arXiv subjects

Yongli Zhu

Publications and source records attributed to Yongli Zhu.

At least 19 recordsLinked to original sources

arXiv2026

Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction

This paper introduces an LLM agent that automates power grid static analysis by converting natural language into MATPOWER scripts. The framework utilizes DeepSeek-OCR to build an enhanced vector database from MATPOWER manuals. To ensure reliability, it devises a three-tier error-correction system: a static pre-check, a dynamic feedback loop, and a semantic validator. Operating via the Model Context Protocol, the tool enables asynchronous execution and automatically debugging in MATLAB. Experimental results demonstrate that the system achieves a 82.38% accuracy regarding the code fidelity, effectively eliminating hallucinations even in complex analysis tasks.

eess.SY↗

arXiv2026

On-Meter Graph Machine Learning: A Case Study of PV Power Forecasting for Grid Edge Intelligence

This paper presents a detailed study of how graph neural networks can be used on edge intelligent meters in a microgrid to forecast photovoltaic power generation. The problem background and the adopted technologies are introduced, including ONNX and ONNX Runtime. The hardware and software specifications of the smart meter are also briefly described. Then, the paper focuses on the training and deployment of two graph machine learning models, GCN and GraphSAGE, with particular emphasis on developing and deploying a customized ONNX operator for GCN. Finally, a case study is conducted using real datasets from a village microgrid. The performance of the two models is compared on both the PC and the smart meter, exhibiting successful deployments and executions on the smart meter.

cs.LG↗

arXiv2025

On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence

In this paper, an edge-side model training study is conducted on a resource-limited smart meter. The motivation of grid-edge intelligence and the concept of on-device training are introduced. Then, the technical preparation steps for on-device training are described. A case study on the task of photovoltaic power forecasting is presented, where two representative machine learning models are investigated: a gradient boosting tree model and a recurrent neural network model. To adapt to the resource-limited situation in the smart meter, "mixed"- and "reduced"-precision training schemes are also devised. Experiment results demonstrate the feasibility of economically achieving grid-edge intelligence via the existing advanced metering infrastructures.

cs.LG↗

arXiv2025

Diffusion-assisted Model Predictive Control Optimization for Power System Real-Time Operation

This paper presents a modified model predictive control (MPC) framework for real-time power system operation. The framework incorporates a diffusion model tailored for time series generation to enhance the accuracy of the load forecasting module used in the system operation. In the absence of explicit state transition law, a model-identification procedure is leveraged to derive the system dynamics, thereby eliminating a barrier when applying MPC to a renewables-dominated power system. Case study results on an industry park system and the IEEE 30-bus system demonstrate that using the diffusion model to augment the training dataset significantly improves load-forecasting accuracy, and the inferred system dynamics are applicable to the real-time grid operation with solar and wind.

eess.SY↗

arXiv2025

Offline Reinforcement Learning for Microgrid Voltage Regulation

This paper presents a study on using different offline reinforcement learning algorithms for microgrid voltage regulation with solar power penetration. When environment interaction is unviable due to technical or safety reasons, the proposed approach can still obtain an applicable model through offline-style training on a previously collected dataset, lowering the negative impact of lacking online environment interactions. Experiment results on the IEEE 33-bus system demonstrate the feasibility and effectiveness of the proposed approach on different offline datasets, including the one with merely low-quality experience.

cs.AI↗

arXiv2025

Deep Reinforcement Learning for Power Grid Multi-Stage Cascading Failure Mitigation

Cascading failures in power grids can lead to grid collapse, causing severe disruptions to social operations and economic activities. In certain cases, multi-stage cascading failures can occur. However, existing cascading-failure-mitigation strategies are usually single-stage-based, overlooking the complexity of the multi-stage scenario. This paper treats the multi-stage cascading failure problem as a reinforcement learning task and develops a simulation environment. The reinforcement learning agent is then trained via the deterministic policy gradient algorithm to achieve continuous actions. Finally, the effectiveness of the proposed approach is validated on the IEEE 14-bus and IEEE 118-bus systems.

