LLM-Slice: Dedicated Wireless Network Slicing for Large Language Models (2410.18499v1)
Abstract: The rapid adoption of LLMs presents new challenges for existing network architectures due to significant peak traffic and high communication uncertainty. Traditional wireless networks struggle to support efficiently, leading to intolerable response delays, disconnections, and resource wastage. To address these issues, we propose LLM-Slice, the first system to provide dedicated communication slices for LLMs within a wireless network environment. By creating LLM-specific network slices, LLM-Slice efficiently binds services with communication resources. Based on user equipment (UE) requests and a permissions database, the system registers specific slices to offer controllable LLM services, integrating a downlink resource control module to optimize response speed, enhance resource utilization, and reduce disconnections. By deploying and validating in a real UE-gNB-CN environment, numerical results demonstrate that LLM-Slice significantly improves response speed and resource efficiency, providing a novel solution for fast and controllable LLM access in wireless networks.
- A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology 15, 3 (2024), 1–45.
- Language Modeling in Logistics: Customer Calling Prediction. In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium. 4–6.
- From natural language to simulations: applying AI to automate simulation modelling of logistics systems. International Journal of Production Research 62, 4 (2024), 1434–1457.
- Singular point probability improve LSTM network performance for long-term traffic flow prediction. In Theoretical Computer Science: 35th National Conference, NCTCS 2017, Wuhan, China, October 14-15, 2017, Proceedings. Springer, 328–340.
- EdgeLoc: A Communication-Adaptive Parallel System for Real-Time Localization in Infrastructure-Assisted Autonomous Driving. arXiv preprint arXiv:2405.12120 (2024).
- Peer-assisted robotic learning: a data-driven collaborative learning approach for cloud robotic systems. In 2021 IEEE international conference on robotics and automation (ICRA). IEEE, 4062–4070.
- ElasticROS: An Elastically Collaborative Robot Operation System for Fog and Cloud Robotics. arXiv preprint arXiv:2209.01774 (2022).
- Roboec2: A novel cloud robotic system with dynamic network offloading assisted by amazon ec2. IEEE Transactions on Automation Science and Engineering (2023).
- Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data. IEEE Robotics and Automation Letters 5, 2 (2019), 3509–3516.
- Lifelong federated reinforcement learning: a learning architecture for navigation in cloud robotic systems. IEEE Robotics and Automation Letters 4, 4 (2019), 4555–4562.
- Experiments of federated learning for covid-19 chest x-ray images. arXiv preprint arXiv:2007.05592 (2020).
- OpenAirInterface: A flexible platform for 5G research. ACM SIGCOMM Computer Communication Review 44, 5 (2014), 33–38.
- Large language models in medicine. Nature medicine 29, 8 (2023), 1930–1940.
- A survey on large language model based autonomous agents. Frontiers of Computer Science 18, 6 (2024), 186345.
- Bloomberggpt: A large language model for finance. arXiv preprint arXiv:2303.17564 (2023).
- Fedcm: A real-time contribution measurement method for participants in federated learning. In 2021 International joint conference on neural networks (IJCNN). IEEE, 1–8.
- Authros: Secure data sharing among robot operating systems based on ethereum. In 2022 IEEE 22nd International Conference on Software Quality, Reliability and Security (QRS). IEEE, 147–156.
- Applications of federated learning in smart cities: recent advances, taxonomy, and open challenges. Connection Science 34, 1 (2022), 1–28.
- Large language model (llm) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities. arXiv preprint arXiv:2405.10825 (2024).
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.