arXiv subjects

Le Xie

Publications and source records attributed to Le Xie.

At least 37 records · Page 2Linked to original sources

arXiv2025

Data Center Control Against Sub-Synchronous Resonance: A Data-Driven Approach

Data centers host a variety of essential services such as cloud computing and artificial intelligence. Electric grid operators, however, have limited knowledge of the reliability risks of data center interconnection due to their unique operational characteristics. An emerging concern is the sub-synchronous resonance (SSR) which refer to unexpected voltage/current oscillations at typical frequencies below 60/50 Hz. It remains unknown whether and how the interactions between data centers and the grid may trigger resonances, equipment damages, and even cascading failures. In this paper, we focus on grid-connected data centers that draw electricity from the grid through power factor correction (PFC) converters. We conduct two-tone frequency sweep to investigate the data centers' impedance characteristics, i.e. magnitude and phase angle variations over frequencies, and showcase their deep dependence on compute workloads. The impedance modeling provides a direct approach to evaluating SSR risks and enable a cooperative mechanism to alarm and avoid resonance-prone situations. Building upon the impedance, a data-driven preventive controller is then established to raise early warnings of risky operation and suggest flexible workload management according to the given grid conditions. Through case study, we demonstrate how to use impedance to understand the unexpected interactions. Data-driven impedance is validated to show decent performance in capturing the unique impedance dips and tracking the impedance variations across a range of workload scenarios. The early warning and preventive control approaches are further effective to improve the safety margins with minimal workload rescheduling. The key findings of this work will provide valuable insights for grid operators and data center managers, and support preparation for future scenarios involving large-scale data center integration.

eess.SY↗

arXiv2025

Predictive Reliability Assessment of Distribution Grids with Residential Distributed Energy Resources

Distribution system end users are transforming from passive to active participants, marked by the push towards widespread adoption of edge-level Distributed Energy Resources (DERs). This paper addresses the challenges in distribution system planning arising from these dynamic changes. We introduce a bottom-up probabilistic approach that integrates these edge-level DERs into the reliability evaluation process. Our methodology leverages joint probability distributions to characterize and model the penetration of rooftop photovoltaic (PV) systems and energy storage across a distribution network at the individual residential level. Employing a scenario-based approach, we showcase the application of our probabilistic method using a Monte Carlo Simulation process to assess average system reliability indices and their variations at the user level. To validate our approach, we applied this methodology to the RBTS test system across various adoption scenarios, effectively showcasing the capability of our proposed method in quantifying the variation in end-user reliability indices for each scenario within the distribution system.

eess.SY↗

arXiv2025

Fréchet Power-Scenario Distance: A Metric for Evaluating Generative AI Models across Multiple Time-Scales in Smart Grids

Generative artificial intelligence (AI) models in smart grids have advanced significantly in recent years due to their ability to generate large amounts of synthetic data, which would otherwise be difficult to obtain in the real world due to confidentiality constraints. A key challenge in utilizing such synthetic data is how to assess the data quality produced from such generative models. Traditional Euclidean distance-based metrics only reflect pair-wise relations between two individual samples, and could fail in evaluating quality differences between groups of synthetic datasets. In this work, we propose a novel metric based on the Fréchet Distance (FD) estimated between two datasets in a learned feature space. The proposed method evaluates the quality of generation from a distributional perspective. Empirical results demonstrate the superiority of the proposed metric across timescales and models, enhancing the reliability of data-driven decision-making in smart grid operations.

cs.LG↗

arXiv2025

A Review of Safe Reinforcement Learning Methods for Modern Power Systems

Given the availability of more comprehensive measurement data in modern power systems, reinforcement learning (RL) has gained significant interest in operation and control. Conventional RL relies on trial-and-error interactions with the environment and reward feedback, which often leads to exploring unsafe operating regions and executing unsafe actions, especially when deployed in real-world power systems. To address these challenges, safe RL has been proposed to optimize operational objectives while ensuring safety constraints are met, keeping actions and states within safe regions throughout both training and deployment. Rather than relying solely on manually designed penalty terms for unsafe actions, as is common in conventional RL, safe RL methods reviewed here primarily leverage advanced and proactive mechanisms. These include techniques such as Lagrangian relaxation, safety layers, and theoretical guarantees like Lyapunov functions to rigorously enforce safety boundaries. This paper provides a comprehensive review of safe RL methods and their applications across various power system operations and control domains, including security control, real-time operation, operational planning, and emerging areas. It summarizes existing safe RL techniques, evaluates their performance, analyzes suitable deployment scenarios, and examines algorithm benchmarks and application environments. The paper also highlights real-world implementation cases and identifies critical challenges such as scalability in large-scale systems and robustness under uncertainty, providing potential solutions and outlining future directions to advance the reliable integration and deployment of safe RL in modern power systems.

