Bo Tian

Bo Tian

Auto-generated profile, based on publicly available information

Bo Tian

North China Electric Power University, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 August 2024 in IEEE Access
Verified
Journal Article
Open access
CYChang Yang
Chang Yang
LWLisha Wu
Lisha Wu
JXJing Xu
Jing Xu
YRYingjie Ren
Yingjie Ren
BTBo Tian
Bo Tian
ZWZhenhua Wei
Zhenhua Wei
The anomaly detection in data links aims to identify the state of the link during data transmission, which is a critical task for ensuring information transmission security. Most anomaly detection methods focus solely on individual link characteristics, disregarding the inter-link structural information, thus hindering effective generalization to graph-structured data. In this study, we introduce a Graph Learning-based Data Link Anomaly Detection model (GLDAE) that considers both the link features and the communication network structure. Specifically, GLDAE comprises a graph enhancement module, a link feature autoencoder, a structure autoencoder, and a discriminator, enabling simultaneous learning of edge features and the latent representation of the graph structure. Moreover, to enhance the model’s generalization capability, we employ contrastive learning between the original graph and its enhanced version. Additionally, to achieve joint learning of edge features and graph structure, we integrate edge feature embeddings and structure embeddings as inputs to the decoder. Finally, utilizing the well-trained encoder to encode link features and derive a new feature representation, we feed it into an MLP classifier to determine the link’s status. Experimental evaluations were conducted on four authentic datasets (NF-UNSW-NB15, NF-UNSW-NB15-v2, NF-ToN-IoT, NF-ToN-IoT-v2), comparing our model against state-of-the-art baseline models, showcasing the substantial potential of our approach.

19 January 2026 in IEEE Access
Verified
Journal Article
Open access
SGShijie Gao
Shijie Gao
LYLufeng Yuan
Lufeng Yuan
BTBo Tian
Bo Tian
ZWZhenhua Wei
Zhenhua Wei
YLYuxi Liu
Yuxi Liu
Accurate power load forecasting plays a critical role in ensuring the stability and efficiency of modern power systems. However, as the penetration of renewable energy increases and user behaviors become more dynamic, power load data exhibit pronounced non-stationarity and complexity, posing significant challenges to existing forecasting models. To address these issues, this paper proposes a Dynamic Multi-Scale Coordination and Large Language Model Cascade Framework (DMC-LLMF) for power load forecasting. The framework aims to achieve two complementary objectives: 1) dynamically extract and coordinate temporal dependencies across multiple scales and 2) enhance contextual knowledge modeling through the semantic reasoning capability of large language models (LLMs). Specifically, the Dynamic Multi-Scale Decomposition Embedding (DMDE) module adaptively segments load sequences to capture temporal patterns at different scales, while the Triad Interaction Module (TIM) simultaneously models intra-patch, inter-patch, and inter-variable relationships for synergistic local–global dependency learning. Subsequently, a Cross-Modality Alignment (CMA) mechanism fuses semantic prompts generated by a pre-trained LLM with numerical load features, and an Adaptive Mixture-of-Experts Decoder (A-MoE) dynamically weighs multi-scale representations for final forecasting. Extensive experiments on four real-world power load datasets demonstrate that DMC-LLMF outperforms state-of-the-art baselines in both accuracy and robustness, achieving the lowest MSE and MAE across multiple prediction horizons. This framework introduces a novel paradigm for integrating data-driven temporal modeling with knowledge-enhanced semantic reasoning.