Machine learning-based modeling and controller tuning of a heat pump

Mohammad Khosravi,Philipp Heer,Annika Eichler,Roy S Smith,Nicolas Schmid

doi:10.1088/1742-6596/1343/1/012065

Abstract

In this paper, we consider the problem of controller tuning for an operating unit in a building energy system. The illustrative example used here is a real heat pump located in the NEST building at Empa, Dubendorf, Zurich, with its outflow temperature controlled by a PI-controller. The plant is in use and accordingly, intervening in its normal operation is not allowed. Moreover, the model of plant is not available or it can be changed due to aging or possible modification. Accordingly, it is desired to utilize a tuning method which is model-free, operates online, does not intervene with the normal operation of the plant and use only the available historical measurement data. Additionally, it is required to guarantee the safety of the plant during the tuning procedure. In this regard, we formulate the controller tuning problem as a black-box optimization and adopt a safe Bayesian optimization approach for controller parameters tuning. In order to assess numerically the performances of the scheme, first we model the plant as a nonlinear ARX model in form of a feedforward neural network. Subsequently, we train the neural network using the available historical measurement data. Finally, the obtained model is used as an oracle in the controller tuning procedure in order to numerically verify the effectivity of the proposed approach.

Highlights

The building sector consumes nearly 40% of the global energy in the industrial countries [4]
In order to assess numerically the performances of the scheme, first we model the plant as a nonlinear AutoRegressive eXogenous (ARX) model in form of a feedforward neural network
The obtained model is used as an oracle in the controller tuning procedure in order to numerically verify the effectivity of the proposed approach

Summary

Introduction

The building sector consumes nearly 40% of the global energy in the industrial countries [4] This has motivated researchers to optimize energy systems in buildings, and designed advanced control schemes have been introduced in the recent years [5, 7]. We focus on the performance optimization in the lower level where the corresponding implemented control scheme is a PI or a PID controller These types of controllers are widely used in industry and various methods are introduced for their tuning [8]. Many of these procedures are either time consuming or require specific experiments, models and system identification, or modifying the plant. This work is the complementary approach to [3] for the proposed tuning method

Problem Formulation

NARX Modeling Using Feedforward Neural Network

Numerical Results of PI-controller Tuning Using Bayesian Optimization

Conclusion