Scheduling Design Research Articles

Optimal vaccination ages for emerging infectious diseases under limited vaccine supply.

Rational allocation of limited vaccine resources is one of the key issues in the prevention and control of emerging infectious diseases. An age-structured infectious disease model with limited vaccine resources is proposed to explore the optimal vaccination ages. The effective reproduction number [Formula: see text] of the epidemic disease is computed. It is shown that the reproduction number is the threshold value for eradicating disease in the sense that the disease-free steady state is globally stable if [Formula: see text] and there exists a unique endemic equilibrium if [Formula: see text]. The effective reproduction number is used as an objective to minimize the disease spread risk. Using the epidemic data from the early spread of Wuhan, China and demographic data of Wuhan, we figure out the strategies to distribute the vaccine to the age groups to achieve the optimal vaccination effects. These analyses are helpful to the design of vaccination schedules for emerging infectious diseases.

Collective combinatorial optimisation as judgment aggregation

AbstractIn many settings, a collective decision has to be made over a set of alternatives that has a combinatorial structure: important examples are multi-winner elections, participatory budgeting, collective scheduling, and collective network design. A further common point of these settings is that agents generally submit preferences over issues (e.g., projects to be funded), each having a cost, and the goal is to find a feasible solution maximising the agents’ satisfaction under problem-specific constraints. We propose the use of judgment aggregation as a unifying framework to model these situations, which we refer to as collective combinatorial optimisation problems. Despite their shared underlying structure, collective combinatorial optimisation problems have so far been studied independently. Our formulation into judgment aggregation connects them, and we identify their shared structure via five case studies of well-known collective combinatorial optimisation problems, proving how popular rules independently defined for each problem actually coincide. We also chart the computational complexity gap that may arise when using a general judgment aggregation framework instead of a specific problem-dependent model.

Airline scheduling optimization: literature review and a discussion of modelling methodologies

Abstract The rapid development of civil aviation in recent decades has not only led to increasing competition among airlines, but also to the rise of irregularities, with challenges concerning the improvement of regulations and schedules under the maximization of profitability. Consequently, the airline scheduling optimization problem has received significant research interest as the foundation for an efficient deployment of airline resources and meeting market demand under complex operational requirements. In this paper, we dissect fundamental airline scheduling problems by reviewing thirteen representative mathematical models for schedule design, fleet assignment, aircraft routing, crew scheduling subproblems and their potential for integration. In contrast to existing review studies on airline scheduling problems, our main contribution lies in the introduction of state-of-the-art mathematical models with a specific focus on integration and robustness. In addition, we highlight a set of promising, yet challenging, directions for future research in this domain.

Solute Enrichment in the Fusion Zone during Resistance Spot Welding of a Third Generation Advanced High Strength Steel

Resistance spot welding is a critical joining technique in automobile assembly. The load carrying properties of spot welds are generally accepted to correlate with weld diameter, which increases with increasing weld current or duration. The formation of a softened layer, or weld halo, surrounding the fusion zone in a spot-welded third generation (Gen3) advanced high strength steel (AHSS) was recently reported in the literature. To optimize weld performance by schedule design, it is necessary to understand the halo formation characteristics and potential impacts. Accordingly, welding of a Gen3 AHSS was performed using weld times between 130 – 1300 ms. Microhardness mapping characterized weld microhardness and the evolution of the halo during welding. Electron probe microanalysis and timeof-flight secondary ion mass spectrometry enabled measurement of solute distributions through the weld halo, while scanning electron microscopy was used for microstructural characterization. The solidified structure was examined using light-optical microscopy, and with the microhardness and compositional data, used to infer the mechanism by which the halo forms during welding. It was found that the halo develops due to solute rejection from a cellular solidification front that advances towards the center of the fusion zone while weld current is applied. Extended weld times increase the size of the weld halo and the solute content of the inner fusion zone. The decrease in weld halo microhardness and the increase in inner fusion zone microhardness is largely explained by the changes in local carbon content associated with halo formation.

