[{"issue":"2","publication":"Real-Time Systems","abstract":[{"lang":"eng","text":"<jats:title>Abstract</jats:title>\n          <jats:p>Reinforcement Learning (RL) has emerged as a promising tool for decision-making in various applications, particularly in uncertain environments. While its adoption in embedded systems—especially hard real-time systems—faces challenges due to stringent timing constraints, integrating shielding mechanisms may offer a pathway for RL to optimize its scheduling decisions, preserving worst-case timing guarantees. This position paper shows a use case where RL selects compliant execution versions for fault-tolerant real-time systems while minimizing the system utilization in runtime. Furthermore, we discuss possible directions for further exploring RL’s role in real-time systems for improved adaptability.</jats:p>"}],"date_created":"2026-07-03T21:07:18Z","type":"journal_article","title":"Shielded reinforcement learning for fault-tolerant scheduling in real-time systems","year":"2025","publication_identifier":{"issn":["0922-6443","1573-1383"]},"author":[{"first_name":"Junjie","last_name":"Shi","full_name":"Shi, Junjie"},{"full_name":"Chen, Kuan-Hsun","last_name":"Chen","first_name":"Kuan-Hsun"}],"date_updated":"2026-07-05T14:48:45Z","publication_status":"published","intvolume":"        61","language":[{"iso":"eng"}],"doi":"10.1007/s11241-025-09441-z","citation":{"short":"J. Shi, K.-H. Chen, Real-Time Systems 61 (2025) 306–310.","chicago":"Shi, Junjie, and Kuan-Hsun Chen. “Shielded Reinforcement Learning for Fault-Tolerant Scheduling in Real-Time Systems.” <i>Real-Time Systems</i> 61, no. 2 (2025): 306–10. <a href=\"https://doi.org/10.1007/s11241-025-09441-z\">https://doi.org/10.1007/s11241-025-09441-z</a>.","ieee":"J. Shi and K.-H. Chen, “Shielded reinforcement learning for fault-tolerant scheduling in real-time systems,” <i>Real-Time Systems</i>, vol. 61, no. 2, pp. 306–310, 2025, doi: <a href=\"https://doi.org/10.1007/s11241-025-09441-z\">10.1007/s11241-025-09441-z</a>.","apa":"Shi, J., &#38; Chen, K.-H. (2025). Shielded reinforcement learning for fault-tolerant scheduling in real-time systems. <i>Real-Time Systems</i>, <i>61</i>(2), 306–310. <a href=\"https://doi.org/10.1007/s11241-025-09441-z\">https://doi.org/10.1007/s11241-025-09441-z</a>","bibtex":"@article{Shi_Chen_2025, title={Shielded reinforcement learning for fault-tolerant scheduling in real-time systems}, volume={61}, DOI={<a href=\"https://doi.org/10.1007/s11241-025-09441-z\">10.1007/s11241-025-09441-z</a>}, number={2}, journal={Real-Time Systems}, publisher={Springer Science and Business Media LLC}, author={Shi, Junjie and Chen, Kuan-Hsun}, year={2025}, pages={306–310} }","ama":"Shi J, Chen K-H. Shielded reinforcement learning for fault-tolerant scheduling in real-time systems. <i>Real-Time Systems</i>. 2025;61(2):306-310. doi:<a href=\"https://doi.org/10.1007/s11241-025-09441-z\">10.1007/s11241-025-09441-z</a>","mla":"Shi, Junjie, and Kuan-Hsun Chen. “Shielded Reinforcement Learning for Fault-Tolerant Scheduling in Real-Time Systems.” <i>Real-Time Systems</i>, vol. 61, no. 2, Springer Science and Business Media LLC, 2025, pp. 306–10, doi:<a href=\"https://doi.org/10.1007/s11241-025-09441-z\">10.1007/s11241-025-09441-z</a>."