{"title":"Extreme wind turbine response extrapolation with the Gaussian mixture model","authors":"Xiaodong Zhang, Nikolay Dimitrov","doi":"10.5194/wes-8-1613-2023","DOIUrl":null,"url":null,"abstract":"Abstract. The wind turbine extreme response estimation based on statistical extrapolation necessitates using a minimal number of simulations to calculate a low exceedance probability. The target exceedance probability associated with a 50-year return period is 3.8×10-7, which is challenging to evaluate with a small prediction error. The situation is further complicated by the fact that the distribution of the wind turbine response might be multimodal, and the extremes belong to a different statistical population than the main body of the distribution. Traditional theoretical probability distributions, mostly unimodal, may not be suitable for this task. The problem could be alleviated by applying a fit specifically on the tail of the distribution. Yet, a single unimodal distribution may not be sufficient for modeling diverse wind turbine responses, and an inappropriate distribution model could lead to significant prediction errors, including bias and variance errors. The Gaussian mixture model, a probabilistic and flexible mixture distribution model used extensively for clustering and density estimation tasks, is infrequently applied in the wind energy sector. This paper proposes using the Gaussian mixture model to extrapolate extreme wind turbine responses. The performance of two approaches is evaluated: (1) parametric fitting first and aggregation afterward and (2) data aggregation first followed by fitting. Different distribution models are benchmarked against the Gaussian mixture model. The results show that the Gaussian mixture model is capable of estimating a low exceedance probability with minor bias error, even with limited simulation data, and demonstrates flexibility in modeling the distributions of varying response variables.","PeriodicalId":46540,"journal":{"name":"Wind Energy Science","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2023-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Wind Energy Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5194/wes-8-1613-2023","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GREEN & SUSTAINABLE SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Abstract. The wind turbine extreme response estimation based on statistical extrapolation necessitates using a minimal number of simulations to calculate a low exceedance probability. The target exceedance probability associated with a 50-year return period is 3.8×10-7, which is challenging to evaluate with a small prediction error. The situation is further complicated by the fact that the distribution of the wind turbine response might be multimodal, and the extremes belong to a different statistical population than the main body of the distribution. Traditional theoretical probability distributions, mostly unimodal, may not be suitable for this task. The problem could be alleviated by applying a fit specifically on the tail of the distribution. Yet, a single unimodal distribution may not be sufficient for modeling diverse wind turbine responses, and an inappropriate distribution model could lead to significant prediction errors, including bias and variance errors. The Gaussian mixture model, a probabilistic and flexible mixture distribution model used extensively for clustering and density estimation tasks, is infrequently applied in the wind energy sector. This paper proposes using the Gaussian mixture model to extrapolate extreme wind turbine responses. The performance of two approaches is evaluated: (1) parametric fitting first and aggregation afterward and (2) data aggregation first followed by fitting. Different distribution models are benchmarked against the Gaussian mixture model. The results show that the Gaussian mixture model is capable of estimating a low exceedance probability with minor bias error, even with limited simulation data, and demonstrates flexibility in modeling the distributions of varying response variables.