Spatial Clustering for Temporal Power Ramp Balance and Wind Power Estimation

Power estimation and power ramp estimation is of crucial importance in renewable energy applications especially for wind power plants that is going to be the focus of this study. Intermittent supply of wind power generation can cause power ramps which are sudden change of power production in time. This is an important problem in power system that aims to keep the load and generation balance. Unbalance in the system can lead to price volatility and grid security issues that will create power stability problems and financial losses. Herein a spatial clustering methodology for improving spatio-temporal relations are investigated to improve wind power estimation and power ramp estimation. To validate the data with the model that will be used in clustering analysis, spatial results of Computational Fluid Dynamics (CFD) tool simulations are employed to test suggested methodology in space. CFD results generate the input data for space clustering process. Via the CFD generated spatial information, the relationship between spatial clustering to wind power ramp rate characteristics of wind turbines are introduced for the spatio-temporal power and power ramp rate relations. Spatial relations for power ramp characteristics of each node in wind resource map is introduced. In space scales, K-means algorithm is used to create spatial Power Ramp Rate (PRR) based clusters to define most related clusters in space so that impact of each spatial cluster can be introduced.