Graph Coloring Implementation Using Welch Powell Algorithm In Lecture Scheduling Design For Mathmatics Department

Designing the scheduling of lecture rosters is one of the common problems faced by all universities. The problem that often occurs as a conflict in the lecture schedule. Lecturers who teach courses, students cannot take certain courses because the lecture schedule they are taking conflicts with other lecture schedules. The main problem in this research is the design of lecture schedules which always conflict due to room availability and lecturer teaching hours. As a result, lecture scheduling becomes more complicated. The case study used is the scheduling of lectures for the Mathematics Department, Faculty of Science and Technology, UIN Sumatera Utara, Medan in the even semester of the 2022/2023 academic year. In this research, a bipartition graph will be formed based on the variables used, namely determining the variable index used in the course, teaching lecturer, teaching time, entry time, exit time, classroom, number of credits, semester and color. After that, the Welch Powell Algorithm will be used to solve the scheduling problem of a bipartition graph which is formed by creating nodes, membership matrix and the final result is a tabulation of the colored bipartition graph as the output of the scheduling. This algorithm also uses MATLAB software. From the results obtained, the algorithm provides an effective digital solution in designing lecture roster scheduling which is still done manually. This will help the mathematics department in overcoming the problems mentioned above. The research results will be explained detail in the results and discussion section.

Design optimization and closed-loop operational planning to achieve sustainability goals in buildings

Given the significant energy consumption and carbon emissions associated with buildings, there is increasing interest in improving sustainability of building operations to reduce impact on climate change. A common goal is to operate buildings as “net-zero” energy users in which all energy consumed by the building is balanced against renewable energy purchased from the grid or produced on site. To achieve net-zero status, many buildings will require significant retrofit so as to both reduce energy consumption in the absolute sense and provide the remainder without consuming fossil fuels. Thus, multi-year planning is required to ensure that goals can be met on time. In addition, due to the inherent uncertainty associated with energy consumption and generation, actually achieving net-zero energy use may require discretionary curtailment actions to be taken, and deciding whether such actions are necessary can be challenging. To address these challenges, we propose in this paper a design optimization and operational planning strategy to make the decisions needed to achieve sustainability goals in buildings. The strategy can be applied to schedule design changes over a long horizon to meet annual targets, and it can also be applied in closed loop on a shorter horizon to determine whether curtailment is needed to stay on track. We discuss the formulation of the optimization problem, solution methods, and modeling approaches for key parameters. Application of the strategy is illustrated via examples. Overall, this approach will help automate planning that is often done manually, allowing buildings to take a significant leap forward toward achieving their sustainability goals.

Hazardous materials facility siting optimization and ranking: A transportation risk mitigation framework

Hazardous material transportation problems have widely been studied in the past especially in the context of routing, scheduling, and network design problems. Yet, the combined hazardous material facility location-routing problem has not been studied adequately. We emphasize that locating a hazardous material facility is a rich process, and a good site can mitigate the potential transportation risk beforehand. A methodological framework is proposed which allows evaluation and ranking of potential sites based on hierarchical relationship utilities. The proposed method attempts to improve the risk functions and applies a stochastic analysis to measure the risk, which relaxes some assumptions in deterministic analysis, and is more realistic while avoiding overestimation of the risk. The study covers multi-objective optimization considering the decision-makers’ preferences on network segments and risk to the population and water bodies. Potential hazardous material facility sites’ rank is determined by the probability of optimality and one-to-one relationship utilities with the points of interests. Results show that the proposed stochastic analysis offers more flexibility to select and rank the potential sites.