eess.SY↗

arXiv2025

Unlocking Multi-Task Electric Energy System Intelligence: Data Scaling Laws and Performance with Limited Fine-Tuning

Data scaling has revolutionized research fields like natural language processing, computer vision, and robotics control, providing foundation models with remarkable multi-task and generalization capabilities. In this paper, we investigate whether similar data scaling laws exist in developing foundation models for power systems, and whether appropriate data scaling can yield multi-task, cross-timescales capabilities that can be deployed in \textit{unseen} operational scenarios. To this end, we conducted a comprehensive empirical study on data scaling by fine-tuning open-source foundation models using labeled data collected from diverse operational tasks and scenarios. We study how a foundation model's scenario generalization performance evolves with the number of training tasks, scenarios, and demonstrations. Our study involved collecting more than 450k demonstrations and implementing independent tests under a rigorous evaluation framework. Our findings reveal several key insights: First, the generalization performance of a fine-tuned foundation model follows an approximate power-law relationship with the number of demonstrations and scenarios. Second, the fine-tuned model also demonstrates impressive multi-task capabilities, where multi-task training shares similar performance improvements with single-task training as the number of demonstrations increases, without interference among tasks. Lastly, models with small parameter sizes could have strong performance as well. Model performance does not scale significantly with parameter size. These findings underscore the feasibility of developing multi-task foundation models tailored for power systems, demonstrating that while larger datasets and models generally improve performance, extreme scaling is unnecessary to achieve satisfactory outcomes.

eess.SY↗

arXiv2024

An Econometric Analysis of Large Flexible Cryptocurrency-mining Consumers in Electricity Markets

In recent years, power grids have seen a surge in large cryptocurrency mining firms, with individual consumption levels reaching 700MW. This study examines the behavior of these firms in Texas, focusing on how their consumption is influenced by cryptocurrency conversion rates, electricity prices, local weather, and other factors. We transform the skewed electricity consumption data of these firms, perform correlation analysis, and apply a seasonal autoregressive moving average model for analysis. Our findings reveal that, surprisingly, short-term mining electricity consumption is not directly correlated with cryptocurrency conversion rates. Instead, the primary influencers are the temperature and electricity prices. These firms also respond to avoid transmission and distribution network (T&D) charges - commonly referred to as four Coincident peak (4CP) charges - during the summer months. As the scale of these firms is likely to surge in future years, the developed electricity consumption model can be used to generate public, synthetic datasets to understand the overall impact on the power grid. The developed model could also lead to better pricing mechanisms to effectively use the flexibility of these resources towards improving power grid reliability.

eess.SY↗

arXiv2024

Unsupervised Congestion Status Identification Using LMP Data

Having a better understanding of how locational marginal prices (LMPs) change helps in price forecasting and market strategy making. This paper investigates the fundamental distribution of the congestion part of LMPs in high-dimensional Euclidean space using an unsupervised approach. LMP models based on the lossless and lossy DC optimal power flow (DC-OPF) are analyzed to show the overlapping subspace property of the LMP data. The congestion part of LMPs is spanned by certain row vectors of the power transfer distribution factor (PTDF) matrix, and the subspace attributes of an LMP vector uniquely are found to reflect the instantaneous congestion status of all the transmission lines. The proposed method searches for the basis vectors that span the subspaces of congestion LMP data in hierarchical ways. In the bottom-up search, the data belonging to 1-dimensional subspaces are detected, and other data are projected on the orthogonal subspaces. This procedure is repeated until all the basis vectors are found or the basis gap appears. Top-down searching is used to address the basis gap by hyperplane detection with outliers. Once all the basis vectors are detected, the congestion status can be identified. Numerical experiments based on the IEEE 30-bus system, IEEE 118-bus system, Illinois 200-bus system, and Southwest Power Pool are conducted to show the performance of the proposed method.

eess.SY↗

arXiv2024

Foundation Models for the Electric Power Grid

Foundation models (FMs) currently dominate news headlines. They employ advanced deep learning architectures to extract structural information autonomously from vast datasets through self-supervision. The resulting rich representations of complex systems and dynamics can be applied to many downstream applications. Therefore, FMs can find uses in electric power grids, challenged by the energy transition and climate change. In this paper, we call for the development of, and state why we believe in, the potential of FMs for electric grids. We highlight their strengths and weaknesses amidst the challenges of a changing grid. We argue that an FM learning from diverse grid data and topologies could unlock transformative capabilities, pioneering a new approach in leveraging AI to redefine how we manage complexity and uncertainty in the electric grid. Finally, we discuss a power grid FM concept, namely GridFM, based on graph neural networks and show how different downstream tasks benefit.

