Wind ramp event prediction with parallelized Gradient Boosted Regression\n Trees

2016/10/17 by Saurav Gupta, Nitin Anand Shrivastava, Gupta, Saurav +5
Engineering · #Artificial Intelligence (cs.AI) #Electric Power System Optimization #Energy Load and Power Forecasting #FOS: Computer and information sciences #Machine Learning (cs.LG) #Power System Reliability and Maintenance #Wind Energy Research and Development

paper · pdf · doi:10.48550/arxiv.1610.05009

openalex publication_date 2016/10/17 · openalex created_date 2022/10/06 · openalex updated_date 2026/07/28

Abstract

Accurate prediction of wind ramp events is critical for ensuring the\nreliability and stability of the power systems with high penetration of wind\nenergy. This paper proposes a classification based approach for estimating the\nfuture class of wind ramp event based on certain thresholds. A parallelized\ngradient boosted regression tree based technique has been proposed to\naccurately classify the normal as well as rare extreme wind power ramp events.\nThe model has been validated using wind power data obtained from the National\nRenewable Energy Laboratory database. Performance comparison with several\nbenchmark techniques indicates the superiority of the proposed technique in\nterms of superior classification accuracy.\n

Related

• Integrating wind variability to modelling wind-ramp events using a non-binary ramp function and deep learning models
• Machine Intelligent Techniques for Ramp Event Prediction in Offshore and Onshore Wind Farms
• An improved wind power prediction via a novel wind ramp identification algorithm
• Estimating the Probability of Wind Ramping Events: A Data-driven Approach
• Evaluating the Prediction of Wind Power Ramping Events in the Belgian Offshore Zone