Power Laws: Detecting Anomalies in Usage Hosted By DrivenData

5 weeks left


This is one of three challenges in the “Power Laws” series being run simultaneoulsy by Schneider Electric. Each challenge explores a different aspect of energy efficiency and smart energy management. The winning algorithms from these competitions will be released under an open source license in order to spread understanding about how energy modeling works and what approaches are most effective.

Power Laws: Detecting Anomalies in Usage

Energy consumption of buildings has steadily increased. There is an increasing realization that many buildings do not perform as intended by their designers. Typical buildings consume 20% more energy than necessary due to faulty construction, malfunctioning equipment, incorrectly configured control systems and inappropriate operating procedures.

The building systems may fail to meet the performance expectations due to various faults. Poorly maintained, degraded, and improperly controlled equipment wastes an estimated 15% to 30% of energy used in commercial buildings.

Therefore, it is of great potential to develop automatic, quick-responding, accurate and reliable fault detection and to provide diagnosis schemes to ensure the optimal operations of systems to save energy.

Schneider Electric already has relevant offers, but would like to determine if alternative techniques can add new detections / functionalities, bring gain in precision, or operate with less data.

Competition End Date:

March 31, 2018, 11:59 p.m. UTC

Place Prize Amount
1st €10,000
2nd €4,000
3rd €2,000
Best Report €10,000

Note: Prizes delivered by DrivenData in USD, based on the exchange rate on February 6, 2018.