Deep belief network based k-means cluster approach for short-term wind power forecasting

Wang, Kejun; Qi, Xin; Liu, Hongda; Song, Jiuzhou

doi:10.1016/j.energy.2018.09.118

Cited by 256 publications

(75 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The k-means algorithm identifies k centroids and then allocates every data point to the nearest cluster [53]. This algorithm has been used in a study done by Wang et al [55], where the k-means clustering algorithm was used to find the largest historical samples that had the greatest influence on forecasting accuracy to improve the efficiency of the proposed model. A method for clustering was proposed by Deng et al [52], which used a Weibull distribution to establish that an unclustered dataset P can be represented using Equation 9:…”

Section: Wind Clusteringmentioning

confidence: 99%

Seasonal Wind Energy Characterization in the Gulf of Mexico

2019

View full text Add to dashboard Cite

In line with Mexico’s interest in determining its wind resources, in this paper, 141 locations along the states of the Gulf of Mexico have been analyzed by calculating the main wind characteristics, such as the Weibull shape (c) and scale (k) parameters, and wind power density (WPD), by using re-analysis MERRA-2 (Modern-Era Retrospective Analysis for Research and Applications version 2) data with hourly records from 1980–2017 at a 50-m height. The analysis has been carried out using the R free software, whose its principal function is for statistical computing and graphics, to characterize the wind speed and determine its annual and seasonal (spring, summer, autumn, and winter) behavior for each state. As a result, the analysis determined two different wind seasons along the Gulf of Mexico;, it was found that in the states of Tamaulipas, Veracruz, and Tabasco wind season took place during autumn, winter, and spring, while for the states of Campeche and Yucatan, the only two states that shared its coast with the Caribbean Sea and the Gulf of Mexico, the wind season occurred only in winter and spring. In addition, it was found that by considering a seasonal analysis, more accurate information on wind characteristics could be generated; thus, by applying the Weibull distribution function, optimal zones for determining wind as a resource of energy can be established. Furthermore, a k-means algorithm was applied to the wind data, obtaining three clusters that can be seen by month; these results and using the Weibull parameter c allow for selecting the optimum wind turbine based on its power coefficient or efficiency.

show abstract

Section: Wind Clusteringmentioning

confidence: 99%

Seasonal Wind Energy Characterization in the Gulf of Mexico

2019

View full text Add to dashboard Cite

show abstract

“…The silhouette method is a measure of the similarity of an object to its cluster compared to other clusters. It ranges from -1 to 1, where a large value means that the object is highly matched to its own cluster and low matched to the other clusters (Wang et al, 2018). If the majority of objects have high values, then the clustering result is considered successful.…”

Section: ) Silhouette Methodsmentioning

confidence: 99%

A Clustering based Approach for Contextual Anomaly Detection in Internet of Things

ElMenshawy¹,

Helmy²,

El-Tazi³

2019

Journal of Computer Science

View full text Add to dashboard Cite

Internet of Things (IoT) is a network which connects different communication devices with the internet to attain quick, robust and realtime information transfer and communication, achieving intelligent management. IoT is still in its infancy so it faces numerous challenges varying from data management to security concerns. Sensors generate enormous quantities of data that need to be handled efficiently to have successful deployment of IoT applications. Concerning data management, a great challenge that faces the IoT environment is the detection of contextual anomalies. Contextual anomaly detection is a sophisticated task because the context has to be taken into consideration in the anomaly detection process rather than checking only the deviation of the data value as in point anomaly detection. As a result, in this paper, a novel clustering based algorithm is proposed to detect contextual anomalies in Internet of Things. Attributes were separated into two different categories, namely contextual attributes and behavioral attributes. K-Means clustering technique was applied on the contextual and behavioral attributes separately, then the intersection between the contextual and behavioral clusters was used to detect the contextual anomalies. Moreover, the algorithm was applied on a real room occupation dataset of size around 20,000 records and the experiments showed promising results.

show abstract

“…After this, the data were segregated into training and testing sets. Since there is no rule for data segregation, we used an earlier researcher's approach [63,64] to divide into 80% (training) and 20% (testing) sub-sets, but 10% of the training data were separated again for the purpose of model validation, mainly to eliminate issues related to a model bias through a cross-validation process.…”

Section: Data Preparation Feature Selection and Sensitivity Analysismentioning

confidence: 99%

Deep Learning Neural Networks Trained with MODIS Satellite-Derived Predictors for Long-Term Global Solar Radiation Prediction

et al. 2019

View full text Add to dashboard Cite

Solar energy predictive models designed to emulate the long-term (e.g., monthly) global solar radiation (GSR) trained with satellite-derived predictors can be employed as decision tenets in the exploration, installation and management of solar energy production systems in remote and inaccessible solar-powered sites. In spite of a plethora of models designed for GSR prediction, deep learning, representing a state-of-the-art intelligent tool, remains an attractive approach for renewable energy exploration, monitoring and forecasting. In this paper, algorithms based on deep belief networks and deep neural networks are designed to predict long-term GSR. Deep learning algorithms trained with publicly-accessible Moderate Resolution Imaging Spectroradiometer (MODIS) satellite data are tested in Australia’s solar cities to predict the monthly GSR: single hidden layer and ensemble models. The monthly-scale MODIS-derived predictors (2003–2018) are adopted, with 15 diverse feature selection approaches including a Gaussian Emulation Machine for sensitivity analysis used to select optimal MODIS-predictor variables to simulate GSR against ground-truth values. Several statistical score metrics are adopted to comprehensively verify surface GSR simulations to ascertain the practicality of deep belief and deep neural networks. In the testing phase, deep learning models generate significantly lower absolute percentage bias (≤3%) and high Kling–Gupta efficiency (≥97.5%) values compared to the single hidden layer and ensemble model. This study ascertains that the optimal MODIS input variables employed in GSR prediction for solar energy applications can be relatively different for diverse sites, advocating a need for feature selection prior to the modelling of GSR. The proposed deep learning approach can be adopted to identify solar energy potential proactively in locations where it is impossible to install an environmental monitoring data acquisition instrument. Hence, MODIS and other related satellite-derived predictors can be incorporated for solar energy prediction as a strategy for long-term renewable energy exploration.

show abstract

Deep belief network based k-means cluster approach for short-term wind power forecasting

Cited by 256 publications

References 34 publications

Seasonal Wind Energy Characterization in the Gulf of Mexico

Seasonal Wind Energy Characterization in the Gulf of Mexico

A Clustering based Approach for Contextual Anomaly Detection in Internet of Things

Deep Learning Neural Networks Trained with MODIS Satellite-Derived Predictors for Long-Term Global Solar Radiation Prediction

Contact Info

Product

Resources

About