Multi-objective Optimization Task Research Articles

Transferring knowledge by budget online learning for multiobjective multitasking optimization

Multiobjective multitasking optimization (MO-MTO) has attracted increasing attention in the evolutionary computation field. Evolutionary multitasking (EMT) algorithms can improve the overall performance of multiple multiobjective optimization tasks through transferring knowledge among tasks. Negative transfer resulting from the indeterminacy of the transferred knowledge may bring about the degradation of the algorithm performance. Identifying the valuable knowledge to transfer by learning the historical samples is a feasible way to reduce negative transfer. Taking this into account, this paper proposes a budget online learning based EMT algorithm for MO-MTO problems. Specifically, by regarding the historical transferred solutions as samples, a classifier would be trained to identified the valuable knowledge. The solutions which are considered containing valuable knowledge will have more opportunity to be transfer. For the samples arrive in the form of streaming data, the classifier would be updated in a budget online learning way during the evolution process to address the concept drift problem. Furthermore, the exceptional case that the classifier fails to identify the valuable knowledge is considered. Experimental results on two MO-MTO test suits show that the proposed algorithm achieves highly competitive performance compared with several traditional and state-of-the-art EMT methods.

Chaotic self-adaptive sine cosine multi-objective optimization algorithm to solve microgrid optimal energy scheduling problems

Researchers are increasingly focusing on renewable energy due to its high reliability, energy independence, efficiency, and environmental benefits. This paper introduces a novel multi-objective framework for the short-term scheduling of microgrids (MGs), which addresses the conflicting objectives of minimizing operating expenses and reducing pollution emissions. The core contribution is the development of the Chaotic Self-Adaptive Sine Cosine Algorithm (CSASCA). This algorithm generates Pareto optimal solutions simultaneously, effectively balancing cost reduction and emission mitigation. The problem is formulated as a complex multi-objective optimization task with goals of cost reduction and environmental protection. To enhance decision-making within the algorithm, fuzzy logic is incorporated. The performance of CSASCA is evaluated across three scenarios: (1) PV and wind units operating at full power, (2) all units operating within specified limits with unrestricted utility power exchange, and (3) microgrid operation using only non-zero-emission energy sources. This third scenario highlights the algorithm’s efficacy in a challenging context not covered in prior research. Simulation results from these scenarios are compared with traditional Sine Cosine Algorithm (SCA) and other recent optimization methods using three test examples. The innovation of CSASCA lies in its chaotic self-adaptive mechanisms, which significantly enhance optimization performance. The integration of these mechanisms results in superior solutions for operation cost, emissions, and execution time. Specifically, CSASCA achieves optimal values of 590.45 €ct for cost and 337.28 kg for emissions in the first scenario, 98.203 €ct for cost and 406.204 kg for emissions in the second scenario, and 95.38 €ct for cost and 982.173 kg for emissions in the third scenario. Overall, CSASCA outperforms traditional SCA by offering enhanced exploration, improved convergence, effective constraint handling, and reduced parameter sensitivity, making it a powerful tool for solving multi-objective optimization problems like microgrid scheduling.

Multi-objective resistance-capacitance optimization algorithm: An effective multi-objective algorithm for engineering design problems

Focusing on practical engineering applications, this study introduces the Multi-Objective Resistance-Capacitance Optimization Algorithm (MORCOA), a new approach for multi-objective optimization problems. MORCOA uses the transient response behaviour of resistance-capacitance circuits to navigate complex optimization landscapes and identify global optima when faced with many competing objectives. The core approach of MORCOA combines a dynamic elimination-based crowding distance mechanism with non-dominated sorting to generate an ideal and evenly distributed Pareto front. The algorithm's effectiveness is evaluated through a structured, three-phase analysis. Initially, MORCOA is applied to five benchmark problems from the ZDT test suite, with performance assessed using various metrics and compared against state-of-the-art multi-objective optimization techniques. The study then expands to include seven problems from the DTLZ benchmark collection, further validating MORCOA's effectiveness. The final phase involves applying MORCOA to six real-world constrained engineering design problems. Notably, the optimization of a honeycomb heat sink, which is crucial in thermal management systems, is a significant part of this study. This phase uses a range of performance measures to assess MORCOA's practical application and efficiency in engineering design. The results highlight MORCOA's robustness and efficiency in both real-world engineering applications and benchmark problems, demonstrating its superior capabilities compared to existing algorithms. The effective use of MORCOA in real-world engineering design problems indicates its potential as an adaptable and powerful tool for complex multi-objective optimization tasks.

