With the increase in environmental pressure and rapid development of renewable energy technologies, an integrated energy system has been recognized as an effective approach to accommodate large-scale renewables and achieve environmental sustainability. While an integrated energy system significantly improves energy efficiency, the interaction between different energy systems may also bring multiple operational risks to its reliability, which necessitates an effective reliability assessment technique. In this paper, we proposed a multi-level fuzzy evaluation model based on combined empowerment for the reliability evaluation of an integrated energy system. The analytic hierarchy process method and entropy weight method were used to calculate the weight of each index in the evaluation model. Fuzzy evaluation matrix was constructed by the membership degree of a single factor, which was defined by the fuzzy comprehensive evaluation method. The multi-level fuzzy evaluation results were obtained based on single-level evaluation results. Finally, case studies were carried out based on a practical integrated energy system; we proposed 5 first-level indicators such as reliability and economy and 12 second-level indicators such as mean time of incapacity. The simulation results (85.15) showed the effectiveness and advantages of the proposed model.

Currently, we are facing an increasing trend in the use of unmanned aerial vehicles (UAV) in various activities, both civilian and military. The application of UAVs in the battlefield has received extensive attention amid a global new military revolution. A UAV cluster is a large and complex real-time feedback system that integrates a communication and sensor network, control system, calculation, and physical process. The heterogeneous UAVs conduct complex behaviors, which requires a comprehensive description and analysis of UAV cluster modeling. The integrated modeling of the heterogeneous UAV cluster is of great significance and value to test and verify the new combat mode. In this paper, we present a novel representation framework based on the Petri nets. We used a spatial-temporal hybrid Petri net to illustrate the discrete state and continuous process of a heterogeneous UAV cluster system, and effectively achieved the fusion of a physical and computational process and interaction event modeling in the cluster system. Finally, the formal verification of UAV cluster attack mission modeling was carried out by UPPAAL, suggesting the proposed modeling method is feasible and effective.

Sensor-based Human Activity Recognition (SHAR) has gained more attention due to the rapid development of the Internet of Things (IoT). The critical issue for SHAR is rescuing the performance bottleneck from expensive feature engineering. Recent works have explored combining hybrid neural networks to improve the SHAR model architecture for learning informative representation. However, existing studies have not adequately provided a hierarchical structure that can represent human activities and capture specific representations hidden beneath interrelated low-level human activity sequences. In this work, we introduce a dual pipeline with a spatio-temporal attention fusion approach, termed the ST-attention dual pipeline, to address this problem. Specifically, the ST-attention dual pipeline employs sequence learning techniques in one pipeline to capture complex dependencies within behavior data and residual learning techniques in another pipeline to extract hierarchical details, then fuse them by the ST-attention fusion mechanism generated across spatial and temporal dimensions to improve presentation capabilities. Extensive experiments on public datasets (i.e., OPPORTUNITY, PAMAP2, and USC-HAD) have shown the ST-attention dual pipeline yields compelling results, and the spatio-temporal attention mechanism also achieves superior performance over other fusion methods.

Abstract: The increasing demand for global seamless coverage and information sharing has propelled the rapid advancement of Space-Air-Ground Integrated Networks (SAGIN). Traditional network architectures are increasingly inadequate to satisfy the complex requirements of large-scale, highly dynamic environments. The multi-controller collaborative architecture of SAGIN, underpinned by Software-Defined Networking (SDN), addresses the load imbalance among SDN controllers induced by dynamic satellite network topologies and uneven user service demands. A phased SDN controller deployment and allocation strategy is proposed to overcome these technical challenges. Initially, the strategy refines the DPC-K-means algorithm by incorporating the K-nearest neighbors algorithm to assist in determining clustering centers and boundaries, thereby optimizing local density and relative distance to enhance clustering accuracy on complex datasets. In addition, the integration of flexible buffer zone technology ensures balanced load distribution among satellite controllers and facilitates appropriate partitioning. Subsequently, the Improved Snow Ablation Optimization (ISAO) algorithm is augmented by introducing a composite chaotic system algorithm and a Levy flight-based optimization strategy. This enhancement increases the diversity and flexibility of sample initialization, improving both the efficiency and accuracy in identifying optimal solutions and achieving better controller allocation in satellite networks. Simulation results demonstrate that the proposed controller allocation strategy effectively balances load, enhances the reliability and load-balancing capabilities of the SDN-based SAGIN, and improves the overall objective function value by 42%, time efficiency by 28.5%, while reducing the average transmission delay by 19%. This strategy more effectively meets the demands for multi-domain collaborative communication, transmission, and management in complex multi-platform network scenarios, providing robust technical support for SAGIN applications.

Discovering tactical knowledge aims to extract tactical data derived from battlefield signal data, which is vital in information warfare. The learning and reasoning from battlefield signal information can help commanders make effective decisions. However, traditional methods are limited in capturing sequential and global representation due to their reliance on prior knowledge or feature engineering. The current models based on deep learning focus on extracting implicit behavioral characteristics from combat process data, overlooking the embedded martial knowledge within the recognition of combat intentions. In this work, we fill the above challenge by proposing a dual fusion pipeline introducing graph representation learning into sequence learning to construct tactical behavior sequence graphs expressing implicit martial knowledge, named TBGCN. Specifically, the TBGCN utilizes graph representation learning to represent prior knowledge by building a graph to induce deep learning paradigms, and sequence learning finds the hidden representation from the target’s serialized data. Then, we employ a fusion module to merge two such representations. The significance of integrating graphs with deep learning lies in using the artificial experience of implicit graph structure guiding adaptive learning, which can improve representation ability and model generalization. Extensive experimental results demonstrate that the proposed TBGCN can effectively discover tactical knowledge and significantly outperform the traditional and deep learning methods.

A reasonable and accurate assessment of the reliability of integrated energy system helps to realize the collaborative planning and optimal regulation of smart energy. In this paper, we propose a multi-level fuzzy evaluation model based on combined empowerment for the reliability evaluation of Integrated Energy System (IES). The evaluation indicators are reasonably graded and scientifically integrated to produce assessment conclusions reflecting the overall system condition. The comparative analysis shows that the proposed method can effectively assess the reliability of IES.