Multi-objective Optimization Approach Research Articles

Sustainable and Resilient Land Use Planning: A Multi-Objective Optimization Approach

Land use allocation (LUA) is of prime importance for the development of urban sustainability and resilience. Since the process of planning and managing land use requires balancing different conflicting social, economic, and environmental factors, it has become a complex and significant issue in urban planning worldwide. LUA is usually regarded as a spatial multi-objective optimization (MOO) problem in previous studies. In this paper, we develop an MOO approach for tackling the LUA problem, in which maximum economy, minimum carbon emissions, maximum accessibility, maximum integration, and maximum compactness are formulated as optimal objectives. To solve the MOO problem, an improved non-dominated sorting genetic algorithm III (NSGA-III) is proposed in terms of mutation and crossover operations by preserving the constraints on the sizes for each land use type. The proposed approach was applied to KaMavota district, Maputo City, Mozambique, to generate a proper land use plan. The results showed that the improved NSGA-III yielded better performance than the standard NSGA-III. The optimal solutions produced by the MOO approach provide good trade-offs between the conflicting objectives. This research is beneficial for policymakers and city planners by providing alternative land use allocation plans for urban sustainability and resilience.

Maximizing efficiency in sunflower breeding through historical data optimization

Genomic selection (GS) has become an increasingly popular tool in plant breeding programs, propelled by declining genotyping costs, an increase in computational power, and rediscovery of the best linear unbiased prediction methodology over the past two decades. This development has led to an accumulation of extensive historical datasets with genotypic and phenotypic information, triggering the question of how to best utilize these datasets. Here, we investigate whether all available data or a subset should be used to calibrate GS models for across-year predictions in a 7-year dataset of a commercial hybrid sunflower breeding program. We employed a multi-objective optimization approach to determine the ideal years to include in the training set (TRS). Next, for a given combination of TRS years, we further optimized the TRS size and its genetic composition. We developed the Min_GRM size optimization method which consistently found the optimal TRS size, reducing dimensionality by 20% with an approximately 1% loss in predictive ability. Additionally, the Tails_GEGVs algorithm displayed potential, outperforming the use of all data by using just 60% of it for grain yield, a high-complexity, low-heritability trait. Moreover, maximizing the genetic diversity of the TRS resulted in a consistent predictive ability across the entire range of genotypic values in the test set. Interestingly, the Tails_GEGVs algorithm, due to its ability to leverage heterogeneity, enhanced predictive performance for key hybrids with extreme genotypic values. Our study provides new insights into the optimal utilization of historical data in plant breeding programs, resulting in improved GS model predictive ability.

A note on Steuer and Utz’s (2023) multi-objective optimization approach for generating sustainability-efficient fronts

Motivated by the increasing importance of sustainability in investing, Steuer and Utz (2023) propose a new approach for integrating environmental, social and governance (ESG) scores into the portfolio selection process. These authors claim that their multi-objective portfolio optimization problem always provides mean-variance-ESG-efficient solutions because it belongs to the class of ϵ-constraint problems. Contending that this classification is problematic, we show that the developed approach cannot guarantee efficient portfolios.

Optimal operation and control of hybrid power systems with stochastic renewables and FACTS devices: An intelligent multi-objective optimization approach

This paper delves into the increasingly complex domain of Optimal Power Flow (OPF) within modern power systems, enhanced by the integration of unpredictable renewable energy sources. The research originally integrates stochastic photovoltaic and wind energy sources, along with a suite of Flexible AC Transmission System (FACTS) components – including thyristor-controlled series compensators, static VAR compensators, and thyristor-controlled phase shifters. The primary objective is to solve the OPF problem by reducing generation costs while accommodating the variable nature of renewable energy sources and load demands. This study prioritizes the examination of both constant and fluctuating load requirements. The inherent variability of PV and wind energy, along with load demand, is captured through the modelling of probability density functions. This approach enables a more detailed optimization process, incorporating not just the cost of thermal energy generation but also the scheduling costs of renewable sources and associated penalty costs. Moreover, the study examines the strategic placement and sizing of FACTS components, an aspect essential in minimizing the overall cost of power production. Employing both single- and multi-objective optimization algorithms, the research addresses the OPF problem in a modified IEEE-30 bus system through various case studies. The application of the recently developed flow direction algorithm, including its multi-objective variant with an ε-based constraint-handling mechanism to OPF problem is the primary contributions of this work. The results, benchmarked against several advanced metaheuristic algorithms, reveal the proposed algorithm's superior performance. This comprehensive study not only underscores the potential of integrating renewable energy sources into the grid but also highlights the efficacy of intelligent optimization strategies in managing the complexities of modern power systems.

