Feature extraction using Hilbert-Huang transform for power system oscillation measurements

Munir, Buyung Sofiarto; Mohajerpoor, Reza; Trisetyarso, Agung; Abbas, Bahtiar Saleh

doi:10.1109/icitacee.2017.8257682

Cited by 7 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Transformation coefficients as input features: In these approaches, the generated transform energy coefficients, representing signals' energy distribution across timefrequency instants, are used directly as input features for the ML model [198], [199], [211], [216], [219], [220], [231], [240]. Feature selection techniques are commonly used here to select the most distinctive representations, which helps reduce redundancy and relaxes computational requirements for training and inference.…”

Section: B Transform-based Methodsmentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

Recent advancements in sensing, measurement, and computing technologies have significantly expanded the potential for signal-based applications, leveraging the synergy between signal processing and Machine Learning (ML) to improve both performance and reliability. This fusion represents a critical point in the evolution of signal-based systems, highlighting the need to bridge the existing knowledge gap between these two interdisciplinary fields. Despite many attempts in the existing literature to bridge this gap, most are limited to specific applications and focus mainly on feature extraction, often assuming extensive prior knowledge in signal processing. This assumption creates a significant obstacle for a wide range of readers. To address these challenges, this paper takes an integrated article approach. It begins with a detailed tutorial on the fundamentals of signal processing, providing the reader with the necessary background knowledge. Following this, it explores the key stages of a standard signal processing-based ML pipeline, offering an in-depth review of feature extraction techniques, their inherent challenges, and solutions. Differing from existing literature, this work offers an application-independent review and introduces a novel classification taxonomy for feature extraction techniques. Furthermore, it aims at linking theoretical concepts with practical applications, and demonstrates this through two specific use cases: a spectral-based method for condition monitoring of rolling bearings and a wavelet energy analysis for epilepsy detection using EEG signals. In addition to theoretical contributions, this work promotes a collaborative research culture by providing a public repository of relevant Python and MATLAB signal processing codes. This effort is intended to support collaborative research efforts and ensure the reproducibility of the results presented.

show abstract

Section: B Transform-based Methodsmentioning

confidence: 99%

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Aburakhia,

Shami,

Karagiannidis

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…McLaughlin, Pdkuiko, and McDaniel [6], and [1] went further than Lopez, Sargolzaei, Santana, and Huerta to demonstrate where energy theft might take place in a given smart grid [4]. McLaughlin, Pdkuiko, and McDaniel studied the phenomenon of energy theft in advanced metering structures and found vulnerabilities that help malicious people steal energy [6].…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, the great development in renewable energy resources and increasing of electric power demand poses new challenges on the distribution networks [1]. The present passive distribution networks (PDN) are of dual structure as they consist of substations and loads [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Developing a Cybersecurity Risk Management Framework for Non-Technical Losses in National Power Distribution Companies

Alzoubaidi,

Najdawi,

Alzoubaidi

2023

jje

View full text Add to dashboard Cite

Traditionally, power companies are the driving force behind a country’s economy and disturbances in its services have severe effects. Advanced metering infrastructure (AMI) grids are vulnerable to network & web security attacks. The objective of this study is to pinpoint the risk mitigation measures that should be integrated into the electric power advanced metering grids of Jordan. The study investigates and proposes a Risk Management Framework (RMF) to minimize the risks of power fraudulent activity. AMI is vulnerable to electricity losses and hence the need to develop a system that would help mitigate this risk. To develop the RMF, we integrate security and privacy into the management activities, to assist in the organizational preparation of the processes and technologies needed for the ongoing energy system IT and OT convergence and digital transformation poses more cybersecurity concerns and essential requirements. We used the Quantitative Risk Management process utilizing the NIST RMF standards for financial risk impacts mitigation of energy losses in the AMI grid. The dependencies and influences between the dimensions considered are investigated, information gathering, and the collection of work data were carried out and used for quantitative analysis. This paper presents a pilot project study in collaboration with EDCO the developed and proposed RMF requirements, risk assessment and, finally recommends the implementation of the selected security controls for the AMI profile protection to mitigate the identified cyber risk.

show abstract

“…Often, it is applied in combination with mode decomposition, which makes it possible to process each mode separately. The combination of Hilbert and mode decomposition is widely known as Hilbert-Huang transform [81]. The difficulty of the Hilbert-Huang transform is that it is empirical and not analytically defined as the Hilbert and Fourier transform.…”

Section: Base-band Representation For Modelling and Simulationmentioning

confidence: 99%

Fundamentals of power systems modelling in the presence of converter-interfaced generation

Paolone

Gaunt

Guillaud

et al. 2020

Electric Power Systems Research

153

View full text Add to dashboard Cite

This survey paper discusses the fundamentals of power systems modelling in the presence of large amounts of converter-interfaced generation (CIG). By referring to real-life events characterised by anomalous dynamics associated to the presence of CIG, the concepts of narrow versus broad band signals are first recalled along with the limitation of the meaning of apparent power, power factor and reactive power. In this regard, the adequacy of the phasor representation of voltages and currents waveforms is thoroughly discussed. Then, with respect to the central subject of control of power converters, a revised definition of grid-following and grid-forming converters is provided along with a thorough discussion of their associated controls and a comprehensive classification for both classes of converters. Several applications inspired by actual case studies are included in the paper in order to provide realistic application examples.

show abstract

Feature extraction using Hilbert-Huang transform for power system oscillation measurements

Cited by 7 publications

References 9 publications

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

On the Intersection of Signal Processing and Machine Learning: A Use Case-Driven Analysis Approach

Developing a Cybersecurity Risk Management Framework for Non-Technical Losses in National Power Distribution Companies

Fundamentals of power systems modelling in the presence of converter-interfaced generation

Contact Info

Product

Resources

About