Ravigopal Vennelakanti

Application of Visual Analytics for Thermal State Management in Large Data Centres

Todays large data centres are the computational hubs of the next generation of IT services. With the advent of dynamic smart cooling and rack level sensing, the need for visual data exploration is growing. If administrators know the rack level thermal state changes and catch problems in real time, energy consumption can be greatly reduced. In this paper, we apply a cell‐based spatio‐temporal overall view with high‐resolution time series to simultaneously analyze complex thermal state changes over time across hundreds of racks. We employ cell‐based visualization techniques for trouble shooting and abnormal state detection. These techniques are based on the detection of sensor temperature relations and events to help identify the root causes of problems. In order to optimize the data centre cooling system performance, we derive new non‐overlapped scatter plots to visualize the correlations between the temperatures and chiller utilization. All these techniques have been used successfully to monitor various time‐critical thermal states in real‐world large‐scale production data centres and to derive cooling policies. We are starting to embed these visualization techniques into a handheld device to add mobile monitoring capability.

Better drilling through sensor analytics: a case study in live operational intelligence

In this paper, we present our Live Operational Intelligence (LOI) framework for developing, deploying, and executing applications that mine and analyze large amounts of data collected from multiple data sources to help operations staff take more informed decisions during management of operations in various industry verticals. We illustrate the use of the LOI framework with a case study from oil and gas drilling operations. The application involves characterizing and profiling on-shore wells being tapped for natural gas, and using this knowledge to construct a real-time operational intelligence engine for monitoring oil and gas drilling operations.

Collaborative Business Intelligence: Enabling Collaborative Decision Making in Enterprises

Enterprises have successfully deployed business intelligence (data warehousing, reporting, data mining, analytics, and information visualization) technologies to enable strategic decision making. Increasingly, there is a realization that the same sort of high quality information and analytics tools are needed by the many knowledge workers who have to make many operational decisions as they engage in the business operations of the enterprise. Most of these business processes are performed by multiple knowledge workers, and require collaborative decision making, sometimes involving business partners such as outsourced vendors, suppliers, and service providers outside the enterprise. In this paper, we introduce the concept of collaborative business intelligence , which is a combination of business intelligence and collaboration technologies targeted at collaborative decision making. We describe the requirements for collaborative BI, and illustrate them via a real-world use case of managing the operations of a large data center. We describe a prototype collaborative BI platform we are developing at HP. We leverage research that we had done earlier on the Business Cockpit, an intelligent business operations management platform, which combined data integration, process modeling, a process data warehouse, and analytics technologies to enable the monitoring and analysis of business processes. For collaborative BI, we add capabilities for collaboration via 3-dimensonal virtual rooms, visual analytics, and multi-modal interaction technologies. We also need richer metadata models: in addition to modeling data, events, and processes, we also have to model the knowledge of human experts. We describe the experience we have gained from this effort, and our ongoing research.

Mobile Visual Analytics for Datacenter Power and Cooling Management

The demand for data center solutions with lower total cost of ownership and lower complexity of management is driving the creation of next generation datacenters. The information technology industry is in the midst of a transformation to lower the cost of operation through consolidation and better utilization of critical data center resources. Successful consolidation necessitates increasing utilization of capital intensive “always-on” data center infrastructure, reduction in the recurring cost of power and management of physical resources. In this paper, we describe a tool that allows the data center facility managers and administrators to view and analyze the Key Performance Indicators (KPIs) associated with their data centers using pixel cell-based [10,11] visual analytics. The basic idea of our technique is to use the smallest element in the display to present the detailed information of the poser and thermal data records. Administrators can quickly recognize the patterns, trends, and anomalies. Furthermore, we discuss case studies of mobile visual analytics for energy and thermal state monitoring utilizing data from a rich sensor network.