Comparative Study of Event Prediction in Power Grids using Supervised Machine Learning Methods

Høiem, Kristian Wang; Santi, Vemund; Torsater, Bendik Nybakk; Langseth, Helge; Andresen, Christian André; Rosenlund, Gjert H.

doi:10.1109/sest48500.2020.9203025

Cited by 5 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Papers [5,16] both apply most of the techniques discussed in this review, and [17] exposes a selection of additional techniques, such as KF, HHT, RMS, and HOS. Other authors prefer the combined use of AI with one another technique; this is what happens in the case of [10] with HHT, [18] with RMS, [19] with THD, [6] with HOS, or [8] with ST. Papers [7,20,21] omit the use of other complementary techniques. Indeed, Figure 2 depicts a timeline relationship among analysis procedures and application fields.…”

Section: Resultsmentioning

confidence: 99%

Current Status and Future Trends of Power Quality Analysis

et al. 2022

View full text Add to dashboard Cite

In this article, a systematic literature review of 153 articles on power quality analysis in PV systems published in the last 20 years is presented. This provides readers with an overview on PQ trends in several fields related to instrumental techniques that are being used in the smart grid to visualize the quality of the energy, establishing a solid literature base from which to start future research. A preliminary appreciation allows us to intuit that higher-order statistics are not implemented in measurement equipment and that traditional instrumentation is still used for the performance of measurement campaigns, not yielding the expected results since the information processed does not come from an electrical network from 20 years ago. Instead, current networks contain numerous coupled load effects; thus, new disturbances are not simple; they are usually complex events, the sum of several types of disturbances. Likewise, depending on the type of installation, the objective of the PQ analysis changes, either by detecting certain events or simply focusing on seeing the state of the network.

show abstract

Section: Resultsmentioning

confidence: 99%

Current Status and Future Trends of Power Quality Analysis

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The event prediction search pillar includes eleven surveys [20,109,120,130,135,205,209,230,250,281,283]. Each of these surveys has a certain scope, e.g., [205,209] focus on time-series data, [281,283] focus on event prediction of business processes, and [20] on unstructured text events.…”

Section: Related Surveysmentioning

confidence: 99%

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

Benzin¹,

Rinderle-Ma²

2023

Preprint

View full text Add to dashboard Cite

Event prediction is the ability of anticipating future events, i.e., future real-world occurrences, and aims to support the user in deciding on actions that change future events towards a desired state. An event prediction method learns the relation between features of past events and future events. It is applied to newly observed events to predict corresponding future events that are evaluated with respect to the user's desired future state. If the predicted future events do not comply with this state, actions are taken towards achieving desirable future states. Evidently, event prediction is valuable in many application domains such as business and natural disasters.The diversity of application domains results in a diverse range of methods that are scattered across various research areas which, in turn, use different terminology for event prediction methods. Consequently, sharing methods and knowledge for developing future event prediction methods is restricted. To facilitate knowledge sharing on account of a comprehensive classification, integration, and assessment of event prediction methods, we combine taxonomies and take a systems perspective to integrate event prediction methods into a single system, elicit requirements and assess existing work with respect to the requirements. Based on the assessment, we identify open challenges and discuss future research directions.

show abstract

“…[55] include anomaly prediction and-by using random forests-obtains inherently explainable models. Similarly, our own recent works have also focused on predicting PQ disturbances using a variety of data sources, methods, and features [56][57][58][59][60][61]. Unfortunately, most works (including our own) omit describing the underlying data, and instead jump straight to feature engineering and machine learning.…”

Section: Production and Assets Transmission And Distribution Consumptionmentioning

confidence: 99%

Lessons for Data-Driven Modelling from Harmonics in the Norwegian Grid

et al. 2022

Self Cite

View full text Add to dashboard Cite

With the advancing integration of fluctuating renewables, a more dynamic demand-side, and a grid running closer to its operational limits, future power system operators require new tools to anticipate unwanted events. Advances in machine learning and availability of data suggest great potential in using data-driven approaches, but these will only ever be as good as the data they are based on. To lay the ground-work for future data-driven modelling, we establish a baseline state by analysing the statistical distribution of voltage measurements from three sites in the Norwegian power grid (22, 66, and 300 kV). Measurements span four years, are line and phase voltages, are cycle-by-cycle, and include all (even and odd) harmonics up to the 96 order. They are based on four years of historical data from three Elspec Power Quality Analyzers (corresponding to one trillion samples), which we have extracted, processed, and analyzed. We find that: (i) the distribution of harmonics depends on phase and voltage level; (ii) there is little power beyond the 13 harmonic; (iii) there is temporal clumping of extreme values; and (iv) there is seasonality on different time-scales. For machine learning based modelling these findings suggest that: (i) models should be trained in two steps (first with data from all sites, then adapted to site-level); (ii) including harmonics beyond the 13 is unlikely to increase model performance, and that modelling should include features that (iii) encode the state of the grid, as well as (iv) seasonality.

show abstract

Comparative Study of Event Prediction in Power Grids using Supervised Machine Learning Methods

Cited by 5 publications

References 13 publications

Current Status and Future Trends of Power Quality Analysis

Current Status and Future Trends of Power Quality Analysis

A Survey on Event Prediction Methods from a Systems Perspective: Bringing Together Disparate Research Areas

Lessons for Data-Driven Modelling from Harmonics in the Norwegian Grid

Contact Info

Product

Resources

About