See it live

The PowerIQ dashboard, on a real site.

Aminobots Lens PowerIQ dashboard — real-time HT energy parameters, ToD tariff slabs, and MD-floor automation

The PowerIQ dashboard — 5-minute HT metering, ToD tariff slabs, MD-floor automation, and PF-rebate capture.

01 · Capabilities

What's inside.

Edge controller — a Raspberry Pi 4 polls L&T or Schneider HT meters via Modbus RS485 at 5-minute granularity.
50+ parameters tracked — voltage, current, power factor, frequency, kWh, kVAh, harmonics. All audit-logged.
ToD tariff engine — the local HT Time-of-Day tariff schedule encoded as executable rules. PF rebate thresholds. MD floor band.
Load forecasting ML — hourly forecast with confidence bands. Anomaly detection on consumption patterns.
MD-floor automation — automated load shedding / shifting commands enforce the MD floor and capture PF rebate.
Edge resilience — an edge buffer survives cloud disconnects. Controllers keep running offline; sync resumes on reconnect.
ESG Scope-2 reporting — an audit-ready Scope-2 emissions reduction report with full methodology.

02 · Architecture

Meters at the edge. Dashboards in the cloud.

A Raspberry Pi reads the HT meter via Modbus. Greengrass pre-processes at the edge. An MQTT broker forwards to the cloud. A time-series store captures 5-minute granularity. A tariff engine + forecast ML decide load actions. Commands flow back to the edge controllers. ESG reports export audit-ready.

Flow

l&t meter ← modbus ← raspberry pi 4 (edge)
  ↓ mqtt
iot core · time-series db · forecast ml
  ↓
tod policy → md-floor automation
  ↓
command queue → edge → switch panel

03 · Live in production

PowerIQ at Omega Transmission.

industrial

PowerIQ at Omega Transmission

An HT power-consuming industrial site. Time-of-day tariff penalties they couldn't shift, MD penalties they couldn't avoid, PF rebates they were leaving on the table. Six months later, ~20% lower bill.

Read the case →

What we won't do

Send your PII to a third-party model — sensitive fields are stripped before any external call.
Ship without a CLEAR scorecard — every deployment gets a baseline across five dimensions before it goes live.
Add an agent that doesn't earn its place — Gate 1 kills decorative multi-agent designs; each agent must add new signal.

Start with a Diagnose.

Two to three weeks. $6K–$12K. A written scorecard with topology recommendation, cost ranges, and remediation plan. No commitment to build.

Book a diagnosis

Cut industrial energy bills with edge AI.

Measured in production.