arXiv subjects

Yiliu He

Publications and source records attributed to Yiliu He.

5 recordsLinked to original sources

arXiv2026

Emergency-Aware and Frequency-Constrained HVDC Planning for A Multi-Area Asynchronously Interconnected Grid

High-voltage direct current (HVDC) technology has played a crucial role for long-distance transmission of renewable power generation. However, the integration of large-capacity HVDC lines introduces significant frequency security challenges during HVDC fault emergencies. This paper proposes an emergency-aware and frequency-constrained HVDC planning method to optimize the capacity of inter-area HVDC tie-lines in a multi-area asynchronously interconnected grid. Firstly, a coordinated emergency frequency control scheme is proposed to allocate the emergency control resources during HVDC faults. Then, an enhanced system frequency response model integrating event-driven emergency frequency control is developed and a weighted oblique decision tree approach is employed to extract frequency nadir security constraints. The proposed planning model considers all potential HVDC fault emergencies while treating candidate HVDC capacities as decision variables. Simulation results demonstrate superior performance in balancing economic efficiency with frequency security requirements, providing a practical solution for inter-area HVDC planning.

eess.SY↗

arXiv2026

EvoOpt-LLM: Evolving industrial optimization models with large language models

Optimization modeling via mixed-integer linear programming (MILP) is fundamental to industrial planning and scheduling, yet translating natural-language requirements into solver-executable models and maintaining them under evolving business rules remains highly expertise-intensive. While large language models (LLMs) offer promising avenues for automation, existing methods often suffer from low data efficiency, limited solver-level validity, and poor scalability to industrial-scale problems. To address these challenges, we present EvoOpt-LLM, a unified LLM-based framework supporting the full lifecycle of industrial optimization modeling, including automated model construction, dynamic business-constraint injection, and end-to-end variable pruning. Built on a 7B-parameter LLM and adapted via parameter-efficient LoRA fine-tuning, EvoOpt-LLM achieves a generation rate of 91% and an executability rate of 65.9% with only 3,000 training samples, with critical performance gains emerging under 1,500 samples. The constraint injection module reliably augments existing MILP models while preserving original objectives, and the variable pruning module enhances computational efficiency, achieving an F1 score of ~0.56 on medium-sized LP models with only 400 samples. EvoOpt-LLM demonstrates a practical, data-efficient approach to industrial optimization modeling, reducing reliance on expert intervention while improving adaptability and solver efficiency.

cs.AI↗

arXiv2023

Look-Ahead AC Optimal Power Flow: A Model-Informed Reinforcement Learning Approach

With the increasing proportion of renewable energy in the generation side, it becomes more difficult to accurately predict the power generation and adapt to the large deviations between the optimal dispatch scheme and the day-ahead scheduling in the process of real-time dispatch. Therefore, it is necessary to conduct look-ahead dispatches to revise the operation plan according to the real-time status of the power grid and reliable ultra-short-term prediction. Application of traditional model-driven methods is often limited by the scale of the power system and cannot meet the computational time requirements of real-time dispatch. Data-driven methods can provide strong online decision-making support abilities when facing large-scale systems, while it is limited by the quantity and quality of the training dataset. This paper proposes a model-informed reinforcement learning approach for look-ahead AC optimal power flow. The reinforcement learning model is first formulated based on the domain knowledge of economic dispatch, and then the physics-informed neural network is constructed to enhance the reliability and efficiency. At last, the case study based on the SG 126-bus system validates the accuracy and efficiency of the proposed approach.

eess.SY↗

arXiv2022

Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

Modern power systems are experiencing a variety of challenges driven by renewable energy, which calls for developing novel dispatch methods such as reinforcement learning (RL). Evaluation of these methods as well as the RL agents are largely under explored. In this paper, we propose an evaluation approach to analyze the performance of RL agents in a look-ahead economic dispatch scheme. This approach is conducted by scanning multiple operational scenarios. In particular, a scenario generation method is developed to generate the network scenarios and demand scenarios for evaluation, and network structures are aggregated according to the change rates of power flow. Then several metrics are defined to evaluate the agents' performance from the perspective of economy and security. In the case study, we use a modified IEEE 30-bus system to illustrate the effectiveness of the proposed evaluation approach, and the simulation results reveal good and rapid adaptation to different scenarios. The comparison between different RL agents is also informative to offer advice for a better design of the learning strategies.

eess.SY↗

arXiv2020

Review of Learning-Assisted Power System Optimization

With dramatic breakthroughs in recent years, machine learning is showing great potential to upgrade the toolbox for power system optimization. Understanding the strength and limitation of machine learning approaches is crucial to decide when and how to deploy them to boost the optimization performance. This paper pays special attention to the coordination between machine learning approaches and optimization models, and carefully evaluates how such data-driven analysis may improve the rule-based optimization. The typical references are selected and categorized into four groups: the boundary parameter improvement, the optimization option selection, the surrogate model, and the hybrid model. This taxonomy provides a novel perspective to elaborate the latest research progress and development. We further compare the design patterns of different categories, and discuss several key challenges and opportunities as well. Deep integration between machine learning approaches and optimization models is expected to become the most promising technical trend.

eess.SY↗