Search arXiv⌕ Search

arXiv subjects

Pedro P. Vergara

Publications and source records attributed to Pedro P. Vergara.

At least 19 recordsLinked to original sources
arXiv2026

Reinforcement Learning to Initialize Newton-Raphson for AC Power Flow with Quantum Annealing-Based Environment Updates

The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance deteriorates under poor initialization or extreme operating scenarios, e.g., high levels of renewable energy penetration. We propose the use of reinforcement learning (RL) to optimize the initialization of NR, and introduce a quantum-enhanced RL environment update mechanism that addresses the combinatorially large action space at each RL timestep by formulating the voltage adjustment task as a Quadratic Unconstrained Binary Optimization (QUBO) problem, solved with an Ising machine. RL initialization is benchmarked against flat start and start from the DC (linearized) PF solution on a standard 4-bus system, Iwamoto's ill-conditioned 11-bus system, and the IEEE 118-bus system under normal and stressed loading and reactive power limits, with verified operational solutions. On all systems, a supervised initializer refined by RL requires fewer NR iterations than flat and DC starts and than the same initializer without RL, for all seeds. For example, on the 118-bus system under normal and stressed loading, it reached 2.04 and 2.86 NR iterations, compared with 3.02 and 5.13 from DC start and 2.61 and 3.09 without RL. In wall-clock time, this pays off only for an initializer integrated into the solver and reused for many solves on a fixed topology. On the 4-bus system, a quantum-enhanced RL agent with a quantum-inspired annealer moved challenging initial states that required 29 and 44 NR iterations to initializations that required three NR iterations within one RL timestep.

eess.SY↗
arXiv2026

Estimating Density Functions for Probabilistic Power Flow Using Invertible Neural Networks

Probabilistic power flow (PPF) is essential for quantifying operational uncertainty in modern power systems with high penetrations of renewable generation and flexible loads. Conventional PPF methods primarily rely on Monte Carlo (MC)- based power flow (PF) simulations or simplified approximations of voltage probability density functions. Although MC methods provide high accuracy, they incur substantial computational and data-storage costs, whereas simplified approximations often sacrifice accuracy. In this paper, we propose a novel PPF density approximation framework that avoids repeated PF simulations during inference and can, in principle, approximate complex voltage distributions without restrictive distributional assumptions. The core idea is to learn an explicit invertible mapping between stochastic power injections and system voltages using invertible neural networks (INNs). By combining this mapping with the change-of-variables theorem, the proposed framework directly evaluates voltage probability densities without repeatedly solving the PF equations. Extensive numerical studies demonstrate that the proposed framework achieves state-of-the-art performance both as an accurate PF surrogate and as an efficient PPF density estimator.

eess.SY↗
arXiv2026

Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Agent

Recent studies use Large language models (LLMs) to simulate human opinions and decisions by prompting models with demographic, attitudinal, or persona-based descriptions. Yet such simulations rarely model the practical, cognitive, or social frictions that shape how people respond to policy interventions. Perceived transaction cost (PTC) provides a useful lens for modeling the practical frictions that shape policy responses, such as information burden, administrative effort, coordination demands, and perceived uncertainty. We use this lens to develop a friction-aware persona modeling approach for LLM-based simulation. In the context of energy-efficient renovation (EER), tenants are represented not only by who they are demographically, but by how they perceive the costs, benefits, barriers, and uncertainties associated with proposed renovation plans. Using survey data collected from 1,068 citizens in the Netherlands, comprising approximately 40,548 survey question and answer pairs, we compare prompt-only and fine-tuned settings across GPT-3.5-turbo, Ministral-8B-Instruct, and Llama-3.1-8B-Instruct, and evaluate supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) for local open-weight models. Results show that incorporating PTC-based personas and reasoning consistently improves model performance across both prompt-only and fine-tuned settings, suggesting that PTC-based persona design provides a useful bridge between institutional policy theory and interpretable LLM-based policy simulation. Code is available at https://github.com/xiaweijie1996/socialagent.

cs.AI↗
arXiv2026

A Dynamic Capacity Allocation Model for DERs under Non-Firm Connection Agreements

