Multi-objective Framework Research Articles

Bi-Level Multiobjective Evolutionary Learning: A Case Study on Multitask Graph Neural Topology Search

The construction of machine learning models involves many bi-level multi-objective optimization problems (BL-MOPs), where upper level (UL) candidate solutions must be evaluated via training weights of a model in the lower level (LL). Due to the Pareto optimality of sub-problems and the complex dependency across UL solutions and LL weights, an UL solution is feasible if and only if the LL weight is Pareto optimal. It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution. This paper proposes a bi-level multi-objective learning framework (BLMOL), coupling the above decision-making process with the optimization process of the UL-MOP by introducing LL preference r. Specifically, the UL variable and r are simultaneously searched to minimize multiple UL objectives by evolutionary multi-objective algorithms. The LL weight with respect to r is trained to minimize multiple LL objectives via gradient-based preference multi-objective algorithms. In addition, the preference surrogate model is constructed to replace the expensive evaluation process of the UL-MOP. We consider a novel case study on multi-task graph neural topology search. It aims to find a set of Pareto topologies and their Pareto weights, representing different trade-offs across tasks at UL and LL, respectively. The found graph neural network is employed to solve multiple tasks simultaneously, including graph classification, node classification, and link prediction. Experimental results demonstrate that BLMOL can outperform some state-of-the-art algorithms and generate well-representative UL solutions and LL weights.

An Interactive Knowledge-Based Multiobjective Evolutionary Algorithm Framework for Practical Optimization Problems

Experienced users often have useful knowledge and intuition in solving real-world optimization problems. User knowledge can be formulated as inter-variable relationships to assist an optimization algorithm in finding good solutions faster. Such inter-variable interactions can also be automatically learned from high-performing solutions discovered at intermediate iterations in an optimization run – a process called innovization. These relations, if vetted by the users, can be enforced among newly generated solutions to steer the optimization algorithm towards practically promising regions in the search space. Challenges arise for large-scale problems where the number of such variable relationships may be high. This paper proposes an interactive knowledge-based evolutionary multi-objective optimization () framework that extracts hidden variable-wise relationships as knowledge from evolving high-performing solutions, shares them with users to receive feedback, and applies them back to the optimization process to improve its effectiveness. The knowledge extraction process uses a systematic and elegant graph analysis method which scales well with number of variables. The working of the proposed is demonstrated on three large-scale real-world engineering design problems. The simplicity and elegance of the proposed knowledge extraction process and achievement of high-performing solutions quickly indicate the power of the proposed framework. The results presented should motivate further such interaction-based optimization studies for their routine use in practice.

Multi-Objective Optimization for Sustainable Pavement Maintenance Decision Making by Integrating Pavement Image Segmentation and TOPSIS Methods

To provide a low-carbon economy maintenance strategy is the most challenging problem faced by pavement management authorities under the restricted budget and significant environmental repercussions. The development of a multi-objective optimization model for pavement maintenance decision making is essential to formulate pavements. Nevertheless, the existing automatic detection can only recognize and classify pavement distress. However, few studies are able to accurately determine the precise dimensions of specific distresses such as cracks and potholes, especially combined with the actual size of the image. This limitation hinders the ability to provide specific maintenance recommendations and make optimal maintenance decisions. Therefore, this paper develops a comprehensive and effective multi-objective decision-making framework for pavement maintenance. This framework consists of four distinct components: (1) recognizing the dimensions of pavement distresses based on the pavement image segmentation technique; (2) compiling a list of viable pavement maintenance strategies; (3) assessing the costs and carbon emissions of these strategies; and (4) optimizing decisions on pavement maintenance. We used the U-Net algorithm to accurately recognize the dimensions of pavement distresses, while an improved entropy-weighted TOPSIS model was proposed to determine the optimal pavement maintenance strategy with the lowest cost and carbon emissions. The results indicated that the pavement distress dimension recognition model achieved a high accuracy of 96.88%, and the TOPSIS model identified the optimal maintenance strategy with a score of 99.16. This maintenance strategy achieved a substantial reduction of 30.80% in carbon emissions and a cost reduction of 20.81% compared to the highest values among all maintenance strategies. This study not only provides a scientifically objective method for making pavement maintenance decisions but also offers specific, quantifiable maintenance programs, marking a stride towards more environmentally friendly and cost-effective road maintenance. It also contributes to the sustainability of pavement maintenance.

