Operation optimization of multi-boiler district heating systems using artificial intelligence-based model predictive control: Field demonstrations

Etienne Saloux, Jason Runge and Kun Zhang

Energy, 2023, vol. 285, issue C

Abstract: District energy systems through fourth and fifth generations have shown great promises to help integrate renewable energy sources at large scale and to decarbonize the built environment. However, older generations using boilers represent a large proportion of systems currently in operation, and significantly contribute to greenhouse gas (GHG) emissions. Moreover, operational data has become increasingly available for these older generation systems and represents a suitable opportunity for Artificial Intelligence (AI)-based modelling and advanced controls. In this context, model predictive control (MPC) has appeared as a powerful control solution; however, field implementation remains relatively scarce. This paper aims to develop an AI-based MPC strategy for multi-boiler district heating systems. It relies on heating load forecasting machine learning models and data-driven boiler performance curves to optimize boiler thermal outputs. This strategy was implemented in two Canadian demonstration sites and showed GHG emissions reductions of 1.3 % and 2.8 %. Although relatively modest, statistical analysis confirmed the realization of these savings. In absolute terms, the strategy helped avoid 45 t and 77 t CO2eq emissions and save $10,268 and $19,975 CAD during the testing period of 2–3 months. The model and strategy developed in this work could be easily scalable to similar district heating systems.

Keywords: Boiler efficiency; District heating; Field demonstration; Load forecasting; Model predictive control; Scheduling (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223029183
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:285:y:2023:i:c:s0360544223029183

DOI: 10.1016/j.energy.2023.129524

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().