Simulation Modelling Practice and Theory最新文献

{"title":"Leveraging machine learning and feature engineering for optimal data-driven scaling decision in serverless computing","authors":"Mustafa Daraghmeh ,&nbsp;Yaser Jararweh ,&nbsp;Anjali Agarwal","doi":"10.1016/j.simpat.2025.103090","DOIUrl":"10.1016/j.simpat.2025.103090","url":null,"abstract":"<div><div>Serverless computing offers scalability and cost-efficiency, but balancing performance and cost remains challenging, particularly in scaling decisions that can lead to cold starts or resource misallocation. This research is motivated by the need to minimize the impact of cold starts and optimize resource utilization in serverless applications by developing intelligent, data-driven scaling decisions. We delve into using machine learning and feature engineering to model and simulate predictions for optimal scaling decisions for Azure Function Apps (AFA). Our focus lies in predicting the ideal timing for provisioning or de-provisioning the Function App’s environment. Using historical invocation data, we applied a sliding window to transform the time-series data into patterns categorized as load or unload classes, considering various target periods. To identify the most effective model, we compared the performance of various baseline models with and without calibration (isotonic and sigmoid) to enhance precision. In addition, we assess multiple feature extraction methods in invocation patterns and explore the use of Principal Component Analysis (PCA) for dimensionality reduction to reduce computation costs. Using the best-identified configurations, we model and simulate the class patterns over time to compare the actual classes with the predicted ones, focusing on memory usage and the costs associated with cold starts. The proposed model is thoroughly evaluated using various metrics under different setups, revealing notable improvements in scaling decisions achieved by applying calibration and feature engineering methods. These findings demonstrate the potential of machine learning for intelligent, data-driven scaling decisions in serverless computing, offering valuable insights for cloud providers to optimize resource allocation and for developers to build more efficient and responsive serverless applications. Specifically, the proposed method can be integrated into serverless platforms to automatically adjust resource provisioning based on predicted workload demands, reducing cold start latency and improving cost-effectiveness.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103090"},"PeriodicalIF":3.5,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical prediction of residual stress and distortion for laser powder bed fusion (LPBF) AM process of Ti-6Al-4V","authors":"J. Mohanraj,&nbsp;Jambeswar Sahu","doi":"10.1016/j.simpat.2025.103094","DOIUrl":"10.1016/j.simpat.2025.103094","url":null,"abstract":"<div><div>The demand of additive manufacturing (AM) processes has increased in the industry due to its realistic printing of complex geometry parts. The process involves with continuous melting of powder and rapid solidification. The heating and cooling attributes to the formation of residual stress which leads to the distortion in the AM part. The prediction of distortion and residual stress before printing could minimize the rejection of parts due to dimensional variation. In the present research work, an attempt was made to simulate LPBF AM process using MSC Simufact software for Ti-6Al-4V material. The simulation results are compared with the existing literature. The simulation parameters are optimized to minimize the deviation between experimental and simulation results. The inherent strain value, voxel size and other simulation parameters are utilized to predict the distortion and residual stress of a micro-tensile specimen. The distortion and residual are predicted in different orientations (0°, 30°, 45°, 60° and 90°) and at position of the base plate. It is observed that voxel size (accumulation of physical layers) has a significant effect on the prediction accuracy. The specimen placed near the power collector bin and gas inlet side shows minimum residual stress. The residual stress in the gauge section of 45° orientation is minimal compared to other-oriented specimens. The limited distortion is noticed for the 0° orientation specimen as the height of the sample is minimal.