Infrastructure-as-a-Service (IaaS) clouds are prone to performance anomalies due to their complex nature. 
Although previous work has shown the effectiveness of using statistical learning to detect performance anomalies, 
existing schemes often assume labelled training data, which requires significant human effort and can only handle 
previously known anomalies. We present an Unsupervised Behavior Learning (UBL) system for IaaS cloud computing 
infrastructures. UBL leverages Self-Organizing Maps to capture emergent system behaviors and predict unknown anomalies. 
For scalability, UBL leverages virtualization technologies to use residual resources in the cloud infrastructure 
for behavior learning and anomaly prediction with little add-on cost. We have implemented a prototype of the UBL 
system on top of the Xen platform and conducted extensive experiments using a range of distributed systems. 
Our results show that UBL can predict performance anomalies with high accuracy and sufficient lead time. 
UBL supports large-scale infrastructure-wide behavior learning with negligible overhead.