L-Lactide ring-opening polymerization: a multi-objective optimization approach through mathematical modeling

L-Lactide ring-opening polymerization: a multi-objective optimization approach through mathematical modeling

Improving continental hydrological models for future climate conditions via multi-objective optimisation

Australian hydrological characteristics vary across the continent, encompassing diverse climate zones with wet and dry extremes. Moreover, Australia’s hydro-climate is projected to change in response to rising greenhouse gas emissions, where change is now evident from observations. Adaptation to these projected-to-be more intense impacts, requires nationally consistent hydro-climate projections along with an historical context.Calibrating a continental hydrological model against multiple objectives and varying hydroclimate conditions will enable a robust model configuration, thereby improving confidence in projections. We propose using a multi-objective optimisation approach to tune a continental model to represent stores and fluxes across the water cycle, current regional hydroclimes and possible future climate changes. By devising a set of experiments or scenarios which represent plausible projected futures and regional hydrological characteristics, trade-offs between different scenarios are assessed. We show that whilst no one parameter set “fits all” scenarios, this approach can provide a model configuration which “fits most”.

Research on Lighting Schemes for College Gymnasiums Based on Dynamic Light Environment Simulation

The purpose of this study is to explore and optimize natural lighting schemes for college gymnasiums through dynamic light environment simulation. The study used Daysim software, combined with Rhino & Grasshopper for modeling and parameter optimization, to evaluate different lighting schemes through a multi-objective optimization approach. The results show that the effective indoor illuminance of the top lighting scheme at DA300lx, UDI100-2000lx, aDGP(0.4), DA580lx, and UDI300-890lx are 91.50%, 88.44%, 90.58\%, 92.56%, and 52.89%, respectively, which show good lighting effects. The side lighting scheme also shows excellent lighting performance in different configurations. In addition, the side + top synergistic light harvesting scheme achieved efficient light environment utilization while ensuring visual comfort. This study suggests that the top and side synergistic lighting scheme can effectively enhance the natural lighting effect of the gymnasium. This study provides a scientific basis for the lighting design of college gymnasiums and is of great significance in guiding the actual engineering design.

Machine Learning Algorithms for Predictive Maintenance in Industrial Environments: A Comparative Study

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases.
 
 While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications

Security Challenges of Vehicular Cloud Computing

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases. While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

Machine Learning Algorithms for Predictive Maintenance in Industrial Environments: A Comparative Study

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases. While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

Multi-objective optimization and theoretical analysis of re-entrant structure with enhanced mechanical properties

In response to the challenge of low stiffness and energy absorption capacity, various designs of negative Poisson's ratio (NPR) structures have emerged. However, these designs often lack a comprehensive analysis of other mechanical properties, leading to subpar mechanical performance. Previous studies have explored the mechanical properties response of enhanced re-entrant honeycombs (ERH) under impact conditions, revealing limitations in optimizing the structure's performance with a single objective. Therefore, this study aims to enhance ERH structural parameters to achieve superior mechanical performance through theoretical derivations and geometric optimizations. The results demonstrate that the proposed theoretical model is consistent with finite element analysis and response surface (RS) predictions. Expressions for Young's modulus, specific energy absorption, and compressive strength are proposed, facilitating the identification of structural parameters that meet specific requirements during reverse design. Furthermore, a multi-objective optimization approach optimizes the geometric parameters based on maximum energy absorption and compressive strength. The mechanical behavior of the optimized ERH is investigated using the finite element method, revealing the energy absorption capacity of 13.78 J/g while maintaining Poisson's ratio at -1.06. Additionally, the deformation mode of the optimized structure showcases enhanced stability compared to traditional honeycomb structures. The theoretical model and RS method were used to guide the design of ERH and promote the application of NPR structures.

Security Challenges of Vehicular Cloud Computing

In the realm of Industry 4.0, the utilization of artificial intelligence (AI) and machine learning for anomaly detection faces challenges due to significant computational demands and associated environmental consequences. This study aims to tackle the need for high-performance machine learning models while promoting environmental sustainability, contributing to the emerging concept of 'Green AI.' We meticulously assessed a wide range of machine learning algorithms, combined with various Multilayer Perceptron (MLP) configurations. Our evaluation encompassed a comprehensive set of performance metrics, including Accuracy, Area Under the Curve (AUC), Recall, Precision, F1 Score, Kappa Statistic, Matthews Correlation Coefficient (MCC), and F1 Macro. Concurrently, we evaluated the environmental footprint of these models by considering factors such as time duration, CO2 emissions, and energy consumption during training, cross-validation, and inference phases.
 
