GECCO 2013 Industrial Competition Computer Engineering Lab, School of Electrical and IT Engineering Farzad Noorian
GECCO 2013 Genetic and Evolutionary Computation Conference -Organized by ACM SIGEVO GECCO Industrial challenge: - -sponsored by GreenPocket GmbH 2
Introduction About the Competition Pre-processing Features Training and Cross-validation Results 3
The Competition Real room climate time series -Outside temperature as an additional input -Irregular time-series -Very noisy 4
Preprocessing 5 From original data
Preprocessing 6 Outliers were removed
Preprocessing A weighted moving average with a small window 7
Preprocessing Regularized using linear approximation 8
Preprocessing Only values at hourly boundaries were used. 9
Features Only the outside temperature was given. No outside humidity. Human perception based on both. 10
Features 11 Publicly available data from Weather Underground for Köln -Temperature -Humidity -Dew Point
Features for Temperature Forecasting Weekday seasonality Only weekdays used -Seasonality removed only from indoor temperature A window of last n hours room temperatures A window of previous m and next m dew points from Wunderground 12
Features for Humidity Forecasting A window of last n hours m previous and m next external humidity from Wunderground -Open, Low, High and Close of that days humidity No seasonality or data filtering 13
Learner Support Vector Machines -With Radial Kernel Advantages of SVMs -Efficiently trained -Unique global optima 14
Cross-validation Using R package caret Cross validation for features and parameters -Using from a 4-day window to 15-day window to train -Validating using next 3 available days Final training on all data 15
Final Results 16 Prediction in hourly, linearly approximated to 10 minutes
Questions? Feel free to 17