In a Mobile Edge Computing (MEC) environment, as massive amounts of data are generated by user-end devices, the need to alleviate network backhaul pressure by offloading tasks to edge base stations closer to users is becoming increasingly critical. However, the dynamic nature of user mobility and varying interests within and across socially-connected user communities pose significant challenges in designing efficient pre-allocation strategies in MEC. In reality, MEC users can be socially connected and thus share common interests for task types. Consequently, we believe that the group interests of socially-connected MEC users can be exploited and propose a novel collaborative and group interest-informed resource pre-allocation, i.e., DeCoPre. It integrates the decentralized architecture that naturally divides the region into smaller zones for mitigating the impacts of the Single Point of Failure, a self-attention model for capturing multi-user interests and mobility patterns, a collaborative filtering approach for refining prediction results, and a grouping-based technique for resource pre-allocation algorithm. Numerical results upon real-world datasets clearly demonstrate that DeCoPre beats its peers across multiple performance metrics.
Recently, Vehicular edge computing (VEC) has been widely acknowledged as a promising solution for provisioning on-demand computational services to mobile users. However, because edge network resources are usually placed and interconnected through unreliable communications in a highly dynamic environment, it remains a great challenge to achieve high fault tolerance when faults and errors are unavoidable at different levels of VEC. In this paper, we propose a fault-tolerant scheduling approach with structured applications in hybrid three-tier VEC environments. The proposed approach synthesizes PB(Primary Backup) fault-tolerance model and DDQN algorithm with a Lyapunov optimization for yielding fault tolerance schedules. The simulation results show that our proposed approach outperforms traditional methods in multiple performance metrics.
As vehicular networks shoulder an ever-expanding workload, smart task offloading has become essential for enhancing system throughput and maximizing resource efficiency. Nonetheless, the fluid topology, rapid node mobility, and varied user requirements make devising robust offloading schemes a persistent challenge. In this study, we proposes a task offloading method that synthesizes a reinforcement learning algorithm and an evolutionary one i.e., PPO-Enhanced NSGA-III Offloading Algorithm (PENOA). This method leverages a PPO reinforcement learning algorithm for dynamically adjusting offloading schedules produced by an NSGA-III algorithm. PENOA is capable of learning to generate near Pareto-optimal solution sets by collaboratively tuning, computational resource allocation and task schedules strategies between vehicles and servers. Experimental studies based on real-world Taxi Trajectory and Telecom Base Station datasets demonstrate that PENOA outperforms benchmark algorithms across multiple performance metrics.
With the rapid development of Internet of Things (IoT) technologies, the massive generation of data has posed significant challenges to traditional cloud computing models, particularly in terms of high latency and energy consumption. As a result, edge computing has emerged as a promising solution. However, in remote or disaster-prone areas, the lack of terrestrial communication infrastructure limits the deployment of edge computing. Satellite communication networks, with their wide coverage and independence from geographical constraints, offer an effective solution to this issue. In this paper, we propose a “UAV-LEO” system framework, where UAVs and Low Earth Orbit (LEO) satellites are utilized as edge computing nodes. We employ an intelligent optimization algorithm to optimize task offloading decisions and incorporate an adaptive checkpointing mechanism to enhance system fault tolerance. Experimental results demonstrate that the proposed method effectively reduces task completion time and energy consumption while significantly improving system reliability.
Traditional Service-Oriented Architecture (SOA) faces growing limitations in flexibility, adaptability, and intelligence, struggling to meet modern enterprises’ evolving demands. This paper proposes the Internet of Intelligent Services (IIS) and the Agent Software Factory (ASF) as comprehensive solutions. IIS transforms conventional services into intelligent, autonomous, and dynamically collaborative entities, guided by principles of decentralized autonomy, dynamic adaptation, and semantic modeling with feedback-driven learning. Built upon IIS, ASF enables end-to-end automation of the intelligent agent lifecycle through specialized assistant agents. Furthermore, this paper presents the INNOVATORS framework, a structured analysis of ten transformative SaaS trends that characterize this new era. Drawing upon industry observations and technological foresight, the framework encompasses: I – Immersive Experience as a Service (IEaaS), N – Niche Market Focus, N – Normal Business Enabler Tools, O – Office Platforms for Collaboration and Business, V – Vertical Industry Solutions, A – AI Plugins Everywhere, T – Transformation Software, O – Orchestrated SaaS Development Platforms, R – Recognition of Data Insights, and S – Service-to-Service (S2S) Integration. To support S2S collaboration among heterogeneous agents, the Agent Service Bus (ASB) is proposed, featuring a layered architecture for standardized access, intention-driven scheduling, and dynamic orchestration. Together, these innovations provide a foundational framework for intelligent, adaptive, and service-centric enterprise software systems.
