Unsupervised anomaly detection for power grid telemetry. Validated against 6 years of public ISO data across ERCOT, CAISO, and NYISO.
Each case study runs HTM-Monitor against publicly available ISO telemetry from January 2020 through April 2026. The system learns each grid's operating signature from scratch with no labeled training data, then flags when real-time behavior departs from the learned envelope.
The engine is Hierarchical Temporal Memory — a biologically-inspired sequence-learning algorithm — extended with a grouped-consensus decision layer that only raises a system alert when multiple independent signal models agree. Each model learns its signal's temporal patterns online. No fixed thresholds. No supervised training. Fully auditable per timestep.
Runs single-process in Python. No GPU. No external API calls. Deploys on a $5/mo VPS or inside an air-gapped VM — operator's choice.
Technical preview — free. Send a 90-day telemetry sample and one past event you'd like scored. You get a preview audit within a week: lead/lag timing, false-positive rate, per-signal analysis. No commitment.
Paid pilot — $2,500. Full historical replay against your event catalog, with a written per-event audit. The fee credits in full against your first subscription month.
Pilots, demos, or a replay of your own data: sam@htm-monitor.com