Spatial and Temporal Wind Power Forecasting by Case-Based Reasoning Using Big-Data

Energies

Alfredo Vaccaro¹  Domenico Villacci¹  Fabrizio De Caro¹ 

[1] Department of Engineering, University of Sannio, 82100 Benevento, Italy;

关键词: wind power forecasting;    knowledge discovery;    big data;    case-based reasoning;    machine learning;   

DOI  :  10.3390/en10020252

来源: DOAJ

【 摘 要 】

The massive penetration of wind generators in electrical power systems asks for effective wind power forecasting tools, which should be high reliable, in order to mitigate the effects of the uncertain generation profiles, and fast enough to enhance power system operation. To address these two conflicting objectives, this paper advocates the role of knowledge discovery from big-data, by proposing the integration of adaptive Case Based Reasoning models, and cardinality reduction techniques based on Partial Least Squares Regression, and Principal Component Analysis. The main idea is to learn from a large database of historical climatic observations, how to solve the windforecasting problem, avoiding complex and time-consuming computations. To assess the benefits derived by the application of the proposed methodology in complex application scenarios, the experimental results obtained in a real case study will be presented and discussed.

【 授权许可】

Unknown