cs.LG↗

arXiv2024

Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models

Foundational Large Language Models (LLMs) such as GPT-3.5-turbo allow users to refine the model based on newer information, known as ``fine-tuning''. This paper leverages this ability to analyze AC-DC converter behaviors, focusing on the ripple current in DC-link capacitors. Capacitors degrade faster under high ripple currents, complicating life monitoring and necessitating preemptive replacements. Using minimal invasive noisy hardware measurements from a full bridge rectifier and 90W Power Factor Correction (PFC) boost converter, an LLM-based models to predict ripple content in DC-link currents was developed which demonstrated the LLMs' ability for near-accurate predictions. This study also highlights data requirements for precise nonlinear power electronic circuit parameter predictions to predict component degradation without any additional sensors. Furthermore, the proposed framework could be extended to any non-linear function mapping problem as well as estimating the capacitor Equivalent Series Resistance (ESR).

eess.SY↗

arXiv2024

The Role of Electric Grid Research in Addressing Climate Change

Addressing the urgency of climate change necessitates a coordinated and inclusive effort from all relevant stakeholders. Critical to this effort is the modeling, analysis, control, and integration of technological innovations within the electric energy system, which plays a crucial role in scaling up climate change solutions. This perspective article presents a set of research challenges and opportunities in the area of electric power systems that would be crucial in accelerating Gigaton-level decarbonization. Furthermore, it highlights institutional challenges associated with developing market mechanisms and regulatory architectures, ensuring that incentives are aligned for stakeholders to effectively implement the technological solutions on a large scale.

eess.SY↗

arXiv2024

Accelerating Chance-constrained SCED via Scenario Compression

This paper studies some compression methods to accelerate the scenario-based chance-constrained security-constrained economic dispatch (SCED) problem. In particular, we show that by exclusively employing the vertices after convex hull compression, an equivalent solution can be obtained compared to utilizing the entire scenario set. For other compression methods that might relax the original solution, such as box compression, this paper presents the compression risk validation scheme to assess the risk arising from the sample space. By quantifying the risk associated with compression, decision-makers are empowered to select either solution risk or compression risk as the risk metric, depending on the complexity of specific problems. Numerical examples based on the 118-bus system and synthetic Texas grids compare these two risk metrics. The results also demonstrate the efficiency of compression methods in both problem formulation and solving processes.

eess.SY↗

arXiv2024

The Transmission Value of Energy Storage and Fundamental Limitations

This study addresses the transmission value of energy storage in electric grids. The inherent connection between storage and transmission infrastructure is captured from a "cumulative energy" perspective, which enables the reformulating of the conventional optimization problem by employing line power flow as the decision variable. The study also establishes the theoretical limitations of both storage and transmission lines that can be replaced by each other, providing explicit closed-form expressions for the minimum capacity needed. As a key departure from conventional practice in which transmission lines are designed according to the peak power delivery needs, with sufficient storage capacity, the transmission line capacity can be designed based on the average power delivery needs. The models of this paper only rely on a few basic assumptions, paving the way for understanding future storage as a transmission asset market design. Numerical experiments based on 2-bus, modified RTS 24-bus, RTS-GMLC, and Texas synthetic power systems illustrate the results.

eess.SY↗

arXiv2024

Exploring the Capabilities and Limitations of Large Language Models in the Electric Energy Sector

Large Language Models (LLMs) as chatbots have drawn remarkable attention thanks to their versatile capability in natural language processing as well as in a wide range of tasks. While there has been great enthusiasm towards adopting such foundational model-based artificial intelligence tools in all sectors possible, the capabilities and limitations of such LLMs in improving the operation of the electric energy sector need to be explored, and this article identifies fruitful directions in this regard. Key future research directions include data collection systems for fine-tuning LLMs, embedding power system-specific tools in the LLMs, and retrieval augmented generation (RAG)-based knowledge pool to improve the quality of LLM responses and LLMs in safety-critical use cases.

