Process data based Anomaly detection in distributed energy generation using Neural Networks

The increasing share of renewable energies in the total energy supply includes a growing number of small, decentralized energy generation which also provides control energy. These decentralized stations are usually combined to a virtual power plant which takes over the monitoring and control of the individual participants via an Internet connection. This high degree of automation and the large number of frequently changing subscribers creates new challenges in terms of detecting anomalies. Quickly adaptable, variable and reliable methods of anomaly detection are required. This paper compares two approaches using Neural Networks (NN) with respect to their ability to detect anomalous behavior in real process data of a combined heat and power plant. In order to include process dynamics, one approach includes specifically engineered features, while the other approach uses Long-Short-Term-Memory (LSTM). Both approaches are able to detect rudimentary anomalies. For more demanding anomalies, the respective strengths and weaknesses of the two approaches become apparent.