Volume 10 Issue 1 - March 2018

  • 1. Prediction and forecasting of electricity consumption using big data

    Authors : D.rukmani, S.muthuraj Kumar

    Pages : 82-85

    DOI : http://dx.doi.org/10.21172/1.101.14

    Keywords : K-Nearest Neighbor algorithmSmart gridShort term load forecasting

    Abstract :

    With the raising of smart grid, lots of renewable energy resources such as wind and solar are utilized in power system. It might make the power system load varied complex than before which will bring drawback in short-term load forecasting area. First, a cluster analysis is accomplished to classify daily load patterns for individual loads using smart meter data. Next, an association analysis is used to decide critical authoritative factors. This is followed by the application of a decision tree to establish classification rules. Then, appropriate forecasting models are chosen for different load patterns. Finally, fore-cast the total system load is obtained through an aggregation of an individual load’s forecasting results [3]. K-Nearest Neighbor is an extensively used classification algorithm due to its simplicity [7]. It is one of the top ten data mining algorithms, has been widely applied in various fields. K-Nearest Neighbor has few limitations affecting its accuracy of classification [5]. It has large memory requirements as well as high time complexity.

    Citing this Journal Article :

    D.rukmani, S.muthuraj Kumar, "Prediction and forecasting of electricity consumption using big data ", https://www.ijltet.org/journal_details.php?id=928&j_id=4382, Volume 10 Issue 1 - March 2018, 82-85, #ijltetorg