arXiv subjects

Guilherme Vieira Hollweg

Publications and source records attributed to Guilherme Vieira Hollweg.

6 recordsLinked to original sources

arXiv2026

Optimal Demand Response-Based Energy Management for Campus Buildings with Battery Energy Storage Systems: A Case Study of the ELB Building

Buildings account for a significant portion of global electricity consumption, making demand response (DR) an effective strategy for reducing energy costs and improving grid flexibility. This paper presents an optimal energy management framework for a campus building that integrates demand response and battery energy storage systems (BESS) to minimize electricity costs while satisfying operational constraints and occupant comfort requirements. The proposed optimization model schedules building loads and battery charging/discharging based on time-varying electricity prices and building demand profiles. The framework is validated using the Engineering Laboratory Building (ELB) at the University of Michigan-Dearborn as a real-world case study. Four operating scenarios are investigated: (i) baseline operation, (ii) demand response without battery energy storage, (iii) battery energy storage, and (iv) demand response with battery energy storage. Simulation results demonstrate that demand alone reduces the building's electricity cost by approximately 12% compared with conventional operation. When battery energy storage is incorporated, the total electricity cost reduction increases to approximately 26%, highlighting the significant economic benefits of coordinated demand response and energy storage scheduling. The results demonstrate that integrating battery energy storage with demand response substantially enhances the operational flexibility of campus buildings and provides an effective solution for cost-effective and sustainable building energy management.

eess.SY↗

arXiv2026

Scalable Impedance Identification of Diverse IBRs via Cluster-Specialized Neural Networks

Modern machine learning approaches typically identify the impedance of a single inverter-based resource (IBR) and assume similar impedance characteristics across devices. In modern power systems, however, IBRs will employ diverse control topologies and algorithms, leading to highly heterogeneous impedance behaviors. Training one model per IBR is inefficient and does not scale. This paper proposes a scalable impedance identification framework for diverse IBRs via cluster-specialized neural networks. First, the dataset is partitioned into multiple clusters with similar feature profiles using the K-means clustering method. Then, each cluster is assigned a specialized feed-forward neural network (FNN) tailored to its characteristics, improving both accuracy and computational efficiency. In deployment, only a small number of measurements are required to predict impedance over a wide range of operating points. The framework is validated on six IBRs with varying control bandwidths, control structures, and operating conditions, and further tested on a previously unseen IBR using only ten measurement points. The results demonstrate high accuracy in both the clustering and prediction stages, confirming the effectiveness and scalability of the proposed method.

eess.SY↗

arXiv2025

ANN-Based Grid Impedance Estimation for Adaptive Gain Scheduling in VSG Under Dynamic Grid Conditions

In contrast to grid-following inverters, Virtual Synchronous Generators (VSGs) perform well under weak grid conditions but may become unstable when the grid is strong. Grid strength depends on grid impedance, which unfortunately varies over time. In this paper, we propose a novel adaptive gain-scheduling control scheme for VSGs. First, an Artificial Neural Network (ANN) estimates the fundamental-frequency grid impedance; then these estimates are fed into an adaptive gain-scheduling function to recalculate controller parameters under varying grid conditions. The proposed method is validated in Simulink and compared with a conventional VSG employing fixed controller gains. The results demonstrate that settling times and overshoot percentages remain consistent across different grid conditions. Additionally, previously unseen grid impedance values are estimated with high accuracy and minimal time delay, making the approach well suited for real-time gain-scheduling control.

eess.SY↗

arXiv2025

Enhancing Forecasting Accuracy in Dynamic Environments via PELT-Driven Drift Detection and Model Adaptation

Accurate time series forecasting models are often compromised by data drift, where underlying data distributions change over time, leading to significant declines in prediction performance. To address this challenge, this study proposes an adaptive forecasting framework that integrates drift detection with targeted model retraining to compensate for drift effects. The framework utilizes the Pruned Exact Linear Time (PELT) algorithm to identify drift points within the feature space of time series data. Once drift intervals are detected, selective retraining is applied to prediction models using Multilayer Perceptron (MLP) and Lasso Regressor architectures, allowing the models to adjust to changing data patterns. The effectiveness of the proposed approach is demonstrated on two datasets: a real-world dataset containing electricity consumption and HVAC system data, and a synthetic financial dataset designed to test cross-domain applicability. Initial baseline models were developed without drift detection using extensive feature engineering. After integrating drift-aware retraining, the MLP model achieved a 44% reduction in mean absolute error (MAE) and a 39% increase in R^2 on the real-world dataset, while even greater improvements were observed on the synthetic financial dataset. Similar enhancements were achieved with the Lasso Regressor. These results highlight the robustness and generalizability of incorporating drift detection and adaptive retraining to sustain forecasting accuracy across diverse domains.

eess.SY↗

arXiv2025

PSO-based Sliding Mode Current Control of Grid-Forming Inverter in Rotating Frame

The Grid-Forming Inverter (GFMI) is an emerging topic that is attracting significant attention from both academic and industrial communities, particularly in the area of control design. The Decoupled Average Model-based Sliding Mode Current Controller (DAM-SMC) has been used to address the need such as fast response, fixed switching frequency, and no overshoot to avoid exceeding current limits. Typically, the control parameters for DAM-SMC are chosen based on expert knowledge and certain assumptions. However, these parameters may not achieve optimized performance due to system dynamics and uncertainties. To address this, this paper proposes a Particle Swarm Optimization (PSO)-based DAM-SMC controller, which inherits the control laws from DAM-SMC but optimizes the control parameters offline using PSO. The main goal is to reduce chattering and achieve smaller tracking errors. The proposed method is compared with other metaheuristic optimization algorithms, such as Genetic Algorithm (GA) and Simulated Annealing (SA). Simulations are performed in MATLAB/Simulink across various scenarios to evaluate the effectiveness of the proposed controller. The proposed approach achieves a substantial reduction in convergence time, decreasing it by 86.36% compared to the GA and by 88.89% compared to SA. Furthermore, the tracking error is reduced by 11.61% compared to the conventional DAM-SMC algorithm. The robustness of the proposed method is validated under critical conditions, where plant and control model parameters varied by up to 40%.

eess.SY↗

arXiv2024

A Critical Review of Safe Reinforcement Learning Techniques in Smart Grid Applications

The high penetration of distributed energy resources (DERs) in modern smart power systems introduces unforeseen uncertainties for the electricity sector, leading to increased complexity and difficulty in the operation and control of power systems. As a cutting-edge machine learning technology, deep reinforcement learning (DRL) has been widely implemented in recent years to handle the uncertainty in power systems. However, in critical infrastructures such as power systems, safety issues always receive top priority, while DRL may not always meet the safety requirements of power system operators. The concept of safe reinforcement learning (safe RL) is emerging as a potential solution to overcome the shortcomings of conventional DRL in the operation and control of power systems. This study provides a rigorous review of the latest research efforts focused on safe RL to derive power system control policies while accounting for the unique safety requirements of power grids. Furthermore, this study highlights various safe RL algorithms applied in diverse applications within the power system sector, from single grid-connected power converters, residential smart homes, and buildings to large power distribution networks. For all methods outlined, a discussion on their bottlenecks, research challenges, and potential opportunities in the operation and control of power system applications is also presented. This review aims to support research in the area of safe RL algorithms, embracing smart power system operation with safety constraints amid high uncertainty from DERs.

eess.SY↗