Features extraction of wind ramp events from a virtual wind park

Mishra, Sweta; Ören, Esin; Bordin, Chiara; Wen, Fushuan; Palu, Ivo

doi:10.1016/j.egyr.2020.08.047

Cited by 7 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the one hand, the accuracy of models can be achieved by increasing the reliability of their input data, but on the other hand it is necessary to choose such problem-solving techniques that support the handling of models with uncertainty. Data science solutions can help to reveal unknown relationships between input data, thereby reducing the level of uncertainty in the inputs [339], while machine learning techniques can further reduce the uncertainty in the solutions of complex optimization models. Fuzzy and stochastic models are of particular importance that can be used to describe uncertainties in optimization problems efficiently.…”

Section: ) Development Of Forecasting Models and Digital Twinsmentioning

confidence: 99%

Scheduling Under Uncertainty for Industry 4.0 and 5.0

et al. 2022

View full text Add to dashboard Cite

This article provides a review about how uncertainties in increasingly complex production and supply chains should be addressed in scheduling tasks. Uncertainty management will be particularly important in Industry 5.0 solutions that will require the close integration of operators and technical systems. To prepare for these challenging developments, this work reviews the sources of uncertainty and the scheduling algorithms that deal with the different types of models developed to handle the uncertain nature of the elements and the environment of complex technological systems. The paper not only identifies the challenges, but also the main building blocks that can help to manage and reduce uncertainties based on the I4.0 and I5.0 solutions. We hope that this study will serve as a starting point for R&D projects and algorithm developments, which will be needed primarily in the field of multi-agent, multistage and inverse optimizations.

show abstract

Section: ) Development Of Forecasting Models and Digital Twinsmentioning

confidence: 99%

Scheduling Under Uncertainty for Industry 4.0 and 5.0

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Wind ramp events are extracted using the

{RBA}_{θ}

methodology proposed in Mishra et al 39 A ramp event can be stated as a swing across the reference axis.

{RBA}_{θ}

classifies the ramp events into significant and stationary events.…”

Section: Prediction Of Eventsmentioning

confidence: 99%

“…Note that all the events are significant events, as stationary events are not considered for this analysis. More details related to the two types of events are presented here 39 …”

Section: Prediction Of Eventsmentioning

confidence: 99%

“…One key pathway for improving wind power forecasting has been identified in “extracting more out of the data.” 38 The ability to identify key features intrinsic to the data set can indeed lead to improved and more accurate predictions. Features extracted from wind ramp events from a virtual wind park have been discussed in Mishra et al 39 where the authors present a novel ramping behavior analysis (RBA) method that identifies and quantifies variations in a time‐varying data set. Two types of events are identified: significant and stationary events.…”

Section: Introductionmentioning

confidence: 99%

“…Descriptive statistics explains the underlying distribution of a data set; however, descriptive statistics is restricted by a set number of features that describe the statistical properties of a specific time‐series. The proposed method extracts events from a time‐series that depends on a threshold and cut‐off frequency 39 . For instance, if the threshold is changed, the same data set is then represented by an alternative set of events.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive analytics beyond time series: Predicting series of events extracted from time series data

et al. 2022

Self Cite

View full text Add to dashboard Cite

Realizing carbon neutral energy generation creates the challenge of accurately predicting time-series generation data for long-term capacity planning and for shortterm operational decisions. The key challenges for adopting data-driven decisionmaking, specifically predictive analytics, can be attributed to data volume and velocity. Data volume poses challenges for data storage and retrieval. Data velocity poses challenges for processing the data near real time for operational decisions or for capacity building. This manuscript proposes a novel prediction method to tackle the above two challenges by using an event-based prediction in place of traditional time series prediction methods. The central concept is to extract meaningful information, denoted by events, from time-series data and use these events for predictive analysis. These extracted events retain the information required for predictive analytics while significantly reducing the volume of the velocity of data; consequently, a series of events present the information at a glance, effectively enabling data-driven decision-making. This method is applied to a data set consisting of six years of historical wind power capacity factor and temperature measurements. Deploying five deep learning models, a comparison is drawn between classical time-series predictions and series of events predictions based on computational time and several error metrics.The computational analysis results are presented in graphical format and a comparative discussion is drawn on the prediction results. The results indicate that the proposed method obtains the same or better prediction accuracy while significantly reducing computational time and data volume.

show abstract