SSFSCE: Design of a Sleep Scheduling based Fan Shaped Clustering Model to enhance working Energy Efficiency of WSN

To enhance energy level in WSN is a research requirement, which assists in improving their lifetime over a series of communications. To achieve this target, a various variety of clustering & sleep scheduling models are discussed by researchers. Most of these models deploy static clustering & sleep scheduling operations, which limits their applicability & scalability levels. Moreover, dynamic clustering & scheduling models are highly complex, which reduces temporal QoS performance under real-time use cases. In order to reduce the probability of these issues, this text discusses design of the proposed Sleep Scheduling based Fan Shaped Clustering Model to enhance working Energy Efficiency of WSN. The proposed model initially deploys a Grey Wolf Optimization (GWO) Method for dynamic sleep scheduling via temporal performance analysis. The GWO Method models a fitness function that combines temporal usage levels, temporal Quality of Service (QoS), and temporal energy levels. Based on this modelling process, nodes were categorized into wake & sleep nodes, which were further clustered via destination-aware Fan Shaped Clustering (FSC), that assisted in improving QoS performance under multiple scenarios. The FSC Model was combined with a QoS-aware routing model, that assisted in selection of routing paths that can achieve low delay, high throughput, and high packet delivery with higher energy efficiency levels. Efficiency of the model was tested on node & network conditions, and its QoS performance was checked in terms of communication delay, consumption of energy, level of throughput, and Packet Delivery Ratio (PDR) levels. On the basis of these comparative evaluations, it is observed that the new proposed model is able to enhance end-to-end delay by 8.5%, reduce level of energy by 15.5%, while increasing throughput by 8.3%, and PDR by 1.5%, thus making it useful for a different real-time conditions.

SD-AETO: Service-Deployment-Enabled Adaptive Edge Task Offloading Scheme in MEC

In recent years, edge computing, as an important pillar for future networks, has been developing rapidly. Task offloading is a key part of edge computing that can provide computing resources for resource-constrained devices to run computing-intensive applications, accelerate computing speed and save energy. An efficient and feasible task offloading scheme can not only greatly improve the quality of experience (QoE) but also provide strong support and assistance for 5G/B5G networks, the industrial Internet of Things (IIoT), computing networks, etc. To achieve these goals, this paper proposes an adaptive edge task offloading scheme assisted by service deployment (SD-AETO) focusing on optimizing the energy utilization ratio (EUR) and the processing latency. In the pre-implementation stage of the SD-AETO scheme, a service deployment scheme is invoked to assist with task offloading considering each service’s popularity. The optimal service deployment scheme is obtained by using the approximate deployment graph (AD-graph). Furthermore, a task scheduling and queue offloading design procedure is proposed to complete the SD-AETO scheme based on task priority. The task priority is generated by corresponding service popularity and task offloading. Finally, we analyze our SD-AETO scheme and compare it with related approaches, and the results show that our scheme has a higher edge offloading rate and lower resource consumption for massive task scenarios in the edge network.

Multi-resource scheduling of moldable workflows

Resource scheduling plays a vital role in High-Performance Computing (HPC) systems. Most scheduling research in HPC has focused on only a single type of resource (e.g., computing cores or I/O resource). With the advancement in hardware architectures and the increase in data-intensive HPC applications, there is a need to simultaneously consider a diverse set of resources (e.g., computing cores, cache, memory, I/O, and network resources) in the design of runtime schedulers for improving the overall application performance. In this paper, we study multi-resource scheduling to minimize the makespan of computational workflows comprised of moldable parallel jobs. Moldable jobs allow the scheduler to flexibly select a variable set of resources before execution, thus can adapt to the available system resources (as compared to rigid jobs) while staying easy to design and implement (as compared to malleable jobs). We propose a Multi-Resource Scheduling Algorithm (MRSA), which combines a novel resource allocation strategy and an extended list scheduling scheme to schedule the jobs. We prove that, on a system with d types of schedulable resources, MRSA achieves an approximation ratio of 1.619d+2.545d+1 for any d≥1, and a ratio of d+3d23+O(d3) when d is large (i.e., d≥22). We also present improved approximation results for workflows comprised of jobs with special precedence constraints (e.g., series-parallel graphs, trees, and independent jobs). Further, we prove a lower bound of d on the approximation ratio of any list-based scheduling algorithm with local priority considerations. Finally, we conduct a comprehensive set of simulations to evaluate the performance of the algorithm using synthetic workflows of different structures and moldable jobs following different speedup models. The results show that MRSA fares better than the theoretical bound predicts, and that it consistently outperforms two baseline heuristics under a variety of parameter settings, illustrating its robust practical performance.

