Presentation is loading. Please wait.

Presentation is loading. Please wait.

GECCO 2013 Industrial Competition Computer Engineering Lab, School of Electrical and IT Engineering Farzad Noorian.

Similar presentations


Presentation on theme: "GECCO 2013 Industrial Competition Computer Engineering Lab, School of Electrical and IT Engineering Farzad Noorian."— Presentation transcript:

1 GECCO 2013 Industrial Competition Computer Engineering Lab, School of Electrical and IT Engineering Farzad Noorian

2 GECCO 2013 Genetic and Evolutionary Computation Conference -Organized by ACM SIGEVO GECCO Industrial challenge: -http://www.spotseven.de/gecco-challenge/ -sponsored by GreenPocket GmbH 2

3 Introduction About the Competition Pre-processing Features Training and Cross-validation Results 3

4 The Competition Real room climate time series -Outside temperature as an additional input -Irregular time-series -Very noisy 4

5 Preprocessing 5 From original data

6 Preprocessing 6 Outliers were removed

7 Preprocessing A weighted moving average with a small window 7

8 Preprocessing Regularized using linear approximation 8

9 Preprocessing Only values at hourly boundaries were used. 9

10 Features Only the outside temperature was given. No outside humidity. Human perception based on both. 10

11 Features 11 Publicly available data from Weather Underground for Köln -Temperature -Humidity -Dew Point

12 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

13 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

14 Learner Support Vector Machines -With Radial Kernel Advantages of SVMs -Efficiently trained -Unique global optima 14

15 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

16 Final Results 16 Prediction in hourly, linearly approximated to 10 minutes

17 Questions? Feel free to 17


Download ppt "GECCO 2013 Industrial Competition Computer Engineering Lab, School of Electrical and IT Engineering Farzad Noorian."

Similar presentations


Ads by Google