A data mining approach: Analyzing wind speed and insolation period data in Turkey for installations of wind and solar power plants

Wind and solar power plant installations have been recently increased rapidly with respect to the depletion of fossil-based fuels all over the world. Due to stochastic nature of meteorological conditions, wind and solar energies have a non-schedulable nature and they require several installation analyses to determine the location and the capacities of wind and solar power to be produced.This paper focuses on the similarity, feasibility and numerical analyses of 75 cities in Turkey based on the monthly average wind speed and insolation period data. The nearest and the farest neighbor algorithms are used as agglomerative hierarchical clustering methods with Euclidean, Manhattan and Minkowski distance metrics in the stage of making the similarity and feasibility analyses. The maximum cophenetic correlation coefficient is achieved by the nearest neighbor algorithm with the Minkowski distance metric in the similarity and feasibility analyses. On the other hand, graphical representations of the monthly average wind speed and insolation period data are utilized for making the numerical analysis. The highest annual average wind speed and insolation period are obtained as 3.88 m/s and 8.45 h/day, respectively. Overall, many inferences were achieved in acceptable and efficient limits for wind and solar energy.

► Wind speed and insolation period data were analyzed using a data mining approach.
► Most of the studies in the literature were based on Weibull and Rayleigh models.
► Nearest and farest neighbor algorithms were used with different distance metrics.
► Many inferences were achieved in efficient limits for wind and solar farm analyses.