Correlation of variables with electricity consumption data

In this paper the correlation between different variables with the hourly consumption of electricity is analyzed. Since the correlation analyses is a basis for predicting, the results of this study may be used as an input to any model for forecasting in the field of machine learning, such as neural networks and support vector machines, as well as to the various statistical models for prediction. In order to calculate the correlation between the variables, in this paper the two main methods for correlation are used: Pearson’s correlation, which measures the linear correlation between two variables and Spearman's rank correlation, which analyzes the increasing and decreasing trends of the variables that are not necessarily linear. As a case study the electricity consumption in Macedonia is used. Actually, the hourly data for electricity consumption, as well as the hourly temperature data for the period from 2008 to 2014 are considered in this paper. The results show that the electricity consumption in the current hour is mostly correlated to the consumption in the same hour the previous day, the same hour-same day combination of the previous week and the consumption in the previous day. Additionally, the results show a great correlation between the temperature data and the electricity consumption.

[1]  David Hsu.  Identifying key variables and interactions in statistical models of building energy consumption using regularization , 2015 .

[2]  Joon Hyung Shim,et al.  Wind-speed prediction and analysis based on geological and distance variables using an artificial neural network: A case study in South Korea , 2015 .

[3]  Danijela Nikolić,et al.  The impact of the mean daily air temperature change on electricity consumption , 2015 .

[4]  Na Tang,et al.  Application of a Load Forecasting Model Based on Improved Grey Neural Network in the Smart Grid , 2011 .

[5]  Markus Wagner,et al.  Predicting the Energy Output of Wind Farms Based on Weather Data: Important Variables and their Correlation , 2011, ArXiv.

[6]  Ali Badri,et al.  Application of Artificial Neural Networks and Fuzzy logic Methods for Short Term Load Forecasting , 2012 .

[7]  S. Beck,et al.  Using regression analysis to predict the future energy consumption of a supermarket in the UK , 2014 .

[8]  Shahaboddin Shamshirband,et al.  Estimating building energy consumption using extreme learning machine method , 2016 .

[9]  Shahaboddin Shamshirband,et al.  Determining the most important variables for diffuse solar radiation prediction using adaptive neuro-fuzzy methodology; case study: City of Kerman, Iran , 2016 .

[10]  Jerome L. Myers,et al.  Research Design and Statistical Analysis , 1991 .

[11]  Lalit Mohan Saini,et al.  Solar energy prediction using linear and non-linear regularization models: A study on AMS (American Meteorological Society) 2013–14 Solar Energy Prediction Contest , 2014 .

[12]  Daryoush Habibi,et al.  Modelling self-optimised short term load forecasting for medium voltage loads using tunning fuzzy systems and Artificial Neural Networks , 2015 .