IEEE Transactions on Services Computing最新文献

{"title":"Integrating Multi-Agent Reinforcement Learning and XGBoost for Efficient Large-Scale Dynamic Workflow Scheduling in Cloud Environments","authors":"Fan Ding;Shuzhan Zhang;Yaqian Yuan","doi":"10.1109/TSC.2026.3707320","DOIUrl":"10.1109/TSC.2026.3707320","url":null,"abstract":"Workflow scheduling in heterogeneous cloud environments must operate under dynamic and heterogeneous conditions. Heuristic algorithms cannot adapt online to changing conditions, while single-agent deep reinforcement learning (DRL) faces issues such as exponential growth in the action space, excessive training time, and limited interpretability. This paper proposes MAR-XGB, a hybrid scheduling framework that combines multi-agent reinforcement learning (MARL) with an XGBoost predictor. The tree ensemble estimates task runtime and execution cost, from which an urgency score is derived. Each agent uses lightweight Monte Carlo Tree Search (MCTS) to select VM locations and make online placement decisions over the Top-<italic>k</i> tasks, ensuring real-time adaptability while reducing action-space complexity and improving prediction transparency and decision auditability. Experiments on representative WfCommons scientific workflows and controlled high-load DAG scenarios show that our approach outperforms traditional and state-of-the-art schedulers in terms of makespan, resource utilization, and cost efficiency. As the complexity and scale of workflows increase, our approach demonstrates improved scalability, indicating its potential to handle dynamic cloud workloads with fluctuating demand.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2829-2842"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148342280","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":"MS$^{2}$2-Diff: Multi-View Guided Diffusion With Active Retrieval for Service Generative Recommendation","authors":"Zhen Chen;Heng Wang;Jinyu Chen;Mengmeng Sun;Dianlong You;Yueshen Xu","doi":"10.1109/TSC.2026.3702081","DOIUrl":"10.1109/TSC.2026.3702081","url":null,"abstract":"Efficient discovery and composition of services from large-scale cloud API repositories are fundamental to Mashup development and the rapid evolution of service-oriented software. However, extreme interaction sparsity severely limits existing recommendation methods, hindering their ability to infer unobserved relationships and capture complex service dependencies. Most prior approaches rely on deterministic point estimation in latent spaces, which leads to several critical issues under sparse supervision: difficulty in modeling preference uncertainty, high susceptibility to overfitting, and static and passive incorporation of multi-source auxiliary information. To address these challenges, we propose MS<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-Diff, a conditional diffusion-based generative framework for service recommendation that reformulates recommendation as a conditional probabilistic denoising process. MS<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-Diff has a three-fold main idea: 1) it characterizes two levels and four types of priors that drive Mashup development, including structural homophily and collaborative reachability at the structural level, as well as functional alignment and intent alignment at the semantic level; 2) it introduces a guidance-driven active retrieval mechanism via inverted attention within the denoising process, which actively retrieves and reconstructs latent relational patterns from noisy representations under the control of multi-view priors; and 3) it adopts a step-aware adaptive fusion strategy that dynamically coordinates structural and semantic priors across different denoising stages, enabling complementary and collaborative effects throughout the generation process. Extensive experiments on two real-world benchmark datasets demonstrate that MS<inline-formula><tex-math>$^{2}$</tex-math></inline-formula>-Diff achieves competitive and overall superior performance across multiple evaluation metrics, while improving robustness in sparse and cold-start scenarios.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2943-2955"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288511","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":"LogMUSE: Log Anomaly Detection via Multi-Scale Semantic Representation","authors":"Mengyao Liu;Tianbo Wang;Yuan Zhao;Chunhe Xia;Yingming Zeng;Yuan Tao","doi":"10.1109/TSC.2026.3700403","DOIUrl":"10.1109/TSC.2026.3700403","url":null,"abstract":"Logs serve as an effective data source for recording and judging system states and abnormal events in complex systems. Current deep learning-based methods have proven effective in detecting anomalies in these system logs. However, existing anomaly detection methods, which predominantly rely on template-based and global window-based approaches, still face challenges in terms of flexibility and practicality. Template-based methods, while widely adopted for their simplicity and efficiency, overlook parameter information and fail to capture the true execution semantics. And global window-based methods, despite their effectiveness in modeling global dependencies, cannot