Drone swarms are increasingly important in IoT applications such as agriculture, disaster response, and industrial inspection. However, effective service discovery remains challenging due to drones’ limited resources and the swarm’s dynamic topology. Existing solutions often suffer from congestion, single points of failure, and poor adaptability. To overcome these limitations, we propose a decentralized and dynamic service discovery framework tailored for drone swarms. Our approach models services using fine-grained sensor-level decomposition and leverages spatiotemporal information from drones to enable timely coordination. The core of the framework is a two-phase affinity propagation mechanism: a fully distributed clustering phase based on spatiotemporal leadership to provide a decentralized service registry, followed by a local adaptation phase for dynamic registry updates. To enhance reliability, a spatiotemporal-driven priority chain is used for service replication and failover. Extensive simulations and a case study in a wildfire suppression scenario across various swarm sizes show that our framework significantly outperforms centralized and existing clustering-based methods in efficiency, robustness with limited resources. This makes it a promising solution for reliable service discovery and flexible, fine-grained collaboration in drone swarms.

Deep neural network(DNN) services are now widely used in industrial defect detection applications. With the increasing number of pre-trained model services on MaaS platforms like HuggingFace and inside smart enterprises, fine-tuning or directly applying DNN services has become a new solution for building intelligent applications. However, selecting appropriate services for tasks with various industrial requirements is also challenging work. Existing DNN model recommendation systems typically categorize models based on a limited set of task types or leverage the training data similarities. However, they fail to reflect the DNN service's native transferability and dynamic ability in the specific industrial scenario (i.e., pragmatics). In this paper, we introduce DSR, a novel pragmatic-information-model-based DNN service recommendation approach, designed to retrieve the most suitable services by incorporating information across the scene of industrial tasks and the ability of services. Through graph convolutional networks, DSR embeds the pragmatic information model of services into unified vectors and applies a regression model for usefulness-oriented recommendation towards specific industrial tasks. Additionally, we established a benchmark dataset with hundreds of customized tasks derived from public datasets with open-source services, on which we evaluate DSR compared to existing methodologies, including ImageDataset2Vec, AutoMRM, and TransferGraph. Our results demonstrate DSR's superior performance in terms of accuracy, efficiency, and generality. We also conduct a case study on an industrial surface defect detection scenario, which illustrates the feasibility of the system.

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.

Tracking the process of remote task execution is critical to timely process analysis by collecting the evidence of correct execution or failure, which generates a process digital twin (DT) for remote supervision. Generally, it will encounter the challenge of constrained communication, high overhead, and high traceability demand, leading to the efficient remote process tracking issue. Existing approaches can address the issue by monitoring or simulating remote task execution. Nevertheless, they do not provide a cost-effective solution, especially when unexpected situation occurs. Thus, we proposed a new cloud-edge collaboration framework for process DT generation. It addresses the efficient remote process tracking issue with a real-virtual collaborative process tracking (RVCPT) approach. The approach contains three patterns of real-virtual collaboration for tracking the entire process of task execution with a coevolution pattern, identifying unexpected situations with a discrimination pattern, and generating a process DT with a real-virtual fusion pattern. This approach can minimize tracking overhead, and meanwhile maintains high traceability, which maximizes the overall cost-effectiveness. With prototype development, case study and experimental evaluation show the applicability and performance advantage of the new cloud-edge collaboration framework in remote supervision.

One of the main goals of the Internet of Things(IoT) systems is to achieve intelligent interaction of IoT devices. Event prediction is one of the approaches to achieve intelligent interaction. Event logic graph can effectively represent the relationship between events and be used for event prediction. However, in IoT systems, the data generated by IoT devices are usually incomplete and there are complex relationships between events, which in turn affect the accuracy of event prediction in the event logic graph. To address the above problems, this paper proposes a scenario-aware event prediction approach based on event logic graph in IoT systems. First, a flexible paradigm is designed for recognizing events and scenarios in IoT devices. Then, a scenario collaboration-based event context extraction method is proposed for extracting event contexts with similar scenario attributes in the event logic graph. Finally, a scenario-based event prediction method is designed to predict the events that will occur subsequently. In this paper, we verify that our approach can improve the accuracy of event prediction through the case of driving, which shows that our approach in this paper can be effectively applied in IoT systems.

Recent trends in the Web of Things (WoT) have led to data explosion. Data lake (DL), as a flexible on-demand heterogeneous data management architecture, has become a feasible solution in data management. Metadata modeling for DLs is the key basis for smart analysis and processing. However, the varieties in structures and semantics of industrial WoT data hinder metadata modeling and maintenance. Moreover, the lack of textual descriptions and the semantics hidden in value streams make it hard to automatically construct semantic metadata. The dynamic nature of WoT requires on-time evolution on metadata. To overcome these challenges, we propose an automated bottom-up metadata generation approach for DL of WoT applications. Applying a data-driven framework, raw data are notated as linked data and self-organizing map-based online clustering is applied to real timely extract data characteristics. To recognize entities, concepts and relations, semantics-based entity discovery approach from short texts is proposed according to the feature of WoT data. The numerical analysis is performed to find the hidden relations from raw values. Full-dimensional metadata with rich semantic knowledge are finally built. Experiments on a real-world dataset are conducted to verify the effectiveness of methods and a case study on an energy WoT system is provided to demonstrate the feasibility of the approach.

One of the primary goals of cyber-physical system is to deeply integrate cyberspace and the physical world to realize intelligent interaction of the system. Event prediction technique is a powerful means to fulfill this goal. Recently, a novel knowledge graph, the event graph, is widely studied in the field of event analysis due to its excellent ability in event relationship modeling. Therefore, this paper proposes constructing the event graph to model the sequential event evolution in the physical world for event prediction. To this end, the sequential event graph construction method and related event prediction mechanism for CPSs are proposed. First, a flexible and universal paradigm is designed to assist in extracting event instances from the data generated by physical devices. Then, an automatic event graph construction method based on frequent episode mining is proposed. Finally, the related prediction mechanism is designed, including the identification of contextual information a nd the prediction of subsequent events. A case study on car usage illustrates the feasibility of our approach. The flexibility and support for complexity are demonstrated by a comparative discussion.

Coordinating of energy networks to form a city-level multidimensional integrated energy system becomes a new trend in Energy Internet (EI). The collaborating in the information layer is a core issue to achieve smart integration. However, the heterogeneity of multiagent data, the volatility of components, and the real-time analysis requirement in EI bring significant challenges. To solve these problems, in this article we propose a stream processing framework based on linked data for information collaboration among multiple energy networks. The framework provides a universal data representation based on linked data and semantic relation discovery approach to model and semantically fuse heterogeneous data. Semantics-based information transmission contracts and channels are automatically generated to adapt to structural changes in EI. A multimodel-based dynamic adjusting stream processing is implemented using data semantics. A real-world case study is implemented to demonstrate the adaptability, feasibility, and flexibility of the proposed framework.