arXiv subjects

Nanpeng Yu

Publications and source records attributed to Nanpeng Yu.

At least 19 recordsLinked to original sources

arXiv2026

Coordinating GPU Data Centers and Power Grid Regulation Service for Exogenous Carbon Benefits

The rapid growth of AI/ML data centers has led to higher energy consumption and carbon emissions. The shift to renewable energy and growing data center energy demands can destabilize the power grid. Power grids rely on frequency regulation reserves, typically fossil-fueled power plants, to stabilize and balance the supply and demand of electricity. This paper sheds light on the hidden carbon emissions of frequency regulation service. Our work explores how modern GPU data centers can coordinate with power grids to reduce the need for fossil-fueled frequency regulation reserves. We first introduce a novel metric, Exogenous Carbon, to quantify grid-side carbon emission reductions resulting from data center participation in regulation service. We additionally introduce EcoCenter, a framework to maximize the amount of frequency regulation provision that GPU data centers can provide, and thus, reduce the amount of frequency regulation reserves necessary. We demonstrate that data center participation in frequency regulation can result in Exogenous carbon savings that can outweigh operational carbon emissions

cs.DC↗

arXiv2025

Stochastic Long-Term Joint Decarbonization Planning for Power Systems and Data Centers: A Case Study in PJM

With the rapid growth of artificial intelligence (AI) and cloud services, data centers have become critical infrastructures driving digital economies, with increasing energy demand heightening concerns over electricity use and carbon emissions, emphasizing the need for carbon-aware infrastructure planning. Most studies assume static power systems, focus only on operational emissions, and overlook co-optimization. This paper proposes a dynamic joint planning framework that co-optimizes long-term data center and power system development over 15 years. The model determines siting, capacity, and type of data centers alongside power generation expansion, storage deployment, and retirements, accounting for both operational and embodied emissions. To handle multi-scale uncertainty, a large-scale two-stage stochastic program is formulated and solved via an enhanced Benders decomposition. Applied to the PJM Interconnection, with curated datasets released on GitHub, results show the system can support up to 55 GW peak data center demand, with Virginia (DOM) and Northern Illinois (ComEd) as optimal hosts. Compared to non-joint planning, the framework cuts investment cost by 12.6%, operational cost by 8.25%, and emissions by 5.63%. Including lifecycle emissions further raises renewable deployment by 25.5%, highlighting embodied carbon's role in deeper decarbonization.

eess.SY↗

arXiv2025

Neural Two-Stage Stochastic Volt-VAR Optimization for Three-Phase Unbalanced Distribution Systems with Network Reconfiguration

The increasing integration of intermittent distributed energy resources (DERs) has introduced significant variability in distribution networks, posing challenges to voltage regulation and reactive power management. This paper presents a novel neural two-stage stochastic Volt-VAR optimization (2S-VVO) method for three-phase unbalanced distribution systems considering network reconfiguration under uncertainty. To address the computational intractability associated with solving large-scale scenario-based 2S-VVO problems, a learning-based acceleration strategy is introduced, wherein the second-stage recourse model is approximated by a neural network. This neural approximation is embedded into the optimization model as a mixed-integer linear program (MILP), enabling effective enforcement of operational constraints related to the first-stage decisions. Numerical simulations on a 123-bus unbalanced distribution system demonstrate that the proposed approach achieves over 50 times speedup compared to conventional solvers and decomposition methods, while maintaining a typical optimality gap below 0.30%. These results underscore the method's efficacy and scalability in addressing large-scale stochastic VVO problems under practical operating conditions.

eess.SY↗

arXiv2025

A Spatio-Temporal Graph Learning Approach to Real-Time Economic Dispatch with Multi-Transmission-Node DER Aggregation