Multi-objective optimization for composition design of civil materials based on data-driven method

The performance of civil materials depends on their compositions. The material design is an important, challenging, and time-consuming work during the construction due to the complex relationship among different compositions and the conflict between properties and economic cost. This study developed a data-driven multi-objective optimization design framework to determine the reasonable material compositions based on laboratory experiment, reduced order model (ROM), and multi-objective optimization (MOO). The ROM was used to capture the complex relationship between the material compositions and the corresponding material performance. The MOO was utilized to determine the pareto optimal solution of compositions in the global space. Taking examples of cement grouts and modified asphalt binders, the develop framework was demonstrated and verified. The developed framework provides an excellent tool for composition design of civil materials.

Hybrid optimized task scheduling with multi-objective framework for crowd sensing in mobile social networks

Hybrid optimized task scheduling with multi-objective framework for crowd sensing in mobile social networks

Multiobjective and Coordinated Reconfiguration and Allocation of Photovoltaic Energy Resources in Distribution Networks Using Improved Clouded Leopard Optimization Algorithm

In this paper, a multiobjective framework for simultaneous reconfiguration and allocation of photovoltaic (PV) energy resources in radial distribution networks is performed for minimizing the power losses, lowering network loading factor, and reducing cost of energy resources as well as increasing the voltage stability index. A novel algorithm called the improved clouded leopard algorithm is used to find the set of optimum decision factors in the combined execution of restructuring and also PV resource distribution. The clouded leopard optimization (CLO) algorithm, which is widely used, takes its cues from the sleeping and foraging habits of the animal, and the improved CLO (ICLO) is formed using adaptive inertia weight to overcome premature convergence. In five cases of base distribution network and different contribution of reconfiguration and PV allocation, single- and multiobjective approach has been applied on 33- and 69-bus distribution networks. According to the findings, the best case includes simultaneous reconfiguration and PV allocation in the radial networks based on the multiobjective approach unlike the single-objective method which obtained the highest network performance with the best compromise between different goals. Also, in the best lowest losses, the decrease in the network loading and cost of energy resources and the better voltage profile and stability are obtained satisfying the constraints. The losses, network loading, voltage profile, and voltage stability are improved by 60.40%, 37.89%, 6.17%, and 27.5% for 33-bus network and also enhanced by 71.77%, 41.23%, 4.76%, and 20.48% for 69-bus network, respectively. Also, the results showed that network reconfiguration only has the weakest performance among other cases based on reconfiguration or photovoltaic sources. Moreover, the superior capability of the ICLO in addressing the aim of the study is proved in comparison with the traditional CLO and well-known particle swarm optimization (PSO) and manta ray foraging optimization (MRFO) to obtain the better objective value and statistical criteria to solve the best case.

Optimizing phosphorus fertilizer use to enhance water quality, food security and social equality

There are large regional differences regarding the use of phosphorus (P) fertilizer in global crop production. Likewise, people's accesses to crop calories and exposure to water pollution differ largely among world regions. The use of P fertilizer is needed to meet agricultural requirement and solve these inequalities. We developed a multi-objective framework for optimizing P fertilizer use that considered water quality, food security and social equality. Different optimal objectives yield contrasting results for the geographical distribution of P fertilizer use, crop calorie production and social equality. Optimized P fertilizer use without recycling P management may pose a threat to global food security. Approximately 3 %–43 % of the current global crop calorie production may be decreased, and inequality in access to crop calories may also increase. Overall, although a multi-objective framework to optimize the use of P fertilizer reduces crop calorie yield, it can help intergenerational equality of P fertilizer use and improve water quality.

Knowledge-transfer based genetic programming algorithm for multi-objective dynamic agile earth observation satellite scheduling problem

