Cyber physical security analytics for transactive energy systems using ensemble machine learning

Demand response and active participation of end-users (prosumers) are expected to play a critical role in the future power grids. Market based transactive exchanges between prosumers are triggered by the increased deployments of renewable generations and microgrid architectures. Transactive Energy Systems (TES) employ economic and control mechanisms to dynamically balance the demand and supply across the electrical grid. Effective transactive mechanisms leverage on a large number of distributed edge-computing and a communication architecture. Given the prolific usage of digital devices, the assets within a transactive environment are vulnerable to various threats. This paper utilizes a machine learning technique to detect possible anomalies within a transactive energy framework. An ensemble based methodology is used to detect anomalies in the market and physical system measurements. The proposed technique is validated for satisfactory performance to detect anomalies and trigger further investigation for root cause analysis and mitigation.