Neighborhood Search Research Articles

Robotic Warehousing Operations: A Learn-Then-Optimize Approach to Large-Scale Neighborhood Search

The rapid deployment of robotics technologies requires dedicated optimization algorithms to manage large fleets of autonomous agents. This paper supports robotic parts-to-picker operations in warehousing by optimizing order–workstation assignments, item–pod assignments, and the schedule of order fulfillment at workstations. The model maximizes throughput, managing human workload at the workstations and congestion in the facility. We solve it via large-scale neighborhood search with a novel learn-then-optimize approach to subproblem generation. The algorithm relies on an off-line machine learning procedure to predict objective improvements based on subproblem features and an online optimization model to generate a new subproblem at each iteration. In collaboration with Amazon Robotics, we show that our model and algorithm generate much stronger solutions for practical problems than state-of-the-art approaches. In particular, our solution enhances the utilization of robotic fleets by coordinating robotic tasks for human operators to pick multiple items at once and by coordinating robotic routes to avoid congestion in the facility. Funding: This research was partially funded by Amazon.com Services LLC under award number 2D-12552417. Supplemental Material: The online appendix is available at https://doi.org/10.1287/ijoo.2024.0033 .

Enhancing offshore parcel delivery efficiency through vessel-unmanned aerial vehicle collaborative routing

Offshore oil and gas production is vital for global energy supply, but it faces logistical challenges due to the high costs and inefficiencies of traditional supply methods. This paper introduces the vessel-unmanned aerial vehicle (UAV) routing problem with multiple visits in a single flight (VURP-M), a novel logistical model that addresses aimed at enhancing the replenishment of offshore platforms with small, essential items. The VURP-M allows the UAV to perform multiple visits during a single flight, optimising the delivery process. To tackle the VURP-M, we propose two mixed-integer second-order cone programs that capture the problem's complexities. Given its NP-hard nature, we employ an adaptive large neighbourhood search (ALNS) method, featuring a segmented initialisation process and problem-specific operators guided by a rule-based mechanism to improve solution efficiency. The ALNS formulates an initial solution by solving a travelling salesman problem to create a giant tour, which is then used to group sequential targets into multiple UAV flights. The subsequent optimal resolution of a SOCP determines the take-off and landing points for each flight. Subsequently, the ALNS refines the initial solution through destroy and repair operators, enhancing the search for superior sequences and allocation schemes. The effectiveness of our approach is demonstrated through a real-world case study and numerical experiments on random instances featuring up to 100 platforms. The results offer implications of the collaborative vessel-UAV model for the offshore logistics industry.

Research on the A* Algorithm for Automatic Guided Vehicles in Large-Scale Maps

The traditional A* algorithm faces the challenges of low search efficiency and large node extension range in the field of path planning. These directly restrict the overall performance of the algorithm. In this study, we aimed to improve the search efficiency and path planning quality of the A* algorithm in complex and large-scale environments through a series of optimisation measures, including the innovation of weight design, flexible adjustment of the search neighbourhood, improvement of the heuristic function, and optimisation of the node selection strategy. Specifically, this study innovatively introduces the local obstacle rate as the core index of weight design, and it dynamically adjusts the weights according to the change of the obstacle rate during the node movement process, which effectively reduces the search space and significantly improves the search speed. At the same time, according to the real-time change of the local obstacle rate, this study dynamically adjusts the range of the search neighbourhood, so that the algorithm can choose the optimal search strategy according to different environmental information. In terms of the improvement of the heuristic function, this study adopted the diagonal distance as the benchmark for cost estimation, and it innovatively introduces the angle coefficient to reflect the complexity of path turning, thus providing the algorithm with a more accurate guidance for the search direction. In addition, this study optimises the node selection method by drawing on the idea of simulated annealing, which eliminates the need to calculate and compare all possible surrogate values during the node selection process, thus significantly reducing the running time of the algorithm. The results of the simulation experiments fully verify the effectiveness and practicality of the improved algorithm. Compared with the traditional A* algorithm, the improved algorithm achieved significant optimisation in terms of the average running time, the number of expansion nodes, and the path length, with the average running time shortened by 84%, the number of expansion nodes reduced by 94%, and the path length also shortened by 2.3%.