The integration of distributed energy resources (DERs) into wholesale electricity markets, as mandated by FERC Order 2222, imposes new challenges on system operations. To remain consistent with existing market structures, regional transmission organizations (RTOs) have advanced the aggregation of transmission-node-level DERs (T-DERs), where a nodal virtual power plant (VPP) represents the mapping of all distribution-level DERs to their respective transmission nodes. This paper develops a real-time economic dispatch (RTED) framework that enables multi-transmission-node DER aggregation while addressing computational efficiency. To this end, we introduce a spatio-temporal graph convolutional network (ST-GCN) for adaptive prediction of distribution factors (DFs), thereby capturing the dynamic influence of individual T-DERs across the transmission system. Furthermore, an iterative constraint identification strategy is incorporated to alleviate transmission security constraints without compromising system reliability. Together, these innovations accelerate the market clearing process and support the effective participation of T-DER aggregators under current market paradigms. The proposed approach is validated on large-scale test systems, including modified 118-, 2383-, and 3012-bus networks under a rolling RTED setting with real demand data. Numerical results demonstrate significant improvements in reducing operational costs and maintaining transmission network feasibility, underscoring the scalability and practicality of the proposed framework.

eess.SY↗

arXiv2025

Carbon-Aware Optimal Power Flow with Data-Driven Carbon Emission Tracing

Quantifying locational carbon emissions in power grids is crucial for implementing effective carbon reduction strategies for customers relying on electricity. This paper presents a carbon-aware optimal power flow (OPF) framework that incorporates data-driven carbon tracing, enabling rapid estimation of nodal carbon emissions from electric loads. By developing generator-to-load carbon emission distribution factors through data-driven technique, the analytical formulas for both average and marginal carbon emissions can be derived and integrated seamlessly into DC OPF models as linear constraints. The proposed carbon-aware OPF model enables market operators to optimize energy dispatch while reducing greenhouse gas emissions. Simulations on IEEE test systems confirm the accuracy and computational efficiency of the proposed approach, highlighting its applicability for real-time carbon-aware system operations.

eess.SY↗

arXiv2025

A Neural Column-and-Constraint Generation Method for Solving Two-Stage Stochastic Unit Commitment

Two-stage stochastic unit commitment (2S-SUC) problems have been widely adopted to manage the uncertainties introduced by high penetrations of intermittent renewable energy resources. While decomposition-based algorithms such as column-and-constraint generation has been proposed to solve these problems, they remain computationally prohibitive for large-scale, real-time applications. In this paper, we introduce a Neural Column-and-Constraint Generation (Neural CCG) method to significantly accelerate the solution of 2S-SUC problems. The proposed approach integrates a neural network that approximates the second-stage recourse problem by learning from high-level features of operational scenarios and the first-stage commitment decisions. This neural estimator is embedded within the CCG framework, replacing repeated subproblem solving with rapid neural evaluations. We validate the effectiveness of the proposed method on the IEEE 118-bus system. Compared to the original CCG and a state-of-the-art commercial solver, Neural CCG achieves up to 130.1$\times$ speedup while maintaining a mean optimality gap below 0.096\%, demonstrating its strong potential for scalable stochastic optimization in power system.

eess.SY↗

arXiv2025

Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem

This paper proposes a neural stochastic optimization method for efficiently solving the two-stage stochastic unit commitment (2S-SUC) problem under high-dimensional uncertainty scenarios. The proposed method approximates the second-stage recourse problem using a deep neural network trained to map commitment decisions and uncertainty features to recourse costs. The trained network is subsequently embedded into the first-stage UC problem as a mixed-integer linear program (MILP), allowing for explicit enforcement of operational constraints while preserving the key uncertainty characteristics. A scenario-embedding network is employed to enable dimensionality reduction and feature aggregation across arbitrary scenario sets, serving as a data-driven scenario reduction mechanism. Numerical experiments on IEEE 5-bus, 30-bus, and 118-bus systems demonstrate that the proposed neural two-stage stochastic optimization method achieves solutions with an optimality gap of less than 1%, while enabling orders-of-magnitude speedup compared to conventional MILP solvers and decomposition-based methods. Moreover, the model's size remains constant regardless of the number of scenarios, offering significant scalability for large-scale stochastic unit commitment problems.