Multi-objective generalized normal distribution optimization: a novel algorithm for multi-objective problems

This study introduces the Multi-objective Generalized Normal Distribution Optimization (MOGNDO) algorithm, an advancement of the Generalized Normal Distribution Optimization (GNDO) algorithm, now adapted for multi-objective optimization tasks. The GNDO algorithm, previously known for its effectiveness in single-objective optimization, has been enhanced with two key features for multi-objective optimization. The first is the addition of an archival mechanism to store non-dominated Pareto optimal solutions, ensuring a detailed record of the best outcomes. The second enhancement is a new leader selection mechanism, designed to strategically identify and select the best solutions from the archive to guide the optimization process. This enhancement positions MOGNDO as a cutting-edge solution in multi-objective optimization, setting a new benchmark for evaluating its performance against leading algorithms in the field. The algorithm's effectiveness is rigorously tested across 35 varied case studies, encompassing both mathematical and engineering challenges, and benchmarked against prominent algorithms like MOPSO, MOGWO, MOHHO, MSSA, MOALO, MOMVO, and MOAOS. Utilizing metrics such as Generational Distance (GD), Inverted Generational Distance (IGD), and Maximum Spread (MS), the study underscores MOGNDO's ability to produce Pareto fronts of high quality, marked by exceptional precision and diversity. The results affirm MOGNDO's superior performance and versatility, not only in theoretical tests but also in addressing complex real-world engineering problems, showcasing its high convergence and coverage capabilities. The source codes of the MOGNDO algorithm are publicly available at https://nimakhodadadi.com/algorithms-%2B-codes.

Multi-Objective Particle Swarm Optimization Algorithm based on Position Vector Offset

In response to the issue that particle swarm optimization algorithms tend to fall into local optima when dealing with multi-objective optimization tasks, a multi-objective optimization algorithm based on particle swarm is proposed. This algorithm is based on the relationship between the position vectors of particles, changing the selection and movement strategies of particles to find the true Pareto front. Firstly, two additional position vectors are added around the iterating particles to enhance their search capability; then, a non-dominated vector archive is established to record the non-dominated solutions of the iterating particles and the additional position vectors, increasing particle diversity. Finally, additional position vectors with high fitness are selected to produce a shift in the iterating particle's position, accelerating particle convergence. Comparing this algorithm with dMOPSO, SMPSO, NMPSO, and MOPSOCD algorithms, simulation experiments show that the proposed PVSPSO algorithm has stronger optimization ability.

A New Global Gas Dynamics Performance Optimization Method for Refrigeration Centrifugal Compressor Stage Based on the Immune Algorithm

Abstract This study proposes a new global gas dynamics optimization method, which was applied to a multi-objective optimization task of centrifugal compressor performance with the aim of determining the improvement probability for achieving high efficiency across a wide operating range. Initially, the original nondominated neighbor immune algorithm (NNIA) was extended to solve constrained multi-objective optimization problems for the first time, which mainly incorporated a procedure for handling inequality and equality constraints without additional parameters. Subsequently, an adaptive topological back-propagation multilayer feed-forward artificial neural network (BP-MLFANN) was trained using the modified NNIA to quickly evaluate the fitness value of the centrifugal compressor stage performance during the optimization. The feasibility of the method was validated using the first stage of a refrigeration centrifugal compressor. The results indicated a substantial enhancement in the stage efficiency of the optimized impeller at the Near-stall, Design, and Near-choke operating points, with increasement of 1.8%, 1.9%, and 4%, respectively, as compared to the baseline stage. The flow field analysis shows that the impact loss at impeller leading edge and flow separation in the passage reduced greatly, the mixing process between the leakage flow and mainstream in the channel is significantly weakened, thus the flow field becomes more uniform after optimization. The new global gas dynamics optimization method provides a reference for the development of efficient and rapid optimization techniques for centrifugal compressor.