Competitive integrated airline schedule design and fleet assignment

Airline profits are significantly influenced by competitive timetables that match passenger demand to fleet resources. In this research, we develop an integrated, mixed-integer optimization model to derive a comprehensive flight schedule, fleet assignment, and average airfares jointly. Passenger choice behavior is incorporated through a prospect theory-adjusted, nested, multinomial logit model which estimates market share. The competitive fleet assignment and schedule design (CFSD) formulation is embedded in a differentiated Bertrand game, such that each transport operator optimizes their best response function connected through the market share model. To solve the integrated optimization problem efficiently, a hybrid algorithm is developed that combines stabilized column generation with a large neighborhood search algorithm.The game-theoretic framework is applied to a case study in China involving legacy airlines, a low-cost carrier, and a high-speed rail (HSR) operator. The equilibrium outcomes suggest that the low-cost carrier is likely to stimulate demand and improve the level of service through secondary airports. The further development of high-speed rail service is expected to intensify competition among airlines and reduce the overall fare level. The low-cost carriers and HSR are able to significantly increase overall consumer surplus, providing insights into the potential for low-cost service in the Chinese aviation markets and the entrance of the public service obligation program at minimum cost.

Intelligent Resource Allocation Using an Artificial Ecosystem Optimizer with Deep Learning on UAV Networks

An Unmanned Aerial Vehicle (UAV)-based cellular network over a millimeter wave (mmWave) frequency band addresses the necessities of flexible coverage and high data rate in the next-generation network. But, the use of a wide range of antennas and higher propagation loss in mmWave networks results in high power utilization and UAVs are limited by low-capacity onboard batteries. To cut down the energy cost of UAV-aided mmWave networks, Energy Harvesting (EH) is a promising solution. But, it is a challenge to sustain strong connectivity in UAV-based terrestrial cellular networks due to the random nature of renewable energy. With this motivation, this article introduces an intelligent resource allocation using an artificial ecosystem optimizer with a deep learning (IRA-AEODL) technique on UAV networks. The presented IRA-AEODL technique aims to effectually allot the resources in wireless UAV networks. In this case, the IRA-AEODL technique focuses on the maximization of system utility over all users, combined user association, energy scheduling, and trajectory design. To optimally allocate the UAV policies, the stacked sparse autoencoder (SSAE) model is used in the UAV networks. For the hyperparameter tuning process, the AEO algorithm is used for enhancing the performance of the SSAE model. The experimental results of the IRA-AEODL technique are examined under different aspects and the outcomes stated the improved performance of the IRA-AEODL approach over recent state of art approaches.

