Meta-heuristic Genetic Algorithm Research Articles

Sustainable planning and decision-making model for sugarcane mills considering environmental issues

Many companies and organizations are pursuing “carbon footprint” projects to estimate their own contribution due to growing concerns about global climate change and carbon emissions. Measures such as carbon taxes are the most powerful means of dealing with the threats of climate change. In recent years, researchers have shown a particular interest in modelling supply chain networks under this scheme. Disorganized disposal of by-products from sugarcane mills is the inspiration of this research. In order to connect the problem with the real world, the proposed sustainable sugarcane supply chain network considers carbon taxes on the emission from industries and during transportation of goods. The presented mixed-integer linear programming modelling is a location-allocation problem and, due to the inherent complexity, it is considered a Non-Polynomial hard (NP-hard) problem. To deal with the model, three superior metaheuristics Genetic Algorithm (GA), Simulated Annealing (SA), Social Engineering Optimizer (SEO) and hybrid methods based on these metaheuristics, namely, Genetic-Simulated Annealing (GASA) and Genetic-Social Engineering Optimizer (GASEO), are employed. The control parameters of the algorithms are tuned using the Taguchi approach. Subsequently, one-way ANOVA is used to elucidate the performance of the proposed algorithms, which compliments the performance of the proposed GASEO.

Element-Based Multi-Objective Optimization Methodology Supporting a Transportation Asset Management Framework for Bridge Planning and Programming

The U.S. Moving Ahead for Progress in the 21st Century Act (MAP-21) mandates the development of a risk-based transportation asset management plan and the use of a performance-based approach in transportation planning and programming. This paper introduces a systematic element-based multi-objective optimization (EB-MOO) methodology integrated into a goal-driven transportation asset management framework to improve bridge management and support state departments of transportation with their transition efforts to comply with these MAP-21 requirements. The methodology focuses on the bridge asset class and is structured around five modules: data processing, improvement, element-level optimization, bridge-level optimization, and network-level optimization modules. It relies on a leading-edge forecasting model, three separate screening processes (i.e., the element deficiency, alternative feasibility, and solution superiority screening processes) to overcome computer memory and processing time limitations, and a simulation arrangement to generate life-cycle alternatives (series of improvement actions). Additionally, the EB-MOO methodology consists of three levels of optimization assessment based on the Pareto optimality concept: element-level, bridge-level, and network-level (following either a top-down or bottom-up approach). A robust metaheuristic genetic algorithm handles the different multi-objective optimization problems. A prototyping tool was developed for the implementation of the methodology through several examples of unconstrained and constrained (by budget, performance, or both) scenarios. Results reveal the capability of the methodology to generate Pareto optimal or near-optimal solutions, predict performance, and determine funding requirements and short- and long-term intervention strategies detailed at the bridge-element level for planning and programming. The EB-MOO methodology can also be expanded to accommodate other asset classes or modes.

Applying hybrid artificial algorithms to the estimation of river flow: a case study of Karkheh catchment area

This study was conducted on the Karkheh catchment area in the country of Iran on the basis of data from four stations of Cham Anjir, Kashkan, Pole-zal, and Jologir. The data were monthly collected for the years from 1997 to 2017, from which 70% were used for calibration and 30% for test validation. Artificial neural networks (ANNs) were used in the prediction of river flow. To optimize the weight coefficients of the network, the meta-heuristic genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO), harmonic balance algorithm (HB), and algorithm of the innovative gunner (AIG) were employed. To assess the modeling performance of the statistic parameters, the coefficient of determination (R2), root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), mean absolute error (MAE), and percentage of bias (PBIAS) were adopted. The achieved best input combination was different for each algorithm. In summary, variables with lower correlations had poorer performances. Hybrid algorithms improved the predicting power of the considered independent model. The results showed that for the studied four stations, among the meta-heuristic algorithms, AIG had the highest predictive power correlation coefficient R2 = 0.985–0.995, root mean square error (RMSE) = 0.036–0.057 m3/s, mean absolute error (MAE) = 0.017–0.036 m3/s, Nash-Sutcliffe coefficient (NSE) = 0.984–0.994, and bias = 0.008–0.024 and had the best performance in estimating the daily flow of the river.

A Heuristic Algorithm for Combined Heat and Power System Operation Management

This paper presents a computationally efficient novel heuristic approach for solving the combined heat and power economic dispatch (CHP-ED) problem in residential buildings considering component interconnections. The proposed solution is meant as a substitute for the cutting-edge approaches, such as model predictive control, where the problem is a mixed-integer nonlinear program (MINLP), known to be computationally-intensive, and therefore requiring specialized hardware and sophisticated solvers, not suited for residential use. The proposed heuristic algorithm targets simple embedded hardware with limited computation and memory and, taking as inputs the hourly thermal and electrical demand estimated from daily load profiles, computes a dispatch of the energy vectors including the CHP. The main idea of the heuristic is to have a procedure that initially decomposes the three energy vectors’ requests: electrical, thermal, and hot water. Then, the latter are later combined and dispatched considering interconnection and operational constraints. The proposed algorithm is illustrated using series of simulations on a residential pilot with a nano-cogenerator unit and shows around 25–30% energy savings when compared with a meta-heuristic genetic algorithm approach.

Parallel machines scheduling with time-dependent deterioration, using meta-heuristic algorithms

In this paper, we consider the identical parallel machines scheduling problem with exponential time-dependent deterioration. The meaning of time-dependent deterioration is that the processing time of a job is not a constant and depends on the scheduled activities. In other words, when a job is processed later, it needs more processing time compared to the jobs processed earlier. The main purpose is to minimize the makespan. To reach this aim, we developed a mixed integer programming formulation for the problem. We solved problem in small scale using GAMS software, while due to the fact that in larger scales the aforesaid case is a complex and intricate optimized problem which is NP-hard, it is not possible to solve it by standard calculating techniques (in logical calculating times); we applied the meta-heuristic genetic algorithm, simulating annealing and artificial immune system, and their performance has been evaluated. In the end, we showed that solving the problem in small scale, with the meta-heuristic algorithms (GA, SA, and AIS) equals the optimal solution (GAMS), And on a large scale, at a time of approximately equal solution, meta-heuristic algorithm simulating annealing, provides a more optimal solution.

Hybrid Vector Autoregression Feedforward Neural Network with Genetic Algorithm Model for Forecasting Space-Time Pollution Data

The exposure rate to air pollution in most urban cities is really a major concern because it results to a life-threatening consequence for human health and wellbeing. Furthermore, the accurate estimation and continuous forecasting of pollution levels is a very complicated task. In this paper, one of the space-temporal models, a vector autoregressive (VAR) with neural network (NN) and genetic algorithm (GA) was proposed and enhanced. The VAR could tackle the issue of multivariate time series, NN for nonlinearity, and GA for parameter estimation determination. Therefore, the model could be used to make predictions, such as the information of series and location data. The applied methods were on the pollution data, including NOX, PM2.5, PM10, and SO2 in Taipei, Hsinchu, Taichung, and Kaohsiung. The metaheuristics genetic algorithm was used to enhance the proposed methods during the experiments. In conclusion, the VAR-NN-GA gives a good accuracy when metric evaluation is used. Furthermore, the methods can be used to determine the phenomena of 10 years air pollution in Taiwan.

Multi-Scale Analyses and Modeling of Metallic Nano-Layers

The current work centers on multi-scale approaches to simulate and predict metallic nano-layers’ thermomechanical responses in crystal plasticity large deformation finite element platforms. The study is divided into two major scales: nano- and homogenized levels where Cu/Nb nano-layers are designated as case studies. At the nano-scale, a size-dependent constitutive model based on entropic kinetics is developed. A deep-learning adaptive boosting technique named single layer calibration is established to acquire associated constitutive parameters through a single process applicable to a broad range of setups entirely different from those of the calibration. The model is validated through experimental data with solid agreement followed by the behavioral predictions of multiple cases regarding size, loading pattern, layer type, and geometrical combination effects for which the performances are discussed. At the homogenized scale, founded on statistical analyses of microcanonical ensembles, a homogenized crystal plasticity-based constitutive model is developed with the aim of expediting while retaining the accuracy of computational processes. Accordingly, effective constitutive functionals are realized where the associated constants are obtained via metaheuristic genetic algorithms. The model is favorably verified with nano-scale data while accelerating the computational processes by several orders of magnitude. Ultimately, a temperature-dependent homogenized constitutive model is developed where the effective constitutive functionals along with the associated constants are determined. The model is validated by experimental data with which multiple demonstrations of temperature effects are assessed and analyzed.