cs.AI↗

arXiv2024

Generative Modeling and Data Augmentation for Power System Production Simulation

As a key component of power system production simulation, load forecasting is critical for the stable operation of power systems. Machine learning methods prevail in this field. However, the limited training data can be a challenge. This paper proposes a generative model-assisted approach for load forecasting under small sample scenarios, consisting of two steps: expanding the dataset using a diffusion-based generative model and then training various machine learning regressors on the augmented dataset to identify the best performer. The expanded dataset significantly reduces forecasting errors compared to the original dataset, and the diffusion model outperforms the generative adversarial model by achieving about 200 times smaller errors and better alignment in latent data distributions.

eess.SY↗

arXiv2024

Embedded Machine Learning for Solar PV Power Regulation in a Remote Microgrid

This paper presents a machine-learning study for solar inverter power regulation in a remote microgrid. Machine learning models for active and reactive power control are respectively trained using an ensemble learning method. Then, unlike conventional schemes that make inferences on a central server in the far-end control center, the proposed scheme deploys the trained models on an embedded edge-computing device near the inverter to reduce the communication delay. Experiments on a real embedded device achieve matched results as on the desktop PC, with about 0.1ms time cost for each inference input.

eess.SY↗

arXiv2024

Edge Computing for Microgrid via MATLAB Embedded Coder and Low-Cost Smart Meters

In this paper, an edge computing-based machine-learning study is conducted for solar inverter power forecasting and droop control in a remote microgrid. The machine learning models and control algorithms are directly deployed on an edge-computing device (a smart meter-concentrator) in the microgrid rather than on a cloud server at the far-end control center, reducing the communication time the inverters need to wait. Experimental results on an ARM-based smart meter board demonstrate the feasibility and correctness of the proposed approach by comparing against the results on the desktop PC.

eess.SY↗

arXiv2024

Distributed Stochastic ACOPF Based on Consensus ADMM and Scenario Reduction

This paper presents a Consensus ADMM-based modeling and solving approach for the stochastic ACOPF. The proposed optimization model considers the load forecasting uncertainty and its induced load-shedding cost via Monte Carlo sampling. The sampled scenarios are reduced using a clustering method combined with simultaneous backward reduction techniques to reduce the computational complexity. The proposed approach is tested on two IEEE systems, achieving about 2% cost reduction and more than 15 times lower reliability index in stochastic load settings compared to the baseline approach.

eess.SY↗

arXiv2023

MAHTM: A Multi-Agent Framework for Hierarchical Transactive Microgrids

Integrating variable renewable energy into the grid has posed challenges to system operators in achieving optimal trade-offs among energy availability, cost affordability, and pollution controllability. This paper proposes a multi-agent reinforcement learning framework for managing energy transactions in microgrids. The framework addresses the challenges above: it seeks to optimize the usage of available resources by minimizing the carbon footprint while benefiting all stakeholders. The proposed architecture consists of three layers of agents, each pursuing different objectives. The first layer, comprised of prosumers and consumers, minimizes the total energy cost. The other two layers control the energy price to decrease the carbon impact while balancing the consumption and production of both renewable and conventional energy. This framework also takes into account fluctuations in energy demand and supply.

cs.LG↗

arXiv2023

Power Grid Transient Analysis via Open-Source Circuit Simulator: A Case Study of HVDC

This paper proposes an electronic circuit simulator-based method to accelerate the power system transient simulation, where the modeling of a generic HVDC (High Voltage Direct Current) system is focused. The electronic circuit simulation equations and the backward differentiation formula for numerical solving are described. Then, the circuit modeling process for power system components such as slack bus, constant power load, and HVDC are respectively illustrated. Finally, a case study is conducted on a four-bus power system to demonstrate the effectiveness of the proposed modeling and simulation method.

eess.SY↗

arXiv2023

A Free Industry-grade Education Tool for Bulk Power System Reliability Assessment