The multi-objective dynamic agile earth observation satellite scheduling problem (MO-DAEOSSP) aims to schedule a set of real-time arrival requests and form a reasonable observation plan to satisfy various criteria. According to the requirements in practical applications, the total profit and the average image quality of scheduled requests are taken as optimization goals in this study. Compared to manually designed heuristics and iterative-based methods used in previous research, genetic programming based hyper heuristics (GPHH) can automatically evolve high-quality heuristic rules (HRs) for real-time scheduling without being highly dependent on expert knowledge. In this paper, a knowledge-transfer based multi-objective GPHH framework (KT-MOGP) is proposed, equipped with a heuristic-based simulation considering the idle monitoring, to evolve non-dominated HRs for solving MO-DAEOSSP. The heuristic-based simulation generates feasible schedules and returns fitness values for given HRs, which are the individuals evolved by KT-MOGP. KT-MOGP applies a knowledge transfer mechanism to accelerate convergence. Once a source problem is trained, its non-dominated solutions are extracted and their feature importance is transferred to guide the initialization of another target problem, by which the knowledge generated during the training process can be fully utilized. Experimental results on three sets of instances show that KT-MOGP outperforms the existing GPHH-based method and that the evolved HRs are competitive compared to several classical constructive heuristics and multi-objective evolutionary algorithms. The results also show the effectiveness of the proposed knowledge transfer-based initialization. To the best of our knowledge, this study is the first attempt to consider both multi-objective scenarios and real-time arrival requests.

Multiobjective Binary Differential Approach with Parameter Tuning for Discovering Business Process Models: MoD-ProM.

Process discovery approaches analyze the business data to automatically uncover structured information, known as a process model. The quality of a process model is measured using quality dimensions, completeness (replay fitness), preciseness, simplicity, and generalization. Traditional process discovery algorithms usually output a single process model. A single model may not accurately capture the observed behavior and overfit the training data. We have formed the process discovery problem in a multiobjective framework that yields several candidate solutions for the end user who can pick a suitable model based on the local environmental constraints (possibly varying). We consider the Binary Differential Evolution approach in a multiobjective framework for the task of process discovery. The proposed method employs dichotomous crossover/mutation operators. The parameters are tuned using grey relational analysis combined with the Taguchi approach. We have compared the proposed approach with the well-known single-objective algorithms and state-of-the-art multiobjective evolutionary algorithm-Nondominated Sorting Genetic Algorithm (NSGA-II). Additional comparison via computing a weighted average of the quality dimensions is also undertaken. Results show that the proposed algorithm is computationally efficient and produces diversified candidate solutions that score high on the fitness functions. It is shown that the process models generated by the proposed approach are superior to or at least as good as those generated by the state-of-the-art algorithms.

A Multi-Objective Stochastic Framework for Coupled Reactive Power and Energy Market Settlement for Wind Energy Integrated System

A Multi-Objective Stochastic Framework for Coupled Reactive Power and Energy Market Settlement for Wind Energy Integrated System

A Multi-Objective Decision-Making Framework for The Choice Between Mutually Exclusive Alternatives Under Uncertainty: Assessing the Competitiveness of Offshore Wind for a Gas Field Electrification on the NCS

A Multi-Objective Decision-Making Framework for The Choice Between Mutually Exclusive Alternatives Under Uncertainty: Assessing the Competitiveness of Offshore Wind for a Gas Field Electrification on the NCS

Higher-order Directed Community Detection by A Multi-objective Evolutionary Framework

Higher-order Directed Community Detection by A Multi-objective Evolutionary Framework

Feasibility assessment of trough concentrated solar power plants with transcritical power cycles based on carbon dioxide mixtures: A 4E analysis and systematic comparison

Medium and low-temperature solar thermal power generation, integrating parabolic trough collectors with transcritical carbon dioxide (CO2)-based mixture power cycles, is explored for enhanced solar energy utilization and improved efficiency. This study assesses the feasibility of parabolic trough concentrated solar power plants utilizing transcritical CO2-based mixtures, considering energy output, efficiency, economics, and environmental (4E) aspects. Seven candidate organic working fluids (R32, R134a, R152a, R1234yf, R161, R290, and R1270) are evaluated within a two-layer decision-making framework based on multi-objective optimization. Results indicate a significant performance improvement with an increased mass fraction of the organic working fluid. Particularly, systems employing CO2/R32 or CO2/R161 demonstrate superior overall performance compared to those with other CO2-based mixtures. Under the base case (at a hot tank temperature of 350 °C), the CO2/R32 (0.3/0.7 wt%) system achieves the maximum energy output (355.22 kW), while the CO2/R161 (0.3/0.7 wt%) system attains the highest efficiency with the lowest levelized cost of electricity and CO2 emissions (9.78%, 0.576 $/kW·h, and 0.0328 kg/kW·h, respectively). Exergy analysis emphasizes the predominant role of the solar collector in exergy destruction (approximately 70%), with the CO2/R161 (0.3/0.7 wt%) system yielding the highest exergy efficiency (14.96%). Across a hot tank temperature range of 250–350 °C and an organic fluid mass fraction of 0.3–0.7, the working fluids are generally ranked as CO2/R161, CO2/R32, CO2/R152a, CO2/R1270, CO2/R134a, CO2/R290, and CO2/R1234yf in terms of the 4E aspects via a multi-objective optimization decision-making framework.

