International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 09 | Sep 2025
p-ISSN: 2395-0072
www.irjet.net
Edge-Driven AI for Automated Analog Energy Meter Reading in Commercial Buildings Adit Amit Kumar [1], Fahad Khan [2] [1]DPS International School, HS-01, Golf Course Ext. Rd, Block W, Sector 50, Gurugram, Haryana, 122001 [2]Founder at Luminox Automation, Mentor at Athena Education
--------------------------------------------------------------------------***---------------------------------------------------------------------------Abstract - In small and medium commercial buildings, 1. Introduction manual reading of analog electricity meters remains prevalent, despite its inefficiency. This process is laborintensive, prone to error, and unable to provide the temporal resolution required for modern energy analytics, resulting in missed anomalies and suboptimal energy management. To address these challenges, we design, implement, and evaluate an AI-on-the-edge prototype based on the ESP32-CAM that can automatically digitize and interpret legacy analog electricity meters without requiring utility integration or dependence on cloud-based inference. The system employs TensorFlow Lite with quantized models for digit recognition, combined with ondevice image pre-processing techniques such as region-ofinterest extraction, thresholding, and perspective correction. Data is transmitted via MQTT for seamless integration with dashboards such as InfluxDB. Our firmware builds on and extends the open-source jomjol AIon-the-edge-device framework with customized ROI configurations and digit recognition models specifically optimized for electricity meters. In a real-world pilot deployment in Gurgaon, India, the system achieved a digit classification accuracy of 98.4% (±1.1%), a perfect reading rate of 93%, a mean end-to-end latency of 290 ms, and a bill of materials cost of less than $15. Over a two-week evaluation, the prototype demonstrated 96.2% successful reading uptime, successfully detected a night-time consumption anomaly, and reduced manual meter-reading labor requirements by approximately two hours per week. These results demonstrate that a low-cost, privacypreserving, edge-computing approach can retrofit legacy analog meters with near-real-time telemetry. By enabling anomaly detection and data-driven energy management without reliance on expensive infrastructure, the proposed system has significant potential for scalable deployment in multi-tenant facilities, schools, and small-to-medium enterprises.
Despite significant advancements in grid digitization, analog energy meters remain the dominant measurement infrastructure across small and medium commercial buildings, offices, light-industrial facilities, retail establishments, and educational campuses. These meters, designed decades ago, continue to operate reliably but lack digital interfaces that enable seamless data acquisition. As a result, routine energy monitoring still relies heavily on manual meter readings, typically performed at coarse intervals ranging from daily to monthly. This conventional approach introduces multiple challenges. First, manual reading imposes a considerable labor burden, creating operational inefficiencies for facilities that require consistent monitoring across multiple meters. Second, transcription errors and inconsistent reporting are common, undermining the reliability of collected data. Third, coarse sampling intervals yield sparse time-series datasets that obscure short-lived anomalies, such as afterhours HVAC leakage or unexpected overnight loads, and conceal latent inefficiencies in energy usage patterns. Furthermore, limited temporal resolution restricts the ability to allocate costs accurately across tenants, floors, or specific equipment circuits within shared facilities.Modern energy optimization strategies including anomaly detection, conservation verification, and demand response depend on frequent, accurate, and granular data collection. Without such visibility, facility managers remain unable to diagnose abnormal loads, validate efficiency measures, or enact data-driven energy management policies. While utilities have deployed advanced metering infrastructure (AMI) and automated meter reading (AMR) systems in select contexts, these solutions remain cost-prohibitive for many small and medium enterprises (SMEs), are frequently tied to proprietary vendor ecosystems, and often fall outside the building owner’s operational control. In this context, there exists a critical gap for a low-cost, interoperable, and retrofit-friendly solution capable of transforming legacy analog meters into real-time data sources.
Keywords: AI-on-the-edge; ESP32-CAM; TensorFlow Lite; smart energy measurement; analog meter reading; IoT
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 37