Optimization of Problems with Multi-Objective Functions and their Applications in Engineering

Many real-world optimization issues typically have multiple competing goals. There is generally no solution in those multi-objective optimization problems that optimizes all objective functions at the same time. Rather, "efficient" in terms of all objective function’s solutions known as Pareto optimum solutions are presented. We typically have a large number of Pareto-optimal options. As a result, we must choose a final solution from among Pareto optimal solutions while considering the objective function balance; this process is known as "trade-off analysis." It is not hyperbole to state that trade-off analysis is the most crucial task in multi-objective optimization. As a result, the methodology's ease of use and comprehension for trade-off analysis should be highlighted. The set of Pareto optimal solutions in the objective function space, or Pareto frontier, can be represented somewhat simply in circumstances when there are two or three objective functions. We can fully understand the trade-off relationship between objectives when we see Pareto boundaries. Thus, in scenarios with two or three objectives, it would be the most appropriate technique to represent Pareto borders. Reading the trade-off relationship between objectives with three dimensions, however, may be challenging. Nonetheless, Pareto frontier cannot be represented in situations where there are more than three objectives. In this case, interactive techniques can assist us in performing a local trade-off analysis that reveals a "certain" Pareto optimal option. Many techniques have been devised, with variations in which the Pareto optimal solution is displayed. The main concerns of such multi-objective optimization techniques, especially as they relate to engineering design problems, are covered in this study.

Complex design and analysis of filament wound composite pressure vessels using data driven evolutionary algorithms

The typical composite pressure vessel manufactured by means of filament winding consists of three elementary construction parts, that is, cylindrical part, end dome and the junction between its cylindrical part and the end dome which are subject of this article. The pressure vessel may fail in each of these three parts. Therefore, all of them must be considered during the design process. This study shows the possible way how to design an optimal pressure vessel related to chosen parameters (which can be mass of the pressure vessel, depth of the end dome, magnitude of internal pressure etc.), so that it does not fail in any construction parts. Any decision, whether the pressure vessel comply or not in studied places, is based on Hoffman's failure index analysis. The finding of an optimal solution requires performing a multi-objective optimization task, which was solved here using data-driven evolutionary algorithms. From the input data, which were generated through analytical approaches, surrogate models were created using the Evolutionary Deep Neural Nets (EvoDN2). These surrogate models were further used as an input to the optimization module which is based upon Constrained Reference Vector Evolutionary Algorithm (cRVEA). The results show that the pressure vessel designed in this way comply in each analyzed location. Moreover, it also finds the most stressed location, which can be useful for the designers.

CrossPrune: Cooperative pruning for camera–LiDAR fused perception models of autonomous driving

Deep neural network pruning is effective in enabling high-performance perception models to be deployed on autonomous driving platforms with limited computation and memory resources. With their rapid development, state-of-the-art autonomous driving perception (ADP) models have advocated the use of multimodal sensors to extract diverse feature categories. However, existing pruning studies in the ADP area focus on single-modal models and neglect multimodal models. Compared with conventional pruning, multimodal pruning presents a new type of redundancy, namely modal-wise redundancy that is caused by multimodal branches extracting similar perception information. When a specific type of information is extracted by more than one modal branch, although this extraction is deemed essential from an individual single-modal standpoint, it becomes redundant when viewed from a modal-wise perspective. Therefore, modal branches must be handled cooperatively to eliminate modal-wise redundancy while concurrently preserving the original perception accuracy. Building on this, we propose CrossPrune, a modal cooperative pruning framework designed for camera–LiDAR fused perception in autonomous driving. The primary objective of CrossPrune is to effectively eliminate redundancy and achieve nondestructive pruning for multimodal ADP models. This was accomplished by approaching the problem as a multi-objective optimization task, encompassing both weight pruning and the restriction of feature distortions caused by pruning. Experiments conducted on the nuScenes and KITTI datasets demonstrated that CrossPrune attained superior pruning ratios while minimizing accuracy loss, surpassing the performance of the baselines. The key results indicated that the proposed CrossPrune achieved relative improvements of 9.6% in mAP and 11.5% in NDS under 89.8% pruning sparsity.

