Linear correlation and regression between the meteorological data and the electricity demand of the Dubrovnik region in a short-term scale

Intermitted patterns of solar and wind generation cause insecurity in the power system supply since they depend on weather conditions. The aim of this work is to perform linear regression and correlation between solar radiation, wind speed, air temperature and electricity demand of the Dubrovnik region. Gained results could help in system energy planning with a high share of renewable energy sources in the electricity production. All of the data are collected for consecutive three year period, years 2012, 2013 and 2014, in the 10 minute time step. Results of the correlation of each of the parameters individually in between the years show slightly variations between the distributions, providing representative line-ar relation in between the years for all the data, except the wind speed data. Cor-relations are also done between all of the parameters for each year separately, based on the mean monthly values. Result showed good relation with negative correlation between solar radiation and wind speed, as well as good relation with positive correlation between solar radiation and electricity demand. The same correlations are done in the 10 minute time step and including time system delay. The results indicate significant decrease in correlation coefficient value and it is less possible that they can be pronounced with linear regression line. Calculations of the correlation and regression, based on the 10 minute time step for summer and winter period separately, gained slightly better results in relation between parameters than the ones including the whole year data