An Object Condensation Pipeline for Charged Particle Tracking at the High Luminosity LHC

Recent work has demonstrated that graph neural networks (GNNs) trained for charged particle tracking can match the performance of traditional algorithms while improving scalability to prepare for the High Luminosity LHC experiment. Most approaches are based on the edge classification (EC) paradigm, wherein tracker hits are connected by edges, and a GNN is trained to prune edges, resulting in a collection of connected components representing tracks. These connected components are usually collected by a clustering algorithm and the resulting hit clusters are passed to downstream modules that may assess track quality or fit track parameters. In this work, we consider an alternative approach based on object condensation (OC), a multi-objective learning framework designed to cluster points belonging to an arbitrary number of objects, in this context tracks, and regress the properties of each object. We demonstrate that OC shows very promising results when applied to the pixel detector of the trackML dataset and can, in some cases, recover tracks that are not reconstructable when relying on the output of an EC alone. The results have been obtained with a modular and extensible open-source implementation that allows us to efficiently train and evaluate the performance of various OC architectures and related approaches.

Simultaneous multi-objective framework of natural gas pipeline network operations

The optimization of gas transportation networks is essential as natural gas demand increases. Conflicting objectives, such as maximizing delivery flow rate, minimizing power consumption, and maximizing line pack, pose challenges in this context. To address these complexities, a novel multi-objective optimization method based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is proposed. The method generates a diverse set of Pareto optimal solutions, empowering decision-makers to select the most suitable solution for gas transportation networks. Three case studies validate the approach's effectiveness, showcasing its advantages in yielding more economical networks and enhancing the cost-effectiveness of natural gas transmission networks. The proposed method's versatility allows application to various gas transportation network scenarios. Decision-makers benefit from a range of Pareto optimal solutions, providing valuable insights. Moreover, the seamless integration of the proposed method into existing gas transportation network optimization frameworks further enhances performance. In conclusion, the study presents a robust multi-objective optimization method based on TOPSIS for gas transportation network optimization. It offers cost-effective solutions and improves the efficiency of natural gas transmission networks. The provision of diverse Pareto optimal solutions enables well-informed decision-making, contributing to sustainable energy solutions in the face of increasing natural gas demand.

Multi-objective price based flexible reserve scheduling of virtual power plant

In this research, multi-objective optimization of VPP is performed by considering multiple renewables and co-generation sources and solved by using the recently developed multi-objective Harris Hawk’s optimization (MOHHO) algorithm. Renewable sources comprise solar Photovoltaic (PV), wind power, fuel cells along with energy storage systems (ESS), electric vehicles (EV), along with CHP units are associated to form a VPP system. The penalty factor approach is implemented along with the weighting factor to develop a multi-objective framework that can simultaneously capitalize on the net profit and minimalize the emission while taking proper care of the related constraints. In this research, EVs are considered as a flexible reserve option along with a dedicated ESS applicable as a spinning reserve. Also, a dynamic pricing-based strategy is also presented and the optimization of VPP is accomplished by implementing a multi-objective-based day-ahead scheduling (MODAS) to see the behaviour of the anticipated system with a suitable method of constraint handling. Four diverse illustrations are considered in three different case study which is performed for hourly-based scheduling and the results are compared with the proposed technique. Statistical analysis is performed and the quality solution sets are attained by the HHO algorithm after performing 100 independent trials and the same is correlated with the available studies that indicate the efficacy and appropriateness of the selected approach.

Interatomic force fields for zirconium based on the embedded atom method and the tabulated Gaussian Approximation Potential

