Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Large Language Models for Power Scheduling: A User-Centric Approach

Thomas Mongaillard, Samson Lasaulce, Othman Hicheur, Chao Zhang, Lina Bariah, Vineeth S. Varma, Hang Zou, Qiyang Zhao, Merouane Debbah

TL;DR

This paper introduces a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector and demonstrates the efficiency of the proposed architecture.

Abstract

While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high quality-of-experience (QoE) and flexibility. This challenge is particularly pronounced in wireless and digitalized energy networks, where users' requirements have largely not been taken into consideration due to the lack of a common language between users and machines. The emergence of powerful large language models (LLMs) marks a radical departure from traditional system-centric methods into more advanced user-centric approaches by providing a natural communication interface between users and devices. In this paper, for the first time, we introduce a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector. Specifically, we design an LLM intent recognition agent to translate the request into an optimization problem (OP), an LLM OP parameter identification agent, and an LLM OP solving agent. To evaluate system performance, we construct a database of typical VRQs in the context of electric vehicle (EV) charging. As a proof of concept, we primarily use Llama 3 8B. Through testing with different prompt engineering scenarios, the obtained results demonstrate the efficiency of the proposed architecture. The conducted performance analysis allows key insights to be extracted. For instance, having a larger set of candidate OPs to model the real-world problem might degrade the final performance because of a higher recognition/OP classification noise level. All results and codes are open source.

Large Language Models for Power Scheduling: A User-Centric Approach

TL;DR

This paper introduces a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector and demonstrates the efficiency of the proposed architecture.

Abstract

While traditional optimization and scheduling schemes are designed to meet fixed, predefined system requirements, future systems are moving toward user-driven approaches and personalized services, aiming to achieve high quality-of-experience (QoE) and flexibility. This challenge is particularly pronounced in wireless and digitalized energy networks, where users' requirements have largely not been taken into consideration due to the lack of a common language between users and machines. The emergence of powerful large language models (LLMs) marks a radical departure from traditional system-centric methods into more advanced user-centric approaches by providing a natural communication interface between users and devices. In this paper, for the first time, we introduce a novel architecture for resource scheduling problems by constructing three LLM agents to convert an arbitrary user's voice request (VRQ) into a resource allocation vector. Specifically, we design an LLM intent recognition agent to translate the request into an optimization problem (OP), an LLM OP parameter identification agent, and an LLM OP solving agent. To evaluate system performance, we construct a database of typical VRQs in the context of electric vehicle (EV) charging. As a proof of concept, we primarily use Llama 3 8B. Through testing with different prompt engineering scenarios, the obtained results demonstrate the efficiency of the proposed architecture. The conducted performance analysis allows key insights to be extracted. For instance, having a larger set of candidate OPs to model the real-world problem might degrade the final performance because of a higher recognition/OP classification noise level. All results and codes are open source.
Paper Structure (12 sections, 2 equations, 8 figures, 2 tables)

This paper contains 12 sections, 2 equations, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Problem Statement
  3. Multi-agent design of the voice request to power vector converter
  4. Design of the LLM-based Intent Recognition Agent
  5. Design of the LLM-based Parameter Identification Agent
  6. Design of the LLM-based OP Solving Agent
  7. Performance evaluation
  8. Database and evaluation metric
  9. Prompt engineering
  10. Simulation results
  11. Conclusion
  12. Appendix

Figures (8)

  • Figure 1: Use-Cases of the Proposed Intelligent Power Scheduling System
  • Figure 2: Proposed multi-agent architecture for a voice request to power scheduling vector converter (VRQ2Vec)
  • Figure 3: Influence of context knowledge for Agent 1 in terms of IRA. The evaluation is performed for 3 types of voice requests (CC, CT, and PP). The gains provided by knowledge files are seen to be significant.
  • Figure 4: Influence of context knowledge in terms of optimality loss for the final power scheduling performance metric.
  • Figure 5: For 5 different performance metrics (CC,...,GD): influence of the set of selected OPs ($\{\mathrm{LP}, \mathrm{LMT}\}$ means for instance that either Linear Programming or Linear Minimum Time has to be chosen) on its ability to select the most suitable OP class.
  • ...and 3 more figures