Grant: Alliance Grants

System, network and service monitoring activities aim to maintain the health of the information technology (IT) infrastructure of an organization while ensuring its availability and improving its performance. It is crucial to predict and detect anomalous behaviours indicating normal / failure / security related events. This challenge represents a 24/7 concern for almost all organizations. Thus, the potential for automating the information extraction, data analysis and decision-making is very important in order to sustain the volume, variety, veracity and velocity of modern IT infrastructure data and services. As the scale and complexity of networks, applications and services increases, it becomes more and more difficult to analyze and predict the state of a network service in IT infrastructures. It is envisioned that this research will provide a new approach to develop techniques and tools for analyzing the heterogeneous data sources in enterprise network data. This research will not only offer further insights into online monitoring and analysis, but also result in improved performance for IT and security operations centers (SOCs). Contributions of the proposed research will promote significant progress in - dynamic and adaptive management of IT services and improve cybersecurity. The long term vision of this research will enhance the resiliency of services for commercial, governmental, and military applications, such as rapid / accurate information retrieval and better fault / security management.