The accuracy of interatomic interaction potentials – also known as force fields – is the main factor determining the physical soundness of classical molecular dynamics (MD) simulations. Here, we present a multi-objective framework to generate embedded-atom-method (EAM) force fields using ab initio data. The EAM force fields were tuned via particle swarm optimization to capture the non-linear association between atomic structures and system energies. Using this framework, 95 standard EAM force fields for zirconium were developed and 45 physical features for each developed force field were tracked. Principal component analysis (PCA) was performed to provide insights into the compromises that must be made when generating EAM force fields. Of note, by assigning large fitting weights to generalized stacking fault energy (GSFE) surfaces, there exist EAM force fields with properly positioned minima on prismatic GSFE surfaces and containing no spurious minima in basal GSFE surfaces. However, while standard EAM force fields achieved this without explicitly taking the angular dependence of atomic interactions into account, they led to a severe mismatch between other important physical properties and benchmarks. Hence, we also constructed two machine-learned tabulated Gaussian approximation potentials (tabGAP) with an additional three-body term, which successfully tackled the aforementioned issue and exhibit acceptable prediction accuracy across many physical properties (lattice parameters, elastic properties, dimer potential energies, melting temperatures, phase stability, point defect formation energies, point defect migration energies, and free surface energies) of Zr. Remarkably, its computational efficiency is only 6 times slower than standard EAM force fields.

Profit- and risk-driven credit scoring under parameter uncertainty: A multiobjective approach

Profit-driven artificial intelligence (AI) systems and profit-based performance measures are widely used in credit scoring. When assessing the performance of an AI system for credit scoring, previous research typically assumes that the cost and benefit parameters and their distributional information are available. In reality, however, these parameters and their distributions are often not precisely known. This study considers parameter uncertainty in the development of credit-scoring models and the estimation of profits and risks generated by those models. We propose a novel profit-based metric—the worst-case expected minimum cost (WEMC)—to estimate the profit of credit-scoring models with uncertain parameters. Furthermore, we introduce the worst-case conditional value-at-risk (WCVaR) metric to measure the loss incurred from employing a classification model in credit scoring under the deterioration of cost parameters. A multiobjective feature-selection framework based on WEMC (or minimum cost) and WCVaR is then presented for model development. Using a comprehensive bankruptcy database, we compare the proposed methods with wrapper methods that use traditional metrics as selection criteria, as well as filter and embedding methods. We conduct extensive experiments to evaluate the economic benefits of the proposed methods under different scenarios that simulate dynamic changes in macroeconomic conditions. The results suggest that the proposed methods outperform other feature-selection methods in the aspects of profit and risk performance metrics in most cases.

Research on multi-dimensional reconstruction mechanism of cloud native full link in the metaverse scenario

Recently, the Microservices whole link whole life cycle optimization framework has been a research hotspot in the academic and engineering fields, especially how to encapsulate the component security mechanism and conduct high concurrency testing based on the existing active framework. The whole link delay, load, and cost have always been the key optimization goals of Microservices splitting and deployment logic. Based on this, this paper proposes a multi-objective optimization Microservices framework that takes into account the security mechanism, Define the fitness function, define the upper and lower limits, and perform multi-dimensional constraints to filter for global and local optima. At the same time, reconstruct the circuit breaker current limiting mechanism, dynamically detect protocol parameters, and perceive the logical relationship of heartbeat status in real-time. Experimental results have shown that this innovative framework can solve scenarios such as high concurrency, high reliability, and high availability Performance bottleneck, business degradation, especially in financial and securities scenarios.

Distributed multi-objective optimization for SNP-SNP interaction detection

The detection of complex interactions between single nucleotide polymorphisms (SNPs) plays a vital role in genome-wide association analysis (GWAS). The multi-objective evolutionary algorithm is a promising technique for SNP-SNP interaction detection. However, as the scale of SNP data further increases, the exponentially growing search space gradually becomes the dominant factor, causing evolutionary algorithm (EA)-based approaches to fall into local optima. In addition, multi-objective genetic operations consume significant amounts of time and computational resources. To this end, this study proposes a distributed multi-objective evolutionary framework (DM-EF) to identify SNP-SNP interactions on large-scale datasets. DM-EF first partitions the entire search space into several subspaces based on a space-partitioning strategy, which is nondestructive because it guarantees that each feasible solution is assigned to a specific subspace. Thereafter, each subspace is optimized using a multi-objective EA optimizer, and all subspaces are optimized in parallel. A decomposition-based multi-objective firework optimizer (DCFWA) with several problem-guided operators was designed. Finally, the final output is selected from the Pareto-optimal solutions in the historical search of each subspace. DM-EF avoids the preference for a single objective function, handles the heavy computational burden, and enhances the diversity of the population to avoid local optima. Notably, DM-EF is load-balanced and scalable because it can flexibly partition the space according to the number of available computational nodes and problem size. Experiments on both artificial and real-world datasets demonstrate that the proposed method significantly improves the search speed and accuracy.