Energy-efficiency diagnoser

As a major sector of energy consumers, buildings account for about 40% of the global usage and contribute over 30% of the CO2 emissions. These figures can be reduced by up to 15% and 30%, respectively, if energy waste is detected promptly and tracked.

IBM's energy-efficiency diagnoser (e2-diagnoser) is a real-time system to monitor, forecast, and diagnose the energy usage of smart buildings. It supports anomaly detection, pattern mining, and monitoring of buildings at a global scale down to individual building's smart meters.


Joern Ploennigs


Managing the energy efficiency of buildings requires adaptable systems that provide:


e2-diagnoser is an adaptable solution to monitor and diagnose energy waste that provides:


e2-diagnoser saves energy by providing tools to plan energy consumption and to detect and diagnose anomalous consumption in real-time by

Example of result

The e2-diagnoser system is currently running for the IBM Technology Campus Dublin and monitors the electrical, gas and water consumption. Using the tools anomalies in the system operation could be successfully identified and solved such as badly scheduled systems, subsystem failures or water leaks.





  • J. Ploennigs, B. Chen, P. Palmes, R. Lloyd
    "e2-Diagnoser: A System for Monitoring, Forecasting and Diagnosing Energy Usage"
    IEEE International Conference on Data Mining (ICDM), 2014.
  • J. Ploennigs, B. Chen, A. Schumann, N. Brady
    "Exploiting Generalized Additive Models for Diagnosing Abnormal Energy Use in Buildings"
    5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings "BuildSys'13," 1-8, 2013.
  • B. Chen, M. Sinn, J. Ploennigs, A. Schumann
    "Statistical Anomaly Detection in Mean and Variation of Energy Consumption"
    22nd International Conference on Pattern Recognition (ICPR), 2014.