SmartLVEnergy: An AIoT Framework for Energy Management Through Distributed Processing and Sensor-Actuator Integration in Legacy Low-Voltage Systems

Digital integration is essential for efficient and sustainable management of energy resources, especially in modernizing outdated infrastructures. This involves embedding sensor and actuator devices for precise energy monitoring and control, supported by distributed computing from edge to cloud, necessary for tailored analytical and predictive decisions. Retrofit strategies incorporate these resources into older systems, enhancing existing infrastructures while adapting to technological progress. Nevertheless, systematic methodologies for sensor-actuator integration are lacking in the literature. Therefore, this article introduces the SmartLVEnergy framework, designed to modernize legacy low-voltage systems with a retrofitting approach, integrating decentralized sensing, control, distributed processing, and predictive analytics. The framework was employed to retrofit the energy distribution panel of a legacy manufacturing plant with sensor devices, which support remote monitoring and decentralized predictive analysis using 15-min energy demand forecast models based on two-layer long-short-term memory (LSTM) networks, adhering to Artificial Intelligence of Things (AIoT) and tiny machine learning (TinyML) principles. Benchmarked against nonquantized and single-layer LSTM models for the installation energy demand forecast between May 8 and July 11, 2023, our approach showed reduced prediction latency and memory consumption. The main circuit breaker exhibited a 96.67% R-squared score (
${R} ^{{2}}$
) and 7.23 kW root mean squared error (RMSE), with the associated sensor showing a prediction latency of 54.55 ms and using 58.45 KB of FLASH memory. These metrics for the best-performing sensor were 97.33%, 0.39 kW, 5.55 ms, and 10.20 KB. This AIoT framework marks a significant advancement in sensor-actuator retrofitting, blending digital technology with legacy systems for intelligent energy management.