IEEE Transactions on Services Computing最新文献_第10页

Joint Service Deployment and Task Offloading for Datacenters With Edge Heterogeneous Servers 边缘异构服务器数据中心的联合服务部署和任务卸载

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-02-05 DOI: 10.1109/TSC.2025.3539199

Fu Xiao;Weibei Fan;Lei Han;Tie Qiu;Xiuzhen Cheng

{"title":"Joint Service Deployment and Task Offloading for Datacenters With Edge Heterogeneous Servers","authors":"Fu Xiao;Weibei Fan;Lei Han;Tie Qiu;Xiuzhen Cheng","doi":"10.1109/TSC.2025.3539199","DOIUrl":"10.1109/TSC.2025.3539199","url":null,"abstract":"Mobile edge computing (MEC) can improve execution efficiency and reduce overhead for offloading computing tasks to edge servers with more resources. In the microservice system, the current research only considers the cross segment communication cost of computing tasks, does not consider the case of the same end, and ignores the discovery and invocation optimization of associated services. In this paper, we propose CACO, which is a novel content-aware classification offloading framework for MEC based on correlation matrix. CACO first designs an adaptive service discovery model, which can make timely response and adjustment to the changes of the external environment. It then investigates an efficient affinity matrix based service discovery algorithm, which expresses the association relationship between services by constructing a service association matrix. In addition, CACO constructs a relational model by giving different weight coefficients to the delay and energy loss, which improves the delay and energy loss of message processing in a satisfying manner. Simulation results indicate that CACO reduces the total traffic of redundant messages by 46.2% <inline-formula><tex-math>$sim$</tex-math></inline-formula>76.5%, respectively compared with state-of-the-art solutions. Testbed benchmarks show that it can also improve the stability by reducing control overhead by 34.5% <inline-formula><tex-math>$sim$</tex-math></inline-formula>81.6% .","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"839-853"},"PeriodicalIF":5.5,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191810","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}

引用次数: 0

BackFillMe: An Energy and Performance Efficient Virtual Machine Scheduler for IaaS Datacenters BackFillMe：用于IaaS数据中心的能源和性能高效的虚拟机调度程序

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-02-05 DOI: 10.1109/TSC.2025.3539190

Muhammad Zakarya;Lee Gillam;Mohammad Reza Chalak Qazani;Ayaz Ali Khan;Khaled Salah;Omer Rana

{"title":"BackFillMe: An Energy and Performance Efficient Virtual Machine Scheduler for IaaS Datacenters","authors":"Muhammad Zakarya;Lee Gillam;Mohammad Reza Chalak Qazani;Ayaz Ali Khan;Khaled Salah;Omer Rana","doi":"10.1109/TSC.2025.3539190","DOIUrl":"10.1109/TSC.2025.3539190","url":null,"abstract":"Backfilling refers to the practice of allowing small jobs to be completed ahead of schedule as long as they do not cause the first job in the line to wait. Users are expected to offer estimates of how long jobs will take to complete in order to make these decisions possible, and these projections are often based on historical data. However, predictions are very hard and may not be accurate, particularly in cloud computing scenarios where jobs or applications run on Virtual Machines (VMs). In addition, scheduling and consolidation techniques can improve the energy efficiency and performance of applications. Consolidation involves VM migrations that can have a negative impact on workload performance and users’ costs. Backfilling can be used as an alternative technique for consolidation (short-term) and/or can be used along with consolidation (long-term). Backfilling methods are well-utilised in single computing systems, but are relatively unexplored in cloud resource allocation. A backfilling-based resource allocation and consolidation technique is proposed. Using real workloads from the Google cluster traces, we investigate the impact of backfilling on infrastructure energy efficiency and performance. For 12583 heterogeneous servers and approximately three million jobs that belong to three different applications, we observed that approximately 19% energy savings and 6% workload performance improvements are achievable using the backfilling approach. Furthermore, our evaluation suggests that using VM runtime as a criterion for the backfilling approach is approximately 3.56%–7.78% more energy and 1.91%–3.38% more performance efficient than using priority as a backfilling criterion.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"660-672"},"PeriodicalIF":5.5,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191811","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}