The growing penetration of distributed energy resources (DERs) intensifies congestion in distribution networks by introducing bidirectional power flows and increasing competition for limited network capacity, underscoring the need for effective and efficient congestion management, including flexible grid-access schemes. This paper proposes a bilevel optimization model for the dynamic allocation of connection capacity to DERs under non-firm connection agreements, aligning the objectives of distribution system operator (DSO) and DER owners. The upper-level problem, representing the DSO, determines the allocated connection capacity for all DERs, defined as maximum time-varying power limits, subject to distribution system constraints and the last-in-first-out (LIFO) allocation rule. The lower-level problem, representing DER owners, maximizes the profit of each DER within the allocated power limits. The proposed model is tested on a modified CIGRE medium-voltage (MV) network, demonstrating a balanced trade-off between grid utilization and economic efficiency. Furthermore, the model enhances DER integration, enforces transparent allocation rules, reduces variability in allocation patterns, and achieves up to an 80% reduction in total curtailment costs compared with benchmark methods.

eess.SY↗
arXiv2026

Quantum Hardware-in-the-Loop for Optimal Power Flow in Renewable-Integrated Power Systems

Quantum computing has emerged as a promising computational paradigm to address unresolved challenges in the modeling and control of modern power systems. However, most existing studies focus on offline simulations, and a practical framework for validating quantum algorithms in real-time operational environments remains lacking. This study proposes a quantum hardware-in-the-loop framework that integrates a real-time digital simulator with quantum and quantum-inspired hardware to solve combinatorial power flow and optimal power flow formulations under dynamic operating conditions. The proposed framework is validated using the IEEE 9-bus test system and a modified version with integrated solar and wind farms. The results confirm successful integration and convergence within a predefined tolerance. The study also identifies key limitations and challenges, such as limited access to quantum and digital annealers and current scalability limitations, that must be considered in future developments. Nevertheless, the results highlight the potential of quantum computing to significantly enhance the modeling and control of future power systems with high penetration of renewable energy sources.

eess.SY↗
arXiv2026

Transformer-based few-shot learning for modeling Electricity Consumption Profiles with minimal data across thousands of domains

Electricity Consumption Profiles (ECPs) are crucial for operating and planning power distribution systems, especially with the increasing number of low-carbon technologies such as solar panels and electric vehicles. Traditional ECP modeling methods typically assume the availability of sufficient ECP data. However, in practice, the accessibility of ECP data is limited due to privacy issues or the absence of metering devices. Few-shot learning (FSL) has emerged as a promising solution for ECP modeling in data-scarce scenarios. Nevertheless, standard FSL methods, such as those used for images, are unsuitable for ECP modeling because (1) these methods usually assume several source domains with sufficient data and several target domains. However, in the context of ECP modeling, there may be thousands of source domains, e.g., households with a moderate amount of data, and thousands of target domains, e.g., households that ECP are required to be modeled. (2) Standard FSL methods usually involve cumbersome knowledge transfer mechanisms, such as pre-training and fine-tuning. To address these limitations, this paper proposes a novel FSL framework that integrates Transformers with Gaussian Mixture Models (GMMs) for ECP modeling. The proposed approach is fine-tuning-free, computationally efficient, and robust even with extremely limited data. Results show that our method can accurately restore the complex ECP distribution with a minimal amount of ECP data (e.g., only 1.6% of the complete domain dataset) and outperforms state-of-the-art time series modeling methods in the context of ECP modeling.

cs.LG↗
arXiv2026

Risk-Based PV-Rich Distribution System Planning Using Generative AI

Hosting capacity (HC) assessment plays a critical role in distribution system planning under increasing penetration of distributed energy resources (DERs) and associated uncertainties in load and generation. However, conventional approaches often rely on deterministic worst-case evaluation, leading to overly conservative HC estimates. This paper introduces a risk-based framework for HC assessment that explicitly accounts for the frequency, intensity, and duration of voltage violations under uncertain operating conditions. A generative AI-based approach is employed to generate realistic, time-correlated load demand scenarios conditioned on projected energy consumption growth levels. These scenarios are then used to assess voltage violations and quantify their risk using probabilistic intensity, duration, and frequency (IDF) metrics. The results show that extreme-percentile (zero-risk) approaches significantly underestimate PV-HC by treating all violations equally, regardless of their likelihood or persistence. For instance, allowing a 5% risk level increases HC by approximately 18% for a 15 min violation duration. The proposed approach provides a practical tool for risk-informed distribution system planning under uncertainty.