Optimization of emergency material distribution routes in flood disaster with truck‐speedboat‐drone coordination

AbstractTo improve the effectiveness of flood disaster relief operations, by ensuring timely and accurate delivery of urgently needed supplies to affected areas, this study focuses on the problem of emergency material distribution during floods. With the objective of minimizing the overall delivery time of emergency materials, we propose a coordinated optimization model that integrates trucks, speedboats, and drones for effective distribution of emergency supplies in flood‐affected areas. To solve this optimization problem, we introduce an improved adaptive large neighborhood search (IALNS) algorithm, which builds on the traditional ALNS framework through refined tuning of deletion and insertion operators. Comparative analyses are conducted with a genetic algorithm, simulated annealing algorithm, and tabu search algorithm. The results reveal that the average performance gap of IALNS compared to these methods is 91.13%, 152.72%, and 16.92%, respectively. The experimental results demonstrate that the efficiency of the proposed model and algorithm in addressing the emergency supply distribution problem during flood disasters, highlighting the superior performance of IALNS. This research contributes to enhancing disaster response strategies, ultimately leading to improved outcomes for flood‐affected communities.

CPLNS: Cooperative Parallel Large Neighborhood Search for Large-Scale Multi-Agent Path Finding

CPLNS: Cooperative Parallel Large Neighborhood Search for Large-Scale Multi-Agent Path Finding

Optimizing task assignment and routing operations with a heterogeneous fleet of unmanned aerial vehicles for emergency healthcare services

This paper studies the optimization of task assignment and pickup and delivery operations using a heterogeneous fleet of unmanned aerial vehicles (UAVs). We specifically address the distribution of emergency medical supplies, including medications, vaccines, and essential medical aid, as well as the collection of biological blood samples for testing and analysis. Unique challenges, such as supply shortages, time windows, and geographical considerations, are explicitly taken into account. The problem is first formulated as a mixed-integer linear programming model aimed at maximizing the total profit derived from the execution of a set of emergency healthcare pickup and delivery tasks. An enhanced Q-learning-based adaptive large neighborhood search (QALNS) is proposed for large-scale benchmark instances. QALNS exhibits a superior performance on benchmark instances. It also improves the quality of the solutions on average by 5.49% and 6.86% compared to the Gurobi solver and a state-of-the-art adaptive large neighborhood search algorithm, respectively. Sensitivity analyses are performed on critical factors contributing to the performance of the QALNS algorithm, such as the learning rate and the discount indicator. Finally, we provide managerial insights on the use of the fleet of UAVs and the design of the network.

Train assignment and handling capacity arrangement in multi-yard railway container terminals: An enhanced adaptive large neighborhood search heuristic approach

Expanding terminal scale and constructing multiple railway handling yards have become popular strategies for leading railway container terminals globally to cope with the ever-increasing handling volume. Although such an approach greatly enhances the terminal’s productivity, it also intensifies handling operations and introduces additional inter-yard interactions, complicating terminal management. To address these challenges, this paper investigates an integrated optimization approach for multi-yard railway container terminals, which feature both rail-road and rail-rail container transshipment operations. The train assignment plan for each yard and the handling capacity arrangement for each train are jointly optimized while considering inter-yard container transits, workload allocation for yards, and safety requirements in train shunting. This problem is formulated as a nonlinear programming model, with the objective to minimize operational delay and service time for each incoming train, and to minimize workload differences and container transit volume among yards. To efficiently solve this problem, this research develops an enhanced adaptive large neighborhood search (EALNS) heuristic, which includes several customized operators and feasibility repair methods, and is further enhanced with a local search method and backtracking mechanism compared to the standard ALNS framework. Computational experiments with different data scales and problem settings demonstrate the superiority of the EALNS in terms of solution quality and stability compared with three other solution methods. Additionally, practical insights for terminal operations are drawn through detailed analysis of different infrastructure configurations, transshipment train characteristics, and unit cost settings.