引用次数: 0

A False Positive Resilient Distributed Trust Management Framework for Collaborative Intrusion Detection Systems 用于协作式入侵检测系统的抗假阳性分布式信任管理框架

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-02-05 DOI: 10.1109/TSC.2025.3539202

Kadhim Hayawi;Imran Makhdoom;Saifullah Khalid;Richard Adeyemi Ikuesan;Mohammed Kaosar;Ishfaq Ahmad

{"title":"A False Positive Resilient Distributed Trust Management Framework for Collaborative Intrusion Detection Systems","authors":"Kadhim Hayawi;Imran Makhdoom;Saifullah Khalid;Richard Adeyemi Ikuesan;Mohammed Kaosar;Ishfaq Ahmad","doi":"10.1109/TSC.2025.3539202","DOIUrl":"10.1109/TSC.2025.3539202","url":null,"abstract":"Collaborative Intrusion Detection System (CIDS) protect large networks against distributed attacks. However, a CIDS is vulnerable to insider attacks that decrease the mutual trust among the CIDS nodes. Most existing trust management approaches rely on a central authority, trusted third parties or network peers for managing trust. The current techniques are prone to high false positives and vulnerable to various reputation attacks. For instance, device attestation manages trust among CIDS nodes by verifying the integrity of a node’s hardware and software configuration. However, it lacks real-time monitoring of the dynamic state, limiting its effectiveness against ongoing attacks and malware. Therefore, incorporating the system’s dynamic state in the trust framework is crucial, but it causes false positives requiring corrective mechanisms. To address these challenges, this paper proposes a blockchain-based integrated trust management framework for CIDS, incorporating the device’s genome attestation, the system’s dynamic parameters, and a false positive resilient reputation mechanism. By storing the reputation scores on the blockchain, the framework alleviates the need for a third party for trust management and thus mitigates attacks applicable to reputation-based systems. The paper performs a comprehensive security and performance analysis of the proposed framework to gauge its efficiency and study the effects of a penalty on a node’s reputation during the recovery and rally phases. We also study the impact of false positives on the reputation of a node. The results show that Hyperledger Fabric offers lower transaction latency and low CPU utilization compared to Ethereum Blockchain.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"513-526"},"PeriodicalIF":5.5,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143191814","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}

引用次数: 0

Uncertainty-Driven Pattern Mining on Incremental Data for Stream Analyzing Service 流分析服务中增量数据的不确定性驱动模式挖掘

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-02-03 DOI: 10.1109/TSC.2025.3536359

Myungha Cho;Hanju Kim;Yoonji Baek;Seungwan Park;Doyoon Kim;Doyoung Kim;Chanhee Lee;Bay Vo;Witold Pedrycz;Unil Yun

{"title":"Uncertainty-Driven Pattern Mining on Incremental Data for Stream Analyzing Service","authors":"Myungha Cho;Hanju Kim;Yoonji Baek;Seungwan Park;Doyoon Kim;Doyoung Kim;Chanhee Lee;Bay Vo;Witold Pedrycz;Unil Yun","doi":"10.1109/TSC.2025.3536359","DOIUrl":"10.1109/TSC.2025.3536359","url":null,"abstract":"Pattern mining, one of the data analysis approaches, provides meaningful assistance for various business services, such as product recommendation and marketing. However, certain real-world data contain uncertain characteristics, and some business services want to consider the uncertainty of data. Uncertain pattern mining is an advanced technique for discovering more useful patterns from uncertainty-driven data with uncertain information about items. However, although many business services create and process incremental data in real-time, most of the previous uncertain pattern mining techniques have limitations in analyzing incremental data since they mainly focus on processing static data. To address the limitations, we present a list-based uncertain pattern mining method that effectively analyzes incremental uncertainty-driven data in real time by scanning stream data only once. In addition, uncertainty-driven data analytics can be executed efficiently due to the list structure that is effective in construction and mining. The tests of performance for runtime, memory consumption, and scalability are performed using real datasets and synthetic datasets, which illustrate that the suggested technique reveals outstanding performance compared to state-of-the-art algorithms. The additional case study evaluations with concept-drifting tests as well as accuracy and significance tests demonstrate the practical applications of the algorithm and the quality of the extracted results.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"1081-1096"},"PeriodicalIF":5.5,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143084098","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}

