Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy

Takahashi, Y.; Fujimoto, Yu; Hayashi, Yasuhiro

doi:10.1016/j.egypro.2017.09.494

Cited by 15 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the situation is similar for wind power generation [101], although it is rare for largescale installations in cities; in the context of grasping wind power generation, the use of data via supervisory control and data acquisition (SCADA) system and the sophistication of numerical weather models [102] play important roles. Various methods have been discussed for forecasting wind power as well [103][104][105][106][107][108]. In particular, the ramp, that is, a sudden change in the amount of power generation depending on weather and wind conditions, is a phenomenon in which characteristics peculiar to renewable energy ‡ Data collected by Himawari-8 comprise solar radiation information with spatial resolution of 1 km collected every 2.5 min.…”

Section: Grasping and Forecasting Energy Fluctuationsmentioning

confidence: 99%

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

Fujimoto

Ishii

Hayashi

2020

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

Smart cities will be an important component for the construction of a sustainable future society. This paper focuses on the functionalities of smart cities from the perspective of electric power systems and reviews recent works on the various types of energy management systems (EMSs), particularly those focusing on the interaction among systems distributed in a city. Furthermore, this paper describes the idea of a platform for evaluating cooperative EMS technologies distributed in a city. The related research and demonstration of the EMS technology in real cities that were evaluated using the proposed platform are presented. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Section: Grasping and Forecasting Energy Fluctuationsmentioning

confidence: 99%

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

Fujimoto

Ishii

Hayashi

2020

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

show abstract

“…Kamath [16], for example, has analyzed historical wind power data to organize the characteristics of the ramp events in relation to time (duration) and intensity. Utilizing such historical data sets plays an important role in ramp event prediction; therefore various data driven frameworks have been studied [17]- [24]. Several studies have suggested that the application of machine learning methods [25], like auto regressive model [21], support vector machine [17], [18], hidden Markov model [19], random forest [17], [24], gradient boosted trees [23], wavelet transform [21], [26], and artificial neural networks [17], [21], [22], [27], particularly containing deep architectures [28]- [30], contributes to improving the accuracy of ramp event prediction.…”

Section: Introductionmentioning

confidence: 99%

“…This approach provided a simple but effective way for warning of the risk of a ramp occurrence. In particular, we addressed challenges, such as the ramp prediction accuracy, based on classification algorithms generally tending to be low, owing to the infrequency of such ramp events [24]. This tendency is known as the class imbalance problem [38]- [40] in the machine learning domain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Alerting to Rare Large-Scale Ramp Events in Wind Power Generation

Fujimoto

Takahashi

Hayashi

2019

IEEE Trans. Sustain. Energy

Self Cite

View full text Add to dashboard Cite

Wind power is an unstable power source, as its output fluctuates drastically according to the weather. Such instability can cause sudden large-scale changes in output, called ramp events; the frequency of such events is relatively low throughout the year but they could negatively affect the supply-demand balance in a power system. This study focuses on an alerting scheme of wind power ramp events for a transmission system operator to support operational decisions on cold reserve power plants. The ramp alerting scheme is implemented from the viewpoint of supervised learning by using the prediction results of wind power output. In particular, the authors address the class imbalance problem, as the accuracy of ramp event prediction tends to be low because of the infrequency of such ramp events in the database used for learning. In this study, several data sampling strategies are proposed and implemented to overcome the problem in the ramp alert task. The effectiveness of the proposed data sampling framework is evaluated experimentally by predicting real-world wind power ramps, based on a dataset collected in Japan. The experimental results show that the proposed framework effectively improves the ramp alert accuracy by addressing the class imbalance problem.

show abstract

“…-The forecast accuracy of the ramp events tends to be low is a class imbalance problem, where take on some data sampling methods to overwhelmed [28]. -The research of detecting anomalies in smart grid is a current topic and is investigated by many researchers, taking into account the use recognized methods of pattern recognition [29].…”

Section: Introductionmentioning

confidence: 99%

Over-sampling imbalanced datasets using the Covariance Matrix

Leguen-devarona¹,

Madera²,

Martínez-López³

et al. 2018

EAI Endorsed Transactions on Energy Web

View full text Add to dashboard Cite

INTRODUCTION: Nowadays, many machine learning tasks involve learning from imbalanced datasets, leading to the miss-classification of the minority class. One of the state-of-the-art approaches to "solve" this problem at the data level is Synthetic Minority Over-sampling Technique (SMOTE) which in turn uses K-Nearest Neighbors (KNN) algorithm to select and generate new instances.OBJECTIVES: This paper presents SMOTE-Cov, a modified SMOTE that use Covariance Matrix instead of KNN to balance datasets, with continuous attributes and binary class. METHODS:We implemented two variants SMOTE-CovI, which generates new values within the interval of each attribute and SMOTE-CovO, which allows some values to be outside the interval of the attributes. RESULTS:The results show that our approach has a similar performance as the state-of-the-art approaches. CONCLUSION: In this paper, a new algorithm is proposed to generate synthetic instances of the minority class, using the Covariance Matrix.

show abstract

Forecast of Infrequent Wind Power Ramps Based on Data Sampling Strategy

Cited by 15 publications

References 6 publications

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

Alerting to Rare Large-Scale Ramp Events in Wind Power Generation

Over-sampling imbalanced datasets using the Covariance Matrix

Contact Info

Product

Resources

About