 While traditional machine learning algorithms like Decision Trees and Random Forests exhibited robust efficiency and performance, optimized MLP configurations yielded superior results, albeit with a proportional increase in resource consumption. To address the trade-offs between model performance and environmental impact, we employed a multi-objective optimization approach based on Pareto optimality principles. The insights gleaned emphasize the importance of striking a balance between model performance, complexity, and environmental considerations, offering valuable guidance for future endeavors in developing environmentally conscious machine learning models for industrial applications.

A multi-objective stacked regression method for distance based colour measuring device

Identifying colour from a distance is challenging due to the external noise associated with the measurement process. The present study focuses on developing a colour measuring system and a novel Multi-target Regression (MTR) model for accurate colour measurement from distance. Herein, a novel MTR method, referred as Multi-Objective Stacked Regression (MOSR) is proposed. The core idea behind MOSR is based on stacking as an ensemble approach with multi-objective evolutionary learning using NSGA-II. A multi-objective optimization approach is used for selecting base learners that maximises prediction accuracy while minimising ensemble complexity, which is further compared with six state-of-the-art methods over the colour dataset. Classification and regression tree (CART), Random Forest (RF) and Support Vector Machine (SVM) were used as regressor algorithms. MOSR outperformed all compared methods with the highest coefficient of determination values for all three targets of the colour dataset. Rigorous comparison with state-of-the-art methods over 18 benchmarked datasets showed MOSR outperformed in 15 datasets when CART was used as a regressor algorithm and 11 datasets when RF and SVM were used as regressor algorithms. The MOSR method was statistically superior to compared methods and can be effectively used to measure accurate colour values in the distance-based colour measuring device.

Computational Investigation of the Influence of Combustion Chamber Characteristics on a Heavy-Duty Ammonia Diesel Dual Fuel Engine

In response to increasingly stringent emissions regulations and the depletion of conventional fuel sources, integrating carbon-free fuels into the transport sector has become imperative. While hydrogen (H2) presents significant technical challenges, ammonia (NH3) could present a better alternative offering ease of transport, storage, and distribution, with both ecological and economic advantages. However, ammonia substitution leads to high emissions of unburned NH3, particularly at high loads. Combustion chamber retrofitting has proven to be an effective approach to remedy this problem. In order to overcome the problems associated with the difficult combustion of ammonia in engines, this study aims to investigate the effect of the piston bowl shape of an ammonia/diesel dual fuel engine on the combustion process. The primary objective is to determine the optimal configuration that offers superior engine performance under high load conditions and with high ammonia rates. In this study, a multi-objective optimization approach is used to control the creation of geometries and the swirl rate under the CONVERGETM 3.1 code. To maximize indicated thermal efficiency and demonstrate the influence of hydrogen enrichment on ammonia combustion in ammonia/diesel dual fuel engines, a synergistic approach incorporating hydrogen enrichment of the primary fuel was implemented. Notably, the optimum configuration, featuring an 85% energy contribution from ammonia, outperforms others in terms of combustion efficiency and pollutant reduction. It achieves over 43% reduction in unburned NH3 emissions and a substantial 31% improvement in indicated thermal efficiency.

Data-Driven Multi-Objective Optimization Approach to Loaded Meshing Transmission Performances for Aerospace Spiral Bevel Gears.

Loaded meshing transmission performance optimization has been an increasingly significant target for the design and manufacturing of aerospace spiral bevel gears with low noise and high strength. An innovative data-driven multi-objective optimization (MOO) method is proposed for the loaded meshing transmission performances of aerospace spiral bevel gears. Data-driven tooth surface modeling is first used to obtain a curvature analysis of loaded contact points. An innovative numerical loaded tooth contact analysis (NLTCA) is applied to develop the data-driven relationships of machine tool settings with respect to loaded meshing transmission performance evaluations. Moreover, the MOO function is solved by using an achievement function approach to accurate machine tool settings output, satisfying the prescribed requirements. Finally, numerical examples are given to verify the proposed methodology. The presented approach can serve as a powerful tool to optimize the loaded meshing transmission performances with higher computational accuracy and efficiency than the conventional methods.