simultaneously capture both global and local dependencies, leading to the obscuration of important local features. To address these issues, we propose a <bold>Log</b> anomaly detection method based on <bold>MU</b>lti-scale <bold>SE</b>mantic representation, <bold>LogMUSE</b>. Specifically, LogMUSE obtains template and parameter information through log parsing, employs a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model for template semantic embedding, and enhances log entry representations via cross-attention mechanisms to effectively capture different parameter features under the same template. Additionally, we design the multi-scale Transformer model to capture global and local anomaly patterns, which enable fixed-length log sequences to focus on features at different scales. Extensive experiments on real-world benchmark datasets, including BGL, Thunderbird and Spirit, show that LogMUSE outperforms existing methods in log anomaly detection, achieving F1-scores of 98.62%, 94.32%, and 99.20% respectively. These results surpass the performance of current state-of-the-art methods and demonstrate the strong generalization across different system scenarios.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2903-2916"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288546","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":"Collaborative Service of On-Device Unimodal Model and Cloud-Based Multimodal Model for Mobile Livestreaming Content Understanding","authors":"Chaoyue Niu;Yufei Zhu;Yutong Dai;Yikai Yan;Zhijie Cao;Hao Jiang;Chengfei Lv;Shaojie Tang;Fan Wu;Guihai Chen","doi":"10.1109/TSC.2026.3697495","DOIUrl":"10.1109/TSC.2026.3697495","url":null,"abstract":"To guide consumers to mobile livestreams that involve their interested products, it is necessary to have a good understanding of livestreaming contents, and the key task is to accurately recognize the products being promoted by streamers. The mainstream cloud-based service framework is challenged by the high concurrency of requests, the high overhead of multimodal recognition, and the requirement of low latency. To break these bottlenecks, we propose a new device-cloud collaborative service framework, where each streamer’s mobile device holds unimodal model that can process most of video frames and also uploads the extracted unimodal features to facilitate the cloud-side multimodal recognition of the remaining few frames. On-device unimodal model is further incrementally trained over the samples constructed by leveraging the streamers’ manual labeling behaviors, leading to personalized version that can adapt to the heterogeneous and dynamic livestreaming contents of different streamers. Nevertheless, the device-side personalized unimodal features are misaligned in feature space and cannot be directly fused into the cloud-side multimodal model. We thus design a pluggable prompt generation module to transform the personalized unimodal features into prompt embeddings and prepend them to the original inputs of the multimodal backbone network, instructing feature fusion in a streamer-specific manner. We extensively evaluate on the public Fashion-Gen dataset and an industrial dataset collected from Taobao Live. We also perform online testing and practical overhead testing in Taobao Live. Evaluation results reveal the effectiveness and efficiency of our design as well as the consistent advantage over existing baselines.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2746-2759"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288581","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":"Skewness-Aware Stream Partitioning: A Key Splitting Suppression Method for Distributed Stream Processing","authors":"Dawei Sun;Weilong Lv;Shang Gao;Keqin Li;Rajkumar Buyya","doi":"10.1109/TSC.2026.3707515","DOIUrl":"10.1109/TSC.2026.3707515","url":null,"abstract":"Partitioning algorithms are crucial in distributed stream computing, as they directly affect load balancing across downstream task instances, cluster performance utilization, and data stream processing efficiency. However, existing algorithms suffer from key limitations: they fail to effectively balance load imbalance and key-splitting overhead as excessive splitting increases aggregation costs and memory usage, while insufficient splitting fails to reduce skew. In addition, they cannot timely identify newly emerging high-frequency keys, because historical frequency records dominate detection, which worsens load imbalance over time. To address these limitations, we propose Sa-Stream, a skewness-aware partitioning framework that rapidly captures changes in stream skewness and dynamically adjusts partitioning decisions, thereby balancing load imbalance and key-splitting overhead under evolving stream distributions. (1) A key frequency decay mechanism progressively reduces the influence of historical frequency statistics to improve the prediction of evolving key frequencies. (2) An adaptive threshold modulation method dynamically adjusts the hot-key threshold based on the current key frequency distribution, balancing load imbalance and aggregation costs. (3) A multi-tiered key segregation mechanism classifies keys into cold, warm, and hot categories: cold keys use deterministic hash routing to minimize aggregation costs, hot keys use degree-adjusted key splitting to reduce load imbalance, and warm keys use one-time key splitting to bridge the two extremes. Experiments conducted on Apache Storm demonstrate that Sa-Stream outperforms existing stream partitioning approaches, increasing throughput by up to 16% and reducing latency by up to 50%. Additionally, key splitting is reduced by up to 18%, and load imbalance is decreased by up to 98%.