Smart buildings as Cyber-Physical Systems: Data-driven predictive control strategies for energy efficiency

Schmidt, Mischa; Åhlund, Christer

doi:10.1016/j.rser.2018.04.013

Cited by 108 publications

(40 citation statements)

References 123 publications

(146 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The papers that investigate big data applications and technologies of building energy management can be found in [40][41][42]. Similarly, the review of [43] focused on the prediction and classifications of building energy consumption on the future micro-scale change for a particular building; the review of [44] addressed the uncertainty analysis and big climate data in assessing building energy performance; from the perspective of data mining techniques and applications, a review of research on building operational performance improving is summarized in [45]; the review of [46] emphasises the cyber-physical systems of smart buildings and the diverse data driven approaches for energy efficiency control, particularly focusing on strategies for existing buildings.…”

Section: Energy Efficiency and Intelligencementioning

confidence: 99%

Big Data and Climate Change

Hassani

Huang

Silva

2019

BDCC

View full text Add to dashboard Cite

Climate science as a data-intensive subject has overwhelmingly affected by the era of big data and relevant technological revolutions. The big successes of big data analytics in diverse areas over the past decade have also prompted the expectation of big data and its efficacy on the big problem—climate change. As an emerging topic, climate change has been at the forefront of the big climate data analytics implementations and exhaustive research have been carried out covering a variety of topics. This paper aims to present an outlook of big data in climate change studies over the recent years by investigating and summarising the current status of big data applications in climate change related studies. It is also expected to serve as a one-stop reference directory for researchers and stakeholders with an overview of this trending subject at a glance, which can be useful in guiding future research and improvements in the exploitation of big climate data.

show abstract

Section: Energy Efficiency and Intelligencementioning

confidence: 99%

Big Data and Climate Change

Hassani

Huang

Silva

2019

BDCC

View full text Add to dashboard Cite

show abstract

“…These cover: building energy demand prediction, building occupancy and occupant behaviour and fault detection and diagnosis (FDD) for building systems. [20] and [21] further argument through broader studies the relevance of data-driven approaches in timely building energy efficiency applications.…”

Section: B Related Workmentioning

confidence: 99%

Data-Driven Modelling of Smart Building Ventilation Subsystem

et al. 2019

View full text Add to dashboard Cite

Considering the advances in building monitoring and control through networks of interconnected devices, effective handling of the associated rich data streams is becoming an important challenge. In many situations the application of conventional system identification or approximate greybox models, partly theoretic and partly data-driven, is either unfeasible or unsuitable. The paper discusses and illustrates an application of black-box modelling achieved using data mining techniques with the purpose of smart building ventilation subsystem control. We present the implementation and evaluation of a data mining methodology on collected data over one year of operation. The case study is carried out on four air handling units of a modern campus building for preliminary decision support for facility managers. The data processing and learning framework is based on two steps: raw data streams are compressed using the Symbolic Aggregate Approximation method, followed by the resulting segments being input into a Support Vector Machine algorithm. The results are useful for deriving the behaviour of each equipment in various modi of operation and can be built upon for fault detection or energy efficiency applications. Challenges related to online operation within a commercial Building Management System are also discussed as the approach shows promise for deployment.

show abstract

“…In the last decades, plenty of control strategies, e.g. Model Predictive Control (MPC), Fuzzy Logic Control, Neuronal Network Control and Cyber-physical control [1], promised to increase the efficiency of building energy systems in order to reduce CO2 emissions and energy consumption [2]. To evaluate the developed control strategies, many researchers compare the developed control strategy with a standard control strategy such as On/Off control, PID control [3] or an ideal controller [4].…”

Section: Introductionmentioning

confidence: 99%

A Representative Simulation Model for Benchmarking Building Control Strategies

KÃ1⁄4mpel¹,

Stinner²,

Gauch³

et al. 2019

Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC)

View full text Add to dashboard Cite

To increase the energy efficiency of building energy systems, many control strategies have been investigated in recent years. Researchers apply control strategies to different building energy systems in order to evaluate their performance. However, the scientific community lacks a commonly accepted reference building model and evaluation criteria. In this paper, we therefore propose a simulationbased benchmark to rate different control strategies for building energy systems. Based on identified requirements for benchmarking, we design a building model on which researchers can apply different control strategies and compare them with each other. The building consists of five different rooms and an energy system with several heat and cold generators. A concrete core activation and a central air-handling unit with additional decentralized cooling and heating registers supply each room individually. To benchmark a control strategy, the model calculates the consumed energy, the primary energy costs and the indicators of indoor air quality. We apply the benchmark to two different control strategies. The benchmark provides reproducible quantitative assessments of the performance of the tested control strategies. The diversity of the energy system as well as the individual airconditioning of the rooms allow complex and sophisticated control strategies to demonstrate their potentials.

show abstract

Smart buildings as Cyber-Physical Systems: Data-driven predictive control strategies for energy efficiency

Cited by 108 publications

References 123 publications

Big Data and Climate Change

Big Data and Climate Change

Data-Driven Modelling of Smart Building Ventilation Subsystem

A Representative Simulation Model for Benchmarking Building Control Strategies

Contact Info

Product

Resources

About