},"status":"public","page":"306-310","_id":"66147","publisher":"Springer Science and Business Media LLC","user_id":"128464","volume":61},{"user_id":"102868","volume":60,"page":"239-290","_id":"63059","publisher":"Springer Science and Business Media LLC","status":"public","citation":{"apa":"Nigade, V., Bauszat, P., Bal, H., &#38; Wang, L. (2024). Inference serving with end-to-end latency SLOs over dynamic edge networks. <i>Real-Time Systems</i>, <i>60</i>(2), 239–290. <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">https://doi.org/10.1007/s11241-024-09418-4</a>","ieee":"V. Nigade, P. Bauszat, H. Bal, and L. Wang, “Inference serving with end-to-end latency SLOs over dynamic edge networks,” <i>Real-Time Systems</i>, vol. 60, no. 2, pp. 239–290, 2024, doi: <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>.","short":"V. Nigade, P. Bauszat, H. Bal, L. Wang, Real-Time Systems 60 (2024) 239–290.","chicago":"Nigade, Vinod, Pablo Bauszat, Henri Bal, and Lin Wang. “Inference Serving with End-to-End Latency SLOs over Dynamic Edge Networks.” <i>Real-Time Systems</i> 60, no. 2 (2024): 239–90. <a href=\"https://doi.org/10.1007/s11241-024-09418-4\">https://doi.org/10.1007/s11241-024-09418-4</a>.","mla":"Nigade, Vinod, et al. “Inference Serving with End-to-End Latency SLOs over Dynamic Edge Networks.” <i>Real-Time Systems</i>, vol. 60, no. 2, Springer Science and Business Media LLC, 2024, pp. 239–90, doi:<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>.","ama":"Nigade V, Bauszat P, Bal H, Wang L. Inference serving with end-to-end latency SLOs over dynamic edge networks. <i>Real-Time Systems</i>. 2024;60(2):239-290. doi:<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>","bibtex":"@article{Nigade_Bauszat_Bal_Wang_2024, title={Inference serving with end-to-end latency SLOs over dynamic edge networks}, volume={60}, DOI={<a href=\"https://doi.org/10.1007/s11241-024-09418-4\">10.1007/s11241-024-09418-4</a>}, number={2}, journal={Real-Time Systems}, publisher={Springer Science and Business Media LLC}, author={Nigade, Vinod and Bauszat, Pablo and Bal, Henri and Wang, Lin}, year={2024}, pages={239–290} }"},"doi":"10.1007/s11241-024-09418-4","language":[{"iso":"eng"}],"date_updated":"2025-12-12T08:18:05Z","publication_status":"published","intvolume":"        60","year":"2024","title":"Inference serving with end-to-end latency SLOs over dynamic edge networks","author":[{"last_name":"Nigade","first_name":"Vinod","full_name":"Nigade, Vinod"},{"first_name":"Pablo","last_name":"Bauszat","full_name":"Bauszat, Pablo"},{"first_name":"Henri","last_name":"Bal","full_name":"Bal, Henri"},{"orcid":"0000-0001-7181-6128","last_name":"Wang","first_name":"Lin","full_name":"Wang, Lin","id":"102868"}],"publication_identifier":{"issn":["0922-6443","1573-1383"]},"type":"journal_article","department":[{"_id":"34"},{"_id":"7"},{"_id":"75"}],"date_created":"2025-12-12T08:16:33Z","abstract":[{"lang":"eng","text":"<jats:title>Abstract</jats:title><jats:p>While high accuracy is of paramount importance for deep learning (DL) inference, serving inference requests on time is equally critical but has not been carefully studied especially when the request has to be served over a dynamic wireless network at the edge. In this paper, we propose Jellyfish—a novel edge DL inference serving system that achieves soft guarantees for end-to-end inference latency service-level objectives (SLO). Jellyfish handles the network variability by utilizing both data and deep neural network (DNN) adaptation to conduct tradeoffs between accuracy and latency. Jellyfish features a new design that enables collective adaptation policies where the decisions for data and DNN adaptations are aligned and coordinated among multiple users with varying network conditions. We propose efficient algorithms to continuously map users and adapt DNNs at runtime, so that we fulfill latency SLOs while maximizing the overall inference accuracy. We further investigate <jats:italic>dynamic</jats:italic> DNNs, i.e., DNNs that encompass multiple architecture variants, and demonstrate their potential benefit through preliminary experiments. Our experiments based on a prototype implementation and real-world WiFi and LTE network traces show that Jellyfish can meet latency SLOs at around the 99th percentile while maintaining high accuracy.\r\n</jats:p>"}],"issue":"2","publication":"Real-Time Systems"}]