eess.SY↗
arXiv2026

Foundation Twins: A New Generation of Power Systems Digital Twins using Foundation AI Models

Power systems are inherently multi-timescale systems, with different physical phenomena and decision-making processes spanning multiple timescales, time horizons, and geographic scopes. I envision power systems digital twins (DTs) as powerful modeling and simulation tools that can accelerate and improve decision-making across different time scales and geographic scopes. However, until now, research has not delivered such a vision, and power systems DTs remain a concept distant from implementation. This is not a regular research paper. This is a position paper that outlines my vision for developing a new generation of power systems DTs that leverage recent advances in artificial intelligence (AI) and machine learning (ML). I call these Foundation Twins. Foundation Twins combines the generalization features of foundation models with the decision-making capabilities of reinforcement learning (RL) architectures to deliver the envisioned power systems DTs.

eess.SY↗
arXiv2026

Community-to-Vehicle: Integrating Electric Vehicles into Energy Communities -- A Swiss Case Study

The institutional separation between local energy communities and public electric vehicle (EV) charging limits the efficient use of locally generated renewable energy. This paper introduces the concept of community-to-vehicle (C2V) as an institutional design mechanism to bridge this gap by enabling EV charging within the community boundary, where locally generated photovoltaic (PV) surplus is preferentially allocated and offered to external users at a community charging price. Building on the recently introduced local electricity community framework in Switzerland, we design scenarios that capture the transition from full separation to coordinated EV charging and evaluate their impacts on EV users and the community. The results show that C2V significantly improves local PV utilization and enhances economic performance, reducing EV charging costs relative to commercial alternatives while generating additional revenue streams for the community. These findings highlight the potential of C2V as a practical, implementable mechanism for integrating EV charging into local energy communities, providing a clear pathway for adopting coordinated community-EV interaction within existing regulatory frameworks.

eess.SY↗
arXiv2026

SAVGO: Learning State-Action Value Geometry with Cosine Similarity for Continuous Control

While representation and similarity learning have improved the sample efficiency of Reinforcement Learning (RL), they are rarely used to shape policy updates directly in the action space. To bridge this gap, a geometry-aware RL algorithm that explicitly incorporates value-based similarity into the policy update, State-Action Value Geometry Optimization (SAVGO), is proposed. In detail, SAVGO learns a joint state-action embedding space in which pairs with similar action-value estimates exhibit high cosine similarity, while dissimilar pairs are mapped to distinct directions. This learned geometry enables the generation of a similarity kernel over candidate actions sampled at each update, allowing policy improvement to be guided directly toward higher-value regions beyond local gradient-based updates. As a result, representation learning, value estimation, and policy optimization are unified within a single geometry-consistent objective, while preserving the scalability of off-policy actor-critic training. The proposed method is evaluated on standard MuJoCo continuous-control benchmarks, demonstrating improvements over strong baselines on challenging high-dimensional tasks. Ablation studies are done to analyze the contributions of value-geometry learning and similarity-based policy updates.

cs.LG↗
arXiv2026

Learning to Route Electric Trucks Under Operational Uncertainty

Electric truck operations require routing decisions that remain feasible under limited battery range, long charging times, travel and energy consumption, and competition for shared charging infrastructure. These features make electric truck routing a coupled logistics and energy problem, limiting the practicality of heuristics-based methods and rendering them computationally infeasible at scale. This paper proposes a learning-based framework for the stochastic electric truck routing under charging constraints and operational uncertainty. The problem, solved by Reinforcement Learning, is formulated as an event-driven semi-Markov decision process with shared charging resources, stochastic travel and energy requirements, and realistic nonlinear fast-charging behavior. To support learning in this setting, a graph-based representation of system state and feasible decisions is introduced, together with a rule-based action mask that restricts policies to operationally admissible actions; thus, improving training efficiency. Building on this formulation, an event-driven simulation environment is developed that supports both Reinforcement Learning and benchmarking against heuristic and mathematical programming baselines. Computational experiments across a range of fleet sizes show that the proposed learning-based algorithm consistently outperforms baselines and attains performance close to optimization benchmarks in many settings, while preserving high success rates under charging congestion and uncertainty.

