An immune system inspired clustering and classification method to detect critical areas in electrical power networks

Authors:
N. C. Woolley;J. V. Milanović
Affiliations:
School of Electrical and Electronic Engineering, The University of Manchester, Manchester, UK M601QD;School of Electrical and Electronic Engineering, The University of Manchester, Manchester, UK M601QD
Venue:
Natural Computing: an international journal
Year:
2011

Citing 11
Cited 0

Support-Vector Networks

Machine Learning
Artificial Immune Systems: A New Computational Intelligence Paradigm

Artificial Immune Systems: A New Computational Intelligence Paradigm
An Evolutionary Immune Network for Data Clustering

SBRN '00 Proceedings of the VI Brazilian Symposium on Neural Networks (SBRN'00)
Asymptotic behaviors of support vector machines with Gaussian kernel

Neural Computation
Artificial Immune Recognition System (AIRS): An Immune-Inspired Supervised Learning Algorithm

Genetic Programming and Evolvable Machines
Computational Techniques for Voltage Stability Assessment and Control (Power Electronics and Power Systems)

Computational Techniques for Voltage Stability Assessment and Control (Power Electronics and Power Systems)
Artificial immune systems---today and tomorrow

Natural Computing: an international journal
Cluster Analysis

Cluster Analysis
Application of AIS Based Classification Algorithms to Detect Overloaded Areas in Power System Networks

ICARIS '09 Proceedings of the 8th International Conference on Artificial Immune Systems
Improved heterogeneous distance functions

Journal of Artificial Intelligence Research
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Identifying critical, failure prone areas in a power system network are often a difficult and computationally intensive task. Artificial Immune System (AIS) algorithms have been shown to be capable of generalization and learning to identify previously unseen patterns. In this paper, a method is developed that uses artificial immune system classification and clustering algorithms to identify critical areas in the network. The algorithm identifies areas of the power system network that are prone to voltage collapse and areas with overloaded lines. The applicability of AIS for this particular task is demonstrated on test electrical power system networks. Its accuracy is compared with an optimised support vector machine (SVM) algorithm and k nearest neighbours algorithm (kNN) across 3 different power system networks.