High-precision Commercial pyranometers and radiometers are often prohibitively expensive, and inexpensive solar power meters lack integrated wireless connectivity, limiting deployment in decentralized monitoring networks. This feasibility study presents a budget-friendly IoT-based sensing platform designed to estimate global horizontal solar irradiance (W/m 2 ) using a multi-model fusion technique. The hardware architecture utilizes a NodeMCU ESP8266 microcontroller to continuously acquire real-time data from three distinct, non-intrusive radiometric proxies: (i) differential surface temperature measured using black (T2) and white (T3) aluminum plates. (ii) optical illuminance (lux) via a BH1750 digital ambient light photo-diode and (iii) electrical short-circuit current drift via a polycrystalline photovoltaic (PV) panel monitored by an INA219 sensor. To eliminate manual logging errors and ensure synchronization, sensor streams are telemetered in real time to a centralized workstation using TCP/IP socket connections. The proxies were calibrated and empirically cross-validated against a commercial reference radiometer (HTC LX-107) under dynamic outdoor solar radiation conditions. Regression models demonstrated strong statistical alignment between proxy signals and absolute solar irradiance. Outdoor validation confirmed that the optical illuminance proxy achieved the highest dynamic responsiveness (R² = 0.69 to 0.94 and RMSE ≈ 51.32 to 115.03 W/m²), followed closely by the differential temperature proxy (R² = 0.81 to 0.88 and RMSE ≈ 70.82 to 94.92 W/m²). The PV panel electrical proxy also demonstrated a strong predictive performance and maintained a solid peak multi-regression fit during outdoor validation (R² = 0.68 to 0.77 and RMSE ≈ 103.06 to 117.45 W/m²). The proposed multi-modal IoT framework offers an automated, scalable, and budget-friendly alternative to standard pyranometers. By combining multi-sensor fusion with automated wireless telemetry, the system successfully tracks diurnal irradiance fluctuations, providing a viable tool for solar energy management, agricultural microclimate monitoring, and smart grid integration at a fraction of the cost of commercial hardware.
No takes yet. Share an insight, caveat, or question.
Sarkar et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: