the time and cost simultaneously, the problem becomes bi-objective. Such problems can be solved by using Multiple Objective Genetic Algorithm (MOGA). We get the different Pareto front at different α-cuts which is called as the Pareto decision space. According to the uncertainty in the market, decision maker has a choice to take decision among the set of alternatives. Here, the proposed solution methodology is fusion of fuzzy set theory and MOGA. Fuzzy set theory is used for uncertainty in parameters and MOGA is used for obtaining non-dominated solutions. The numerical example is given to illustrate the proposed methodology and industrial case study is solved by using proposed methodology.

Multi-objective optimization for resin transfer molding process

A multi-objective optimization (MOO) approach for multi-point injection of resin-transfer molding (RTM) is proposed to investigate the trade-off relationship between productivity and quality for composite structures. With this approach, the optimum gate positions for their molding properties are evaluated using finite-element analysis (FEA) with a multiple-objective genetic algorithm (MOGA), and the trade-offs are visualized with the combination of a self-organizing map (SOM) and a scatter plot matrix (SPM). We applied this approach to RTM for flat-plate and rib models. For the flat-plate model, we found a negative correlation between fill time and weld line contents, and between fill time and dry spot contents. These results imply difficulty for simultaneous reduction of cycle time and void contents. For the rib model, some tendencies agree with those of the flat-plate model, and others do not. This difference comes from complexity of structure. We also found Pareto solutions that satisfy both productivity and quality for the flat-plate and rib models (i.e., gate positions such as a combination of diagonal and quadrangle positions for the flat-plate model, and aggregation of gate positions at a beam part for the rib model). Furthermore, we conducted simple experiments for the flat-plate model to validate the simulation result. The trends acquired from MOO qualitatively agree with the experiments.

Development of a High Irradiance LED Configuration for Small Field of View Motion Estimation of Fertilizer Particles.

Better characterization of the fertilizer spreading process, especially the fertilizer pattern distribution on the ground, requires an accurate measurement of individual particle properties and dynamics. Both 2D and 3D high speed imaging techniques have been developed for this purpose. To maximize the accuracy of the predictions, a specific illumination level is required. This paper describes the development of a high irradiance LED system for high speed motion estimation of fertilizer particles. A spectral sensitivity factor was used to select the optimal LED in relation to the used camera from a range of commercially available high power LEDs. A multiple objective genetic algorithm was used to find the optimal configuration of LEDs resulting in the most homogeneous irradiance in the target area. Simulations were carried out for different lenses and number of LEDs. The chosen configuration resulted in an average irradiance level of 452 W/m2 with coefficient of variation less than 2%. The algorithm proved superior and more flexible to other approaches reported in the literature and can be used for various other applications.

A hybrid grey-based fuzzy C-means and multiple objective genetic algorithms for project portfolio selection

Project portfolio selection is an important issue in project portfolio management (PPM) process. This paper presents a novel decision support system (DSS) to aid the manager in project portfolio selection approach. The selection model is based on grey relational analysis (GRA) with intuitionistic trapezoidal fuzzy number as well as fuzzy C-means (FCM) algorithm. The proposed approach of this paper first clusters different projects based on fuzzy C-means algorithm and then ranks various projects in each cluster by grey relational analysis (GRA) concept. Finally, Pareto combination of rank and risk in a portfolio is determined by multiple objective genetic algorithm. The proposed framework is tested in a case study to show its usefulness and applicability in practice.