Exploring the ALNS method for improved cybersecurity: A deep learning approach for attack detection in IoT and IIoT environments

With the emergence of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), the flow of data across the world is experiencing a rapid expansion. Unfortunately, this exponential growth is accompanied by a proportional increase in cyber threats, jeopardizing the security and integrity of computer systems. In this context, intrusion detection becomes a necessity to protect networks and systems against potential attacks, ensuring their proper functioning and reliability. In this paper, we propose a deep learning-based model for attack detection. This model utilizes a convolutional neural network to train the datasets, which are first cleaned and preprocessed. The model inputs are selected using an optimization method called adaptive large neighborhood search. The results obtained for the four datasets used - CICIDS2017, Edge-IIoTset, ToN-IoT windows7, and ToN-IoT windows10 - demonstrate the model’s effectiveness for both multi-class and binary classification cases. In the binary case, the accuracy reaches 99.85%, 100%, 99.97%, and 100%, respectively, and in the multi-class case, it stands at 99.81%, 94.98%, 99.92%, and 99.84%, respectively.

A risk-averse latency location-routing problem with stochastic travel times

In this paper, a latency location-routing problem with stochastic travel times is investigated. The problem is cast as a two-stage stochastic program. The ex-ante decision comprises the location of the depots. The ex-post decision regards the routing, which adapts to the observed travel times. A risk-averse decision-maker is assumed, which is conveyed by adopting the latency CVaRα as the objective function. The problem is formulated mathematically. An efficient multi-start variable neighborhood search algorithm is proposed for tackling the problem when uncertainty is captured by a finite set of scenarios. This procedure is then embedded into a sampling mechanism so that realistic instances of the problem can be tackled, namely when the travel times are represented by random vectors with an infinite support. An extensive computational analysis is conducted to assess the methodological developments proposed and the relevance of capturing uncertainty in the problem. Additional insights include the impact of the risk level in the solutions.

Proximal Policy Optimization with Population-based Variable Neighborhood Search Algorithm for Coordinating Photo-Etching and Acid-Etching Processes in Sustainable Storage Chip Manufacturing

In the complex process of manufacturing storage chips, the photo-etching and acid-etching stages play a crucial role, significantly affecting energy consumption and environmental impact. This paper introduces a novel Bi-Level Programming Model for Storage Chip Manufacturing (BLPM-SCM) aimed at optimizing the coordination between these two stages. The upper-level model focuses on minimizing the time it takes to complete wafer production, while the lower-level model seeks to reduce the number of acid-etching tanks used, thereby balancing production efficiency with resource utilization. To address the inherent complexity of the bi-level model, we present a hybrid meta-heuristic algorithm that combines Proximal Policy Optimization (PPO) with a Population-based Variable Neighborhood Search (PVNS) method. The PPO-PVNS algorithm enhances the intensification phase by adaptively selecting shaking and local search strategies, while PVNS supports the diversification phase, ensuring comprehensive exploration of the search space through iterative updates of the solution population. Extensive numerical experiments demonstrate the algorithm's superior performance and generalization capabilities in optimizing the manufacturing process. It significantly improves the coordination between the photo-etching and acid-etching stages, achieving dual optimization of energy consumption and environmental benefits. Furthermore, this study provides valuable insights and decision-making tools for industry practitioners, offering innovative solutions for scheduling optimization in the semiconductor sector and promoting more sustainable and efficient production practices.

Optimizing the Number of Clusters for Billion-Scale Quantization-Based Nearest Neighbor Search

Optimizing the Number of Clusters for Billion-Scale Quantization-Based Nearest Neighbor Search

A Simheuristic Approach to Scheduling Sustainable and Reliable Maintenance for Bridge Infrastructure

Designing maintenance strategies for a vast portfolio of aging infrastructures requires decision-makers to ensure adequate safety levels while addressing the requirements on service interruptions, costs, and workforce availability. This study addresses the problem of scheduling maintenance interventions for a portfolio of bridges, aiming to minimize CO2 emissions while meeting minimum reliability requirements and adhering to workforce and budget constraints. To achieve this, we present a Simheuristic algorithm that combines a metaheuristic core based on the Adaptive Large Neighborhood Search metaheuristic with a Monte Carlo simulation module. This integration allows for the evaluation of optimized scheduling solutions, accounting for the inherent randomness in the structural deterioration process. The proposed approach is tested in a comparative analysis against traditional time-based and condition-based scheduling methods. Results from diverse bridge portfolios demonstrate that the proposed algorithm offers improved performance in terms of both total costs and CO2 emissions.

