Web-Books
in the Austria-Forum
Austria-Forum
Web-Books
Informatik
Short-Term Load Forecasting by Artificial Intelligent Technologies
Page - 296 -
  • User
  • Version
    • full version
    • text only version
  • Language
    • Deutsch - German
    • English

Page - 296 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Image of the Page - 296 -

Image of the Page - 296 - in Short-Term Load Forecasting by Artificial Intelligent Technologies

Text of the Page - 296 -

Energies2018,11, 1561 InMOSSA, thefirst issue is settledbyequipping theSSAalgorithmwitha repositoryof food sources. The repository can store a limitednumberofnon-dominated solutions. In theprocessof optimization,eachsalp iscomparedwithall theresidents inrepositoryusingtheParetodominance operators. If a salp dominates only one solution in the repository, it will be swapped. If a salp dominatesasetof solutions in therepository, theyall shouldberemovedfromtherepositoryandthe salpshouldbeaddedintherepository. Ifat leastoneof therepositoryresidentsdominatesasalpinthe newpopulation, itshouldbediscardedstraightaway. Ifasalpisnon-dominatedincomparisonwithall repositoryresidents, ithastobeaddedtothearchive. If therepositorybecomesfull,weneedtoremove oneof thesimilarnon-dominatedsolutions in therepository. For thesecondissue,anappropriateway is toselect it fromasetofnon-dominatedsolutionswith the leastcrowdedneighborhood.Thiscan bedoneusing the same rankingprocess and roulettewheel selection employed in the repository maintenanceoperator. ThepseudocodeofMOSSAisshowedinAlgorithm1: Algorithm1.Pseudo-codeofMOSSA. 1 Set the hyper-parameter: 2 Max_iter: Maximum of iteration 3 ArchiveMaxSize: Max capacity of archive (repository) 4 Dim: The number of parameters on each salp 5 Ub and lb: The upper bound and the lower bound of salp population 6 Obj_no: The objective number to be estimated 7 Initialize the salp population L[ L Q depending on the ub and lb 8 Define the objective function (loss function): @ Ob_func 9 While (end criterion is not met) 10 Calculate the fitness of each search agent (salp) with Ob_func 11 Determine the non-dominated salps 12 Update the repository considering the obtained non-dominated salps 13 If (the repository become full) 14 Call the repository maintenance procedure to remove one repository resident 15 Add the non-dominated salp to the repository 16 End If 17 Choose a source of food from repository: F = SelectFood (repository) 18 Update c1 by O /F H § · ¨ ¸© ¹ 19 For each salp ( L[ ): 20 If (i==1): 21 Update the position of the leading salp by: M M M M M M M M M ) F XE OE F OE F [ ) F XE OE F OE F ­ t° ® °¯ 22 Else: 23 Update the position of the leading salp by: L L LM W M W M W[ [ [ 24 End If 25 End For 26 Amend the salps based on the upper and lower bound of variables 27 End While 28 Return repository 296
back to the  book Short-Term Load Forecasting by Artificial Intelligent Technologies"
Short-Term Load Forecasting by Artificial Intelligent Technologies
Title
Short-Term Load Forecasting by Artificial Intelligent Technologies
Authors
Wei-Chiang Hong
Ming-Wei Li
Guo-Feng Fan
Editor
MDPI
Location
Basel
Date
2019
Language
English
License
CC BY 4.0
ISBN
978-3-03897-583-0
Size
17.0 x 24.4 cm
Pages
448
Keywords
Scheduling Problems in Logistics, Transport, Timetabling, Sports, Healthcare, Engineering, Energy Management
Category
Informatik
Web-Books
Library
Privacy
Imprint
Austria-Forum
Austria-Forum
Web-Books
Short-Term Load Forecasting by Artificial Intelligent Technologies