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"3059-3071"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148342276","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":"Matching and Exchange-Based Utility Maximization for Fog Computing-Enabled Smart Healthcare","authors":"Moirangthem Biken Singh;Ajay Pratap;Mihir Kumar Badkur;Dhruv Mishra","doi":"10.1109/TSC.2026.3708126","DOIUrl":"10.1109/TSC.2026.3708126","url":null,"abstract":"The rapid growth of Wireless Body Area Network (WBAN) and the increasing demand for real-time healthcare services have emerged fog computing as a promising paradigm to reduce latency and energy consumption in health monitoring. However, the growing need for computation-intensive services increases computational load on Fog Servers (FSs) and WBANs, leading to high latency and energy costs. Nevertheless, existing approaches often optimize either latency or energy while neglecting Healthcare Service Providers’ (HSPs) profit and the diverse computational needs of patients. Thus, this paper presents a fog computing-enabled WBAN framework that minimizes patients’ latency and energy costs while maximizing HSPs’ profit by formulating utility maximization as an NP-hard problem, where utility is a weighted combination of latency, energy costs, and profit, while prioritizing critical patients. To solve this, we design a matching and exchange-based suboptimal algorithm with polynomial-time complexity <inline-formula><tex-math>$O(PFlog PF, P^{2})$</tex-math></inline-formula>, where <inline-formula><tex-math>$P$</tex-math></inline-formula> and <inline-formula><tex-math>$F$</tex-math></inline-formula> denote the number of patients and FSs, respectively, leveraging the concept of preferences. Furthermore, we introduce a dynamic pricing scheme that allows patients to pay in proportion to their computational needs. Extensive simulations and analyses using real-world health data demonstrate that the proposed approach achieves an average utility of 99.01% of the optimal solution.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2917-2928"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148371843","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":"OptiFog: A Framework for Acquiring State Information and Predicting Resource Availability for Task Offloading in Cooperative Fog-Networks","authors":"Mehbub Alam;Nurzaman Ahmed;Shyamal Ghosh;Rakesh Matam;Ferdous Ahmed Barbhuiya","doi":"10.1109/TSC.2024.3414371","DOIUrl":"10.1109/TSC.2024.3414371","url":null,"abstract":"The primary objective of fog computing is to minimize the reliance of IoT devices on the cloud by leveraging the resources of fog network. Typically, IoT devices offload computation tasks to fog to meet different task requirements such as latency in task execution, computation costs, etc. So, selecting such a fog node that meets task requirements is a crucial challenge. To choose an optimal fog node, access to each node's resource availability information is essential. Existing approaches often assume state availability or depend on a subset of state information to design mechanisms tailored to different task requirements. In this paper, <italic>OptiFog:</i> a cluster-based fog computing architecture for acquiring the state information followed by optimal fog node selection and task offloading mechanism is proposed. Additionally, a continuous time Markov chain based stochastic model for predicting the resource availability on fog nodes is proposed. This model prevents the need to frequently synchronize the resource availability status of fog nodes, and allows to maintain an updated state information. Extensive simulation results show that <italic>OptiFog</i> lowers task execution latency considerably, and schedules almost all the tasks at the fog layer compared to the existing state-of-the-art.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2622-2633"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141944134","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":"HyDuo: A Low-Latency and Cost-Efficient Storage System for Stateful Serverless Applications","authors":"Zhuo Huang;Yijie Liu;Yucheng Xu;Hao Fan;Kun Wang;Hanxiang Huang;Song Wu","doi":"10.1109/TSC.2026.3704762","DOIUrl":"10.1109/TSC.2026.3704762","url":null,"abstract":"More applications are adopting serverless architectures for elasticity and fine-grained billing. However, stateful workloads suffer performance degradation due to frequent cross-stage data exchanges that rely on expensive remote storage access. Existing work rarely considers both data access patterns and heterogeneous storage media, limiting its ability to reduce this overhead. Modern storage spans multiple tiers, from fast but expensive DRAM and NVMe to slower, cheaper SSDs and HDDs. We also observe that stateful serverless workloads exhibit clear patterns, including read-heavy behavior, high access intensity, periodicity, and strong inter-stage correlation. We model intermediate data placement as a generalized assignment problem by capturing both storage heterogeneity and access patterns. Based on this model, we design a dynamic migration algorithm that promotes and demotes data across tiers to reduce latency while controlling cost. Experiments show that our approach achieves latency close to an in-memory SOTA system for serverless analytics workloads, while reducing storage cost by about 95%.