Comparative analysis of space layouts and facade systems for office retrofit design in hot climate

ABSTRACT Worldwide, office buildings account for almost one-third of global energy consumption. Therefore, the energy retrofit design of office buildings could reduce total energy consumption. Considering the benefits of advanced facade systems, retrofit facade design is an effective strategy for energy conservation while improving daylight performance, occupant well-being, and productivity. This paper compares the daylight and energy performance of single and double-skin facade systems used in a typical office building in a hot climate with different space layouts. The main objective is to optimize the daylight and energy performance of various facade systems in combination with a wide range of design variables. Simulations were conducted in DesignBuilder software using a multi-objective optimization approach. Eleven design variables and 103 simulations were considered with the objective of enhancing daylight performance while reducing cooling and lighting loads. Based on the results, single-skin facade configurations could enhance daylight performance significantly compared to double-skin facades, while double-skin facades performed better by reducing the risk of glare and annual energy consumption. Using single and double-skin facade systems could reduce annual total energy consumption by 50% and 60% compared to the existing building.

A novel implicit decision variable classification approach for high-dimensional robust multi-objective optimization in order scheduling

This paper efficiently addresses the high-dimensional robust order scheduling problem. A novel algorithm named dynamic cooperative coevolution based on an implicit decision variable classification approach (DCC/IDVCA) is developed to search for robust order schedules. To significantly reduce the computational resources required for solving the high-dimensional robust order scheduling problem, we propose decomposing the original decision variables through implicit classification methods. First, a novel estimation method is introduced to evaluate the weighted contribution of variables to robustness. This method utilizes historical information, including the variation of the overall mean effective fitness and the frequency of variables being classified into highly robustness-related subcomponents in previous cycles, for evaluating their weighted contribution to robustness. Then, based on the corresponding weighted robustness contributions, the original variables are classified into highly and weakly robustness-related variables. Finally, these two types of variables are decomposed into highly and weakly robustness-related subgroups within a dynamic cooperative coevolution framework and optimized separately. In the experimental section, the proposed algorithm is applied to two practical order scheduling problems in discrete manufacturing industry. The experimental results demonstrate that the proposed algorithm achieves competitive outcomes compared to state-of-the-art high-dimensional robust multi-objective optimization algorithms.

Improving the mechanical and thermal performance of bio-based concrete through multi-objective optimization

Bio-based concrete, which utilizes recycled agricultural waste as aggregates, has emerged as a sustainable alternative material in the construction industry. Optimizing its combined mechanical and thermal performance can promote its environmental and energy benefits. To achieve this, this paper presents a multi-objective optimization approach to improve the overall performance of bio-based concrete based on multiscale structural features, considering the porosity, shape, orientation, and volume fraction. Optimization strategies are provided for three main industrial applications. Furthermore, this study addresses multiple design requirements, including high-volume bio-aggregates, more demanding performance requirements, low densities, and humid environments. The optimization results demonstrate that the optimal solution varies with industrial applications and requirements. Consequently, we quantitatively provide specific optimal solutions for each case, and offer designers three preferences for mechanical properties, insulation, or balanced performance. Overall, this study optimizes the comprehensive performance of bio-based concrete in terms of multiscale structures, thereby contributing to a more sustainable construction industry.

A Multi-Objective Optimization Approach for Low Volume Rural Road Maintenance Management Incorporating Socioeconomic Importance

A Multi-Objective Optimization Approach for Low Volume Rural Road Maintenance Management Incorporating Socioeconomic Importance

Multi-objective optimisation of a logistics area in the context of factory layout planning

ABSTRACT The manufacturing factory layout planning process is commonly supported by the use of digital tools, enabling creation and testing of potential layouts before being realised in the real world. The process relies on engineers’ experience and inputs from several cross-disciplinary functions, meaning that it is subjective, iterative and prone to errors and delays. To address this issue, new tools and methods are needed to make the planning process more objective, efficient and able to consider multiple objectives simultaneously. This work suggests and demonstrates a simulation-based multi-objective optimisation approach that assists the generation and assessment of factory layout proposals, where objectives and constraints related to safety regulations, workers’ well-being and walking distance are considered simultaneously. The paper illustrates how layout planning for a logistics area can become a cross-disciplinary and transparent activity, while being automated to a higher degree, providing objective results to facilitate informed decision-making.