eess.SY↗

arXiv2024

Sample Complexity of Chance Constrained Optimization in Dynamic Environment

We study the scenario approach for solving chance-constrained optimization in time-coupled dynamic environments. Scenario generation methods approximate the true feasible region from scenarios generated independently and identically from the actual distribution. In this paper, we consider this problem in a dynamic environment, where the scenarios are assumed to be drawn sequentially from an unknown and time-varying distribution. Such dynamic environments are driven by changing environmental conditions that could be found in many real-world applications such as energy systems. We couple the time-varying distributions using the Wasserstein metric between the sequence of scenario-generating distributions and the actual chance-constrained distribution. Our main results are bounds on the number of samples essential for ensuring the ex-post risk in chance-constrained optimization problems when the underlying feasible set is convex or non-convex. Finally, our results are illustrated on multiple numerical experiments for both types of feasible sets.

math.OC↗

arXiv2024

Efficient Scenario Generation for Chance-constrained Economic Dispatch Considering Ambient Wind Conditions

Scenario generation is an effective data-driven method for solving chance-constrained optimization while ensuring desired risk guarantees with a finite number of samples. Crucial challenges in deploying this technique in the real world arise due to the absence of appropriate risk-tuning models tailored for the desired application. In this paper, we focus on designing efficient scenario generation schemes for economic dispatch in power systems. We propose a novel scenario generation method based on filtering scenarios using ambient wind conditions. These filtered scenarios are deployed incrementally in order to meet desired risk levels while using minimum resources. In order to study the performance of the proposed scheme, we illustrate the procedure on case studies performed for both 24-bus and 118-bus systems with real-world wind power forecasting data. Numerical results suggest that the proposed filter-and-increment scenario generation model leads to a precise and efficient solution for the chance-constrained economic dispatch problem.

math.OC↗

arXiv2023

Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems

This paper addresses the problem of Neural Network (NN) based adaptive stability certification in a dynamical system. The state-of-the-art methods, such as Neural Lyapunov Functions (NLFs), use NN-based formulations to assess the stability of a non-linear dynamical system and compute a Region of Attraction (ROA) in the state space. However, under parametric uncertainty, if the values of system parameters vary over time, the NLF methods fail to adapt to such changes and may lead to conservative stability assessment performance. We circumvent this issue by integrating Model Agnostic Meta-learning (MAML) with NLFs and propose meta-NLFs. In this process, we train a meta-function that adapts to any parametric shifts and updates into an NLF for the system with new test-time parameter values. We demonstrate the stability assessment performance of meta-NLFs on some standard benchmark autonomous dynamical systems.

eess.SY↗

arXiv2023

Electromagnetic Transient Model of Cryptocurrency Mining Loads for Low-Voltage Ride Through Assessment in Transmission Grids

In this paper, we developed an Electromagnetic Transient (EMT) model tailored for large cryptocurrency mining loads to understand the cross-interaction of these loads with the electric grid. The load model has been built using Electromagnetic Transients Program (EMTP) software. We have cross-validated the performance of the EMT model of the load with commercial application-specific integrated circuit miners, typically used by large-scale mining facilities, by comparing their low-voltage ride-through (LVRT) capabilities. Subsequently, LVRT capabilities of the large-scale miners have been tested against various fault scenarios both within the miner's remote facility as well as at one of the distant buses of the interconnected grid. The significance of this model lies in its scalability to accommodate larger blocks of mining loads and its seamless integration into a larger electric grid.

eess.SY↗

arXiv2023

Voltage Constrained Heavy Duty Vehicle Electrification: Formulation and Case Study

The electrification of heavy-duty vehicles (HDEVs) is a rapidly emerging avenue for decarbonization of energy and transportation sectors. Compared to light duty vehicles, HDEVs exhibit unique travel and charging patterns over long distances. In this paper, we formulate an analytically tractable model that considers the routing decisions for the HDEVs and their charging implications on the power grid. Our model captures the impacts of increased vehicle electrification on the transmission grid, with particular focus on HDEVs. We jointly model transportation and power networks coupling them through the demand generated for charging requirements of HDEVs. In particular, the voltage constraint violation is explicitly accounted for in the proposed model given the signifcant amount of charging power imposed by HDEVs. We obtain optimal routing schedules and generator dispatch satisfying mobility constraints of HDEVs while minimizing voltage violations in electric transmission network. Case study based on an IEEE 24-bus system is presented using realistic data of transit data of HDEVs. The numerical results suggest that the proposed model and algorithm effectively mitigate the voltage violation when a significant amount of HDEVs are integrated to the power transmission network. Such mitigation includes reduction in the voltage magnitude, geographical dispersion of voltage violations and worst-case voltage violations at critical nodes.

eess.SY↗