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.