引用次数: 0

Scalable Large Model for Unlabeled Anomaly Detection With Trio-Attention U-Transformer and Manifold-Learning Siamese Discriminator 基于三注意u型变压器和流形学习暹罗鉴别器的无标记异常检测可扩展大模型

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536306

Muyan Yao;Dan Tao;Peng Qi;Ruipeng Gao

{"title":"Scalable Large Model for Unlabeled Anomaly Detection With Trio-Attention U-Transformer and Manifold-Learning Siamese Discriminator","authors":"Muyan Yao;Dan Tao;Peng Qi;Ruipeng Gao","doi":"10.1109/TSC.2025.3536306","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536306","url":null,"abstract":"To identify pattern deviations in large-scale industrial infrastructures, anomaly detection is crucial yet challenging. Previous research has not adequately addressed the characteristics and deployment considerations in these complex scenarios. In this paper, we present <italic>InoU, a scalable anomaly detection framework to process unlabeled multivariate time-series data. We incorporate a VAE filter to ease impacts from noisy components in training materials. We propose a scalable trio-attention U-Transformer to construct the typical representation of high-dimensional streams and produce pseudo labels that enable the later training process. The ultra perception and intra-/ inter-flow attention mechanisms are delicately designed to aggregate information from different flows with variable granularities while keeping a global view of the data. Its nested structure helps to maintain high efficiency even when the model is scaled down. We introduce a Siamese discriminator that projects target data into manifolds, and collates discrepancies at the embedding level. This paradigm elevates detection performance far beyond segment-wise error comparison in prior works. We apply contrastive and adversarial learning techniques to optimize manifold projection and detection performance when processing unseen samples. Extensive experiments on five large-scale datasets demonstrate the effectiveness of <italic>InoU with an average <italic>F1-Score improvement of 5.58%, significantly outperforming the state-of-the-art.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"1012-1025"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821665","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}

引用次数: 0

An Anonymous, Trust and Fairness Based Privacy Preserving Service Construction Framework in Mobile Crowdsourcing 移动众包中基于匿名、信任和公平的隐私保护服务构建框架

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536318

Xuechi Chen;Bochang Yang;Qian He;Shaobo Zhang;Tian Wang;Houbing Song;Anfeng Liu

{"title":"An Anonymous, Trust and Fairness Based Privacy Preserving Service Construction Framework in Mobile Crowdsourcing","authors":"Xuechi Chen;Bochang Yang;Qian He;Shaobo Zhang;Tian Wang;Houbing Song;Anfeng Liu","doi":"10.1109/TSC.2025.3536318","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536318","url":null,"abstract":"The proliferation of mobile smart devices with ever-improving sensing capacities means that Mobile Crowd Sensing (MCS) can economically provide a large-scale and flexible solution. However, existing MCSs face threats to privacy and fairness when recruiting workers due to information sensitivity, uncertainty about worker behavior, and budget constraints. To address the above issues, we propose an Anonymity, Trust, and Fairness in Privacy Protection (ATFPP) service construction framework to cost-effectively improve the quality of data at MCS. The main innovations are as follows: Firstly, on anonymity, in order to protect the privacy of workers, we propose a Privacy-Preserving (PP) framework based on an anonymous three-party platform, which realizes a full-process privacy-preserving scheme for workers. Second, on trust, we design more efficient Truth Discovery (TD) algorithm and adopt multifactor trust assessment method to identify more trustworthy workers. In addition, in terms of fairness, the fair distribution of compensation is realized through reasonable budget and approximate Shapley method. Finally, the proposed ATFPP scheme is theoretically proven to be correct and effective. Simulations based on real-world datasets illustrate that our ATFPP service construction scheme outperforms the state-of-the-art method in terms of both privacy protection and data quality.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"618-632"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824645","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}