Dynamic Scheduling Stochastic Multiworkflows With Deadline Constraints in Clouds

Nowadays, more and more workflows with different computing requirements are migrated to clouds and executed with cloud resources. In this work, we study the problem of stochastic multi-workflows scheduling in clouds and formalize this problem as an optimization problem that is NP-hard. To solve this problem, an efficient stochastic multi-workflows dynamic scheduling algorithm called SMWDSA is designed to schedule multi-workflows with deadline constraints for optimizing multi-workflows scheduling cost. The proposed SMWDSA consists of three stages including multi-workflows preprocessing, multi-workflow scheduling and scheduling feedback. In SMWDSA, a novel task sub-deadlines assignment stretagy is design to assign the task sub-deadlines to each task of multi-workflows for meeting workflow deadline constraints. Then, we propose a task scheduling method based on the minimal time slot availability to execution task for minimizing workflow scheduling cost while meetingt workflow deadlines. Finally, a scheduling feedback strategy is adopted to update the priorities and sub-deadlines of unscheduled tasks, for further minimizing workflow scheduling cost. We conduct the experiments using both synthetic data and real-world data to evaluate SMWDSA. The results demonstrate the superiority of SMWDSA as compared with the state-of-the-art algorithms. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Workflow scheduling in clouds is significantly challenging due to not only the large scale of workflows but also the elasticity and heterogeneity of cloud resources. Moreover, minimizing workflow scheduling cost and satisfying workflow deadlines are two critical issues in scheduling with cloud resources, especially the uncertainty of workflow arrive time and task execution time are considered. To meet workflow deadlines, it is an effective strategy to decompose workflow deadline constraints into task sub-deadline constraints. To minimize the workflow scheduling cost, each task in a workflow needs to be assigned to their most suitable VMs for execution. This article presents a novel workflow scheduling algorithm to schedule stochastic multi-workflows in clouds for optimizing multi-workflows scheduling cost and meeting workflows deadlines. This algorithm obtains the task sub-deadline constraints based on the characteristics of workflows for meeting the worklfow deadline constraint. Under the premise of meeting task deadlines, it schedules tasks to a VM with minimum the slot time, for minimizing the cost. Case studies based on well-known real-world workflows data sets suggest that it outperforms traditional ones in terms of success and cost of multi-workflows scheduling. It can thus aid the design and optimization of multi-workflows scheduling in a cloud environment. It can help practitioners better manage the scheduling cost and performance of real-world applications built upon cloud services.

A Secure Robot Learning Framework for Cyber Attack Scheduling and Countermeasure

The problem of learning-based control for robots has been extensively studied, whereas the security issue under malicious adversaries has not been paid much attention to. Malicious adversaries can invade intelligent devices and communication networks used in robots, causing incidents, achieving illegal objectives, and even injuring people. This article first investigates the problems of optimal false data injection attack scheduling and countermeasure design for car-like robots in the framework of deep reinforcement learning. Using a state-of-the-art deep reinforcement learning approach, an optimal false data injection attack scheme is proposed to deteriorate the tracking performance of a robot, guaranteeing the tradeoff between the attack efficiency and the limited attack energy. Then, an optimal tracking control strategy is learned to mitigate attacks and recover the tracking performance. More importantly, a theoretical stability guarantee of a robot using the learning-based secure control scheme is achieved. Both simulated and real-world experiments are conducted to show the effectiveness of the proposed schemes.

An Adaptive Shift Schedule Design Method for Multi-Gear AMT Electric Vehicles Based on Dynamic Programming and Fuzzy Logical Control

This paper proposes an adaptive shift schedule design framework based on dynamic programming (DP) algorithm and fuzzy logical control to promote the shift schedule’s adaptability whilst improving the comprehensive performance of the multi-gear automated manual transmission (AMT) electric vehicles in real-time application. First, the DP algorithm is employed to extract an offline optimal gear-shift schedule based on a set of driving conditions, including 11 groups of typical driving cycles. Second, a fuzzy logical controller is formulated considering the variation in the vehicle load and acceleration, where a velocity increment is exported online to adjust the gear-shift velocity of the predesigned DP-based schedule to develop a Fuzzy-DP shift schedule. In addition, multi-objective particle swarm optimization (MOPSO) is utilized to construct a comprehensive shift schedule by simultaneously considering the dynamic and economic performance of the vehicle. Then, the dynamic and economic shift schedules are deployed as the benchmark to examine the performance of the proposed shift schedule. Finally, the effectiveness of the Fuzzy-DP shift schedule is evaluated by comparison with others under various combined driving cycles (including vehicle load and velocity). The comparisons demonstrate the remarkable promotion in the adaptability of the Fuzzy-DP shift schedule in terms of acceleration time, energy-saving potential, and shift frequency. The most significant improvements in the dynamic, economic, and shift frequency can reach 8.86%, 10.12%, and 8.56%, respectively, in contrast to the MOPSO-based shift schedule.