A Compliant Self-Stabilization Nanopositioning Device With Modified Active–Passive Hybrid Vibration Isolation Strategy

Micro/mini light-emitting diodes (LEDs) display panel inspection and repairs have a high demand for vibration isolating devices to protect industrial-level atomic force microscopes (AFM scanning head) against vibrations. The motivation of this work is to combine the advantages of both passive and active vibration isolation strategies to improve inspection performance. The developed self-stabilization device achieves this objective with a design that incorporates a suspension-type passive vibration isolation unit and integrates it with the modified active–passive hybrid (MAPH) vibration isolation strategy using piezoelectric ceramics (PZT) and voice coil motors (VCM) as compensators. First, the design, modeling, and optimization of a self-stabilization device are presented based on the MAPH vibration isolation strategy. To satisfy the requirements of vibration isolation performance and a lightweight design, a multiobjective optimization task was conducted. Next, a tailor-made double compensating PID controller was designed to allow this mechanism to run in the MAPH method to effectively isolate vibrations. Finally, a series of validation experiments, including passive vibration isolation performance tests and MAPH closed-loop tests, were applied. From 1 to 500 Hz, more than 98% frequency domain achieved a vibration isolation rate of 90%, the vibration amplification effect of the passive vibration isolation was significantly suppressed, the steady-state positioning accuracy reached <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm 0.1\;\mu$</tex-math></inline-formula> m, load capacity was up to 2.5 kg, the attenuation ratio of the disturbances reached up to 70%, and the heat of the VCM was effectively reduced. All results comprehensively confirmed that the developed compliant MAPH vibration isolation system has achieved a satisfactory self-stabilization function.

Three-Phase Transformer Optimization Based on the Multi-Objective Particle Swarm Optimization and Non-Dominated Sorting Genetic Algorithm-3 Hybrid Algorithm

The performance of transformers directly determines the reliability, stability, and economy of the power system. The methodologies of minimizing the transformer manufacturing cost under the premise of ensuring performance is of great significance. This paper presented an innovative multi-objective optimization model to analyze the relationship between design parameters and transformer indicators. In addition, the sensitive analysis is conducted to exploit the interaction relationships between design parameters and targets. The reliability of the model was demonstrated in 50 MVA/110 kV and 63 MVA/110 kV prototypes, compared with the actual material usage, short-circuit impedance, and load loss, and the maximum error is less than 7%. Due to this problem having many optimization objectives and the high dimension of variables, a two-stage algorithm called MOPSO-NSGA3 (multi-objective particle swarm optimization and non-dominated sorting genetic algorithm-3) is presented. MOPSO is used to find non-domain solutions within the search space in the first stage, and the solution will be used as prior knowledge to initialize the population in NSGA3. The result shows that this algorithm can be effectively used in multi-objective optimization tasks and best meets the requirements of transformer designs that minimize the short-circuit deviation, operating loss, and manufacturing costs.

Comparative performance analysis of binary variants of FOX optimization algorithm with half-quadratic ensemble ranking method for thyroid cancer detection