引用次数: 0

DeFedGCN: Privacy-Preserving Decentralized Federated GCN for Recommender System DeFedGCN：用于推荐系统的隐私保护分散式联合 GCN

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536320

Qian Chen;Zilong Wang;Mengqing Yan;Haonan Yan;Xiaodong Lin;Jianying Zhou

{"title":"DeFedGCN: Privacy-Preserving Decentralized Federated GCN for Recommender System","authors":"Qian Chen;Zilong Wang;Mengqing Yan;Haonan Yan;Xiaodong Lin;Jianying Zhou","doi":"10.1109/TSC.2025.3536320","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536320","url":null,"abstract":"Federated recommender system (RS), a prevailing distributed paradigm, has been spawning significant interest in exploiting locally stored but tremendous data to predict items best aligned with clients. However, federated RS suffers severely from a single point of failure due to the dependency on the central server, leading to potential denial of service (DoS) attacks. To address this security weakness, in this paper, we propose a decentralized privacy-preserving federated graph convolutional network for RS, dubbed DeFedGCN. Specifically, DeFedGCN aggregates local updates by a decentralized consensus-reaching process and customizes local models for personalized recommendation, where the aggregation is enhanced by local differential privacy to resist model inversion attacks. More importantly, to promote the recommendation performance, DeFedGCN conducts a <italic>sub-graph expansion based on the private set interaction to explore high-order interactions among clients and items. Theoretical analysis confirms the effectiveness and privacy guarantee of DeFedGCN. Additionally, we conduct extensive experiments on four widespread real-world databases. The recommendation performance of DeFedGCN outperforms the state-of-the-art federated RS algorithms without security protection against DoS attacks by up to 7.4%.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"729-742"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824647","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}

引用次数: 0

Proof of Random Leader: A Fast and Manipulation-Resistant Proof-of-Authority Consensus Algorithm for Permissioned Blockchains Using Verifiable Random Function 随机领导者的证明：使用可验证随机函数的许可区块链的快速和抗操纵的权威证明共识算法

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536315

Md. Mainul Islam;Mpyana Mwamba Merlec;Hoh Peter IN

{"title":"Proof of Random Leader: A Fast and Manipulation-Resistant Proof-of-Authority Consensus Algorithm for Permissioned Blockchains Using Verifiable Random Function","authors":"Md. Mainul Islam;Mpyana Mwamba Merlec;Hoh Peter IN","doi":"10.1109/TSC.2025.3536315","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536315","url":null,"abstract":"Proof of Authority (PoA) is a widely adopted consensus algorithm for permissioned blockchain networks, where a group of trusted entities governs the network. PoA is known for achieving rapid consensus with minimal computational and energy requirements. However, existing PoA variants such as Aura and Clique suffer from low transaction throughput in high workload conditions and provide limited randomness in leader selection. They are also vulnerable to time and order manipulation attacks. To overcome these limitations, this paper introduces a novel PoA-based consensus algorithm called Proof of Random Leader (PoRL), which utilizes a verifiable random function to enhance transaction throughput, improve scalability, and ensure fair and unpredictable leader selection. The proposed PoRL algorithm was implemented in Python and evaluated using a network of six consensus nodes with varying computational capabilities. The performance of PoRL was assessed based on key metrics, including security, consistency, availability, fault tolerance, block time, and transaction throughput. Experimental results indicate that PoRL achieves lower consensus times and higher transaction throughput compared to Aura and Clique, making it a more efficient solution for permissioned blockchain networks. The findings of this study provide valuable insights for blockchain practitioners in selecting the most suitable PoA implementation based on their specific network requirements.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 3","pages":"1655-1668"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10858440","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264240","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}

引用次数: 0

Dynamically Scheduling Deadline-Constrained Interleaved Workflows on Heterogeneous Computing Systems 异构计算系统中时限约束交错工作流的动态调度

