Folie 1 - NeWater
Contents
1. Evolutionary Optimisation for Microsoft Excel R Farman r farmani exeter ac uk v v v v VWF wv Outline General description Structure amp features of the application Definition of the optimisation problem Live demonstration Software amp hardware requirements Getting GANetXL do Description gt A user friendly add in which integrates into Microsoft Excel E ff mi am cP Configuration P Run 3 Resume amp d Results About gt Uses evolutionary algorithms to solve complex optimisation problems gt Interacts with Excel using COM interface gt Structure of GANetXL lel KOX Xo l gt Cox fo UNIVERSITY GE wW Centre for Water Svetems v yv VF VF Y Y VF WT vY WT WH List of Features Single and multiple objective optimisation techniques Support for integration with simulation packages Suspend resume Multiple objective results browser Batch runs User defined constraints amp penalty multipliers Automatic saving of population Backups of intermediate population Visualisation of results and progress Built in help User manual Defining the Problem gt Decision variables Genes altered by GA within their ranges X X5 X9 Xq gt Objective function s used to evaluate the fitness of solutions formula in C6 gt Constraints used to limit values of objective funct2. ing values of design variables objective functions etc 4 Decide in which cell you want to put x and in which cell f x 5 Start configuration wizard 6 Under genetic algorithm set the following type single objective population 5 Algorithm Generational Crossover simple one point and crossover rate 0 95 selector Tournament Mutator Simple by gene and mutation rate 0 05 Problem setting continued 7 Under Excel Link 8 Enter the location of variable in the box and set Its type and range in the table 9 Do the same for objective function 10 Problem setting can be viewed by unhiding the setting worksheet 11 Run button starts the optimisation To run the algorithm cursor has to be on the problem worksheet 12 Results can be accessed from the results worksheet which was selected prior to starting the GA Multi objective Advertising Selection Media Quan Cost TV 15 sec ad 2 O00 Magazine monthly 3 000 Newspaper half page 1 000 Radio 30 sec adi 300 Direct Mail 5K pieces 6 000 total spent Infeasibility Per Ad Cast quantity Tv 2000 1800 1650 1600 Magazine S000 2700 2300 2250 optimisation of an advertising campaign do Potential Sub Total Audience total aud b b 14 000 b 25 500 0 00 EXETER Centre for Water Systems Optimum ma p gt nagement of groundwater contamination ca
3. ion s formula in C8 Practical Examples Single objective optimisation of an advertising campaign optimisation of a simple mathematical problem learning by doing Multiple objective optimisation of an advertising campaign Link with simulation software Generating policy options for optimum management of groundwater contamination risks a gt lt a optimisation of an advertising campaign E2 d single objective Advertising Selection Potential Media Quan Cost Sub Total Audience total aud TY 15 sec adi 0 Magazine monthly 0 Newspaper half page 13 000 Radio 30 sec ad 4 800 Direct Mail SK pieces 31 500 total spent 49 300 133 500 Optimize Penalty 0 Per Ad Cost quantity Tv Magazine 0 2000 S000 4 1800 2700 8 1650 2300 12 1600 2250 EXETER Centre for Water Systems Optimisation of a simple mathematical problem learning by doing Maximise f x x O lt x lt 3l l e x O L 30 31 EXETE OF Centre for Water Systems Main steps of setting up a problem in GANetXL 1 To create an empty workbook it is recommended to use the Empty Project template which is located in GANetXL s folder in Start menu 2 This template creates an initial workbook 3 Configuration wizard is used to configure all required parameters of the application It allows setting up various options of genetic algorithm defining cells contain
4. se study from Denmark i All farm economy Fanning contract ae to B Farm economics Hunting fishine Biodiversity Biological abnormal EXETER m ae Centre for Water Systems Supported Platforms gt Microsoft Windows Vista not tested but should work XP 2000 gt Microsoft Excel 2007 2003 XP 2000 Licensing gt Licenses are bound to specific computer Registration Details Registration HW Identifier _ _ Serial No Serial Number gt Serial number contains expiration date valid for limited number of days chromosome size population size objectives count generations count Getting GANetXL To get a copy of GANetXL please contact Prof Dragan Savic d savic ex ac uk Intranet website dedicated to GANetXL http cws ganetxl Support reporting bugs and problems Josef Bicik j bicik ex ac uk
Download Pdf Manuals
Related Search