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103094"},"PeriodicalIF":3.5,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BRAVE: Benefit-aware data offloading in UAV edge computing using multi-agent reinforcement learning","authors":"Odyssefs Diamantopoulos Pantaleon,&nbsp;Aisha B Rahman,&nbsp;Eirini Eleni Tsiropoulou","doi":"10.1016/j.simpat.2025.103091","DOIUrl":"10.1016/j.simpat.2025.103091","url":null,"abstract":"<div><div>Edge computing has emerged as a transformative technology in public safety and has the potential to support the rapid data processing and real-time decision-making during critical events. This paper introduces the BRAVE framework, a cutting-edge solution where the UAVs act as Mobile Edge Computing (MEC) servers, addressing users’ computational demands across disaster-stricken areas. An accurate UAV energy consumption model is introduced, including the UAV’s travel, processing, and hover energy. BRAVE accounts for both the users’ Quality of Service (QoS) requirements, such as latency and energy constraints, and UAV energy limitations in order to determine the UAVs’ optimal path planning. The BRAVE framework consists of a two-level decision-making mechanism: a submodular game-based model ensuring the users’ optimal data offloading strategies, with provable Pure Nash Equilibrium properties, and a reinforcement learning-driven UAV path planning mechanism maximizing the data collection efficiency. Furthermore, the framework extends to collaborative multi-agent reinforcement learning (BRAVE-MARL), enabling the UAVs’ coordination for enhanced service delivery. Extensive experiments validate the BRAVE framework’s adaptability and effectiveness and provide tailored solutions for diverse public safety scenarios.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103091"},"PeriodicalIF":3.5,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A mesoscopic link-transmission-model able to track individual vehicles","authors":"Felipe de Souza ,&nbsp;Omer Verbas ,&nbsp;Joshua Auld ,&nbsp;Chris M.J. Tampère","doi":"10.1016/j.simpat.2025.103088","DOIUrl":"10.1016/j.simpat.2025.103088","url":null,"abstract":"<div><div>Macroscopic traffic flow is a common choice for large-scale traffic simulations. These models do not provide individual-specific metrics as outputs. However, this treatment is necessary in agent-based-models, as in, for example, assigning routes based on personal characteristics. In this paper, we propose an extension of the link-transmission-model, an efficient and yet accurate discretization of the Lighthill–Whitham–Richards (LWR) model, which allow vehicles to be tracked individually while keeping the main features of the underlying model. The extension comprises modifying the link and node models to ensure that the flow between links is always at discrete levels. Therefore, every unit of flow is associated with one individual vehicle moving from its current to its next link. An upper bound of the discretization error is provided. We show that the proposed model resembles its continuous counterpart on lane drop, merge, and diverge cases. In addition, we apply the model into three different networks to validate its applicability in large networks. Finally, we also confirm the parameter transferability between continuous and discrete models and that both can well reproduce field data.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103088"},"PeriodicalIF":3.5,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of communication performance measures for the Internet of Vehicles in an intersection scenario","authors":"Haijian Li ,&nbsp;Qi Zhang ,&nbsp;Lijun Wu ,&nbsp;Zihan Zhang","doi":"10.1016/j.simpat.2025.103086","DOIUrl":"10.1016/j.simpat.2025.103086","url":null,"abstract":"<div><div>With the development of the Internet of Vehicles (IoV) technology and the advancement of autonomous driving technology, the efficiency of traffic flow has improved and the safety of driving and the convenience of travel have becoming better and better. However, in real-world intersection scenarios, there are still circumstances where the delay between vehicles is increased and the communication distance is largely decreased. Many scholars worldwide have analyzed and discussed the performance of LTE Mode 4 and the development of autonomous driving, such as the application and design of the LTE Mode 4. Therefore, this paper constructs a virtual IoV communication environment and conducts research on intersection control methods under the influence of communication performance. This paper provides reference values for the stability of vehicle communication network in actual road traffic pattern and provides a theoretical basis and data support for subsequent research on autonomous and adaptive sensor-based intersections.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103086"},"PeriodicalIF":3.5,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harnessing coloured Petri nets to enhance machine learning:A simulation-based method for healthcare and beyond","authors":"Andressa C.M. da Silveira ,&nbsp;Álvaro Sobrinho ,&nbsp;Leandro Dias da Silva ,&nbsp;Danilo F.S. Santos ,&nbsp;Muhammad Nauman ,&nbsp;Angelo Perkusich","doi":"10.1016/j.simpat.2025.103080","DOIUrl":"10.1016/j.simpat.2025.103080","url":null,"abstract":"<div><div>Many industries use Machine Learning (ML) techniques to enhance systems’ performance. However, integrating ML into these systems poses challenges, often requiring improved explainability and accuracy. Using formal methods is a potential solution to address these challenges. This paper presents a simulation-based method using Coloured Petri Nets (CPN) to enhance the