A k-nearest neighbor space-time simulator with applications to large-scale wind and solar power modeling

Amonkar, Yash; Farnham, David; Lall, U.

doi:10.1016/j.patter.2022.100454

Cited by 13 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where WS = daily maximum windspeed, a = 634. 228, b = 1248.5, c = 999.57, d = 426.224, e = 105.617, f = 15.5487, g = 1.3223, h = 0.0609186, and i = 0.001162565. a-i are coefficients from the wind power curve for a V90-2.0 MW Vestas turbine from Amonkar et al (2022). These coefficients and the cut-in (3 m s −1 ; speed at which the turbine starts to generate power), rated (13 m s −1 ), and cut-out (25 m s −1 ; speed at which the turbine is mechanically limited and needs to shut down to avoid damage) speed thresholds are turbine-specific and could vary for different turbines.…”

Section: Solar and Wind Potentialmentioning

confidence: 99%

Enhanced solar and wind potential during widespread temperature extremes across the U.S. interconnected energy grids

Singh,

Bekris,

Rogers

et al. 2024

Environ. Res. Lett.

View full text Add to dashboard Cite

Several recent widespread temperature extremes across the United States have been associated with power outages, disrupting access to electricity at times that are critical for the health and well-being of communities. Building resilience into the energy infrastructure to such extremes needs a comprehensive understanding of their spatial and temporal characteristics. In this study, we systematically quantify the frequency, extent, duration and intensity of widespread temperature extremes and their associated energy demand in the six North American Electric Reliability Corporation (NERC) regions using ERA5 reanalysis data. We show that every region has experienced hot or cold extremes that affected nearly their entire extent, imposing simultaneous stresses on the system, and such events are associated with substantially higher energy demand. The western U.S. experienced significant increases in the frequency (123%), extent (32%), duration (55%) and intensity (29%) for hot extremes and Texas experienced significant increases in the frequency (132%) of hot extremes. The frequency of cold extremes is decreasing across most regions without substantial changes in other characteristics. Using power outage data, we show that recent widespread extremes in nearly every region have coincided with power outages, and such outages account for between 12-52% of all weather-related outages in the past decade depending on the region. Importantly, we find that solar potential is significantly higher during widespread hot extremes in all six regions and during widespread cold extremes in five of the six regions. Further, wind potential is significantly higher during widespread hot or cold extremes in at least three regions. Our findings indicate that increased solar and wind capacity could be leveraged to meet the higher energy demand during such widespread extremes, improving the resilience and reliability of our energy systems in addition to limiting carbon emissions.

show abstract

Section: Solar and Wind Potentialmentioning

confidence: 99%

Enhanced solar and wind potential during widespread temperature extremes across the U.S. interconnected energy grids

Singh,

Bekris,

Rogers

et al. 2024

Environ. Res. Lett.

View full text Add to dashboard Cite

show abstract

“…The second dataset concerns meteorological and solar-related parameters from NASA's POWER project 2 , which provides a list of explanatory variables. We speak of explanatory variables when the variable explains the explained variable.…”

Section: Definitions and Datasetsmentioning

confidence: 99%

“…In the field of artificial intelligence for agriculture, several applications of Data Mining and Machine Learning can be used to help farmers, bringing information about crop estimations and weather conditions. Indeed, [1] have implemented the K-Means algorithm to predict pollution in the atmosphere, while the K Nearest Neighbor method is applied [2] to simulate daily precipitation as well as other meteorological variables. Crop prediction is also a popular subject [3], and several machine learning algorithms have been studied to support crop yield prediction research [4].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Forecast of Soybean Yields on South Brazil

Hollard

Durigon

Steffenel

2022

Ambient Intelligence and Smart Environments

View full text Add to dashboard Cite

This article investigates the problem of agricultural yield prediction, including that of soybeans. Soya is a very nutritious legume and one of the species producing the most protein per hectare. It is used in particular as a source of protein in animal feed and as an oilseed. However, agricultural systems are dependent on climatic variability, and farmers must deal with this factor to optimize their activities. This article describes a method for predicting soybean yields based on machine learning. The comparative study shows that one can obtain forecasts with less than 2% margin of error using the Random Forest algorithm. In addition, the results obtained in this study can be extended to many other crops such as maize or rice.

show abstract

“…However, The KNN and K-means methods have different approaches. KNN uses learning information to predict new events, while K-means performs clustering to categorise the information and define the properties of a future event (Amonkar et al, 2022;Troccoli et al, 2022). In this study, KNN and K-means machine learning methods are applied for the lithological interpretation of seven boreholes in Shushufindi Oilfield.…”

Section: Introductionmentioning

confidence: 99%

Comparative Analysis of the K-Nearest-Neighbour Method and K-Means Cluster Analysis for Lithological Interpretation of Well Logs of the Shushufindi Oilfield, Ecuador

Gómez¹,

Flores²,

Vadászi³

2022

MGPB

View full text Add to dashboard Cite

The lithological interpretation of well logs is a fundamental task in Earth science that can be accomplished with the application of various machine learning algorithms. The current investigation attempts to evaluate the performance of the K-nearest-neighbour Density Estimate (KNN) and K-means cluster analysis methods for predicting lithology in a dataset of logs measured in the siliciclastic reservoir of the Shushufindi Oilfield of Ecuador. The comparison of lithological interpretation is assembled using classical methods, such as qualitative interpretation and density-neutron cross plot. The lithological interpretation results showed that the supervised method KNN has a higher fitting level with the comparison interpretation data (87.3%, 1145 m predicted of 1311.1 m interpreted) than the results of the K-means method (71.6%, 939.7 m predicted of 1311.1 m interpreted). The geological nature of the reservoir creates a level of a discrepancy because of the near geophysical responses between limestone and intermedia grain size rocks. The possibility of controlling this in the KNN algorithm makes it preferable for usage in these types of reservoir lithological interpretation.

show abstract

A k-nearest neighbor space-time simulator with applications to large-scale wind and solar power modeling

Cited by 13 publications

References 40 publications

Enhanced solar and wind potential during widespread temperature extremes across the U.S. interconnected energy grids

Enhanced solar and wind potential during widespread temperature extremes across the U.S. interconnected energy grids

Machine Learning Forecast of Soybean Yields on South Brazil

Comparative Analysis of the K-Nearest-Neighbour Method and K-Means Cluster Analysis for Lithological Interpretation of Well Logs of the Shushufindi Oilfield, Ecuador

Contact Info

Product

Resources

About