Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/16611
Full metadata record
DC FieldValueLanguage
dc.contributor.authorRahimi, I-
dc.contributor.authorAhmadi, A-
dc.contributor.authorZobaa, AF-
dc.contributor.authorEmrouznejad, A-
dc.contributor.authorAbdel Aleem, SHE-
dc.date.accessioned2018-07-20T12:07:29Z-
dc.date.available2018-07-20T12:07:29Z-
dc.date.issued2017-
dc.identifier4-
dc.identifier4-
dc.identifier.citationBig Data Analytics in Future Power Systems, pp. 55 - 84en_US
dc.identifier.issn4-
dc.identifier.issn4-
dc.identifier.issn4-
dc.identifier.issn4-
dc.identifier.issn4-
dc.identifier.issn4-
dc.identifier.urihttp://bura.brunel.ac.uk/handle/2438/16611-
dc.description.abstractThere are different definitions of big data, and among them, the most common definition refers to three or five characteristics, called volume, velocity, variety, value, and veracity from (Laney (2001)). Volume could include Tera Byte, Peta Byte, Exa Byte, and Zetta Byte. Velocity describes how fast the data are retrieved and processed ‘‘Batch or streaming”. Variety describes structured, semi-structured, and unstructured data (Laney, 2001, Zikopoulos and Eaton, 2011). Veracity explains the integrity and disorderliness of data, while value refers to how good is the “value” we derive from analyzing data? (Zicari et al., 2016). Electrical power systems are networks of components arrayed to supply, transfer, and use electric power. In power system since models are used to predict and characterize operations. However, there is a necessity for powerful optimization algorithms for information processing to learn models as the size increase of data is becoming a global problem to solve large-scale optimization problems. Any optimization problem includes a real function to be maximized or minimized by systematically determination of input values from an allowed set of values. Richness and quantity of large data sets provide the potential to enhance statistical learning performance but require smart models that use the latent low-dimensional structure for effective 2 data separation. This chapter reviews the most recent scientific articles related to large and big data optimization in power systems. Optimization issues such as logistics in power systems and techniques including nonsmooth, nonconvex, and unconstrained large-scale optimization are presented. After a brief review of big data, scientometric analysis has been applied using keywords of “big data” and “power system.” Besides, keywords analysis, network visualization, journal map, and bibliographic coupling analysis have been done to draw a path on big data works in power system problems. Also, the most common useful techniques in large-scale optimization in power system have been reviewed. At the end of this chapter, metaheuristic techniques in big data optimization are reviewed to show that many efforts have been involved in big data optimization in power system and systematically highlight some perspectives on big data optimization.en_US
dc.format.extent55 - 84-
dc.language.isoenen_US
dc.publisherCRC Pressen_US
dc.titleBig data optimization in electric power systems: a reviewen_US
dc.typeBook chapteren_US
dc.relation.isPartOfBig Data Analytics in Future Power Systems-
pubs.publication-statusAccepted-
Appears in Collections:Dept of Electronic and Computer Engineering Embargoed Research Papers

Files in This Item:
File Description SizeFormat 
Fulltext.pdfEmbargoed until 15 Feb 20201.47 MBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.