An efficient genetic algorithm for solving open multiple travelling salesman problem with load balancing constraint

The multiple travelling salesman problem (MTSP) is one of the widely studied combinatorial optimization problems with various theoretical and practical applications. However, most of the studies intended to deal with classical MTSP, very limited attention has been given to an open multiple travelling salesman problem and its variants. In this paper, an open multiple travelling salesman problem with load balancing constraint (OMTSPLB) is addressed. The OMTSPLB differs from the conventional MTSP, in which all the salesmen start from the central depot and need not come back to it after visiting the given number of cities by accomplishing the load balance constraint, which helps in fairly distributing the task among all salesmen. The problem aims to minimize the overall traversal distance/cost for operating open tours subject to the load balancing constraint. A zero-one integer linear programming (0-1 ILP) model and an efficient metaheuristic genetic algorithm (GA), is established for the OMTSPLB. Since no existing study on OMTSPLB, the proposed GA is tested on the relaxed version of the present model, comparative results are reported. The comparative results show that the proposed GA is competent over the existing algorithms. Furthermore, extensive experiments are carried out on OMTSPLB and the results show that proposed GA can find the global solution effectively.

Appropriate search techniques to estimate Weibull function parameters in a Pinus spp. plantation

The Weibull function, a continuous probability distribution, is widely used for diameter distribution modelling, in which parameter estimation performance is affected by stand attributes and fitting methods. The Weibull cumulative distribution function is nonlinear, and classical fitting methods may provide a not optimal solution. Invoking the use of artificial intelligence by metaheuristics is reasonable for this optimisation task. Therefore, aimed and compared (1) the metaheuristics genetic algorithm and simulated annealing performance over the moment and percentile methods; (2) the hybrid strategy merging the metaheuristics tested and the percentile method and, (3) the metaheuristics fitness functions under basal area and density errors. A long-term experiment in a Pinus taeda stand subjected to crown thinning was used. According to our findings, all methods have a similar performance, independent of the thinning regimes and age. The pattern of the estimated parameters tends to be acceptable, as b increases over time and c increases after thinning. Overall, our findings suggest that methods based on metaheuristics have a higher precision than classical methods for estimating Weibull parameters. According to the classification test, the methods that involved simulated annealing stood out. The hybrid method involving this metaheuristic also stood out, with accurate estimates. Classical methods showed the poorest performance, and we therefore suggest the use of simulated annealing due to its faster processing time and high-quality solution.

Genetic Algorithm Based on Natural Selection Theory for Optimization Problems

The metaheuristic genetic algorithm (GA) is based on the natural selection process that falls under the umbrella category of evolutionary algorithms (EA). Genetic algorithms are typically utilized for generating high-quality solutions for search and optimization problems by depending on bio-oriented operators such as selection, crossover, and mutation. However, the GA still suffers from some downsides and needs to be improved so as to attain greater control of exploitation and exploration concerning creating a new population and randomness involvement happening in the population at the solution initialization. Furthermore, the mutation is imposed upon the new chromosomes and hence prevents the achievement of an optimal solution. Therefore, this study presents a new GA that is centered on the natural selection theory and it aims to improve the control of exploitation and exploration. The proposed algorithm is called genetic algorithm based on natural selection theory (GABONST). Two assessments of the GABONST are carried out via (i) application of fifteen renowned benchmark test functions and the comparison of the results with the conventional GA, enhanced ameliorated teaching learning-based optimization (EATLBO), Bat and Bee algorithms. (ii) Apply the GABONST in language identification (LID) through integrating the GABONST with extreme learning machine (ELM) and named (GABONST-ELM). The ELM is considered as one of the most useful learning models for carrying out classifications and regression analysis. The generation of results is carried out grounded upon the LID dataset, which is derived from eight separate languages. The GABONST algorithm has the capability of producing good quality solutions and it also has better control of the exploitation and exploration as compared to the conventional GA, EATLBO, Bat, and Bee algorithms in terms of the statistical assessment. Additionally, the obtained results indicate that (GABONST-ELM)-LID has an effective performance with accuracy reaching up to 99.38%.

