Deep Learning Explicit Differentiable Predictive Control Laws for Buildings
This work addresses control law optimization for building energy management, but it is incremental as it builds on existing predictive control methods with a differentiable approach.
The authors tackled the problem of learning constrained control laws for unknown nonlinear systems by introducing a differentiable predictive control (DPC) methodology, which optimizes neural control laws offline without expert supervision and demonstrated its performance in simulations of building thermal dynamics.
We present a differentiable predictive control (DPC) methodology for learning constrained control laws for unknown nonlinear systems. DPC poses an approximate solution to multiparametric programming problems emerging from explicit nonlinear model predictive control (MPC). Contrary to approximate MPC, DPC does not require supervision by an expert controller. Instead, a system dynamics model is learned from the observed system's dynamics, and the neural control law is optimized offline by leveraging the differentiable closed-loop system model. The combination of a differentiable closed-loop system and penalty methods for constraint handling of system outputs and inputs allows us to optimize the control law's parameters directly by backpropagating economic MPC loss through the learned system model. The control performance of the proposed DPC method is demonstrated in simulation using learned model of multi-zone building thermal dynamics.