eess.SY↗
arXiv2026

A Framework for Solving Continuous Energy and Power System Problems using Adiabatic Quantum Computing

The increasing scale and nonlinearity of modern energy and power system problems pose significant challenges to classical numerical solvers. In parallel, advances in quantum and quantum-inspired hardware are expected to improve scalability and offer performance advantages for large-scale optimization problems. Therefore, we propose a novel combinatorial optimization framework that reformulates continuous energy and power system problems into a format executable on quantum/digital annealers. The proposed framework accommodates both real and complex numbers and can represent both linear and nonlinear equations. As a proof of concept, we demonstrate its use in three applications: (i) 2D steady conductive heat transfer for a plate with constant temperature at each edge, where coefficient and boundary condition matrices are developed to solve linear system of equations, (ii) power system parameter identification, where the admittance matrix is estimated given voltage and current measurements, and (iii) power flow analysis, which solves the governing equations for active and reactive power balance. As a proof of concept, the applications are run on small test cases. The results show that the framework effectively and efficiently addresses the three applications and therefore suggest its potential to solve a wide range of energy and power system problems.

cs.ET↗
arXiv2026

Robust Operation of Distribution Networks: Generalized Uncertainty Modelling in Confidence-Level-Based Information Gap Decision

This paper studies the robust optimal operation of distribution networks (DNs) under renewable generation and load demand uncertainties, seeking an improved trade-off between robustness and economic performance. Building upon information gap decision theory (IGDT), a generalized uncertainty modelling is proposed to enhance the expressiveness of the uncertainty characterization. The proposed modelling captures both symmetric and asymmetric uncertainty features, and supports linear or nonlinear expansion of the uncertainty sets driven by confidence level. This advancement leads to the development of a confidence-level-based IGDT (CL-IGDT) framework for DN operation. To solve the resulting model, its equivalence to a family of two-stage robust optimization problems (TSROs) is established, enabling a Fibonacci search over the confidence level. To further improve computational efficiency, a cut-recycling strategy is proposed to exploit invariant information across TSROs. These techniques are integrated into a novel Fibonacci-Parametric Column-and-Constraint Generation algorithm with guaranteed asymptotic convergence. Case studies validate the effectiveness of the proposed framework and demonstrate the performance advantages of the proposed algorithm.

eess.SY↗
arXiv2026

A data-driven approach for topology correction in low voltage distribution networks with PVs

Most existing phase balancing and topology reconfiguration problems are formulated as mixed-integer optimization problems that depend on network topologies~\cite{10098964,11017695,10571996}. However, these topologies are often inaccurate and outdated for distribution system operators~(DSOs) due to missing recordings, topology maintenance and reconfiguration, such as congestion management ~\cite{vanin2024phase}. Thus, the topology of the low-voltage distribution network (LVDN) needs to be checked and corrected when it is outdated. The increasing uncertainty of distributed energy resources (DERs), including household photovoltaic (PV), heating pumps, etc., impacts the frequency of topology reconfiguration and challenges the correction of the low-voltage distribution network topology~\cite{10026490, 10347462, 10475702}. Moreover, the available smart meter (SM) datasets are often limited due to privacy concerns and random communication channel failure, challenging the topology correction~\cite{9696306, costa2022identification, dande2025consumer}. Synthetic European networks and benchmark models presented in~\cite{birchfield2016grid,2020Non} are benchmarks for research but insufficient to represent the diversity of European LVDNs for practical use by DSOs (e.g., state estimation). Thus, practical topology identification and correction approaches are required for real-time topology updating for active management of LVDNs.

eess.SY↗
arXiv2026

Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks

Optimal dispatch of energy storage systems (ESSs) in distribution networks involves jointly improving operating economy and voltage security under time-varying conditions and possible topology changes. To support fast online decision making, we develop a topology-aware Reinforcement Learning architecture based on Twin Delayed Deep Deterministic Policy Gradient (TD3), which integrates graph neural networks (GNNs) as graph feature encoders for ESS dispatch. We conduct a systematic investigation of three GNN variants: graph convolutional networks (GCNs), topology adaptive graph convolutional networks (TAGConv), and graph attention networks (GATs) on the 34-bus and 69-bus systems, and evaluate robustness under multiple topology reconfiguration cases as well as cross-system transfer between networks with different system sizes. Results show that GNN-based controllers consistently reduce the number and magnitude of voltage violations, with clearer benefits on the 69-bus system and under reconfiguration; on the 69-bus system, TD3-GCN and TD3-TAGConv also achieve lower saved cost relative to the NLP benchmark than the NN baseline. We also highlight that transfer gains are case-dependent, and zero-shot transfer between fundamentally different systems results in notable performance degradation and increased voltage magnitude violations. This work is available at: https://github.com/ShuyiGao/GNNs_RL_ESSs and https://github.com/distributionnetworksTUDelft/GNNs_RL_ESSs.

