Hierarchical Temporal Memory based One-pass Learning for Real-Time Anomaly Detection and Simultaneous Data Prediction in Smart Grids


A neuro-cognitive inspired architecture based on the Hierarchical Temporal Memory (HTM) is proposed for anomaly detection and simultaneous data prediction in real-time for smart grid μPMU data. The key technical idea is that the HTM learns a sparse distributed temporal representation of sequential data that turns out to be very useful for anomaly detection and simultaneous data prediction in real-time. Our results show that the proposed HTM can predict anomalies within 83%-90% accuracy for three different application profiles, namely Standard, Reward Few False Positive, Reward Few False Negative for two different datasets. We show that the HTM is competitive to five state-of-the-art algorithms for anomaly detection. Moreover, for the multi-step prediction in the online setting, the same HTM achieves a low 0.0001 normalized mean square error, a low negative log-likelihood score of 1.5 and is also competitive to six state-of-the-art prediction algorithms. We demonstrate that the same HTM model can be used for both the tasks and can learn online in one-pass, in an unsupervised fashion and adapt to changing statistics. The other state-of-the-art algorithms are either less accurate or are limited to one of the tasks or cannot learn online in one-pass, and adapt to changing statistics.