eess.SY↗

arXiv2024

Generating Synthetic Net Load Data with Physics-informed Diffusion Model

This paper presents a novel physics-informed diffusion model for generating synthetic net load data, addressing the challenges of data scarcity and privacy concerns. The proposed framework embeds physical models within denoising networks, offering a versatile approach that can be readily generalized to unforeseen scenarios. A conditional denoising neural network is designed to jointly train the parameters of the transition kernel of the diffusion model and the parameters of the physics-informed function. Utilizing the real-world smart meter data from Pecan Street, we validate the proposed method and conduct a thorough numerical study comparing its performance with state-of-the-art generative models, including generative adversarial networks, variational autoencoders, normalizing flows, and a well calibrated baseline diffusion model. A comprehensive set of evaluation metrics is used to assess the accuracy and diversity of the generated synthetic net load data. The numerical study results demonstrate that the proposed physics-informed diffusion model outperforms state-of-the-art models across all quantitative metrics, yielding at least 20% improvement.

cs.LG↗

arXiv2024

Joint Planning of Charging Stations and Power Systems for Heavy-Duty Drayage Trucks

As global concerns about climate change intensify, the transition towards zero-emission freight is becoming increasingly vital. Drayage is an important segment of the freight system, typically involving the transport of goods from seaports or intermodal terminals to nearby warehouses. This sector significantly contributes to not only greenhouse gas emissions, but also pollution in densely populated areas. This study presents a holistic optimization model designed for an efficient transition to zero-emission drayage, offering cost-effective strategies for the coordinated investment planning for power systems, charging infrastructure, and electric drayage trucks. The model is validated in the Greater Los Angeles area, where regulatory goals are among the most ambitious. Furthermore, the model's design allows for easy adaptation to other regions. By focusing on drayage trucks, this study also paves the way for future research into other freight categories, establishing a foundation for a more extensive exploration in this field.

math.OC↗

arXiv2024

Impact of Flexible and Bidirectional Charging in Medium- and Heavy-Duty Trucks on California's Decarbonization Pathway

California has committed to ambitious decarbonization targets across multiple sectors, including decarbonizing the electrical grid by 2045. In addition, the medium- and heavy-duty truck fleets are expected to see rapid electrification over the next two decades. Considering these two pathways in tandem is critical for ensuring cost optimality and reliable power system operation. In particular, we examine the potential cost savings of electrical generation infrastructure by enabling flexible charging and bidirectional charging for these trucks. We also examine costs adjacent to enabling these services, such as charger upgrades and battery degradation. We deploy a large mixed-integer decarbonization planning model to quantify the costs associated with the electric generation decarbonization pathway. Example scenarios governing truck driving and charging behaviors are implemented to reveal the sensitivity of temporal driving patterns. Our experiments show that cost savings on the order of multiple billions of dollars are possible by enabling flexible and bidirectional charging in medium- and heavy-duty trucks in California.

eess.SY↗

arXiv2024

On the Selection of Intermediate Length Representative Periods for Capacity Expansion

As the decarbonization of power systems accelerates, there has been increasing interest in capacity expansion models for their role in guiding this transition. Representative period selection is an important component of capacity expansion modeling, enabling computational tractability of optimization while ensuring fidelity between the representative periods and the full year. However, little attention has been devoted to selecting representative periods longer than a single day. This prevents the capacity expansion model from directly simulating interday energy sharing, which is of key importance as energy generation becomes more variable and storage more important. To this end, we propose a novel method for selecting representative periods of any length. The method is validated using a capacity expansion model and production cost model based on California's decarbonization goals. We demonstrate that the representative period length has a substantial impact in the results of the capacity expansion investment plan.

eess.SY↗

arXiv2023

Solve Large-scale Unit Commitment Problems by Physics-informed Graph Learning

Unit commitment (UC) problems are typically formulated as mixed-integer programs (MIP) and solved by the branch-and-bound (B&B) scheme. The recent advances in graph neural networks (GNN) enable it to enhance the B&B algorithm in modern MIP solvers by learning to dive and branch. Existing GNN models that tackle MIP problems are mostly constructed from mathematical formulation, which is computationally expensive when dealing with large-scale UC problems. In this paper, we propose a physics-informed hierarchical graph convolutional network (PI-GCN) for neural diving that leverages the underlying features of various components of power systems to find high-quality variable assignments. Furthermore, we adopt the MIP model-based graph convolutional network (MB-GCN) for neural branching to select the optimal variables for branching at each node of the B&B tree. Finally, we integrate neural diving and neural branching into a modern MIP solver to establish a novel neural MIP solver designed for large-scale UC problems. Numeral studies show that PI-GCN has better performance and scalability than the baseline MB-GCN on neural diving. Moreover, the neural MIP solver yields the lowest operational cost and outperforms a modern MIP solver for all testing days after combining it with our proposed neural diving model and the baseline neural branching model.

