Development of new building HVAC control algorithms has grown due to needs for energy efficiency and operational flexibility. However, case studies demonstrating new algorithms are largely individualized, making algorithm performance difficult to compare directly. In addition, the effort and expertise required to implement case studies in real or simulated buildings limits rapid prototyping potential. Therefore, this paper presents the Building Optimization Testing Framework (BOPTEST) and associated software for simulation-based benchmarking of building HVAC control algorithms. A containerized run-time environment (RTE) enables rapid, repeatable deployment of common building emulators representing different system types. Emulators use Modelica to represent realistic physical dynamics, embed baseline control, and enable overwriting supervisory and local-loop control signals. Finally, a common set of key performance indicators are calculated within the RTE and reported to the user. This paper details the design and implementation of software and demonstrates its usage to benchmark a Model Predictive Control strategy.

Dynamical systems see widespread use in natural sciences like physics, biology, and chemistry, as well as engineering disciplines such as circuit analysis, computational fluid dynamics, and control. For simple systems, the differential equations governing the dynamics can be derived by applying fundamental physical laws. However, for more complex systems, this approach becomes exceedingly difficult. Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. In recent years, there has been an increased interest in applying data-driven modeling techniques to solve a wide range of problems in physics and engineering. This article provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome. Based on the reviewed literature and identified challenges, we provide a discussion on promising research areas.

We present differentiable predictive control (DPC), a method for offline learning of constrained neural control policies for nonlinear dynamical systems with performance guarantees. We show that the sensitivities of the parametric optimal control problem can be used to obtain direct policy gradients. Specifically, we employ automatic differentiation (AD) to efficiently compute the sensitivities of the model predictive control (MPC) objective function and constraints penalties. To guarantee safety upon deployment, we derive probabilistic guarantees on closed-loop stability and constraint satisfaction based on indicator functions and Hoeffding’s inequality. We empirically demonstrate that the proposed method can learn neural control policies for various parametric optimal control tasks. In particular, we show that the proposed DPC method can stabilize systems with unstable dynamics, track time-varying references, and satisfy nonlinear state and input constraints. Our DPC method has practical time savings compared to alternative approaches for fast and memory-efficient controller design. Specifically, DPC does not depend on a supervisory controller as opposed to approximate MPC based on imitation learning. We demonstrate that, without losing performance, DPC is scalable with greatly reduced demands on memory and computation compared to implicit and explicit MPC while being more sample efficient than model-free reinforcement learning (RL) algorithms.