Improved Whale Optimization Algorithm with Variable Neighbourhood Search Strategy (WOA-VNS) in Solving Vehicle Routing Problem (VRP) for Recommending Multi-days Tourist Routes in Yogyakarta

Improved Whale Optimization Algorithm with Variable Neighbourhood Search Strategy (WOA-VNS) in Solving Vehicle Routing Problem (VRP) for Recommending Multi-days Tourist Routes in Yogyakarta

Cross-modal similar clinical case retrieval using a modular model based on contrastive learning and k-nearest neighbor search

ObjectiveElectronic health record systems have made it possible for clinicians to use previously encountered similar cases to support clinical decision-making. However, most studies for similar case retrieval were based on single-modal data. The existing studies on cross-modal clinical case retrieval were limited. We aimed to develop a CRoss-Modal Retrieval (CRMR) model to retrieve similar clinical cases recorded in different data modalities. Materials and methodsThe publically available Medical Information Mart for Intensive Care-Chest X-ray (MIMIC-CXR) dataset was used for model development and testing. The CRMR model was designed as a modular model containing two feature extraction models, two feature transformation models, one feature transformation optimization model, and one case retrieval model. The ability to retrieve similar clinical cases recorded in different data modalities was facilitated by the use of contrastive deep learning and k-nearest neighbor search. ResultsThe average retrieval precision, denoted as AP@k, of the developed CRMR model, were 76.9 %@5, 76.7 %@10, 76.5 %@20, 76.3 %@50, and 77.9 %@100, respectively. Here k is the number of similar cases returned after retrieval. The average retrieval time varied from 0.013 ms to 0.016 ms with k varying from 5 to 100. Moreover, the model can retrieve similar cases with the same multiple radiographic manifestations as the query case. DiscussionThe CRMR model has shown promising cross-modal retrieval performance in clinical case analysis, with the potential for future scalability and improvement in handling diverse disease types and data modalities. The CRMR model has promising potential to aid clinicians in making optimal and explainable clinical decisions.

VNS-BA*: An Improved Bidirectional A* Path Planning Algorithm Based on Variable Neighborhood Search.

The A* algorithm is an effective method for path planning; however, it has certain drawbacks, such as a high number of turns, low planning efficiency, and redundant searches. To address these issues, this paper proposes an improved bidirectional A* global path planning algorithm based on a variable neighborhood search strategy, named VNS-BA*. The new algorithm first employs an 8-11-13 neighborhood search method for node expansion. Then, the bidirectional search strategy is optimized by using the current nodes of the opposite path and the global target point, enabling the two paths to meet in the middle of the map. Finally, redundant turns are removed from the path, and cubic spline interpolation is applied to achieve local smoothing at the turns. The effectiveness of the improved algorithm was validated on different maps and compared with A* and its three derived improved versions. The simulation results indicate that VNS-BA* shows significant improvements in terms of the number of path turns, turn angles, and planning efficiency.

Re-Supplying Autonomous Mobile Parcel Lockers in Last-Mile Distribution

This paper investigates a practical last-mile delivery scenario where a fleet of trucks replenishes autonomous mobile parcel lockers (AMPLs) in an urban setting. The lockers move along specified paths within restricted zones to reach customers’ locations. Ensuring seamless coordination between trucks and AMPLs requires the identification of suitable locations to exchange empty or loaded modular lockers. We first introduce a mixed-integer linear programming (MILP) formulation for the investigated problem. The proposed formulation establishes the basis for optimizing meeting point selection and routing decisions. Additionally, the study introduces a cluster-based simulated annealing (CSA) algorithm tailored for addressing larger-scale instances of the studied problem. The CSA algorithm incorporates the K-means clustering method with specialized operators rooted in an extensive neighborhood search, aiming to improve the effectiveness of solution discovery. We generated a new set of benchmark instances to assess the MILP formulation’s efficiency and the proposed metaheuristic algorithm and conducted comprehensive numerical experiments.

