A Causal-Guided Multimodal Large Language Model for Generalized Power System Time-Series Data Analytics
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917072898883584 |
|---|---|
| author | Zhou, Zhenghao Li, Yiyan Yu, Xinjie Liu, Runlong Guo, Zelin Yan, Zheng Chow, Mo-Yuen Yang, Yuqi Xu, Yang |
| author_facet | Zhou, Zhenghao Li, Yiyan Yu, Xinjie Liu, Runlong Guo, Zelin Yan, Zheng Chow, Mo-Yuen Yang, Yuqi Xu, Yang |
| contents | Power system time series analytics is critical in understanding the system operation conditions and predicting the future trends. Despite the wide adoption of Artificial Intelligence (AI) tools, many AI-based time series analytical models suffer from task-specificity (i.e. one model for one task) and structural rigidity (i.e. the input-output format is fixed), leading to limited model performances and resource wastes. In this paper, we propose a Causal-Guided Multimodal Large Language Model (CM-LLM) that can solve heterogeneous power system time-series analysis tasks. First, we introduce a physics-statistics combined causal discovery mechanism to capture the causal relationship, which is represented by graph, among power system variables. Second, we propose a multimodal data preprocessing framework that can encode and fuse text, graph and time series to enhance the model performance. Last, we formulate a generic "mask-and-reconstruct" paradigm and design a dynamic input-output padding mechanism to enable CM-LLM adaptive to heterogeneous time-series analysis tasks with varying sample lengths. Simulation results based on open-source LLM Qwen and real-world dataset demonstrate that, after simple fine-tuning, the proposed CM-LLM can achieve satisfying accuracy and efficiency on three heterogeneous time-series analytics tasks: missing data imputation, forecasting and super resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07777 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Causal-Guided Multimodal Large Language Model for Generalized Power System Time-Series Data Analytics Zhou, Zhenghao Li, Yiyan Yu, Xinjie Liu, Runlong Guo, Zelin Yan, Zheng Chow, Mo-Yuen Yang, Yuqi Xu, Yang Signal Processing Power system time series analytics is critical in understanding the system operation conditions and predicting the future trends. Despite the wide adoption of Artificial Intelligence (AI) tools, many AI-based time series analytical models suffer from task-specificity (i.e. one model for one task) and structural rigidity (i.e. the input-output format is fixed), leading to limited model performances and resource wastes. In this paper, we propose a Causal-Guided Multimodal Large Language Model (CM-LLM) that can solve heterogeneous power system time-series analysis tasks. First, we introduce a physics-statistics combined causal discovery mechanism to capture the causal relationship, which is represented by graph, among power system variables. Second, we propose a multimodal data preprocessing framework that can encode and fuse text, graph and time series to enhance the model performance. Last, we formulate a generic "mask-and-reconstruct" paradigm and design a dynamic input-output padding mechanism to enable CM-LLM adaptive to heterogeneous time-series analysis tasks with varying sample lengths. Simulation results based on open-source LLM Qwen and real-world dataset demonstrate that, after simple fine-tuning, the proposed CM-LLM can achieve satisfying accuracy and efficiency on three heterogeneous time-series analytics tasks: missing data imputation, forecasting and super resolution. |
| title | A Causal-Guided Multimodal Large Language Model for Generalized Power System Time-Series Data Analytics |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2511.07777 |