Thermostatic control for demand response using distributed averaging and deep neural networks

TL;DR

This paper presents a distributed control method using averaging protocols and deep neural networks to manage thermostatically controlled loads in buildings, providing grid support and reducing power oscillations.

Contribution

It introduces a novel combination of distributed averaging and deep learning for demand response in TCLs, verified through simulations and hardware experiments.

Findings

Effective power aggregation achieved for demand response

Reduced power system oscillations with proposed control

Feasibility demonstrated through hardware implementation

Abstract

Smart buildings are the need of the day with increasing demand-supply ratios and deficiency to generate considerably. In any modern non-industrial infrastructure, these demands mainly comprise of thermostatically controlled loads (TCLs), which can be manoeuvred. TCL loads like air-conditioner, heater, refrigerator, are ubiquitous, and their operating times can be controlled to achieve desired aggregate power. This power aggregation, in turn, helps achieve load management targets and thereby serve as ancillary service (AS) to the power grid. In this work, a distributed averaging protocol is used to achieve the desired power aggregate set by the utility using steady-state desynchronization. The results are verified using a computer program for a homogeneous and heterogeneous population of TCLs. Further, load following scenario has been implemented using the utility as a reference. Apart from providing a significant AS to the power grid, the proposed idea also helps reduce the amplitude of power system oscillations imparted by the TCLs. Hardware-based results are obtained to verify its implementation feasibility in real-time. Additionally, we extend this idea to data-driven paradigm and provide comparisons therein.