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536317

Kun Cai;Quanwang Wu;Mengchu Zhou;Chao Chen;Junhao Wen;Shouguang Wang

{"title":"Dynamically Scheduling Deadline-Constrained Interleaved Workflows on Heterogeneous Computing Systems","authors":"Kun Cai;Quanwang Wu;Mengchu Zhou;Chao Chen;Junhao Wen;Shouguang Wang","doi":"10.1109/TSC.2025.3536317","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536317","url":null,"abstract":"Heterogeneous computing systems are extensively utilized to execute a wide range of time-critical services, which encompass numerous interdependent tasks organized in the form of workflows. In practice, the dynamic arrival of workflows often interleaves with their execution, leading to resource contention among multiple workflows and potentially causing QoS (Quality of Service) degradation. However, compared to the extensive research on single workflow scheduling, interleaved workflow scheduling has received relatively less attention. Moreover, the challenge of effectively scheduling limited computing resources to promptly complete consecutively arriving workflows remains underexplored, despite its practical importance. To fill this gap, this work proposes a method called Urgency-based List Scheduling (ULS) for dynamically scheduling deadline-constrained interleaved workflows. In ULS, a novel task property called urgency is introduced to prioritize tasks from multiple workflows by capturing real-time execution information, and each newly arrived workflow is scheduled with the outstanding tasks of prior workflows based on a list-based strategy to make more informed decisions. Extensive evaluation experiments are performed and the findings illustrate that ULS can achieve a reduction of at least 68% in deadline miss rates and 77% in overall tardiness compared to existing methods.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"758-769"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143824130","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}

引用次数: 0

MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction 基于卷积的长期云工作负载预测的多尺度网络

IF 5.5 2区计算机科学

IEEE Transactions on Services Computing Pub Date : 2025-01-30 DOI: 10.1109/TSC.2025.3536313

Feiyu Zhao;Weiwei Lin;Shengsheng Lin;Shaomin Tang;Keqin Li

{"title":"MSCNet: Multi-Scale Network With Convolutions for Long-Term Cloud Workload Prediction","authors":"Feiyu Zhao;Weiwei Lin;Shengsheng Lin;Shaomin Tang;Keqin Li","doi":"10.1109/TSC.2025.3536313","DOIUrl":"https://doi.org/10.1109/TSC.2025.3536313","url":null,"abstract":"Accurate workload prediction is crucial for resource allocation and management in large-scale cloud data centers. While many approaches have been proposed, most existing methods are based on Recurrent Neural Networks (RNNs) or their variants, focusing on short-term cloud workload prediction without considering or identifying the long-term changes and different periodic patterns of cloud workloads. Due to variations in user demands or workload dynamics, cloud workloads that appear stable in the short term often exhibit distinct patterns in the long term. This can lead to a significant decline in prediction accuracy for existing methods when applied to long-term cloud workload forecasting. To address these challenges and overcome the limitations of current approaches, we propose a Multi-Scale Network with Convolutions (MSCNet) for accurate long-term cloud workload prediction. MSCNet employs multi-scale modeling of the original cloud workload to effectively extract multi-scale features and different periodic patterns, learning the long-term dependencies among the cloud workload. Our core component, the Multi-Scale Block, combines the Multi-Scale Patch Block, Transformer Encoder, and Multi-Scale Convolutions Block for comprehensive multi-scale learning. This enables MSCNet to adaptively learn both short-term and long-term features and patterns of cloud workloads, resulting in accurate long-term cloud workload predictions. Extensive experiments are conducted using real-world cloud workload data from Alibaba, Google, and Azure to validate the effectiveness of MSCNet. The experimental results demonstrate that MSCNet achieves accurate long-term cloud workload prediction with a computational complexity of <inline-formula><tex-math>$O(L^{2}d)$</tex-math></inline-formula>, outperforming existing state-of-the-art methods.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"18 2","pages":"969-982"},"PeriodicalIF":5.5,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821683","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}

引用次数: 0