Identification of non-linear autoregressive models with exogenous inputs for room air temperature modelling

Thilker, Christian Ankerstjerne; Bacher, Peder; Calı̀, Davide; Madsen, Henrik

doi:10.1016/j.egyai.2022.100165

Cited by 11 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although complex approaches such as neural networks are being explored for heating and cooling system thermal predictions with positive outcomes for objective oriented control, 10,18 the success of physics based numerical methods such as electrical-thermal analogies, makes them well suited to demonstrative studies such as this one. Non-linear auto-regressive models have been used for predicting building thermal behaviour which have suited the purpose of their study well, 19 but without great effort only moderately capture the finer higher frequency response details of building behaviour. Such approaches require a significant body of appropriate experimental data which was both unnecessary and unavailable in the delivery of this study.…”

Section: Methodsmentioning

confidence: 99%

Opportunities for improved space heating energy efficiency from fluid property modifications

Williams

Innerdale

2022

Indoor and Built Environment

View full text Add to dashboard Cite

Unsteady behaviour of hydronic heating systems causes higher mean room temperatures than are required for comfort. Peak room temperatures depend on interactions between thermostats, heat emitters and the room. The importance of fluid properties on such unsteady heating is often misunderstood meaning potential energy savings are overlooked. This paper demonstrates the influence of fluid modifications and indicates a plausible magnitude of the energy saving opportunity. The results showed that fluid side heat transfer coefficient in isolation had negligible effect. Specific heat capacity of the fluid and flow rates were important, as they altered the amount of embedded energy in the heat emitter when thermostat conditions were met. Reductions in mean heating power for steady demand conditions were between 0 and 7% for plausible changes to fluid properties, depending on heat emitter size, room insulation and external temperature. Reductions in individual cycle energy were between 5 and 25%. When considered in the context of intermittent finite duration heating events, those that contained a small number of thermostat cycles demonstrated energy savings that tended towards the reductions in individual cycle energy. Heating events with larger numbers of cycles showed energy savings tending towards the reduction in mean heating power.

show abstract

Section: Methodsmentioning

confidence: 99%

Opportunities for improved space heating energy efficiency from fluid property modifications

Williams

Innerdale

2022

Indoor and Built Environment

View full text Add to dashboard Cite

show abstract

“…Unlike other methods, we mainly rely on real data, which is more challenging to deal with. Among these black box models, we can cite linear polynomial model (ARX, OE, ARMAX), linear state space (LSS) [19], neural network (NN), linear parameter varying (LPV) [20] and many more. This large dictionary allows users to choose the appropriate model complexity depending on the problem.…”

Section: A State Of Artmentioning

confidence: 99%

Operating data of a specific Aquatic Center as a Benchmark for dynamic model learning: search for a valid prediction model over an 8-hour horizon

Gauthier-Clerc,

Capitaine,

Claveau

et al. 2023

2023 European Control Conference (ECC)

View full text Add to dashboard Cite

This article presents an identification benchmark based on data from a public swimming pool in operation. Such a system is both a complex process and easily understandable by all with regard to the stakes. Ultimately, the objective is to reduce the energy bill while maintaining the level of quality of service. This objective is general in scope and is not limited to public swimming pools. This can be done effectively through what is known as economic predictive control. This type of advanced control is based on a process model. It is the aim of this article and the considered benchmark to show that such a dynamic model can be obtained from operating data. For this, operational data is formatted and shared, and model quality indicators are proposed. On this basis, the first identification results illustrate the results obtained by a linear multivariable model on the one hand, and by a neural dynamic model on the other hand. The benchmark calls for other proposals and results from control and data scientists for comparison.

show abstract

“…The second modeling type does not involve any specific physical or mathematical description of the process, but rather uses data measured over time. It applies methods such as neural networks [ 21 , 22 , 23 ], nonlinear autoregressive models [ 24 , 25 , 26 , 27 ], or fuzzy networks [ 28 , 29 ] to approximate the output and model the thermal phenomena.…”

Section: Introductionmentioning

confidence: 99%

The Development of an Energy Efficient Temperature Controller for Residential Use and Its Generalization Based on LSTM

Alexandru

Popescu

et al. 2023

Sensors

View full text Add to dashboard Cite

Thermostats operate alongside intelligent home automation systems for ensuring both the comfort of the occupants as well as the responsible use of energy. The effectiveness of such solutions relies on the ability of the adopted control methodology to respond to changes in the surrounding environment. In this regard, process disturbances such as severe wind or fluctuating ambient temperatures must be taken into account. The present paper proposes a new approach for estimating the heat transfer of residential buildings by employing a lumped parameter thermal analysis model. Various control strategies are adopted and tuned into a virtual environment. The knowledge gained is generalized by means of a long short-term memory (LSTM) neural network. Laboratory scale experiments are provided to prove the given concepts. The results achieved highlight the efficiency of the implemented temperature controller in terms of overshoot and energy consumption.

show abstract

Identification of non-linear autoregressive models with exogenous inputs for room air temperature modelling

Cited by 11 publications

References 31 publications

Opportunities for improved space heating energy efficiency from fluid property modifications

Opportunities for improved space heating energy efficiency from fluid property modifications

Operating data of a specific Aquatic Center as a Benchmark for dynamic model learning: search for a valid prediction model over an 8-hour horizon

The Development of an Energy Efficient Temperature Controller for Residential Use and Its Generalization Based on LSTM

Contact Info

Product

Resources

About