Multi-objective optimization of battery capacity of grid-connected PV-BESS system in hybrid building energy sharing community considering time-of-use tariff

The use of renewable energy and storage systems in energy sharing communities relieves the strain on the grid and reduces the cost of electricity, making the design of community energy management strategies particularly important. In this paper, a shared energy storage operation strategy considering the time-of-use tariff is proposed for the grid-connected PV-BESS system of hybrid building community including factories, offices and dormitories. Aiming at maximizing the photovoltaic self-consumption ratio, minimizing the payback period and power transportation loss, the system is optimized by non-dominated sequencing genetic algorithm II to obtain the optimal battery capacity of each building under the designed strategy. The results show that when the total battery capacity of the community is determined, the photovoltaic power generation of each building and the building load are the main factors that affect the allocation of battery capacity, and the proportion of battery allocation in each building changes little when the values of other influencing parameters are changed. The photovoltaic array area of the building, the difference between peak and valley electricity price and the power input and output limits of the grid are the main factors affecting the optimal battery capacity and system performance. When the photovoltaic array area increases from 65% to 80%, the difference between peak and valley price increases from 0.52RMB/kWh to 0.82RMB/kWh, and the grid power output limit increases from 7500 kW to 9000 kW, the total optimal battery capacity is increased by 9.8%, 20%, 2.2%, the corresponding payback period is increased by 4%, 3.1%, 2%, the photovoltaic self-consumption ratio is increased by 3.3%, 1.9%, 0.2%, and the electricity transportation loss is increased by 6%, 21%, 2.4%, respectively. On the contrary, when the grid power input limit increases from 5500 kW to 7000 kW, the optimal total battery capacity, the corresponding payback period, photovoltaic self-consumption ratio, and power transport loss are reduced by 2.8%, 2.5%, 0.3% and 3.3%, respectively. This study provides theoretical guidance for community battery capacity optimization and energy scheduling design under the peak-valley policy of power grid.

System Design of Optimal Pig Shipment Schedule through Prediction Model

We propose an optimal system for determining the shipping schedule for pigs using a predictive model using machine learning based on big data. This system receives photographic and weight measurement information for each pig from a camera and a weighing machine installed in a pig pen for raising pigs corresponding to a predetermined fattening period. Then, the photographic information of each of these pigs is applied to a predictive model machine-learned in advance to determine whether or not there are candidate pigs for determining the presence or absence of abdominal fat-forming pigs. And if there is a candidate pig, it is determined using a machine-learning model for predicting whether the candidate pig is an abdominal fat-forming pig by analyzing the pattern of weight increase of the abdominal fat-forming pig and changes in weight of a candidate. If the candidate pig is an abdominal fat-forming pig, the timing of shipping is determined by predicting when the weight of the candidate pigs, specifically the abdominal fat-forming pigs, will reach a predetermined minimum shipping weight. This prediction is made using a machine-learning model that considers the weight gain trend pattern of abdominal fat-forming pigs and tracks changes in the weight of the candidate pig. A machine-learning model is used to predict the timing of weight gain in candidate pigs, specifically those that develop abdominal fat, in order to determine the optimal shipping time. By analyzing the weight gain patterns of abdominal fat-forming pigs and monitoring the weight changes in the candidate pig, the model can predict when the candidate pig will reach the minimum weight required for shipping. In this paper, we would like to present a point of view based on the body type and weight of pigs corresponding to the fattening period through this system, whether intramuscular fat has adhered or abdominal fat is excessively formed by the fed feed and appropriate shipment as the fattening status of pigs.