explainability and accuracy of Decision Tree (DT) and Random Forest (RF) models, which industries such as healthcare widely adopt. Our simulation-based method, named RuleXtract/CPN, provides procedures for the automatic extraction of decision rules from an implemented ML model, the generation of these decision rules into a CPN model, the analysis of the CPN model through simulations, and the adjustment of the CPN model to improve explainability and accuracy. Automating the transformation from DT/RF to a CPN model and the analysis procedures can reduce the time and effort needed for modeling tasks. We used web technologies and the Access/CPN framework to implement the procedures defined in our simulation-based method so that users would not need CPN expertise to generate and simulate models, running them in the background. An experiment with three datasets for COVID-19 and five for Influenza screening shows that applying our simulation-based method results in more explainable models. The experiment also shows improvement in accuracy measures for RF models. For instance, the accuracy of the RF model using the Influenza rapid test balanced dataset increased from 84.02% to 86.34%, and the unbalanced dataset from 84.78% to 87.53%. Our results underscore the importance of eliminating duplicated, poorly generalized, and incorrect rules to improve explainability and accuracy. These findings also emphasize the effectiveness of using CPN to improve the models, paving the way for future research.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103080"},"PeriodicalIF":3.5,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An efficient congestion control scheme for railway transport networks","authors":"Zongtao Duan,&nbsp;Jianrong Cao,&nbsp;Xing Sheng,&nbsp;Junzhe Zhang","doi":"10.1016/j.simpat.2025.103085","DOIUrl":"10.1016/j.simpat.2025.103085","url":null,"abstract":"<div><div>As the complexity of railway transmission network services continues to increase, burst traffic and the mixing of signaling have become significant challenges in congestion control. This paper presents a congestion control strategy based on the stochastic flow queue-controlled delay (SFQ-CoDel) algorithm, developed through an analysis of the traffic characteristics and operational demands of contemporary railway transmission networks. The scheme primarily integrates a random flow queue mechanism with a dynamic Hurst coefficient calculation method. The random flow queue employs hash mapping to distinguish data packets, thereby ensuring fair bandwidth allocation across active sub-flows. The dynamic computation of the Hurst coefficient, coupled with a minimum queue delay, formulates a packet loss strategy that effectively mitigates the effects of burst traffic. Experimental results indicate that the SFQ-CoDel algorithm excels in minimizing packet loss, enhancing throughput, and maintaining stable queue lengths, regardless of the load. Additionally, an analysis of parameter adjustability confirms that, even with the inclusion of the stochastic flow queue (SFQ) mechanism, the CoDel parameters consistently sustain optimal algorithm performance. Therefore, the proposed congestion control scheme provides a robust and adaptable framework for managing congestion within railway transmission networks.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"140 ","pages":"Article 103085"},"PeriodicalIF":3.5,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Numerical study on the reinforcement mechanism of prestressed bolts based on the reconstruction of coal fracture structures","authors":"Guanghui Wang ,&nbsp;Xiangyu Wang ,&nbsp;Jiaxin Zhao ,&nbsp;Jianbiao Bai","doi":"10.1016/j.simpat.2024.103046","DOIUrl":"10.1016/j.simpat.2024.103046","url":null,"abstract":"<div><div>The presence of structural weak planes severely affects the stability of the surrounding rocks in underground engineering and the safety of deep resource extraction. This study utilized the discrete element method to simulate and reconstruct the fracture network in the surrounding rocks. A model of the anchored solid containing a fracture network was established using a synthetic rock mass approach. Confined compression tests were conducted on anchored models with different support densities and pretension forces. The results indicate that both high support density and high pretension force can enhance the mechanical properties of fractured anchored solids to varying degrees, significantly improving the bearing capacity during the plastic phase. Additionally, high support density and pretension force can notably alter the failure mode of the anchored solid under load, reducing lateral displacement, delaying the initiation of primary fractures, and decreasing the number of newly formed fractures. From the perspective of prestressed load bearing, increasing anchor density or applying a high pretension force facilitates the formation of a wide and high-strength effective compressive stress zone. This in turn reduces the opening and sliding of primary fracture fields, the generation and propagation of secondary fractures, improves the stress state of the anchored solid, and enhances the overall strength of the surrounding rocks within the anchoring range. From the viewpoint of energy absorption and dissipation, increasing anchor support density and pretension force can significantly improve the ability of surrounding rocks to absorb external input energy, enhance the disturbance resistance of the anchored solid, and slow down the release of strain energy. The modeling process and research findings of this study offer valuable insights for analyzing structural failure and stability control in fractured rock masses.