Thyroid cancer is a life-threatening condition that arises from the cells of the thyroid gland located in the neck’s frontal region just below the adam’s apple. While it is not as prevalent as other types of cancer, it ranks prominently among the commonly observed cancers affecting the endocrine system. Machine learning has emerged as a valuable medical diagnostics tool specifically for detecting thyroid abnormalities. Feature selection is of vital importance in the field of machine learning as it serves to decrease the data dimensionality and concentrate on the most pertinent features. This process improves model performance, reduces training time, and enhances interpretability. This study examined binary variants of FOX-optimization algorithms for feature selection. The study employed eight transfer functions (S and V shape) to convert the FOX-optimization algorithms into their binary versions. The vision transformer-based pre-trained models (DeiT and Swin Transformer) are used for feature extraction. The extracted features are transformed using locally linear embedding, and binary FOX-optimization algorithms are applied for feature selection in conjunction with the Naïve Bayes classifier. The study utilized two datasets (ultrasound and histopathological) related to thyroid cancer images. The benchmarking is performed using the half-quadratic theory-based ensemble ranking technique. Two TOPSIS-based methods (H-TOPSIS and A-TOPSIS) are employed for initial model ranking, followed by an ensemble technique for final ranking. The problem is treated as multi-objective optimization task with accuracy, F2-score, AUC-ROC and feature space size as optimization goals. The binary FOX-optimization algorithm based on the V_1 transfer function achieved superior performance compared to other variants using both datasets as well as feature extraction techniques. The proposed framework comprised a Swin transformer to extract features, a Fox optimization algorithm with a V1 transfer function for feature selection, and a Naïve Bayes classifier and obtained the best performance for both datasets. The best model achieved an accuracy of 94.75%, an AUC-ROC value of 0.9848, an F2-Score of 0.9365, an inference time of 0.0353 seconds, and selected 5 features for the ultrasound dataset. For the histopathological dataset, the diagnosis model achieved an overall accuracy of 89.71%, an AUC-ROC score of 0.9329, an F2-Score of 0.8760, an inference time of 0.05141 seconds, and selected 12 features. The proposed model achieved results comparable to existing research with small features space.

Applications of genetic algorithm in prediction of the best achievable combination of hardness and tensile strength for graphene reinforced magnesium alloy (AZ61) matrix composite

Due to lack of knowledge about role of process variables in the hot rolling of magnesium alloy composites, the most desirable wrought products of magnesium alloy-based composites could not be successfully produced till date. Moreover, use of wrought graphene reinforced magnesium alloy-based composite has emerged as a lucrative option for developing novel light alloy products in structural applications. The implicative need to obtain the best possible properties of the composite dictates to fix the optimized process variables in rolling operation. The present study envisages the development of data driven model that enables to derive desirable properties of the said composite; so, in order to secure the optimized subset of requirements (process parameters), a metaheuristic optimization tool is employed. We invoke the use of Genetic Algorithm (GA) optimizing tool in association with linear regression, so as to achieve the best combination of hardness and tensile strength of AZ-61-graphene nanoplate (GNP) composite.Modified magnesium AZ-61 alloy composites of varying GNP content (0, 1 and 2 wt.%) are produced by stir casting. The cast composites are homogenized at 450 °C for 12 h, followed by iced water quenching. The quenched materials are subjected to hot rolling and the process variables of hot rolling operation consist of rolling temperature, number of rolling passes as well as the initial stock thickness. The rolled materials are tested for hardness and tensile strength as the response variables. Instead of using artificial neural network to fix the objective function of GA, a mathematical model is developed by regression analysis; the derived equation is used as the objective function for multi-objective optimization task. The present paper explores the usefulness of implementing evolutionary algorithm (as in genetic algorithm) to correctly forecast the effect of rolling process variables onto the hardness and tensile strength of the stir cast AZ alloy-GNP nanocomposite.The experimental results show that the maximum achievable hardness value happens to be 106.6 VHN and is very close to that predicted by GA, ∼107.41VHN. Similarly, the maximum experimental tensile strength is found to be 266.82 MPa whereas, the corresponding GA predicted value is seen to be 253 MPa. A close fit can thus be noticed between the GA predicted and the experimentally obtained values. Barring a couple of exceptions, the difference between the experimental and GA predicted data lies within 1 % to 5 % (based on [Experimental value ∼ predicted value]/ [experimental value]). This entices to believe that the adopted muti-objective optimization strategy is quite useful in determining the optimum combination of rolling parameters that aids in achieving the most desirable property combination.

