| 1. |
- Antonios, Marinopoulos, et al.
(author)
-
Investigating the impact of wake effect on wind farm aggregation
- 2011
-
In: PowerTech, 2011 IEEE Trondheim. - 9781424484171 ; :19-23 June 2011, s. 1 - 5
-
Conference paper (peer-reviewed)abstract
- Aggregation methodologies for creating equivalent wind farm models are needed for power system transient stability studies involving large wind farms. One strong argument in the literature suggests single machine equivalent representation of wind farm with the assumption that all wind turbines receive the same incoming wind speed and thus operate at the same loading condition. In this paper, we examine how the validity of such single machine equivalent is affected under different wind speeds across a feeder in a wind farm with many WTGs. In particular, we compare the total active power output from the WTGs which indicates significant difference between single machine equivalent and full wind farm model under certain wind speed ranges and distances between the WTGs. We then conclude the need to use multi-machine equivalent representation for large wind farm in order to achieve adequate accuracy under the full range of wind conditions.
|
|
| 2. |
- Osman, M.H., et al.
(author)
-
An analysis of machine learning algorithms for condensing reverse engineered class diagrams
- 2013
-
In: IEEE International Conference on Software Maintenance, ICSM. - : IEEE. - 1063-6773.
-
Conference paper (peer-reviewed)abstract
- There is a range of techniques available to reverse engineer software designs from source code. However, these approaches generate highly detailed representations. The condensing of reverse engineered representations into more high-level design information would enhance the understandability of reverse engineered diagrams. This paper describes an automated approach for condensing reverse engineered diagrams into diagrams that look as if they are constructed as forward designed UML models. To this end, we propose a machine learning approach. The training set of this approach consists of a set of forward designed UML class diagrams and reverse engineered class diagrams (for the same system). Based on this training set, the method 'learns' to select the key classes for inclusion in the class diagrams. In this paper, we study a set of nine classification algorithms from the machine learning community and evaluate which algorithms perform best for predicting the key classes in a class diagram. © 2013 IEEE.
|
|