cs.LG↗
arXiv2026

Power flow and optimal power flow using quantum and digital annealers: a computational scalability analysis

This study further explores reformulating power flow (PF) analysis as a discrete combinatorial optimization problem, proposed in our earlier study using the Adiabatic Quantum Power Flow (AQPF) algorithm, which can be executed on Ising machines, including quantum and quantum-inspired hardware. This approach provides a new representation of the underlying equations, analogous to how neural networks approximate complex functions using simple operations. While the resulting combinatorial optimization problem is NP-hard, it is compatible with emerging quantum hardware designed to address such complexity. We introduce the Adiabatic Quantum Optimal Power Flow (AQOPF) algorithm, which transforms the classical optimal power flow (OPF) equations into quadratic unconstrained binary optimization (QUBO) models. Furthermore, the AQPF and AQOPF algorithms are evaluated on standard test cases ranging from 4- to 1354-bus systems using D-Wave's Advantage\texttrademark\ system (QA), its hybrid quantum-classical solver (HA), and Fujitsu's third-generation Digital Annealer (DAv3) and Quantum-Inspired Integrated Optimization (QIIO) platform. Both full and partitioned formulations are investigated, with particular attention to scalability and robustness in ill-conditioned scenarios. The results demonstrate that the algorithms can reproduce feasible PF and OPF solutions and exhibit promising computational scalability when supported by scalable hardware.

eess.SY↗
arXiv2026

Performance Comparison of Gate-Based and Adiabatic Quantum Computing for AC Power Flow Problem

We present the first direct comparison between gate-based quantum computing (GQC) and adiabatic quantum computing (AQC) paradigms for solving the AC power flow (PF) equations. The PF problem is reformulated as a combinatorial optimization problem. For the GQC approach, the Quantum Approximate Optimization Algorithm (QAOA) is employed, while for the AQC approach, the problem is formulated as an Ising model. Numerical experiments on a 4-bus test system evaluate solution accuracy and computational performance. Results obtained using QAOA are benchmarked against those produced by D-Wave's Advantage system and Fujitsu's latest-generation Digital Annealer, implemented through the Quantum-Inspired Integrated Optimization (QIIO) software. The findings provide quantitative insights into the performance trade-offs, scalability, and practical viability of GQC and AQC paradigms for PF analysis, highlighting the potential of quantum optimization algorithms to address the computational challenges associated with the operation of modern electricity grids in the fault-tolerant era.

quant-ph↗
arXiv2026

SmartMeterFM: Unifying Smart Meter Data Generative Tasks Using Flow Matching Models

Smart meter data is the foundation for planning and operating the distribution network. Unfortunately, such data are not always available due to privacy regulations. Meanwhile, the collected data may be corrupted due to sensor or transmission failure, or it may not have sufficient resolution for downstream tasks. A wide range of generative tasks is formulated to address these issues, including synthetic data generation, missing data imputation, and super-resolution. Despite the success of machine learning models on these tasks, dedicated models need to be designed and trained for each task, leading to redundancy and inefficiency. In this paper, by recognizing the powerful modeling capability of flow matching models, we propose a new approach to unify diverse smart meter data generative tasks with a single model trained for conditional generation. The proposed flow matching models are trained to generate challenging, high-dimensional time series data, specifically monthly smart meter data at a 15 min resolution. By viewing different generative tasks as distinct forms of partial data observations and injecting them into the generation process, we unify tasks such as imputation and super-resolution with a single model, eliminating the need for re-training. The data generated by our model not only are consistent with the given observations but also remain realistic, showing better performance against interpolation and other machine learning based baselines dedicated to the tasks.

cs.LG↗