ADAPTIVE RESOURCE ALLOCATION METHOD FOR DATA PROCESSING AND SECURITY IN CLOUD ENVIRONMENT

Subject of research: methods of resource allocation of the cloud environment. The purpose of the research: to develop a method of resource allocation that will improve the security of the cloud environment. At the same time, effective data processing should be achieved. Method characteristics. The article discusses the method of adaptive resource allocation in cloud environments, focusing on its significance for data processing and enhanced security. A notable feature of the method is the consideration of external influences when calculating the characteristics of cloud resource requests and predicting resource requests based on a time series test. The main idea of this approach lies in the ability to intelligently distribute resources while considering real needs, which has the potential to optimize both productivity and confidentiality protection simultaneously. Integrating adaptive resource allocation methods not only improves data processing efficiency in cloud environments but also strengthens mechanisms against potential cyber threats. Research results. To ensure timely resource allocation, the NSGA-II algorithm has been enhanced. This allowed reducing the resolution time of multi-objective optimization tasks by 5%. Additionally, research results demonstrate that effective utilization of various types of resources on a physical machine reduces resource losses by 1.2 times compared to SPEA2 and NSGA-II methods.

Intelligent Task Scheduling Approach for IoT Integrated Healthcare Cyber Physical Systems

Cyber-physical systems (CPS) based on cloud computing provides resources over the Internet and allow a variety of applications to be deployed to provide services for various industries. We proposed IoT-based healthcare cyber-physical system that provides effective resource utilization at fog and cloud levels with minimum execution cost. In addition, we also consider data from social media networking and drug review for the analysis. Furthermore, two different feature extraction approaches were applied based on data collection. Homogeneity score-based K-means clustering is used as a feature extraction and selection method for sensor data features, while text mining and sentiment analysis approach is used for social media networking and drug review data feature extraction. We proposed efficient resource utilization and cost-effective task scheduling at the Fog level and multi-objective heuristic approach Ant colony optimization task scheduling (MOHACO-TS) at cloud level. Both task scheduling algorithms focus on executing maximum task tasks in minimum time with effective resource utilization. We consider five different datasets and existing task scheduling and classification approaches for performance evaluation of the proposed IoT-HCPS framework. From the results, it is evident that the proposed work IoT-HCPS outperformed the exisitng techniques and algorithms.

Modeling and Optimization of Surface Integrity and Sliding Wear Resistance of Diamond-Burnished Holes in Austenitic Stainless Steel Cylinder Lines

This article outlines a technology for hole-finishing in short-length cylinder lines to improve wear resistance. The technology is based on an optimized diamond-burnishing (DB) process. The latter was implemented on conventional and CNC lathes, milling machines, and machining centers using a simple burnishing device with an elastic beam. The material used in this study was AISI 321 austenitic stainless steel. The governing factors used were the radius of the diamond insert, burnishing force and feed rate. The objective functions relating to surface integrity characteristics were selected on the basis of their functional importance relative to the wear resistance of the processed hole surface: height and shape roughness parameters, surface microhardness, and surface residual axial and hoop stresses. The one-factor-at-a-time method (used to reduce the factor space), a planned experiment, and regression analyses were used. The multi-objective optimization tasks, which were defined for three diamond insert radius values of 2, 3, and 4 mm, were solved via the Pareto-optimal solutions approach available for a non-dominated sorting genetic algorithm (NSGA-II). Using the optimal values of the governing factors selected from the Pareto fronts, cylinder lines were processed. Samples were then cut from these cylinder lines for reciprocating sliding wear tests under two modes: dry friction and boundary lubrication friction. Additionally, wear test samples were cut from the cylinder line, which was finished with traditional grinding. A finite element simulation was then used to select an appropriate pressing force. The results obtained from the reciprocating sliding wear tests under both the dry and boundary lubrication friction regimes show that to minimize the wear on cylinder lines made of AISI 321 steel, DB with a diamond insert of radius 2 mm is the optimal finishing process.