Energy-efficient routing optimization algorithm in WBANs for patient monitoring

With the recent technological innovations for measuring the physiological characteristics in the human body, Wireless Body Area Networks (WBANs) have received much attention from the industry and academics. One of the feasible solutions provided by today’s WBAN is the continuous health monitoring in which sensors planted in various parts of the body, which measure and send information about physiological health status to a sink. The energy constraint WBAN has to perform these measurements with minimum energy consumptions of the nodes, maintaining the durable health monitoring process. This paper uses the meta-heuristic Genetic Algorithm (GA) to select the best routing path by calculating distances between the nodes under multiple scenarios, in contrast to the available direct distance optimization method. This study considers the use of energy by sensor nodes, number of rounds, number of sensors, the position of the deployed sensors and distance between the sensors. The comprehensive results show that direct distance optimization method drops more packets, i.e. 12,000 as compared to 8000 packets by the genetic algorithm when 8000 rounds were executed. The proposed optimization also outperforms the previous approach in terms of the number of dead nodes, which results in saving the energy to increase the lifetime of the WBAN significantly.

Hybrid of Meta Heuristic Firefly and Genetic Algorithm for Optimization Approach in the Cloud Environment

Hybrid of Meta Heuristic Firefly and Genetic Algorithm for Optimization Approach in the Cloud Environment

Determination of Necessary Subsidiary Track According to Train Operation Frequency in a Heterogeneous Train Pattern

In this study, a genetic algorithm was used to calculate the scheduled waiting time according to the train operation frequency of heterogeneous trains operating on one track. The acquired data were then used to determine the appropriate subsidiary track at which high-speed trains can load or release cargo away from low-speed trains. A metaheuristic genetic algorithm was applied and implemented using Javascript/jQuery. Six cases were investigated, which provided values of subsidiary track that vary according to the operation frequencies of different types of trains, and solutions were derived through 100 simulations using a stochastic method. The analysis results showed that the train overtaking frequency was the highest at the third intermediate station within the simulation, suggesting that this particular station requires a subsidiary track, even if the operating frequency of each train differs across the entire track considered in this study. The results of this study are expected to facilitate objective and practical planning during railway construction.

RETRACTED ARTICLE: Meta heuristic QoS based service composition for service computing

In Service Computing, Service selection plays a vital role in delivering an appropriate service to the end user based on the request. Service composition methodology is the major factor affecting the appropriate need for the user or the consumer. The proposed technique involve the use of hybrid meta heuristics genetic algorithm with tabu search to retrieve the best suitable web service to the end user based on the Quality of service parameters. The existing techniques use the parameters response time, cost and reliability. The technique used in hybrid algorithm is used computes the availability of service, response time, throughput and interoperability between the services. Hence the result of service composition gives high reliable service to the end user with maximum throughput and interoperability. The location based service selection mechanism is considered for service composition as almost 90% of the services are available in cloud.

Optimization of Marketing Workforce Scheduling Using Metaheuristic Genetic Algorithms

Optimization of Marketing Workforce Scheduling Using Metaheuristic Genetic Algorithms

Performance of four meta-heuristics to solve a forestry production planning problem

The use of artificial intelligence as a tool to aid in the planning of forest production has gained more and more space. Highlighting the metaheuristics, due to the ability to generate optimal solutions for a given optimization problem in a short time, without great computational effort. The present study aims to evaluate the performance of the metaheuristics Genetic Algorithm, Simulated Annealing, Variable Neighborhood Search and Clonal Selection Algorithm applied in a model of regulation of forest production. It was considered a planning horizon of 16 years, in which the model aims to maximize the Net Present Value (NPV), having as restrictions age of cut between 5 and 7 years and minimum and maximum logging demand of 140,000 and 160,000 m3, respectively. Different combinations of configurations were considered for each of the metaheuristics, 30-second processing time and 30 replicates for each configuration, all processing being performed in MeP - Metaheuristics for forest Planning software. The Simulated Annealing metaheuristic obtained the best results when compared to the others, reaching the minimum and maximum demand demanded in all tested configurations, in contrast, the Genetic Algorithm was the one with the worst performance. Thus, the capacity to use metaheuristics as a tool for forest planning is observed.