Mobile Edge Computing is an emerging paradigm that offloads tasks to edge servers located near end users, effectively reducing backhaul network congestion and enhancing Quality of Service. However, due to the limited caching capacity and computational resources of edge servers, MEC systems continue to face significant challenges in service caching and task offloading. Existing approaches fail to simultaneously ensure user QoS and maintain computational reliability under high failure rates. To address these challenges in failure-prone MEC environments, we propose a fault-tolerant approach for service caching and task offloading. Our method incorporates a primary-backup replication mechanism to enhance fault tolerance and employs a Deep Q-Network-based framework to optimize service caching distribution. Experimental results demonstrate that the proposed method outperforms benchmarks.
To meet the rapidly growing demands for services and applications in Mobile Edge Computing (MEC) environments, there is an increasing need to alleviate backhaul network pressure and enhance user experience. However, the dynamic nature of user mobility, fluctuating content popularity, and varying interest similarities within and across user communities pose significant challenges in designing efficient caching strategies. To address these challenges, this paper proposes a user interest-informed edge caching method by using a dynamic User-interest-based Clustring Caching (UCC) model. The proposed framework includes an improved density-based spatial clustering algorithm which employs the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and a caching decision algorithm which adopts a federated deep reinforcement learning model for yielding high-quality and dynamic caching schedules. Experiments based on real-world urban taxi datasets and user interest datasets clearly demonstrates that the proposed method outperforms several existing algorithms across multiple performance metrics.
In microservice management, engineers analyze numerous heterogeneous performance metrics, including latency, CPU, and memory usage, to resolve incidents swiftly. Consequently, a metric-based root cause analysis (RCA) must demonstrate interpretability, accuracy, and efficiency. However, recent causal-discovery-based RCAs have been identified as having challenges in terms of accuracy and efficiency. This paper highlights the issues arising from the heterogeneity of metrics and attempts to improve causal-aware RCA while leveraging the metadata associated with the metrics. We adopt the validated concept from existing RCA methods that metrics showing greater deviations during a failure are likely the root causes. The proposed method quantifies metric deviations comparable among heterogeneous metrics and searches for propagation trees that best explain the observed deviations. Experimental results on microservice-based system benchmark datasets demonstrate that the proposed method outperforms existing RCA methods in terms of accuracy and efficiency.
With the widespread adoption of microservice architectures, system complexity has increased significantly, making fault root cause localization a critical issue in system operations. Under resource constraints or load pressure, the monitoring metrics that reflect system status often exhibit incompleteness, negatively impacting operational accuracy and system stability. To address this challenge, we propose ReconRCA, which consists of an offline reconstruction stage and an online localization stage. During reconstruction, ReconRCA leverages historical data, along with spatio-temporal models and attention mechanisms, to reconstruct missing metrics. In the online stage, it captures both intra and inter-metric correlations of microservices to achieve precise root cause localization. Experiments show that ReconRCA outperforms existing methods with both incomplete and complete data, achieving average top-1 hit rates at 33.28% and 39.74%, respectively.
Smart factories and homes represent resourceasymmetric environments where gateways offer abundant resources, while user and edge devices remain constrained. Existing authentication and key agreement (AKA) protocols for the settings typically overlook threats from malicious gateways and cannot reconcile dynamic anonymity with minimal overhead. To address these challenges, we propose the Secure dynamic Anonymity updates and Gateway-side secure Authentication (SAGA), a lightweight AKA protocol based on three synergistic layers: dual-threshold Shamir's Secret Sharing (SSS) to distribute trust across multiple gateways, a Merkle Tree mechanism with one-time password algorithm based on hash chains (HOTP) for efficient gateway verification, and an active shared key-refresh method to maintain dynamic anonymity and session keys. Formal security proofs using Burrows-Abadi-Needham (BAN) logic and ProVerif validate SAGA's rigorous security, while experimental results show it achieves stronger security properties with lower computational and communication costs than existing schemes.
Object-centric Predictive Monitoring has recently gained attention due to advances in machine learning and rise of Object-Centric Event Logs (OCELs), which comprehensively capture object interactions. This paper presents a modular framework supporting customizable pipelines for predictive analysis across diverse event logs. The framework comprises three core components: Preprocessing (preserving object relationships via graph structures), Graph Embedding Model, and Prediction Model. We experimentally evaluated various combinations of embeddings and predictors on three public OCELs. Results show that no single configuration consistently dominates. However, GAT and Graph Transformer models perform best for predicting remaining time and the number of events. Performance improves with larger embedding and subgraphs, particularly for neuralbased models. Finally, GAT delivered the most stable and highperforming results across all event logs in generalization tests.