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"139 ","pages":"Article 103046"},"PeriodicalIF":3.5,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143145488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adversarial domain adaptation based on contrastive learning for bearings fault diagnosis","authors":"Xiaolei Pan ,&nbsp;Hongxiao Chen ,&nbsp;Wei Wang ,&nbsp;Xiaoyan Su","doi":"10.1016/j.simpat.2024.103058","DOIUrl":"10.1016/j.simpat.2024.103058","url":null,"abstract":"<div><div>Accurate fault diagnosis of machines is crucial for increasing efficiency, reducing maintenance costs, and preventing catastrophic consequences.While data-driven methods have shown promise in fault diagnosis, most existing models frequently encounter challenges in achieving satisfactory results in industrial fault diagnosis due to varying working conditions. Studies on domain adaptation have made significant contributions to addressing this problem. However, most of these methods concentrate on aligning the inter-domain distributions, whereas the degradation of intra-domain classification performance is overlooked, resulting in confusion at the class boundaries of the target domain during cross-domain diagnosis. To address this issue, a self-supervised domain contrastive discrimination network (SDCDN) is proposed for bearing fault diagnosis under variable working conditions. The proposed method takes the data from both the source and target domains as input for contrastive learning training. Through self-supervised learning, the feature enhancer is trained to capture domain-contrastive features and effectively distinguish the target category. By aligning the distribution of the source and target domains through adversarial learning, the cross-domain diagnosis is achieved without supervision. To validate the effectiveness of the proposed method, six cross-conditional diagnostic tasks are performed on each dataset, utilizing two bearing datasets containing different damage types and a gearbox dataset. The evaluation indicators employed are diagnostic accuracy and computational efficiency. Furthermore, an ablation study is conducted to evaluate the contribution of the domain contrast and discrimination modules. The results demonstrate that the average accuracy of the proposed method is markedly superior to that of the comparison methods for all six cross-domain diagnostic tasks in each of the three datasets, highlighting the superiority of the proposed method.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"139 ","pages":"Article 103058"},"PeriodicalIF":3.5,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143145489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An improved parallel scheduling algorithm for periodic directed acyclic graphs","authors":"Junfan Zhang ,&nbsp;Xiao Song ,&nbsp;Lin Qin ,&nbsp;Ying Cui","doi":"10.1016/j.simpat.2024.103045","DOIUrl":"10.1016/j.simpat.2024.103045","url":null,"abstract":"<div><div>The periodic directed acyclic graph (DAG) is an important system model widely used to describe the structure and function of time-critical applications. The nodes in periodic DAGs are not only coupled with each other by input-output relations but also connected via the preceding period, making it hard to find an optimal schedule. This paper proposes an improved parallel scheduling algorithm for periodic DAGs (PSA-PDAG), decoupling the dependencies between nodes. In each period, PSA-PDAG computes more nodes in parallel, greatly improving the parallelism during computation. By applying PSA-PDAG, the computation time of each period is only the maximum update time among all nodes, which is superior to existing parallel algorithms. In typical periodic DAG examples, theoretical analysis and experimental results show that PSA-PDAG generally outperforms existing serial and hierarchical scheduling parallel algorithms. For instance, in the hybrid-structure large-scale experiment with 128 DAG nodes, compare with the 2.0x speedup of the hierarchical scheduling parallel algorithm, PSA-PDAG can achieve a considerable 48.6x speedup with 128 cores.</div></div>","PeriodicalId":49518,"journal":{"name":"Simulation Modelling Practice and Theory","volume":"139 ","pages":"Article 103045"},"PeriodicalIF":3.5,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143145490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}