Simple Efficient Hybridization of Classic Global Optimization and Genetic Algorithms for Multiobjective Optimization

This paper considers the combined use of a hybrid numerical method for the modeling of acoustic mufflers and a genetic algorithm for multiobjective optimization. The hybrid numerical method provides accurate modeling of sound propagation in uniform waveguides with non-uniform obstructions. It is based on coupling a wave based modal solution in the uniform sections of the waveguide to a finite element solution in the non-uniform component. Finite element method provides flexible modeling of complicated geometries, varying material parameters, and boundary conditions, while the wave based solution leads to accurate treatment of non-reflecting boundaries and straightforward computation of the transmission loss (TL) of the muffler. The goal of optimization is to maximize TL at multiple frequency ranges simultaneously by adjusting chosen shape parameters of the muffler. This task is formulated as a multiobjective optimization problem with the objectives depending on the solution of the simulation model. NSGA-II genetic algorithm is used for solving the multiobjective optimization problem. Genetic algorithms can be easily combined with different simulation methods, and they are not sensitive to the smoothness properties of the objective functions. Numerical experiments demonstrate the accuracy and feasibility of the model-based optimization method in muffler design.

In this research, a grid-connected hybrid renewable electricity system was studied with the aim of providing the required electricity to the buildings of Yazd city in Iran. All possible structures of the proposed system were simulated using the genetic algorithm and TRNSYS software. Then the final stable population was categorised into three clusters using the statistical quartiles. Based on the results, only about 1% of all investigated structures were optimum considering energy cost and CO2 emission. Investigating the best-identified structures showed that it could decrease the CO2 emission by about 92% and energy cost by about 35% compared to the case where only the grid electricity was used. Moreover, wind energy had the highest priority, and using batteries was not an appropriate solution for the study area. The results showed that identifying an optimum cluster can be used efficiently instead of as a unique solution for the studied system. Highlights Hybrid electricity supply system. Combination of Cluster Analysis and Genetic algorithm for multi-objective optimisation. Simulating the control strategies for energy systems.

A genetic algorithm (GA) based on mulii niche crowding ('C) is capable of locating all the peaks of a multi-modal function. By associating these peaks with the utility accrued >om diflerent sets of decision variables, it is possible to extend the use of GAS to multi criteria decision making. This concept is applied io the remediation of a contaminated aquifer. The MNC GA is used to decide the optimal location of pumping wells. Aquifer dynamics are simulated by solving the partial diflerential equations describing the flow of water using SUTRA code. Output of this simulation constitutes the input to the GA. Kqwordr: Genetic algorithms, multi-modal functions, multi-objective optimization, aquifer remediation, ground water management

Abstract: Inversion of self-potential anomaly for 2-D inclined sheets of infinite horizontal extent has been studied. Least-square inversion and very fast simulated annealing global optimization has been used to model the five parameters of self potential anomaly. The method of least square and very fast simulated annealing global optimization method is compared and analyzed. Very fast simulated annealing can model the noisy and field data of self potential anomaly very precisely than linear inversion technique. However, time taken by very fast simulated annealing inversion is larger than linearized inversion. The comparative analysis has been done on synthetic data (noise free and noisy) and two field data from Bavarian woods anomaly, Germany and Surda anomaly, India to show the efficacy of both the methods. The estimated parameters were compared with those from previous studies using various global optimization algorithms, mainly neural network, genetic algorithm and particle swarm optimization on the same field data sets. It can be concluded that the global optimization algorithms considered in this study were able to yield compatible solutions with those from least-square methods. The present global optimization method is in good agreement with the other global optimization methods in terms of results and computation time.

Rotary travelling wave oscillator (RTWO) represents a transmission line based technology for multigigahertz clock generation. RTWO design is a multi-parameter-multi-objective problem with tradeoffs of performance measures, power and phase noise. In this paper, non-dominated based genetic algorithm for multi-objective optimization is used to determine the Pareto optimal front of solutions for low power and phase noise with emphasis on variation of transmission line width and spacing. Optimization is followed by sensitivity assessment wherein Monte Carlo simulations and corner analysis are performed on the Pareto points with respect to process variations. The algorithm is validated in the design of RTWO whose frequency varies between 3 to 5 GHz due to varying dimensions of coupled transmission line. The optimization is a two step process. A neural network is developed from experimental data to estimate phase noise and power with transmission line width and spacing as inputs. The neural network is then coupled with genetic algorithm for subsequent design optimization. Our results show a set of solutions for width and spacing with objective functions less sensitive to process variations.