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2815-2828"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11569366","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288504","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":"Reverse-Offloading Incentive Mechanism With Long-Term Optimization in Social-Aware Cloud-Edge Systems","authors":"Gailun Zeng;Jianxiong Guo;Xingjian Ding;Zhiqing Tang;Tian Wang;Weijia Jia","doi":"10.1109/TSC.2026.3704824","DOIUrl":"10.1109/TSC.2026.3704824","url":null,"abstract":"Reverse-offloading services to edges in cloud-edge systems play a pivotal role since they can effectively facilitate the resource utilization of edges, such as crowdsensing, where tasks are offloaded to workers via incentives. Additionally, edges are objectively closer to mobile end users, which aligns more closely with the latency-sensitive task requirements, such as real-time inference tasks. However, the natural complexity caused by social relationships between edges is non-trivial for modeling, as these relationships provide potential extra benefits, such as data sharing between edges. The real-time interactions between the cloud and edges bring the system dynamics, which is also challenging to meet long-term constraints, such as total energy or payment costs. To end this, we revisit these challenges and propose a novel multi-service and multi-edge reverse-offloading incentive mechanism, where the cloud utilizes reward strategies to recruit social-aware edges, and the edges employ appropriate task strategies, including the choice of cooperation with social-connected edges, to maximize their benefits. The natural bilateral framework is modeled as a two-stage Stackelberg game (SG), where both sides can selfishly optimize their strategies. To tackle the dynamics of the system, we design a coupled Lyapunov optimization approach for the bilateral framework, which effectively decomposes the long-term optimizations for both sides into online optimizations. Theoretical analysis proves the existence and uniqueness of the Stackelberg equilibrium, along with error gap guarantees for the coupled Lyapunov-based approach. An algorithm is designed to get approximate optimal solutions. Extensive simulations using both synthetic and real-world datasets validate the outperformance of our method and investigate critical factors, such as the impact of social relationships.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2998-3014"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288505","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":"LEABS: A Latency- and Resource-Aware Bi-Directional Service Scheduling Framework for Relay Chains in the Internet of Vehicles","authors":"Yawen Zhao;Nan Ding;Chengyi Shuai;Li Xu","doi":"10.1109/TSC.2026.3696713","DOIUrl":"10.1109/TSC.2026.3696713","url":null,"abstract":"Multiple stakeholders such as automakers, service providers, and regulators tend to maintain their own blockchain systems in the Internet of Vehicles (IoV). This fragmentation leads to data silos and hinders service interoperability across domains. Relay Chains are emerging as a cross-chain service-governance layer, enabling coordination among heterogeneous blockchains. However, scheduling multi-input multi-output (MIMO) transactions introduces new challenges, including complex transaction dependencies, heterogeneous node capabilities, and strict latency constraints. To address these issues, this paper proposes LEABS, a bi-directional service-aware scheduling framework that simultaneously considers user-side service quality and relay-chain-side resource governance. LEABS formulates cross-chain transaction scheduling as a service-delivery optimization problem, modeled by a Mixed-Integer Nonlinear Programming (MINLP) formulation and stabilized through Lyapunov-based queue governance. A Deep Reinforcement Learning (DRL) method is further introduced to learn adaptive policies under dynamic workloads and heterogeneous network conditions. Extensive experiments demonstrate that LEABS achieves a superior balance among confirmation latency and load fairness, highlighting its effectiveness as a Quality-of-Service(QoS)-driven cross-chain service-governance mechanism for future IoV ecosystems.","PeriodicalId":13255,"journal":{"name":"IEEE Transactions on Services Computing","volume":"19 4","pages":"2857-2875"},"PeriodicalIF":6.2,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148288573","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}