arXiv subjects

Gabriel Intriago

Publications and source records attributed to Gabriel Intriago.

4 recordsLinked to original sources

arXiv2024

Power System Quasi-Steady State Estimation: An Echo State Network Approach

The operating point of a power system may change due to slow enough variations of the power injections. Rotating machines in the bulk system can absorb smooth changes in the dynamic states of the system. In this context, we present a novel reservoir computing (RC) method for estimating power system quasi-steady states. By exploiting the behavior of an RC-based recurrent neural network, the proposed method can capture the inherent nonlinearities in the power flow equations. Our approach is compared with traditional methods, including least squares, Kalman filtering, and particle filtering. We demonstrate the estimation performance for all the methods under normal operation and sudden load change. Extensive experiments tested on the standard IEEE 14-bus and 300-bus cases corroborate the merit of the proposed approach.

math.OC↗

arXiv2022

A Novel Observer-Centric Approach for Detecting Faults in Islanded AC Microgrids with Uncertainties

Fault detection is vital in ensuring AC microgrids' reliable and resilient operation. Its importance lies in swiftly identifying and isolating faults, preventing cascading failures, and enabling rapid power restoration. This paper proposes a strategy based on observers and residuals for detecting internal faults in grid-forming inverters with power-sharing coordination. The dynamics of the inverters are captured through a nonlinear state space model. The design of our observers and residuals considers $H_{-}/H_{\infty}$ conditions to ensure robustness against disturbances and responsiveness to faults. The proposed design is less restrictive than existing observer-based fault detection schemes by leveraging the properties of quadratic inner-boundedness and one-sided Lipschitz conditions. The internal faults considered in this paper include actuator faults, busbar faults, and inverter bridge faults, which are modeled using vector-matrix representations that modify the state space model of the inverters. One significant advantage of the proposed approach is its cost-effectiveness, as it does not require additional sensors. Experiments are conducted on an islanded AC microgrid with three inductive lines, four inductive loads, and four grid-forming inverters to validate the merits of the proposed fault detection strategy. The results demonstrate that our design outperforms existing methods in the field.

eess.SY↗

arXiv2022

Real-Time Power System Event Detection: A Novel Instance Selection Approach

Instance selection is a vital technique for energy big data analytics. It is challenging to process a massive amount of streaming data generated at high speed rates by intelligent monitoring devices. Instance selection aims at removing noisy and bad data that can compromise the performance of data-driven learners. In this context, this paper proposes a novel similarity based instance selection (SIS) method for real-time phasor measurement unit data. In addition, we develop a variant of the Hoeffding-Tree learner enhanced with the SIS for classifying disturbances and cyber-attacks. We validate the merits of the proposed learner by exploring its performance under four scenarios that affect either the system physics or the monitoring architecture. Our experiments are simulated by using the datasets of industrial control system cyber-attacks. Finally, we conduct an implementation analysis which shows the deployment feasibility and high-performance potential of the proposed learner, as a part of real-time monitoring applications.

eess.SP↗

arXiv2021

Online Dictionary Learning Based Fault and Cyber Attack Detection for Power Systems

The emerging wide area monitoring systems (WAMS) have brought significant improvements in electric grids' situational awareness. However, the newly introduced system can potentially increase the risk of cyber-attacks, which may be disguised as normal physical disturbances. This paper deals with the event and intrusion detection problem by leveraging a stream data mining classifier (Hoeffding adaptive tree) with semi-supervised learning techniques to distinguish cyber-attacks from regular system perturbations accurately. First, our proposed approach builds a dictionary by learning higher-level features from unlabeled data. Then, the labeled data are represented as sparse linear combinations of learned dictionary atoms. We capitalize on those sparse codes to train the online classifier along with efficient change detectors. We conduct numerical experiments with industrial control systems cyber-attack datasets. We consider five different scenarios: short-circuit faults, line maintenance, remote tripping command injection, relay setting change, as well as false data injection. The data are generated based on a modified IEEE 9-bus system. Simulation results show that our proposed approach outperforms the state-of-the-art method.

cs.CR↗