Assessing Geological and Mining Condition Nuisance and its Impact on the Cost of Exploitation in Hard Coal Mines with the Use of a Multi-Criterion Method

This article presents the use of a multi-criterion Analytic Hierarchy Process (AHP) method to assess geological and mining condition nuisance in longwall mining operations in selected coal mines in Poland. For this purpose, a methodology has been developed which was used to calculate the operational nuisance indicator (WUe) in relation to the cost of mining coal in individual longwalls. Components of the aggregate operational nuisance indicator include four sub-indicators: the natural hazards indicator (UZN), an indicator describing the seam parameters (UPZ), an indicator describing the technical parameters (UT) and an environmental impact indicator (UŚ). In total, the impact of 28 different criteria, which formed particular components of the nuisance indicators were analysed. In total 471 longwalls in 11 coal mines were analysed, including 277 longwalls that were mined in the period of 2011 to 2016 and 194 longwalls scheduled for exploitation in the years 2017 to 2021. Correlation analysis was used to evaluate the relationships between nuisance and the operating costs of longwalls. The analysis revealed a strong correlation between the level of nuisance and the operating costs of the longwalls under study. The design of the longwall schedule should therefore also take into account the nuisance arising from the geological and mining conditions of the operations. Selective operations management allows for the optimization of costs for mining in underground mines using the longwall system. This knowledge can also be used to reduce the total operating costs of mines as a result of abandoning the mining operations in entire longwalls or portions of longwalls that may be permanently unprofitable. Currently, underground mines do not employ this optimization method, which even more emphasizes the need for popularizing this approach.

Integrated Planning of Feeder Route Selection, Schedule Design, and Fleet Allocation with Multimodal Transport Path Selection Considered

In the shipping network optimization, the feeder liner companies not only need to decrease the operation cost by comprehensively optimizing the route, schedule, and fleet but also try to increase the operation income by attracting more shippers, with multimodal transport-path selection considered. Therefore, this paper proposes the integrated planning of feeder route selection, schedule design, and fleet allocation with shippers’ transport-path selection considered. We utilize the nested Logit model to analyze the shipper selection behavior for the multimodal transport path and then formulate a mixed-integer nonlinear programming model of integrated optimization for route, schedule, and fleet. To solve our nonlinear model, we propose a particle swarm optimization (PSO) framework embedded with CPLEX solver by combining the constraint relaxations and the linearization techniques with the heuristic rules. Based on the multimodal transport system in Northern China, computational experiments were conducted to verify the effectiveness of our model and algorithm. The sensitivity analyses of model parameters show that with the increase in ship rent, feeder liner companies should reduce the ship capacity or try to increase the number of port call. With the increase in fuel price, feeder liner companies should reduce the ship speed under the constraints of the arrival-time window and schedule interval. If shippers’ time utility coefficient is high, feeder liner companies should shorten the sailing time of ships by decreasing the number of port calls or shorten the at-port time of ships by increasing the service frequency. If the multimodal transport paths are cost-advantaged or if the waterway transport time has a small impact on multimodal transport time, feeder liner companies should weigh the increase in income and cost when using the measures of time saving. These management insights provide decision support for the operation practice of liner shipping network optimization.

A Combination of Chaotic Harris Hawks Optimizer‐Stacking Model and Kernel Density Estimation Method for Pressing Force Prediction During Slab Sizing Press Process

During the slab sizing press (SP) process, the pressing force corresponds to the slab profile, which guides the production schedule design and the final profile control. To accomplish the prediction of pressing force for SP, an improved ensemble method based on chaotic Harris hawks optimizer (CHHO) and stacking is proposed. A mechanistic knowledge is introduced for feature selection that enhances the rationality of input features. Subsequently, 11 machine learning models are compared and 5 of them are selected as candidate learners for the stacking method. Based on the candidates learners, 8 stacking strategies are constructed, which the stacked model with extratree regressor, gradient boosted decision trees, and kernel ridge regression (KRR) as base‐learners and KRR as meta‐learner performs the best. The R2, MAE, mean square error, mean squared log error, and mean absolute percentage error for the test dataset are 0.9912, 0.0856, 0.0167, 0.0005, and 2.00%, respectively, and 95% of the prediction errors are less than 0.15 MN. Then, sensitivity analysis and predictive analysis based on Shapley Additive Explanations are performed to demonstrate the good alignment of the proposed model with physical reality. Furthermore, to cope with the complexity and uncertainty of the production process, the proposed CHHO‐stacking model and the kernel density estimation method are integrated to model the prediction interval.