Coordination Architecture Shapes Continuous Demand Response Outcomes in Building Districts

TL;DR

This study compares different coordination architectures for building districts to optimize energy flexibility, balancing load tracking, occupant comfort, and control distribution, with the hybrid approach offering the best overall trade-offs.

Contribution

It systematically evaluates how various control architectures impact demand response performance and introduces a hybrid MPC--SAC method that balances accuracy and comfort.

Findings

Hybrid MPC--SAC achieves the best balance of tracking and comfort.

Centralized MPC has low tracking bias but causes comfort violations.

Decentralized RL distributes control effort but struggles with tracking accuracy.

Abstract

Grid-integrated building districts must provide energy flexibility while preserving occupant comfort and equitable distribution of control burden. We study how coordination architecture influences the ability of building clusters to track aggregated load profiles, comparing four paradigms: centralized model predictive control (MPC), decentralized independent reinforcement learning (SAC), centralized-training-decentralized-execution multi-agent RL (MAPPO), and a hybrid MPC--SAC controller that separates district-level battery optimization from building-level HVAC regulation. A rule-based controller serves as a baseline. We evaluate a 25-building residential district across three metrics: aggregate load tracking, thermal comfort, and spatial variability of control actions. We find that architecture choice determines the trade-off structure. Centralized MPC achieves low tracking bias (8.8% NMBE) but concentrates actuation on a subset of buildings, causing elevated comfort violations (24.8% exceedance) and spatial imbalance. Decentralized RL distributes control effort more evenly but fails to sustain accurate tracking. The hybrid architecture achieves the best balance: accurate tracking (4.8% NMBE), moderate comfort impact (16.8% exceedance), and the lowest spatial variability. These findings demonstrate that architecture choice determines the trade-off structure between tracking and comfort.