eess.SY↗

arXiv2023

Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models

The global deployment of the phasor measurement units (PMUs) enables real-time monitoring of the power system, which has stimulated considerable research into machine learning-based models for event detection and classification. However, recent studies reveal that machine learning-based methods are vulnerable to adversarial attacks, which can fool the event classifiers by adding small perturbations to the raw PMU data. To mitigate the threats posed by adversarial attacks, research on defense strategies is urgently needed. This paper proposes an effective adversarial purification method based on the diffusion model to counter adversarial attacks on the machine learning-based power system event classifier. The proposed method includes two steps: injecting noise into the PMU data; and utilizing a pre-trained neural network to eliminate the added noise while simultaneously removing perturbations introduced by the adversarial attacks. The proposed adversarial purification method significantly increases the accuracy of the event classifier under adversarial attacks while satisfying the requirements of real-time operations. In addition, the theoretical analysis reveals that the proposed diffusion model-based adversarial purification method decreases the distance between the original and compromised PMU data, which reduces the impacts of adversarial attacks. The empirical results on a large-scale real-world PMU dataset validate the effectiveness and computational efficiency of the proposed adversarial purification method.

eess.SY↗

arXiv2023

Optimizing Deep Decarbonization Pathways in California with Power System Planning Using Surrogate Level-based Lagrangian Relaxation

With California's ambitious goal to achieve decarbonization of the electrical grid by the year 2045, significant challenges arise in power system investment planning. Existing modeling methods and software focus on computational efficiency, which is currently achieved by simplifying the associated unit commitment formulation. This may lead to unjustifiable inaccuracies in the cost and constraints of gas-fired generation operations, and may affect both the timing and the extent of investment in new resources, such as renewable energy and energy storage. To address this issue, this paper develops a more detailed and rigorous mixed-integer model, and more importantly, a solution methodology utilizing surrogate level-based Lagrangian relaxation to overcome the combinatorial complexity that results from the enhanced level of model detail. This allows us to optimize a model with approximately 12 million binary and 100 million total variables in under 48 hours. The investment plan is compared with those produced by E3's RESOLVE software, which is currently employed by the California Energy Commission and California Public Utilities Commission. Our model produces an investment plan that differs substantially from that of the existing method and saves California over 12 billion dollars over the investment horizon.

eess.SY↗

arXiv2023

Toward Efficient Transportation Electrification of Heavy-Duty Trucks: Joint Scheduling of Truck Routing and Charging

The timely transportation of goods to customers is an essential component of economic activities. However, heavy-duty diesel trucks used for goods delivery significantly contribute to greenhouse gas emissions within many large metropolitan areas, including Los Angeles, New York, and San Francisco. To reduce GHG emissions by facilitating freight electrification, this paper proposes Joint Routing and Charging scheduling for electric trucks. The objective of the associated optimization problem is to minimize the cost of transportation, charging, and tardiness. A large number of possible combinations of road segments as well as a large number of combinations of charging decisions and charging durations leads to a combinatorial explosion in the possible decisions electric trucks can make. The resulting mixed-integer linear programming problem is thus extremely challenging because of the combinatorial complexity even in the deterministic case. Therefore, a Surrogate Level-Based Lagrangian Relaxation (SLBLR) method is employed to decompose the overall problem into significantly less complex truck subproblems. In the coordination aspect, each truck subproblem is solved independently of other subproblems based on the values of Lagrangian multipliers. In addition to serving as a means of guiding and coordinating trucks, multipliers can also serve as a basis for transparent and explanatory decision-making by trucks. Testing results demonstrate that even small instances cannot be solved using the off-the-shelf solver CPLEX after several days of solving. The SLBLR method, on the other hand, can obtain near-optimal solutions within a few minutes for small cases, and within 30 minutes for large ones. Furthermore, it has been demonstrated that as battery capacity increases, the total cost decreases significantly; moreover, as the charging power increases, the number of trucks required decreases as well.

