Regional electricity consumption analysis for consumers using data mining techniques and consumer meter reading data

• Data mining methods are very useful for electricity consumption analysis.
• Association rules are more suitable to describe electricity consumption pattern.
• Atmospheric temperature change plays an important role on electricity consumption.
• Electricity consumption depends on proximity to geographical features.
• GIS, GPS and RS are helpful for detailed electricity consumption analysis.

Data Mining (DM) techniques are employed to discover electricity consumption pattern at regional level in a city and used to extract knowledge concerning to the electricity consumption with respect to atmospheric temperature and physical distance from geographic features like river, farm, ground and highway. In order to form the different clusters of temperature and consumers based on the basis of electricity consumption K-means clustering algorithm is applied. Association rule analysis is carried out to form association rules on electricity consumption to describe the result of physical distance between natural geographic objects and various regions. The work includes pre-processing of data, application of DM algorithms and the interpretation of the discovered knowledge. To validate the proposed work, real databases of around twenty thousand consumers from Sangli city are used.