A MODELING FRAMEWORK OF HIERARCHICAL EARTHQUAKE RELIEF CENTER LOCATIONS UNDER DEMAND UNCERTAINTY

This paper presents a modeling framework for locating earthquake disaster relief centers, developed through multidimensional and integrated perspectives of transportation engineering and humanitarian logistics planning. The proposed framework consists of three sequential steps: 1) Seismic risk analysis, to evaluate the vulnerability of both road network and area-covering disruptions, using the spaghetti and meatballs method, which is a geographic information system (GIS) based analytical approach enriched with historical earthquake statistics and earthquake fault data; 2) Travel demand analysis, to forecast travel demand, travel behavior, travel pattern, and traffic volume, using the four-step transportation model developed based on field traffic survey data and seismic risk analysis data; and 3) Facility location problem analysis, to locate optimal earthquake disaster relief centers, using the hierarchical location problem model formulated based on a meta-heuristic genetic algorithm (GA) optimization technique. To evaluate model mechanism and performance, a preliminary model was then applied to the simulated geographical area with simulated road network of Chiang Rai Province, Thailand. As a result, two-level hierarchical disaster relief centers in response to earthquakes, taking into account accessibility and functional ability of transportation networks, risk covered/uncovered demand and supply distribution, can be viably determined. In the upperlevel, a central disaster relief center is functioned to collect rescue equipment and survival bags from both inside and outside the area and to distribute those to local disaster relief centers in the area. In the lowerlevel, three local disaster relief centers were optimally located, functioned to receive supplies from the central disaster relief center and then distribute to demand points affected by earthquakes. The resulting model can provide government and related agencies profound information in planning and developing either pre-disaster or post-disaster operations.

Test Case Optimization for Enhancing System Software Quality using Genetic Algorithm

Software Product Lines (SPLs) embraces an enormous capacity of feature mixtures which cause challenges for evaluating software programs. Testsuite optimization plays major role to develope the quality of SPLs. In combinatorial testing (CT), pair wise fault coverage maximization and test case reduction accomplishes a substantial role for shrinking the testing cost of software programs. Many research works have been developed and designed for CT using different test suite reduction techniques. However Fuzzy clustering and TSRSO techniques do not provide a finest solution for test suite optimization problem. For that, Genetic Algorithm (GA) Technique is recommended and designed for test suite reduction in CT. Metaheuristic genetic algorithm delivers optimum solution in an effective manner. GA chooses and consolidates the testcases in a testsuite based on some principles such that maximum faults covered with minimum execution time. In Proposed GA, finest individuals are nominated for reproduction in order to create descendants of the succeeding generation. In addition, GA is a superior type of evolutionary algorithms generate finest solutions to optimization problems using selection, crossover and mutation operators. Consequently, GA is applied for resolving test suite reduction problem in CT.

Challenging soft computing optimization approaches in modeling complex hydraulic phenomenon of aeration process

ABSTRACT This study investigates and challenges the capability of standard and hybrid soft computing models of fuzzy c-means clustering adaptive neuro-fuzzy inference system (ANFIS), wavenet and artificial neural networks (MLPNN and RBFNN) to estimate the spillway aerator air demand in dams. For the learning process, four different meta-heuristic optimization methods (particle swarm optimization (PSO), genetic algorithm (GA), firefly algorithm (FA) and biogeography-based optimization (BBO)) are considered as alternatives to the classical optimization algorithms of the data-driven models. In addition to the data-driven models, the multiple linear regressions and some empirical relations are used to evaluate the performance of the models. Evaluation of the models is assessed with five different statistical parameters as well as the diagnostic tool of the Taylor’s diagram. Analysis of the models’ outcome reveals that the ANFIS-GA has the best performance associated with a standard root mean square error of 0.309 and a coefficient of determination (R2 ) of 0.93.

Adaptive Protection Coordination Scheme Using Numerical Directional Overcurrent Relays

Dynamically changing distribution system operating conditions compromises the coordination of the existing protection schemes. This paper proposes an online adaptive protection coordination scheme by utilizing numerical directional overcurrent relays (DOCRs) and commercial A Mathematical Programming Language (AMPL) based Interior Point OPTimization (IPOPT) solver. The proposed scheme also utilizes intelligent electronic devices and a communication channel to obtain real-time system information and to update relays settings. The presented approach is able to handle different operating conditions of the system, including loss of loads, generations, and lines. Further, the miscoordination arising due to injections of distributed generations (DGs) is also handled. The proposed approach has been tested on the IEEE 14-bus system (with and without DG), under various operating conditions. Overall system reliability enhancement using the proposed approach has been analyzed in terms of the amount of energy not supplied. Further, the optimum settings of DOCRs obtained using AMPL based IPOPT solver has been compared with those obtained by General Algebraic Modeling System based Sparse Nonlinear OPTimizer solver, OPTI Toolbox based IPOPT solver, MATLAB based interior point method, and metaheuristic genetic algorithm and differential evolution. It has been found that the proposed coordination approach gives good results in reasonably small time and thus, is suitable for the adaptive protection scheme.