Orchestration of Edge Controller and Cloud Metric Engine for Managing OPC UA-Based Microgrids

Microgrids are independent power sources distributed across large areas and utilize multiple IoT sensors to collect data. The inherent nature of sensor operations generates considerable data transmission redundancy, increasing overall computational overhead across the entire pipeline. This study proposes a novel cloud-edge collaborative framework for managing OPC unified architecture (UA)-based microgrids and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">OPC-CLOUD</i>. Its salient point is the orchestration of the cloud metric engine (CME) and edge controller (EC). CME tactically determines the transmission configuration by analyzing the collected data. In particular, it adaptively responds to the variations in the data. EC enables effective transmission control of reducing network overhead and resource consumption through frequency-based and threshold-based transmission configured by CME. Through the comparison with the state-of-the-art deep learning prediction approach, we confirm the effectiveness of OPC-CLOUD that significantly reduces computational overhead at the edges, while maintaining stable network transmission. We also demonstrate that OPC-CLOUD can maintain the performance of the time-series prediction model, while reducing network traffic.