Knowledge Graphs (KGs) have emerged as a critical technique to enhance recommendation performance by modeling complex relationships and semantics within heterogeneous networks. However, it faces issues such as longtail distribution, structural redundancy caused by semantically similar relations, and susceptibility to noise interference, which severely limit the effectiveness of graph-based recommendations. Aiming to tackle the challenges, we propose Relation-aware Contrastive Learning (RACL), a brand-new framework for knowledge-enhanced recommendations. Specifically, relationdriven subgraph construction is employed to cluster the KG into subgraphs with potential semantic associations, addressing the issue of structural redundancy while alleviating the long-tail effect through the integration of relationship types. Besides, we introduce a relation-aware aggregation module to inject relation-specific semantic features from KG into neighborhood propagation, effectively encoding multi-type relational contexts into user and item embeddings. Furthermore, a graph learner is established, which significantly improves the model's robustness in contexts with sparse and noisy data by integrating selfsupervised signals into model training. Comprehensive experiments on two publicly accessible datasets verify that our RACL surpasses the state-of-the-arts in terms of recommendation efficacy.
Chatbots have advanced from basic conversational agents to versatile tools by integrating external services. However, traditional chatbots are constrained by predefined service boundaries, limiting their ability to handle complex tasks with unintegrated services. While most research focuses on improving service discovery and invocation through data-intensive pretraining, only 13.29% of services are well-documented, hindering practical deployment. This paper proposes a self-improving workflow for chatbots, using a “wide in, strict out” self-supervised learning approach to acquire domain knowledge efficiently and generate high-quality service documents. Compatible with existing methods, it eliminates the need for dataset collection or pre-training. Experiments demonstrate that our workflow significantly improves the pass and success rate of chatbots in utilizing unintegrated services, offering a powerful solution for real-world applications where service integration is limited.
Deploying convolutional neural networks (CNNs) on resource-constrained Internet of Things (IoT) devices facilitates convenient intelligent services, which has attracted extensive attention. However, the dynamic resource availability poses significant challenges for resource-intensive CNNs. Recent advancements in efficient CNNs have two limitations: i) elevated resource consumption due to extensive datasets and post-training calibration; ii) lacking flexibility facing dynamic resources due to static model structure. To this end, we propose a RESourCe-Aware oncE-for-alL (ReScale) framework for efficient CNN deployment on IoT devices. Specifically, we propose a hierarchical filter generation mechanism to generate different amounts of filters dynamically, mapping a few learnable filters to abundant filters for discriminative feature extraction. Besides, we set a coefficient. to modulate the filter generation according to the available resources of IoT devices. With this framework, we only need to train CNN models once to handle different resource availability of IoT devices. Experimental results show that our proposed ReScale framework can generate more efficient models with lower resource consumption while maintaining high accuracy. Through the coefficient., our method enables continuous model generation, ensuring robust adaptation to dynamic resource constraints.
The rapid expansion of Internet of Things (IoT) devices has led to an explosion of event data, posing significant challenges for traditional process model discovery techniques in terms of scalability and discovery accuracy. These techniques rely on centralized storage and processing, which are hindered by data transfer limitations, storage capacity, and computational overhead in distributed IoT environments. Edge-based model discovery techniques offer a promising solution for analyzing large-scale IoT data. However, existing techniques suffer from low efficiency and an inability to handle complex process structures. To address these challenges, we propose EdgeIM, an efficient edge-based process model discovery technique that enhances efficiency and model accuracy. EdgeIM operates in three key stages: preprocessing and feature-preserving sampling to eliminate redundant data, local processing at edge nodes to extract key structural features, and global feature aggregation at a central node for model discovery. EdgeIM has been implemented on the open-source process mining platform PM4Py, and experimental results on nine public event logs demonstrate that, compared to existing edge-based model discovery techniques, EdgeIM significantly improves discovery efficiency while maintaining high model quality.