• Seasonally adaptive PV–BESS dispatch framework for high EV penetration grids. • CNN–BiLSTM model achieves >92 % accuracy in short-term PV forecasting. • GA optimizes multi-objective PV-EV-BESS scheduling. • Reduces feeder losses by 63.55 % and Voltage Unbalance Factor by 55 %. • Enhances PV utilization, power quality, and grid resilience under stress. The rapid proliferation of photovoltaic (PV) systems and electric vehicles (EVs) poses significant challenges for distribution networks, including voltage unbalance, high feeder losses, and deteriorating power quality, further complicated by seasonal variability in solar output and demand. This paper proposes a seasonally adaptive PV–battery energy storage system (BESS) dispatch strategy that integrates short-term PV forecasting with multi-objective optimization. The primary novelty of this work lies in the tight integration of a seasonally adaptive, forecasting-driven dispatch strategy that synergistically combines a hybrid CNN-BiLSTM model for high-accuracy PV prediction with a Genetic Algorithm for multi-objective optimization in unbalanced distribution grids. A hybrid CNN–BiLSTM model, trained on distinct seasonal datasets (summer and winter) from NASA irradiance data, enables accurate real-time PV prediction, achieving an RMSE of 13.99 kWh, MAE of 12.94 kWh, and MAPE of 7.45 %, corresponding to a forecasting accuracy of 92.55 %. Meanwhile, a genetic algorithm (GA) optimizes coordinated PV–BESS scheduling under diverse seasonal scenarios. The approach is validated on a modified IEEE 13-bus system, demonstrating robustness across a wide range of EV penetration levels (40–70 %) and both summer and winter conditions, and showing reductions of up to 55 % in Voltage Unbalance Factor (VUF) and 63.55 % in feeder losses, alongside enhanced PV utilization. Compared to uncoordinated dispatch, the proposed framework delivers superior power quality, higher grid resilience, and practical scalability. The framework is designed for real-world application, with the forecasting model providing high-frequency predictions and the GA-based optimization operating on a computationally feasible hourly rolling horizon, making it suitable for deployment in larger distribution networks. These findings highlight the potential of forecast-driven, seasonally aware coordinated dispatch as a practical pathway toward reliable and sustainable smart grid operation.

This article investigates the impact of SiC MOSFET module’s drive and parasitic parameters on common-mode voltage (CMV). A time-domain model of the switching noise source is derived, considering drive and parasitic parameters, and its frequency spectrum is obtained through the Fourier transform. The propagation path of CM noise based on a double-pulse test circuit is, furthermore, analyzed. Second, an ANSYS/Simplorer-based simulation test platform is established to evaluate the comprehensive sensitivity analysis of the impact of various parameters on electrical stress, loss, and CMV. Based on this, this article proposes a multiobjective optimization algorithm where the simulation solution is used as the initial solution set. The optimization of the parameters with high comprehensive sensitivity is performed using a multiobjective genetic optimization algorithm, and the optimal design was selected from the Pareto front generated by Nondominated Sorting Genetic Algorithm (NSGA-II). The importance of these proper drive parameters is verified by a 1500 V/150 kW Boost converter. The results show that the optimized selected drive parameters operating at rated conditions, provide attenuation of up to 5.2 dB in the 0.15–30 MHz frequency bands, and reduce the voltage stress and the current stress by 33.8 V and 31 A.

Many simple decision processes are based on a single objective such as minimizing cost, maximizing profit, minimizing runtime and so forth. However decisions must be made in an environment where more than one objective, constrains the problem, and the relative value of each of these objective is different. Such problems where multiple objectives are to be optimized are known as Multi-objective optimization (MOO) problems. The problem becomes challenging in case of mutually conflicting objectives i.e. the optimal solution widely varies with the shifting of focus from one objective to the other while all of them are quite relevant for the problem. MOO is used in various fields viz. Production Planning, Structural Design etc. There are various genetic approaches to solve multi-objective optimization problems like Non-dominated sorting GA (NSGA-II), Strength Pareto Evolutionary Approach (SPEA) etc. Each of these methods has their pros and cons and none of these is found to be perfect. In this paper we present a comparative study of the various available methods based on evolutionary genetic algorithms for Multi-Objective Optimization on different performance metrics.

In this study, a problem space genetic algorithm (PSGA) is used to solve bicriteria tool management and scheduling problems simultaneously in flexible manufacturing systems. The PSGA is used to generate approximately efficient solutions minimizing both the manufacturing cost and total weighted tardiness. This is the first implementation of PSGA to solve a multiobjective optimization problem (MOP). In multiobjective search, the key issues are guiding the search towards the global Pareto-optimal set and maintaining diversity. A new fitness assignment method, which is used in PSGA, is proposed to find a well-diversified, uniformly distributed set of solutions that are close to the global Pareto set. The proposed fitness assignment method is a combination of a nondominated sorting based method which is most commonly used in multiobjective optimization literature and aggregation of objectives method which is popular in the operations research literature. The quality of the Pareto-optimal set is evaluated by using the performance measures developed for multiobjective optimization problems.

