Graph-Enabled Reinforcement Learning for Time Series Forecasting With Adaptive Intelligence
Article
Shaik, Thanveer, Tao, Xiaohui, Xie, Haoran, Li, Lin, Yong, Jianming and Li, Yuefeng. 2024. "Graph-Enabled Reinforcement Learning for Time Series Forecasting With Adaptive Intelligence." IEEE Transactions on Emerging Topics in Computational Intelligence. 8 (4), pp. 2908-2918. https://doi.org/10.1109/TETCI.2024.3398024
| Article Title | Graph-Enabled Reinforcement Learning for Time Series Forecasting With Adaptive Intelligence |
|---|---|
| ERA Journal ID | 212763 |
| Article Category | Article |
| Authors | Shaik, Thanveer, Tao, Xiaohui, Xie, Haoran, Li, Lin, Yong, Jianming and Li, Yuefeng |
| Journal Title | IEEE Transactions on Emerging Topics in Computational Intelligence |
| Journal Citation | 8 (4), pp. 2908-2918 |
| Number of Pages | 11 |
| Year | 2024 |
| Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
| Place of Publication | United States |
| ISSN | 2471-285X |
| Digital Object Identifier (DOI) | https://doi.org/10.1109/TETCI.2024.3398024 |
| Web Address (URL) | https://ieeexplore.ieee.org/document/10530910 |
| Abstract | Reinforcement learning (RL) is renowned for its proficiency in modeling sequential tasks and adaptively learning latent data patterns. Deep learning models have been extensively explored and adopted in regression and classification tasks. However, deep learning has limitations, such as the assumption of equally spaced and ordered data, and the inability to incorporate graph structure in time-series prediction. Graph Neural Network (GNN) can overcome these challenges by capturing the temporal dependencies in time-series data effectively. In this study, we propose a novel approach for predicting time-series data using GNN, augmented with Reinforcement Learning(GraphRL) for monitoring. GNNs explicitly integrate the graph structure of the data into the model, enabling them to naturally capture temporal dependencies. This approach facilitates more accurate predictions in complex temporal structures, as encountered in healthcare, traffic, and weather forecasting domains. We further enhance our GraphRL model's performance through fine-tuning with a Bayesian optimization technique. The proposed framework surpasses baseline models in time-series forecasting and monitoring. This study's contributions include introducing a novel GraphRL framework for time-series prediction and demonstrating GNNs' efficacy compared to traditional deep learning models, such as Recurrent Neural Networks (RNN) and Long Short-Term Memory Networks(LSTM). Overall, this study underscores the potential of GraphRL in yielding accurate and efficient predictions within dynamic RL environments. |
| Keywords | Bayesian optimization; Graph neural networks; reinforcement learning; intelligent monitoring |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 461103. Deep learning |
| Public Notes | The accessible file is the accepted version of the paper. Please refer to the URL for the published version. |
| Byline Affiliations | School of Mathematics, Physics and Computing |
| Lingnan University of Hong Kong, China | |
| Wuhan University of Technology, China | |
| School of Business | |
| Queensland University of Technology |
Permalink -
https://research.usq.edu.au/item/z8592/graph-enabled-reinforcement-learning-for-time-series-forecasting-with-adaptive-intelligence
Download files
15
total views6
total downloads1
views this month1
downloads this month