izpis_h1_title_alt

Podatkovni tokovi in rezervoarsko vzorčenje pri napovedovanju proizvodnje sončnih elektrarn
Kotnik, Denis (Author), Kukar, Matjaž (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (25,78 MB)

Abstract
Sončna, vetrna in vodna energija kot obnovljivi viri energije vzbujajo vedno večjo pozornost, saj je njihov vpliv na okolje, v primerjavi s fosilnimi gorivi, mnogo manjši. V elektroenergetskih sistemih učinkovito shranjevanje električne energije skoraj ni mogoče, zato so se distributerji primorani ukvarjati s problemom ohranjanja ravnovesja med porabo in proizvodnjo električne energije. Kvalitetno napovedovanje proizvodnje in porabe električne energije omenjeni problem močno olajša. Delo obravnava kratkoročno napovedovanje proizvodnje električne energije sončnih elektrarn na območju primorske Slovenije na podlagi vremenskih napovedi, pri čemer se podatke obravnava kot podatkovni tok. Za napovedovanje se uporablja in primerja klasične algoritme strojnega učenja in algoritme, ki se iz podatkov učijo sproti. Dopolni se jih z algoritmom ADWIN, ki s prilagodljivimi drsečimi okni in zaznavanjem sprememb koncepta vzdržuje vzorec zadnjih primerov. Uporablja se tudi algoritem rezervoarskega vzorčenja z eksponentnim staranjem elementov, s katerim se vzdržuje vzorec iz celotnega podatkovnega toka. S sprotnimi modeli naučenimi na vzorcu podatkovnega toka so bile pridobljene uporabne napovedi in povsem primerljivi rezultati s sorodnimi deli.

Language:Slovenian
Keywords:podatkovno rudarjenje, podatkovni tokovi, sprememba koncepta, rezervoarsko vzorčenje, sončne elektrarne, napovedovanje proizvodnje
Work type:Master's thesis/paper (mb22)
Organization:FRI - Faculty of computer and information science
Year:2018
Views:645
Downloads:349
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:Data streams and reservoir sampling for predicting production of solar power plants
Abstract:
In the electrical power systems the efficient storage of electricity is almost impossible, therefore the electrical distributors are forced to deal with the problem of maintaining a balance between consumption and production of electricity. Quality forecasts of electricity production and consumption make this problem easier. This thesis deals with the short-term forecasting of electricity production from solar power plants for the Primorska region in Slovenia, whereby data is treated as a data stream. Attributes used for this predictions are usually obtained from weather forecast model. Classical machine learning algorithms as well as algorithms that are capable of online/incremental learning are being used for forecasting power production and mutually comparison. Machine learning algorithms are being upgraded with ADWIN algorithm, which detects concept drifts and maintains a sample of the last examples using adaptive size sliding window. A reservoir sam- pling algorithm with exponential decay of older elements is also being used to maintain a sample from the entire data stream. Useful predictions with a performance comparable to other results have been obtained with online algorithms learned on the sample of the data stream.

Keywords:data mining, data streams, concept drift, reservoir sampling, solar power plants, production forecasting

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back