Predictive Process Monitoring (PPM) is a critical technology for analyzing log data to forecast future events in ongoing process traces, enabling early warnings of business risks and timely interventions. Traditional PPM methods primarily focus on predicting a subsequent activity based solely on activity sequences. However, such approaches often neglect the suffix variability reflected by branching behavior, where identical prefixes may lead to multiple potential outcomes. To address this limitation, we propose a two-stage PPM model based on enabled state filtering for coarse-to-fine activity prediction. In the first stage, the model identifies all enabled activities based on the activity prefix, enhancing flexibility to handle variable suffixes. In the second stage, the model further integrates multi-attribute trace information along with the candidate activity set, employing a context-aware attention mechanism tailored to these candidates for fine-grained prediction. The constraints of the first stage allow the second stage to focus on the possible activities and relevant attributes, effectively reducing the search space and mitigating overfitting. Experimental results on four real-world datasets show that our approach outperforms traditional methods, particularly with variable suffixes. Ablation studies further highlight the critical role of the enabled state filtering strategy in reducing overfitting when modeling multi-attribute information.
Edge service deployment has attracted significant attention in recent years, aiming to optimize service placement on edge servers while satisfying diverse requirements. However, existing approaches often overlook the influence of geographical contexts on service demands, where user needs vary significantly across regions with distinct characteristics. They also fail to account for differences between direct responses and multi-hop forwarding in edge network topology, leading to unsatisfactory edge service deployment strategies. To this end, we formulate the Points of Interest-Based Edge Service Deployment (POIESD) problem with topology-aware optimization, integrating POI attributes and spatial distributions while incorporating edge network topology to enhance service placement. By proving the NP-hardness of POI-ESD problem, we propose a novel graph-encoded genetic algorithm, MTGA, to efficiently generate highquality deployment strategies. It ensures strategic placement of edge services in regions that best match user demands, improving the service utilization and satisfiability for edge users. Extensive experiments on a real-world dataset combining Shanghai Telecom and Baidu Maps POI data demonstrate that MTGA significantly outperforms existing competing approaches, achieving superior performance of edge service deployment.
Autoregressive transformer models have achieved state-of-the-art performance in advanced services such as text generation and machine translation. Given the significant computational bottlenecks of model inference, layer-wise skipping has emerged as a promising method to accelerate inference by bypassing redundant layers. However, existing methods face challenges, including sub-optimal performance resulting from the premature skipping of critical layers and an unbalanced focus on either multi-head attention or feed-forward sub-blocks, ultimately leading to global performance degradation. In light of the above challenges, we propose a Dynamic Inference Method, named DIM, for autoregressive transformer models. DIM dy-namically selects sub-blocks from both multi-head attention and feed-forward networks through the importance score alignment, ensuring a balanced selection that optimizes both efficiency and model performance. To further mitigate the potential performance loss of skipped sub-blocks, a lightweight adjustment is developed to approximate the computations of skipped sub-blocks. Finally, extensive experiments using several benchmarks validate that DIM outperforms existing inference methods.
We propose a new workflow task execution time prediction approach, DAG-FGL, by integrating Flash attention mechanism with a GraphLSTM model. It addresses the challenge of low task execution time prediction accuracy in the presence of complex dependencies among workflow subtasks. The GraphLSTM model captures and conveys subtask dependencies through the adjacency matrix of sub task relationships modeled as a directed acyclic graph (DAG). The Flash attention mechanism enhances the model by incorporating customized positional encoding of subtask priority. The encoding ensures that the model accurately reflects each subtask's importance and relative order when calculating attention weight. Therefore, DAG- FG L can more accurately predict task execution time in the context of complex dependencies. Experimental results show that DAG-FGL outperforms the best-performing baseline model. It achieves 7.82 % to 44.52 % improvements in prediction accuracies over the best-performing baselines across three cloud workflow datasets of varying lengths.
Unmanned aerial vehicle (UAV) swarms are useful for mobile and collaborative applications due to their flexibility, scalability, and reliability. However, managing their communication and collaboration in complex environments is challenging. Service mesh has demonstrated excellent performance in managing communication between microservices in cloudnative environments. However, its centralized and static network structure design hinders its adaptability to dynamic topologies, increases vulnerability to single points of failure, and exacerbates resource constraints when applied to UAV swarms. To address these challenges, we propose UAV-Mesh, a graph-based decentralized service mesh framework for UAV swarms. It models the swarm as a dynamic graph for enabling the data plane to adapt to changing topologies, mitigates the risk of single points of failure through a decentralized control plane, and addresses resource constraints by optimizing consensus mechanism and algorithm. UAV Mesh offers a decentralized perspective for the application of service mesh in UAV swarms. Through experiments and analysis involving varying numbers of UAVs in a complex scenario, we demonstrate the effectiveness and efficiency of UAV Mesh in managing and controlling UAV services.