Model Predictive Evolutionary Temperature Control via Neural-Network-Based Digital Twins

In this study, we propose a population-based, data-driven intelligent controller that leverages neural-network-based digital twins for hypothesis testing. Initially, a diverse set of control laws is generated using genetic programming with the digital twin of the system, facilitating a robust response to unknown disturbances. During inference, the trained digital twin is utilized to virtually test alternative control actions for a multi-objective optimization task associated with each control action. Subsequently, the best policy is applied to the system. To evaluate the proposed model predictive control pipeline, experiments are conducted on a multi-mode heat transfer test rig. The objective is to achieve homogeneous cooling over the surface, minimizing the occurrence of hot spots and energy consumption. The measured variable vector comprises high dimensional infrared camera measurements arranged as a sequence (655,360 inputs), while the control variable includes power settings for fans responsible for convective cooling (3 outputs). Disturbances are induced by randomly altering the local heat loads. The findings reveal that by utilizing an evolutionary algorithm on measured data, a population of control laws can be effectively learned in the virtual space. This empowers the system to deliver robust performance. Significantly, the digital twin-assisted, population-based model predictive control (MPC) pipeline emerges as a superior approach compared to individual control models, especially when facing sudden and random changes in local heat loads. Leveraging the digital twin to virtually test alternative control policies leads to substantial improvements in the controller’s performance, even with limited training data.

A Graph-Based Optimization Framework for Large Water Distribution Networks

Water distribution networks (WDNs) have a crucial task: to reliably provide sufficient and high-quality water while optimizing financial resources. Achieving both reliability and resilience is vital. However, oversizing capacities can be costly and detrimental to water quality due to stagnation. Designing WDNs requires the consideration of these factors, resulting in a multi-objective optimization task typically addressed with evolutionary algorithms. Yet, for large WDNs with numerous decision variables, such algorithms become impractical. Complex network analysis offers an efficient approach, particularly with mathematical graphs representing WDNs. Recently, a graph-based multi-objective design approach using a customized measure (demand edge betweenness centrality) and a surrogate method for water quality assessment in large WDNs were developed. This paper combines these graph-based approaches into an optimization framework suitable for complex, real-world WDNs. The framework aims to minimize costs, maximize resilience, and exclude designs with poor water quality. It is demonstrated on a toy example, and its computational efficiency is shown by a real case study with 4000 decision variables, obtaining results in just 18.5 s compared to weeks of computation time with a state-of-the-art evolutionary algorithm.

Dynamic Multi-Objective Optimization Framework With Interactive Evolution for Sequential Recommendation

In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequential models learn the ranking score of an item only based on its relevance property, and the personalized user demands in terms of different learning objectives, such as diversity, tail novelty or recency, which have been played essential roles in multi-objective recommendation (MOR), are often neglected in SR. In this paper, we first discuss the importance of considering multiple different objectives within a learning model for recommender system. Next, to capture users' objective-level preferences by utilizing interactive information in the sequential context, we propose a novel Dynamic Multi-objective Recommendation (DMORec) framework with interactive evolution for SR. In particular, DMORec formulates a dynamic multi-objective optimization task to simultaneously optimize more than two varying objectives in an interactive recommendation process. Moreover, to resolve this optimization task in SR, we develop an evolutionary algorithm with supervised learning approach to obtain the Pareto-optimal solutions of the formulated problem. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of the proposed DMORec for dynamic multi-objective recommendation in sequential recommender systems.

Reliability Enhancement on Distribution System Using Modified Multi-Objective Particle Swarm Optimization Technique

This research paper introduces an innovative approach for optimizing the placement of fault indicators (FIs) within electric distribution systems. The primary focus is on addressing how the presence of existing protection and control devices affects the time it takes to restore service to customers in the event of a fault. Unlike conventional FI placement methods, this extended approach considers the uncertainties associated with automatic switching and introduces a novel technical objective function known as the Customers' Average Restoration Time Index (CARTI). To tackle the complex task of multi-objective optimization, a solution approach has been devised, with the goal of simultaneously minimizing both economic and technical objectives. This methodology harnesses a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm and incorporates a Modified Particle Swarm Optimization technique to select the most suitable solution from the set of Pareto optimal solutions generated. The proposed method's effectiveness is demonstrated through its application in two scenarios: firstly, in the context of bus number four within the Roy Billinton test system (RBTS4), and secondly, in a practical real-life distribution network. The study assesses technical objectives, specifically the System Average Interruption Duration Index (SAIDI) and CARTI, providing insights into the method's practical utility and its capacity to enhance FI placement for improved distribution system performance.