A Distributed ADMM-Based Deep Learning Approach for Thermal Control in Multi-Zone Buildings Under Demand Response Events

The increasing electricity use and reliance on intermittent renewable energy sources challenge power grid management during peak demand, making Demand Response programs and energy conservation measures essential. This research combines distributed optimization using ADMM with deep learning models to plan indoor temperature setpoints effectively. A two-layer hierarchical structure is used, with a central building coordinator at the upper layer and local controllers at the thermal zone layer. The coordinator must limit the building’s maximum power by translating the building’s total power to local power targets for each zone. Local controllers can modify the temperature setpoints to meet the local power targets. While most algorithms are either centralized or require prior knowledge about the building’s structure, our approach is distributed and fully data-driven. The proposed algorithm, called Distributed Planning Networks, is designed to be both adaptable and scalable to many types of buildings, tackling two of the main challenges in the development of such systems. The proposed approach is tested on an 18-zone building modeled in EnergyPlus. The algorithm successfully manages Demand Response peak events.Note to Practitioners—This article addresses the problems faced by multizone buildings in maintaining thermal comfort while participating in Demand Response events. A centralized control approach is nonscalable, raises privacy concerns, and requires huge communication bandwidth. This work introduces a distributed algorithm that adapts the temperature setpoints of multi-zone buildings to enhance Demand Response participation and energy conservation. The proposed approach is fully data-driven and only requires historical data on weather, indoor temperature, and HVAC power consumption. The blueprint of the building and details about the HVAC system’s architecture are not needed. Energy savings will be spread across all the zones depending on the user’s choice of comfort temperature interval for each zone. The distributed optimization makes the approach scalable to large buildings with multiple zones. The algorithm is designed to work for buildings with various insulated zones such as apartment buildings and hotels, and may be extended to other types of buildings.