Unlocking the Potential of Model-Predictive Control in Non-domestic Building Energy Management: Automated Configuration and Optimisation of Control

Lead Research Organisation: University of Sheffield
Department Name: Electronic and Electrical Engineering


Non-domestic buildings currently generate 18% of the UK's carbon emissions, >40% of which is due to space heating/cooling. Innovations in control are predicted to save > 25% of this figure making a sizeable contribution to the UK's carbon reduction target. Such innovations, however, must also address building refurbishment as well as new build since the rate of building replacement is rather low.

This proposal aims to effect a step change in the building energy management of non-domestic buildings by making model-predictive control (MPC) an economically-viable control technology for buildings. MPC is well-suited to controlling buildings, which typically have a large time delay between the application of an input and observable response. Importantly, MPC is based explicitly on optimisation as distinct from current building management systems, which use empirically-crafted rules. Currently, the generation and updating of the predictive dynamical model, which lies at the heart of MPC, has to be done manually by highly-skilled control engineers. Although MPC has been demonstrated to achieve energy savings >25% in non-domestic buildings in a research setting with hand-crafted predictive models, the cost of hand tuning these models is currently prohibitive for commercial deployment. We will use advanced machine learning techniques to automatically produce the predictive dynamical model from data acquired from the building-in-operation; hence we will capture key characteristics of the actual building, such as the profound influence of occupants on the building's energy performance. More than this, our approach will be able to periodically update the predictive model to accommodate the inevitable changes in building fabric, use and local environment, all of which will affect the building's thermal dynamics and hence its energy efficiency.

To cost-effectively demonstrate the potential of the research idea, we will make extensive use of building simulation by computer to explore a diverse range of different building forms, weather conditions, and modifications. We will also develop a stochastic model suitable for use in the simulation of non-domestic buildings allowing us to to better account for the impact of building occupants on energy performance. We will supplement these extensive simulation studies with a practical demonstration on different real buildings, one of which will be a passive design school; controlling peak temperatures in passive design buildings is a known challenge particularly in the summer months.

The overall outcome of this project will be to facilitate a step change in building control, producing an acceptable internal environment with the minimum use of primary, non-renewable energy. This derives from the fact that MPC is explicitly based on optimisation. As well as contributing to carbon reduction targets and greater workplace well-being, this will also produce significant cost savings for building operators.

We will disseminate knowledge about MPC and its potential contributions to carbon reduction to the UK building services community using a variety of channels, including an end-of-project workshop.

Planned Impact

It is well known that current building control systems are not fit for purpose. Model-predictive control (MPC) has the potential to enable optimisation of building systems. However, it is not currently economically viable due to the cost and complexity of developing an appropriate predictive dynamical model. This research will develop a methodology for the automated generation and updating of predictive models for use in the model-predictive control of non-domestic buildings, allowing the economically-viable commercial exploitation of MPC in this sector. This will reduce energy use and improve the indoor environment because MPC is explicitly based on optimisation. The benefits will be numerous, including world-leading business opportunities, and improving the quality of the indoor environment for the working public who spend the majority of their time in offices and other internal spaces.

The direct beneficiaries of this research will be commercial building owners and occupiers who will benefit from both an improved working environment and a reduction in energy costs. By optimising the performance of a building, the drive for energy reductions should not reduce the quality of the indoor environment. On the contrary, MPC should improve internal conditions due to its direct use of optimisation. The importance of a good-quality environment on occupant health and well-being should not be under-estimated. Studies in the US suggest better indoor environmental quality could equate to a $40 billion annual saving for businesses from reduced sick days (not to mention the improvement in quality of the lives for the occupants), and improved business productivity of the order of $160 billion.

The contribution towards the UK's reduction in CO2 emissions will also be significant. Facilitating the adoption of MPC provides a technology for a substantial reduction in end-user energy demand, with a projected estimate of >25% energy savings per commercial building. If rolled-out across the majority of UK office buildings, this will have a massive impact on both peak and total energy demand. Further, by improving the control of passive / hybrid buildings (making use of natural ventilation and thermal mass) these building forms become more attractive, leading to reduced use of energy-intensive air conditioning systems.

Finally, there are wider benefits for the economy. This research will open up opportunities for product development for building control and building analytics for both the UK market place and for export. To maximise these opportunities, we have developed a Steering Group of key partners who design, manufacture and specify building control systems in the UK. This will ensure our research is focussed on end-users, and also provide routes for future development into a commercial product once this initial proof-of-concept study has been successfully completed.
Description We have successfully demonstrated the automated machine learning of a predictive model for the model predictive control of a non-domestic building.
Exploitation Route They may be exploited to make model predictive control of buildings economically viable in non-domestic buildings
Sectors Construction,Energy

Description The research programme has stimulated two of our industrial collaborators to independently investigate model predictive control with a view to industrial products/services.
First Year Of Impact 2016
Sector Construction
Impact Types Economic

Description Disseminating research in the academic/user community 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Delivered talks at TEDDINet meetings and CIBSE professional group
Year(s) Of Engagement Activity 2017