IoT-Based DC/DC Deep Learning Power Converter Control: Real-Time Implementation

Abstract

Recently, a modularized smart grid (SG) architecture, entitled the Internet of Things (IoT) grid, is developed that accommodates the IoT technology into the dc-dc converters to build a programmable grid with a single voltage bus. This modern architecture can be established with low computing hardware that facilitates the control and management of the IoT-based grids. Due to the uncertainties originated from the integration of the IoT technology and power electronic converters, the deterministic methodologies are unable to precisely model the SG anymore. In response to these challenges, this article addresses a novel adaptive data-driven method based on the active disturbance rejection controller (ADRC) for the voltage regulation of an IoT-based dc-dc buck converter feeding constant power loads. In particular, a deep deterministic policy gradient (DDPG) with the actor-critic architecture is adopted for the online adjusting of the ADRC controller. The established DDPG takes into account the ADRC controller coefficients into the design objective and offers the ADRC controller with the online coefficient setting ability through the neural network learning. The IoT-based system is tested on a real-time testbed with the constrained application protocol protocol and IEEE 802.11 (Wi-Fi) network to assess the applicability of the suggested controller in the presence of network degradations. The impact of both packet loss and interfering traffic on the reduction performance of the DDPG adaptive ADRC controller is investigated, simultaneously. The supremacy of the suggested adaptive data-driven controllers is verified by a comprehensive comparative analysis with the state-of-the-art methodologies.