eess.SY↗

arXiv2022

pmuBAGE: The Benchmarking Assortment of Generated PMU Data for Power System Events

This paper introduces pmuGE (phasor measurement unit Generator of Events), one of the first data-driven generative model for power system event data. We have trained this model on thousands of actual events and created a dataset denoted pmuBAGE (the Benchmarking Assortment of Generated PMU Events). The dataset consists of almost 1000 instances of labeled event data to encourage benchmark evaluations on phasor measurement unit (PMU) data analytics. PMU data are challenging to obtain, especially those covering event periods. Nevertheless, power system problems have recently seen phenomenal advancements via data-driven machine learning solutions. A highly accessible standard benchmarking dataset would enable a drastic acceleration of the development of successful machine learning techniques in this field. We propose a novel learning method based on the Event Participation Decomposition of Power System Events, which makes it possible to learn a generative model of PMU data during system anomalies. The model can create highly realistic event data without compromising the differential privacy of the PMUs used to train it. The dataset is available online for any researcher or practitioner to use at the pmuBAGE Github Repository: https://github.com/NanpengYu/pmuBAGE.

eess.SY↗

arXiv2022

Toward Robust Manufacturing Scheduling: Stochastic Job-Shop Scheduling

Manufacturing plays a significant role in economic development, production, exports, and job creation, which ultimately contribute to improving the quality of life. The presence of manufacturing defects is, however, inevitable leading to products being discarded, i.e. scrapped. In some cases, defective products can be repaired through rework. Scrap and rework cause a longer completion time, which can contribute to orders being shipped late. Moreover, the presence of uncertainties and combinatorial complexity significantly increases the difficulty of complex manufacturing scheduling. This paper tackles this challenge, exemplified by a case study on stochastic job-shop scheduling in low-volume, high-variety manufacturing contexts. To ensure on-time delivery, high-quality solutions are required, and near-optimal solutions must be obtained within strict time constraints to ensure smooth operations on the job-shop floor. To efficiently solve the stochastic job-shop scheduling (JSS) problem, a recently-developed Surrogate "Level-Based" Lagrangian Relaxation is used to reduce computational effort while efficiently exploiting the geometric convergence potential inherent to Polyak's stepsizing formula thereby leading to fast convergence. Numerical testing demonstrates that the new method is two orders of magnitude faster as compared to commercial solvers.

math.OC↗

arXiv2022

An Optimization Method-Assisted Ensemble Deep Reinforcement Learning Algorithm to Solve Unit Commitment Problems

Unit commitment (UC) is a fundamental problem in the day-ahead electricity market, and it is critical to solve UC problems efficiently. Mathematical optimization techniques like dynamic programming, Lagrangian relaxation, and mixed-integer quadratic programming (MIQP) are commonly adopted for UC problems. However, the calculation time of these methods increases at an exponential rate with the amount of generators and energy resources, which is still the main bottleneck in industry. Recent advances in artificial intelligence have demonstrated the capability of reinforcement learning (RL) to solve UC problems. Unfortunately, the existing research on solving UC problems with RL suffers from the curse of dimensionality when the size of UC problems grows. To deal with these problems, we propose an optimization method-assisted ensemble deep reinforcement learning algorithm, where UC problems are formulated as a Markov Decision Process (MDP) and solved by multi-step deep Q-learning in an ensemble framework. The proposed algorithm establishes a candidate action set by solving tailored optimization problems to ensure a relatively high performance and the satisfaction of operational constraints. Numerical studies on IEEE 118 and 300-bus systems show that our algorithm outperforms the baseline RL algorithm and MIQP. Furthermore, the proposed algorithm shows strong generalization capacity under unforeseen operational conditions.

eess.SY↗