A Dataset of 3M Single-DOF Planar 4-, 6-, and 8-bar Linkage Mechanisms with Open and Closed Coupler Curves for Machine Learning-Driven Path Synthesis

Abstract In recent years, there has been a strong interest in applying machine learning techniques to path synthesis of linkage mechanisms. However, progress has been stymied due to a scarcity of high-quality datasets. In this paper, we present a comprehensive dataset comprising nearly three million samples of four-, six-, and eight-bar linkage mechanisms with open and closed coupler curves. Current machine learning approaches to path synthesis also lack standardized metrics for evaluating outcomes. To address this gap, we propose six key metrics to quantify results, providing a foundational framework for researchers to compare new models with existing ones. We also present a Variational AutoEncoder based model in conjunction with a k-nearest neighbor search approach to demonstrate the utility of our dataset. In the end, we provide example mechanisms that generate various curves along with numerical evaluation of the proposed metrics.

Fuzzy flexible job shop dynamic scheduling considering machine remaining processing capacity

Dynamic fuzzy flexible job shop scheduling (DFFJSP) is significant in the medical equipment industry. Generally the dynamic flexible job shop scheduling problem considers a single dynamic factor or ignores resources such as machine itself also plays a huge role in dealing dynamic issues. Thus fuzzy processing time and machine breakdowns are considered in this paper. In order to copy with two problems mentioned above, the model of DFFJSP containing two objectives of makespan and energy consumption is established. To solve this problem, the remaining processing capacity of broken machine is applied to weaken the impacts of machine breakdowns and a multi-objective evolutionary algorithm (NG-WOA) is proposed, which integrating NSGA-II and whale optimal algorithm (WOA). Furthermore, the joining of variable neighborhood search makes NG-WOA skip the local optimum solution in time. Through experiments, the validity of remaining processing capacity is verified in rescheduling scheme. Then NG-WOA algorithm is proven can find better solutions when compared with other two algorithms according to the distribution of pareto forefront solutions in benchmark examples. The results of this paper show that the remaining processing capacity has greater advantages in guaranteeing the stability of dynamic scheduling problems, because the machine’s processing capacity can be utilized fully compared to previous strategies for fault disturbances.

Delivery routing for electric vehicles with en-route mobile battery swapping

Amid increasing environmental concerns, electric vehicles (EVs) are gaining traction as a sustainable transportation alternative. However, the widespread adoption of EVs is hindered by range limitations, inadequate charging infrastructure, and unpredictable access to charging facilities. The battery swapping van (BV) has been proposed as an innovative approach to actively offer on-demand charging at designated locations. This study leverages the novel BV concept and proposes a novel electric vehicle routing model with time windows and en-route mobile battery swapping (EVRPTW-EMBS). This achieves flexible mobile battery swapping services provided by BVs to EVs that are either en route or at customer sites. A tailored heuristic algorithm called CIP-TDP-ILNS is adopted, combining improved large neighborhood search (ILNS) with tree-template dynamic programming (TDP) and cluster-aided integer programming (CIP) to reduce the search space and enhance solving efficiency. Through extensive testing, the CIP-TDP-ILNS algorithm exhibits robust performance, yielding up to 16% cost reductions for the EVRPTW-EMBS compared to the benchmark model. The findings of this study suggest that (1) the EVRPTW-EMBS system is particularly beneficial for servicing clients with wider time windows, and (2) the optimal balance between the quantity of batteries carried and their capacity should be tailored to the logistics network’s size.

A multi-strategy improved sparrow search algorithm for indoor AGV path planning

To address the problems of weak search ability, easily falling into local optimal solutions and poor path quality of sparrow search algorithm in AGV path planning, a multi-strategy improved sparrow search algorithm (MISSA) is proposed in this paper. MISSA improves the global search ability by improving the discoverer position update operator and introducing the sine cosine algorithm; adopts the adaptive number of vigilantes and adaptive adjustment step size to improve the convergence speed; introduces the Levy flight variation strategy to reduce the probability of falling into any local optimal solution; optimizes the boundary handling mechanism to prevent the loss of population diversity at a later stage; finally, uses the large-scale neighborhood search strategy and path smoothing mechanism for path optimization to further improve the path quality. The superiority-seeking ability of MISSA was verified by 12 standard test functions, and then 30 simulation experiments were conducted in grid maps with two specifications of 20×20 and 30×30. The experimental results showed that, by using MISSA, the path length was reduced by 44.1% and 63.1%, the number of turns was reduced by 68.4% and 78.4%, and the risk degree was reduced by 61.3% and 77.2%, which verifies the superiority of MISSA in path planning. Finally, MISSA was ported to the QBot2e mobile robot for physical verification to prove its feasibility in practical applications.