Searcharxiv⌕ Search

arXiv subjects

Xueyuan Cui

Publications and source records attributed to Xueyuan Cui.

3 recordsLinked to original sources

B2G-Agent: An LLM-Based Multi-Agent Tool for End-to-End Building-Grid Interactions

Buildings are major electricity consumers and can interact with distribution network dispatch through flexible power scheduling. These interactions require distribution network operators (DNOs) and building energy managers (BEMs) to reconcile their operational constraints and perform complex cross-field computations. The lack of cross-domain expertise and unified computational workflows could lead to inefficient or physically infeasible interactions. To address this bottleneck, we develop an end-to-end large language model (LLM)-based multi-agent tool, B2G-Agent, that bridges DNOs and BEMs. The tool deploys three collaborative agents: a Translator for bidirectional cross-domain semantic mapping via hybrid retrieval-augmented generation (RAG); an Actor for automated configuration and execution of joint simulation and optimization through directed acyclic graphs; and a Reviewer for memory-augmented reflective failure diagnosis. This workflow abstracts away cross-field modeling complexities and enables both sides to focus on high-level operational decisions. Comprehensive evaluations across 200 synthesized tasks show that B2G-Agent improves the interaction quality score from 66.71 to 85.57 and increases the task success rate from 38.0% to 69.0% over the baseline while satisfying operational constraints. The open-source tool and interface are available at https://github.com/hkuedl/B2G-Agent.

cs.HC↗

Dimension-reduced Optimization of Multi-zone Thermostatically Controlled Loads

This study proposes a computationally efficient method for optimizing multi-zone thermostatically controlled loads (TCLs) by leveraging dimensionality reduction through an auto-encoder. We develop a multi-task learning framework to jointly represent latent variables and formulate a state-space model based on observed TCL operation data. This significantly reduces the dimensionality of TCL variables and states while preserving critical nonlinear interdependencies in TCL control. To address various application scenarios, we introduce optimization algorithms based on system identification (OptIden) and system simulation (OptSim) tailored to the latent variable representation. These approaches employ automatic differentiation and zeroth-order techniques, respectively, for efficient implementation. We evaluate the proposed method using a 90-zone apartment prototype, comparing its performance to traditional high-dimensional optimization. Results demonstrate that our approach effectively reduces control costs while achieving significantly higher computational efficiency.

eess.SY↗

Load Data Valuation in Multi-Energy Systems: An End-to-End Approach

Accurate load forecasting serves as the foundation for the flexible operation of multi-energy systems (MES). Multi-energy loads are tightly coupled and exhibit significant uncertainties. Many works focus on enhancing forecasting accuracy by leveraging cross-sector information. However, data owners may not be motivated to share their data unless it leads to substantial benefits. Ensuring a reasonable data valuation can encourage them to share their data willingly. This paper presents an end-to-end framework to quantify multi-energy load data value by integrating forecasting and decision processes. To address optimization problems with integer variables, a two-stage end-to-end model solution is proposed. Moreover, a profit allocation strategy based on contribution to cost savings is investigated to encourage data sharing in MES. The experimental results demonstrate a significant decrease in operation costs, suggesting that the proposed valuation approach more effectively extracts the inherent data value than traditional methods. According to the proposed incentive mechanism, all sectors can benefit from data sharing by improving forecasting accuracy or receiving economic compensation.

eess.SY↗