The CBR-PNN approach to real-time voltage security assessment of power systems
by N.P. Patidar, Jaydev Sharma
International Journal of Energy Technology and Policy (IJETP), Vol. 5, No. 6, 2007

Abstract: This paper presents the Case-based Reasoning (CBR) technique, a novel approach to voltage security assessment of power system in a real-time environment. The Probabilistic Neural Network (PNN) is used for determining the solution to a new case, using the old cases from the case base of the CBR system. A feature selection technique based on the information gained has been employed to identify the relevant input features for PNN. The CBR technique extracts the information of voltage security from large sets of possible operating conditions of the power system, generated by computer simulation. Also the ranking of contingencies is done by CBR as accurately as the one done by the Continuation Power Flow (CPF) method. Security classes are defined by the threshold value of maximum loadability margins, calculated by the CPF method. The effectiveness of the proposed approach is tested on IEEE test systems. The proposed method gives fast and accurate voltage security information for unknown patterns and it is found to be suitable for real-time monitoring of voltage security in energy management systems.

Online publication date: Mon, 05-Nov-2007

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Energy Technology and Policy (IJETP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com