Using clustering techniques to provide simulation scenarios for the smart grid

Miguel, Pedro; Gonçalves, José; Pires Neves, Luís; Martins, A. Gomes

http://hdl.handle.net/10400.8/12942

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
1-s2.0-S2210670716300658-main.pdf		2.15 MB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

tThe objective of this work is to obtain characteristic daily profiles of consumption, wind generationand electricity spot prices, needed to develop assessments of two different options commonly regardedunder the smart grid paradigm: residential demand response, and small scale distributed electric energystorage. The approach consists of applying clustering algorithms to historical data, namely using a hierar-chical method and a self-organizing neural network, in order to obtain clusters of diagrams representingcharacteristic daily diagrams of load, wind generation or electricity price. These diagrams are useful notonly to analyze different scenarios of combined existence, but also to understand their individual relativeimportance. This study enabled also the identification of a probable range of variation around an averageprofile, by defining boundary profiles with the maximum and minimum values of any cluster prototypes.

Keywords

Data clustering Demand response Energy box Energy storage Smart grid Distribution system operator

URI

http://hdl.handle.net/10400.8/12942

Citation

Pedro Miguel, José Gonçalves, Luís Neves, A.Gomes Martins, Using clustering techniques to provide simulation scenarios for the smart grid, Sustainable Cities and Society, Volume 26, 2016, Pages 447-455, ISSN 2210-6707, https://doi.org/10.1016/j.scs.2016.04.012. (https://www.sciencedirect.com/science/article/pii/S2210670716300658)