A free industry-grade education tool is developed for bulk-power-system reliability assessment. The software architecture is illustrated using a high-level flowchart. Three main algorithms of this tool, i.e., sequential Monte Carlo simulation, unit preventive maintenance schedule, and optimal-power-flow-based load shedding, are introduced. The input and output formats are described in detail, including the roles of different data cards and results categorization. Finally, an example case study is conducted on a five-area system to demonstrate the effectiveness and efficiency of this tool.

eess.SY↗

arXiv2022

End-to-End Topology-Aware Machine Learning for Power System Reliability Assessment

Conventional power system reliability suffers from the long run time of Monte Carlo simulation and the dimension-curse of analytic enumeration methods. This paper proposes a preliminary investigation on end-to-end machine learning for directly predicting the reliability index, e.g., the Loss of Load Probability (LOLP). By encoding the system admittance matrix into the input feature, the proposed machine learning pipeline can consider the impact of specific topology changes due to regular maintenances of transmission lines. Two models (Support Vector Machine and Boosting Trees) are trained and compared. Details regarding the training data creation and preprocessing are also discussed. Finally, experiments are conducted on the IEEE RTS-79 system. Results demonstrate the applicability of the proposed end-to-end machine learning pipeline in reliability assessment.

cs.LG↗

arXiv2021

Power Grid Cascading Failure Mitigation by Reinforcement Learning

This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL). The motivation of the Multi-Stage Cascading Failure (MSCF) problem and its connection with the challenge of climate change are introduced. The bottom-level corrective control of the MCSF problem is formulated based on DCOPF (Direct Current Optimal Power Flow). Then, to mitigate the MSCF issue by a high-level RL-based strategy, physics-informed reward, action, and state are devised. Besides, both shallow and deep neural network architectures are tested. Experiments on the IEEE 118-bus system by the proposed mitigation strategy demonstrate a promising performance in reducing system collapses.

cs.LG↗

arXiv2021

A Two-Level Simulation-Assisted Sequential Distribution System Restoration Model With Frequency Dynamics Constraints

This paper proposes a service restoration model for unbalanced distribution systems and inverter-dominated microgrids (MGs), in which frequency dynamics constraints are developed to optimize the amount of load restoration and guarantee the dynamic performance of system frequency response during the restoration process. After extreme events, the damaged distribution systems can be sectionalized into several isolated MGs to restore critical loads and tripped non-black start distributed generations (DGs) by black start DGs. However, the high penetration of inverter-based DGs reduces the system inertia, which results in low-inertia issues and large frequency fluctuation during the restoration process. To address this challenge, we propose a two-level simulation-assisted sequential service restoration model, which includes a mixed integer linear programming (MILP)-based optimization model and a transient simulation model. The proposed MILP model explicitly incorporates the frequency response into constraints, by interfacing with transient simulation of inverter-dominated MGs. Numerical results on a modified IEEE 123-bus system have validated that the frequency dynamic performance of the proposed service restoration model are indeed improved.

eess.SY↗

arXiv2020

Parallel Betweenness Computation in Graph Database for Contingency Selection

Parallel betweenness computation algorithms are proposed and implemented in a graph database for power system contingency selection. Principles of the graph database and graph computing are investigated for both node and edge betweenness computation. Experiments on the 118-bus system and a real power system show that speed-up can be achieved for both node and edge betweenness computation while the speeding effect on the latter is more remarkable due to the data retrieving advantages of the graph database on the power network data.

cs.DC↗

arXiv2019

Mitigating Multi-Stage Cascading Failure by Reinforcement Learning

This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is presented and its challenges are investigated. The problem is then tackled by the RL based on DC-OPF (Optimal Power Flow). Designs of the key elements of the RL framework (rewards, states, etc.) are also discussed in detail. Experiments on the IEEE 118-bus system by both shallow and deep neural networks demonstrate promising results in terms of reduced system collapse rates.

cs.LG↗