In this paper a new method for solving multicriteria optimization problems by Genetic Algorithms is proposed. Standard Genetic Algorithms use a population, where each individual has the same sex (or has no sex) and any two individuals can be crossed over. In the proposed Multisexual Genetic Algorithm (MSGA), individuals have an additional feature, their sex or gender and one individual from each sex is used in the recombination process. In our multicriteria optimization application there are as many sexes as optimization criteria and each individual is evaluated according to the optimization criterion related to its sex. Furthermore, a multi-parent crossover is applied to generate offspring of parents belonging to all different sexes, so the offspring represents intermediate solutions not totally optimal with respect to any single criterion. During the execution of the algorithm the set of nondominated solutions is updated and this set is presented as the output of MSGA at the end.

It is well understood that binary classifiers have two implicit objective functions (sensitivity and specificity) describing their performance. Traditional methods of classifier training attempt to combine these two objective functions (or two analogous class performance measures) into one so that conventional scalar optimization techniques can be utilized. This involves incorporating a priori information into the aggregation method so that the resulting performance of the classifier is satisfactory for the task at hand. We have investigated the use of a niched Pareto multiobjective genetic algorithm (GA) for classifier optimization. With niched Pareto GA's, an objective vector is optimized instead of a scalar function, eliminating the need to aggregate classification objective functions. The niched Pareto GA returns a set of optimal solutions that are equivalent in the absence of any information regarding the preferences of the objectives. The a priori knowledge that was used for aggregating the objective functions in conventional classifier training can instead be applied post-optimization to select from one of the series of solutions returned from the multiobjective genetic optimization. We have applied this technique to train a linear classifier and an artificial neural network (ANN), using simulated datasets. The performances of the solutions returned from the multiobjective genetic optimization represent a series of optimal (sensitivity, specificity) pairs, which can be thought of as operating points on a receiver operating characteristic (ROC) curve. All possible ROC curves for a given dataset and classifier are less than or equal to the ROC curve generated by the niched Pareto genetic optimization.

This paper demonstrates two approaches to achieve faster convergence and a better spread of Pareto solutions in fewer numbers of generations, compared to a few existing algorithms, including NSGA-II and SPEA2 to solve multi-objective optimization problems (MOP's). Two algorithms are proposed based on progressive stepping mechanism, which is obtained by the hybridization of existing Non-dominated Sorting Genetic Algorithm II (NSGA-II) with novel guided search schemes, and modified chromosome selection and replacement mechanisms. Progressive Stepping Non-dominated Sorting based on Local search (PSNS-L) controls the step size, and Progressive Stepping Non-dominated Sorting based on Utopia point (PSNS-U) method controls the number of divisions to generate better chromosomes in each generation to achieve faster convergence. Four multi-objective evolutionary algorithms (EA's) are compared for different benchmark functions and PSNS outperforms them in most cases based on various performance metric values. Finally a mechanical design problem has been solved with PSNS algorithms.

Life cycle cost, embodied energy and loss of power supply probability for the optimal design of hybrid power systems

This paper presents a new memory-based variable-length encoding genetic algorithm for solving multiobjective optimization problems. The proposed method is a binary implementation of the NSGA2 and it uses a Hash Table for storing all the solutions visited during algorithm evolution. This data structure makes possible to avoid the re-visitation of solutions and it provides recovering and storage of data with low computational cost. The algorithm memory is used for building crossover, mutation and local search operators with a parameterless variable-length encoding. These operators control the neighborhood based on the density of points already visited on the region of the new solution to be evaluated. Two classical multiobjective problems are used to compare two variations of the proposed algorithm and two variations of the binary NSGA2. A statistical analysis of the results indicates that the memory-based adaptive neighborhood operators are able to provide significant improvement of the quality of the Pareto-set approximations.KeywordsGenetic AlgorithmLocal SearchHash FunctionMultiobjective OptimizationHash TableThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Glass fiber reinforced polymer (GFRP)-stainless steel stacks used in the aircraft structural components. The assembly process of this components requires mechanical joining using bolt and nut. The conventional drilling process is commonly used for producing hole to position the bolt correctly. Drilling is the complex machining process due to the variation in geometrical chance along the cutting edge. Thrust force and hole surface roughness are responses that used to evaluate the performance of drilling process. The quality characteristic of these responses are “smaller-is-better.” The aim of this experiment is to identify the combination of process parameters for achieving required multiple performance characteristics in drilling process of GFRP-stainless steel stacks materials. The three important process parameters,i.e., point angle, spindle speed, and feed rate were used as input parameters. Point angle was set at two different levels, while the other two were set at three different levels. Hence, a 2 × 3 × 3 full factorial was used as design experiments. The experiments were replicated two times. The optimization was conducted by using the combination of backpropagation neural network method and genetic algorithm method. The architecture of developed BPNN network had 3 input layers, 1 hidden layers with 8 neurons and 2 output layers. The activation functions of the hidden layer, the output layer and the network training were tansig, purelin and trainlm respectively. The minimum thrust force and hole surface roughness could be obtained by using point angle, spindle speed and feed rate of 118°, 2380 rpm, 61 mm/min respectively.