Using Clustering Of Electricity Consumers To Produce More Accurate Predictions #1 R<-Slovakia meetup Peter Laurinec 22.3.2017 FIIT STU R <- Slovakia 0 Why are we here? Rrrr CRAN-about10300packages- https://cran.r-project.org/web/packages/. Popularity-http://redmonk.com/sogrady/: 1 Why prediction of electricity consumption? Importantfor: • Distribution(utility) companies. Producersof electricity. Overload. • Deregularizationofmarket • Buyandsellofelectricity. • Sourceofenergy-windand photo-voltaicpower-plant. Hardlypredictable. • Activeconsumers. producer +consumer)prosumer. • Optimalsettingsofbill. 2 Smart grid • smartmeter • demandresponse • smartcities Goodfor: • Sustainability-Blackouts... • Greenenergy • Savingenergy • Dynamictariffs)saving money 3 Slovak data • Numberofconsumersare21502. Fromthat11281areOK.Enterprises. • Timeintervalofmeasurements: 01.07.2011–14.05.2015. Butmainlyfrom the01.07.2013. 96measurementsperday. Irishdata: • Numberofconsumersare6435. Fromthat3639areresidences. • Timeinterval: 14.7.2009–31.12.2010. 48measurementsperday. 4 Smart meter data OOM_ID DIAGRAM_ID TIME LOAD TYPE_OF_OOM DATE ZIP 1: 11 202004 (cid:0)45 4:598 O 01/01/2014 4013 2: 11 202004 195 4:087 O 01/01/2014 4013 3: 11 202004 (cid:0)30 5:108 O 01/01/2014 4013 4: 11 202004 345 4:598 O 01/01/2014 4013 5: 11 202004 825 2:554 O 01/01/2014 4013 6: 11 202004 870 2:554 O 01/01/2014 4013 41312836: 20970 14922842 90 18:783 O 14/02/2015 4011 41312837: 20970 14922842 75 20:581 O 14/02/2015 4011 41312838: 20970 14922842 60 18:583 O 14/02/2015 4011 41312839: 20970 14922842 45 18:983 O 14/02/2015 4011 41312840: 20970 14922842 30 17:384 O 14/02/2015 4011 5 41312841: 20970 14922842 15 18:583 O 14/02/2015 4011 Random consumer from Kosice vol. 1 6 Random consumer from Kosice vol. 2 7 Aggregate load from Zilina 8

Using Clustering Of Electricity Consumers To Produce More Accurate Predictions PDF

86 Pages

2017

5.28 MB

English

by Peter Laurinec

Checking for file health...

Preview Using Clustering Of Electricity Consumers To Produce More Accurate Predictions

Using Clustering Of Electricity Consumers To Produce More Accurate Predictions #1 R<-Slovakia meetup Peter Laurinec 22.3.2017 FIIT STU R <- Slovakia 0 Why are we here? Rrrr CRAN-about10300packages- https://cran.r-project.org/web/packages/. Popularity-http://redmonk.com/sogrady/: 1 Why prediction of electricity consumption? Importantfor: • Distribution(utility) companies. Producersof electricity. Overload. • Deregularizationofmarket • Buyandsellofelectricity. • Sourceofenergy-windand photo-voltaicpower-plant. Hardlypredictable. • Activeconsumers. producer +consumer)prosumer. • Optimalsettingsofbill. 2 Smart grid • smartmeter • demandresponse • smartcities Goodfor: • Sustainability-Blackouts... • Greenenergy • Savingenergy • Dynamictariffs)saving money 3 Slovak data • Numberofconsumersare21502. Fromthat11281areOK.Enterprises. • Timeintervalofmeasurements: 01.07.2011–14.05.2015. Butmainlyfrom the01.07.2013. 96measurementsperday. Irishdata: • Numberofconsumersare6435. Fromthat3639areresidences. • Timeinterval: 14.7.2009–31.12.2010. 48measurementsperday. 4 Smart meter data OOM_ID DIAGRAM_ID TIME LOAD TYPE_OF_OOM DATE ZIP 1: 11 202004 (cid:0)45 4:598 O 01/01/2014 4013 2: 11 202004 195 4:087 O 01/01/2014 4013 3: 11 202004 (cid:0)30 5:108 O 01/01/2014 4013 4: 11 202004 345 4:598 O 01/01/2014 4013 5: 11 202004 825 2:554 O 01/01/2014 4013 6: 11 202004 870 2:554 O 01/01/2014 4013 41312836: 20970 14922842 90 18:783 O 14/02/2015 4011 41312837: 20970 14922842 75 20:581 O 14/02/2015 4011 41312838: 20970 14922842 60 18:583 O 14/02/2015 4011 41312839: 20970 14922842 45 18:983 O 14/02/2015 4011 41312840: 20970 14922842 30 17:384 O 14/02/2015 4011 5 41312841: 20970 14922842 15 18:583 O 14/02/2015 4011 Random consumer from Kosice vol. 1 6 Random consumer from Kosice vol. 2 7 Aggregate load from Zilina 8

See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.