Procreating V-detectors for nonself recognition: an application to anomaly detection in power systems

The artificial immune system approach for self-nonself discrimination and its application to anomaly detection problems in engineering is showing great promise. A seminal contribution in this area is the V-detectors algorithm that can very effectively cover the nonself region of the feature space with a set of detectors. The detector set can be used to detect anomalous inputs. In this paper, a multistage approach to create an effective set of V-detectors is considered. The first stage of the algorithm generates an initial set of V-detectors. In subsequent stage, new detectors are grown from existing ones, by means of a mechanism called procreation. Procreating detectors can more effectively fill hard-to-reach interstices in the nonself region, resulting in better coverage. The effectiveness of the algorithm is first illustrated by applying it to a well-known fractal, the Koch curve. The algorithm is then applied to the problem of detecting anomalous behavior in power distribution syst...

• Type: Conference
• Year: 2007
• Where: GECCO
• Authors: Min Gui, Sanjoy Das, Anil Pahwa
• Keywords: Algorithm, Anomaly Detection, Artificial Immune Systems, GECCO 2007